User classification method, apparatus, device and computer-readable medium

Abstract

The present invention discloses a method, device, equipment and computer-readable medium for user classification, and relates to the field of computer technology. A specific implementation of the method includes: the server determines the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy, the original payment amount and the original compensation amount based on the user's insurance policy information; the server establishes a time interval classification parameter, a frequency classification parameter and a payment amount classification parameter according to the user's behavior information, combined with the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy and the original payment amount; the server classifies users into multiple categories based on the time interval classification parameter, the frequency classification parameter, the payment amount classification parameter and the original compensation amount. This implementation can improve the accuracy of user classification.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device, equipment and computer-readable medium for user classification. Background Art

[0002] Currently, merchants need to obtain detailed information about users to achieve user classification. On the one hand, they can start from the user himself and use the user information related to the products purchased by the user; on the other hand, merchants can obtain the product information involved through historical sales records. Then, users can be classified based on the user information and the above product information.

[0003] In the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art: users are classified according to user information and product information, the classification granularity is relatively coarse, and it is difficult to implement personalized strategy formulation for users. Summary of the invention

[0004] In view of this, embodiments of the present invention provide a method, apparatus, device and computer-readable medium for user classification, which can improve the accuracy of user classification.

[0005] To achieve the above object, according to one aspect of an embodiment of the present invention, a method for user classification is provided, comprising:

[0006] The server determines the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy, the original payment amount and the original compensation amount based on the insurance policy information of the user;

[0007] The server establishes a time interval classification parameter, a frequency classification parameter and a payment amount classification parameter according to the user's behavior information, combined with the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy and the original payment amount;

[0008] The server classifies users into multiple categories based on the time interval classification parameter, the frequency classification parameter, the payment amount classification parameter and the original compensation amount.

[0009] The users include multiple members of a family;

[0010] The server determines the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy, the original payment amount and the original compensation amount based on the insurance policy information of the user, including:

[0011] The server determines, based on the policy information of the multiple members, the time intervals for originally purchasing the policies of the multiple members, the frequencies for originally purchasing the policies of the multiple members, the original payment amounts and the original compensation amounts of the multiple members;

[0012] The user's behavior information includes behavior information of the multiple members.

[0013] The time interval for originally purchasing insurance policies includes: the time interval for the most recent insurance policy purchase and the average time interval for purchasing insurance policies;

[0014] The frequency of original policy purchases includes: the number of policy purchases in a preset period, the ratio of the number of policy purchases in a preset period to the total number of policy purchases by the user, and the ratio of the total number of policy purchases by the user to the average total number of policy purchases by all users;

[0015] The original payment amount includes: the payment amount within a preset period, the ratio of the payment amount within the preset period to the total payment amount of the user, and the ratio of the total payment amount of the user to the average total payment amount of all users;

[0016] The original compensation amount includes: the compensation amount within a preset period, the ratio of the compensation amount within the preset period to the total compensation amount of the user, and the ratio of the total compensation amount of the user to the average total compensation amount of all users.

[0017] The server establishes a time interval classification parameter, a frequency classification parameter and a payment amount classification parameter according to the user's behavior information, in combination with the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy and the original payment amount, including:

[0018] The server establishes a time interval classification parameter according to the time interval of the user's access behavior in the behavior information and the time interval of the original purchase of the insurance policy;

[0019] The server establishes the frequency classification parameter according to the number of insurance policies involved in the user's access behavior in the behavior information and the frequency of the original purchase of insurance policies;

[0020] The server establishes the payment amount classification parameter according to the policy amount involved in the user access behavior in the behavior information and the original payment amount.

[0021] The user's behavior information includes searching and / or browsing insurance-related information, and the insurance-related information is determined by multiple keywords.

[0022] The server classifies the users into multiple categories based on the time interval classification parameter, the frequency classification parameter, the payment amount classification parameter and the original compensation amount, including:

[0023] The server determines a time interval score according to the interval parameter in the time interval classification parameter and the weight of the interval parameter;

[0024] The server determines a frequency score according to the frequency parameter in the frequency classification parameter and the weight of the frequency parameter;

[0025] The server determines the payment score according to the payment parameter in the payment amount classification parameter and the weight of the payment parameter;

[0026] The server determines the compensation score according to the compensation parameter in the original compensation amount and the weight of the compensation parameter;

[0027] The server classifies users into multiple categories according to the time interval score, the frequency score, the payment score and the compensation score.

[0028] After the users are divided into multiple categories, the method further includes:

[0029] The server sends recommendation information of the category to which the user belongs to the user;

[0030] and / or,

[0031] The server pushes the category of the user and / or recommendation information of the category to which the user belongs to the insurance agent.

[0032] According to a second aspect of an embodiment of the present invention, there is provided a device for user classification, comprising:

[0033] The insurance policy module is used to determine the time interval of the original insurance policy purchase, the frequency of the original insurance policy purchase, the original payment amount and the original compensation amount based on the user's insurance policy information;

[0034] An updating module, configured to establish a time interval classification parameter, a frequency classification parameter and a payment amount classification parameter according to the user's behavior information, in combination with the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy and the original payment amount;

[0035] The classification module is used to classify users into multiple categories based on the time interval classification parameter, the frequency classification parameter, the payment amount classification parameter and the original compensation amount.

[0036] According to a third aspect of an embodiment of the present invention, there is provided an electronic device for user classification, comprising:

[0037] one or more processors;

[0038] a storage device for storing one or more programs,

[0039] When the one or more programs are executed by the one or more processors, the one or more processors implement the above method.

[0040] According to a fourth aspect of an embodiment of the present invention, there is provided a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, the method as described above is implemented.

[0041] One embodiment of the above invention has the following advantages or beneficial effects: the server determines the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy, the original payment amount and the original compensation amount based on the user's insurance policy information; the server establishes time interval classification parameters, frequency classification parameters and payment amount classification parameters according to the user's behavior information, combined with the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy and the original payment amount; the server divides the user into multiple categories based on the time interval classification parameters, the frequency classification parameters, the payment amount classification parameters and the original compensation amount. By combining the user's behavior information with the parameters of the original purchase of the insurance policy, since the behavior information can represent the user's actual recent behavior, the user can be classified using the established parameters, which can improve the accuracy of the classification.

[0042] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0044] Figure 1 is a schematic diagram of the main process of the method for user classification according to an embodiment of the present invention;

[0045] Figure 2 is a schematic diagram of a process for determining classification parameters according to an embodiment of the present invention;

[0046] Figure 3 is a schematic diagram of a process of classifying users into multiple categories based on classification parameters according to an embodiment of the present invention;

[0047] Figure 4 is a schematic diagram of information of an original purchased insurance policy according to an embodiment of the present invention;

[0048] Figure 5 is an information schematic diagram of determining user classification by using behavior information according to an embodiment of the present invention;

[0049] Figure 6 is a schematic diagram of the main structure of a device for user classification according to an embodiment of the present invention;

[0050] Figure 7 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0051] Figure 8It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0053] In actual applications, there are many variations in the data dimensions referenced according to different businesses. However, classifying users according to user information and product information still has the problem of coarse classification granularity, making it difficult to formulate personalized strategies for users.

[0054] In order to solve the problem of low accuracy of user classification, the following technical solution in the embodiment of the present invention may be adopted.

[0055] See also Figure 1 , Figure 1 Schematic diagram of the main process of the method for user classification according to an embodiment of the present invention, the behavior information represents the actual behavior of the user, and then the classification is performed after the classification parameters are determined based on the behavior information. Figure 1 As shown, the specific steps include:

[0056] The execution subject of the embodiment of the present invention is a server, that is, the server can execute the following steps.

[0057] S101. The server determines the time interval for original policy purchase, the frequency of original policy purchase, the original payment amount and the original compensation amount based on the policy information of the user.

[0058] In an embodiment of the present invention, it is suitable to classify users according to their insurance policy information and their behavior information. The insurance policy information of a user is used to represent the information related to the purchase of an insurance policy by the user over a period of time. The behavior information of the user represents the non-purchase behavior of the user related to the insurance policy in the recent period of time.

[0059] In the present embodiment, firstly, it is necessary to determine the relevant parameters of the original purchased insurance policy based on the user's insurance policy information. The original purchased insurance policy refers to the insurance policy purchased within a preset time period. This is mainly because the insurance policy is a written proof of the insurance contract signed between the insurer and the insured. Generally speaking, insurance policies have the characteristics of low purchase frequency and compensation compared to ordinary commodities. Obviously, the technical solution of classifying users based on the goods purchased by users in the prior art is not applicable to insurance policies.

[0060] In view of the characteristics of the insurance policy itself, in the embodiment of the present invention, it is necessary to determine the following parameters based on the user's insurance policy information: the time interval for the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy, the original payment amount and the original compensation amount.

[0061] In other words, the parameters are determined from four aspects: the purchase period of the policy, the purchase frequency of the policy, the payment amount and the compensation amount.

[0062] Specifically, considering the purchase period of the policy, determine the time interval for the original purchase of the policy; considering the purchase frequency of the policy, determine the frequency of the original purchase of the policy; considering the payment amount, determine the original payment amount; considering the compensation amount, determine the original compensation amount.

[0063] An exemplary description of each parameter is given below.

[0064] The time interval of the original purchase of the insurance policy measures the purchase of the insurance policy from the dimension of time. As an example, the time interval of the original purchase of the insurance policy includes: the time interval of the most recent purchase of the insurance policy and the average time interval of the purchase of the insurance policy.

[0065] For users, there are situations where they purchase insurance policies multiple times. Then, the reference value of the most recent insurance policy purchase is greater than the reference value of the historical insurance policies purchased. This is because users often purchase different types of insurance policies due to actual needs. The most recent insurance policy purchase reflects the user's recent insurance needs. Therefore, the time interval of the most recent insurance policy purchase is added to the time interval of the original insurance policy purchase.

[0066] In addition, the time point at which the actual demand is present is different for each user. In order to measure a single user from the perspective of multiple users, i.e., a user group, the time interval for originally purchasing the insurance policy includes the average time interval for purchasing the insurance policy.

[0067] In other words, from the perspective of a single user, determine the original policy purchase parameters of a single user: the time interval between the last policy purchase; and then measure the original policy purchase parameters of the user from the perspective of the user group: the average time interval between policy purchases. As an example, a user group is a group of users who purchase the same type of policy, such as: a car insurance user group; a life insurance user group. As another example, a user group is a group of users who purchase the same type of policy. For example: a group of users who purchase the same type of policy.

[0068] The frequency of original policy purchase measures the purchase of policies from the frequency dimension. As an example, the frequency of original policy purchase includes the number of policy purchases in a preset period, the ratio of the number of policy purchases in a preset period to the total number of policy purchases by the user, and the ratio of the total number of policy purchases by the user to the average total number of policy purchases by all users.

[0069] The specific parameters of the original frequency of purchasing insurance policies can be considered from two aspects. On the one hand, from the user's perspective, the parameters of the user's personal purchase of insurance policies; on the other hand, from the group's perspective, that is, the parameters of the user's personal purchase of insurance policies relative to the group.

[0070] Specifically, the number of times the policy is purchased in the preset period and the ratio of the number of times the policy is purchased in the preset period to the total number of times the user purchases the policy are used as parameters for the user's personal purchase of the policy. The preset period can be preset according to the actual application scenario. As an example, the preset period is the first three years from the current date. The total number of times the user purchases the policy is all the times the user purchases the policy recorded in the database.

[0071] The specific parameter of the user's individual purchase of insurance policies relative to the group is: the ratio of the total number of times the user purchases insurance policies to the average total number of times all users purchase insurance policies. It can be understood that when the above ratio is greater than or equal to 1, it means that the number of insurance policies purchased by the user is greater than or equal to the number of insurance policies purchased by the group; when the above ratio is less than 1, it means that the number of insurance policies purchased by the user is less than the number of insurance policies purchased by the group.

[0072] The solution of the embodiment of the present invention is applicable to insurance policies. For insurance policies, not only the payment amount but also the compensation amount needs to be determined. Ordinary goods mostly involve payment amounts, but the compensation amount does not need to be considered. Since insurance policies have a compensation function, the compensation amount needs to be determined.

[0073] The payment amount is specifically represented by the original payment amount. In one embodiment of the present invention, the original payment amount includes: the payment amount within a preset period, the ratio of the payment amount within the preset period to the total payment amount of the user, and the ratio of the total payment amount of the user to the average total payment amount of all users.

[0074] That is, the original payment amount is measured from both individual and group perspectives. From the individual perspective, it includes the following two parameters: the payment amount within a preset period, and the ratio of the payment amount within the preset period to the total payment amount of the user. From the group perspective, it includes the ratio of the total payment amount of the user to the average total payment amount of all users. As an example, the preset period is the first three years from the current date.

[0075] The compensation amount is specifically represented by the original compensation amount. In one embodiment of the present invention, the original compensation amount includes: the compensation amount within a preset period, the ratio of the compensation amount within the preset period to the total compensation amount of the user, and the ratio of the total compensation amount of the user to the average total compensation amount of all users.

[0076] On the one hand, the parameters of personal compensation amount are determined from the perspective of individual users: the compensation amount within the preset period, and the ratio of the compensation amount within the preset period to the total compensation amount of the user; on the other hand, the parameters of the individual compensation amount relative to the group are determined from the perspective of the group: the ratio of the user's total compensation amount to the average total compensation amount of all users.

[0077] At this point, four parameters are determined: the time interval for the original policy purchase, the frequency of the original policy purchase, the original payment amount and the original compensation amount.

[0078] The above four parameters fully reflect the characteristics of the insurance policy, and determine the individual parameters and group parameters included in the four parameters from both individual and group perspectives. Compared with other commodities, insurance policies have their own characteristics, and the above four parameters are suitable for application scenarios where users are classified based on insurance policies.

[0079] S102. The server establishes time interval classification parameters, frequency classification parameters and payment amount classification parameters according to the user's behavior information, combined with the time interval for original policy purchase, the frequency for original policy purchase and the original payment amount.

[0080] The embodiment of the present invention is applied to classify users based on insurance policies. Commodities are purchased much more frequently than insurance policies. If users are classified based on insurance policies, the accuracy of user classification will be much lower due to the low number of insurance policy purchases.

[0081] Through many practices and studies, it is found that users often search and / or browse information related to the insurance policy before purchasing the insurance policy. In the embodiment of the present invention, searching and / or browsing information related to the insurance policy is referred to as non-purchase behavior. Among them, the information related to the insurance policy is determined by multiple keywords. As an example, the insurance policy keywords include one or more of the following: insurance terms, claim terms, life insurance, auto insurance, pension and property insurance, etc.

[0082] In the embodiment of the present invention, for the above-mentioned non-purchase behavior of the insurance policy, the time interval classification parameter, the frequency of the original purchase of the insurance policy, the original payment amount and the original compensation amount are combined to establish the time interval classification parameter, the frequency classification parameter and the payment amount classification parameter. Specifically, the user's behavior information represents the user's non-purchase behavior involving the insurance policy in the recent period. Then, according to the user's behavior information, combined with the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy and the original payment amount, the time interval classification parameter, the frequency classification parameter and the payment amount classification parameter are established.

[0083] That is, the user's behavior information includes searching and / or browsing information related to insurance. The user's behavior information is used to establish classification parameters to make up for the application scenario where fewer insurance policies are purchased. Moreover, since searching and / or browsing reflects the user's actual demand for insurance policies from a non-purchase perspective, the classification parameters are determined based on the user's behavior information, which can not only enrich the insurance policy information, but also reflect the user's recent actual demand for insurance policies.

[0084] See also Figure 2 , Figure 2 is a schematic diagram of a process for determining classification parameters according to an embodiment of the present invention. Figure 2 Specifically, the specific process of establishing the time interval classification parameter, frequency classification parameter and payment amount classification parameter by using the user's behavior information in combination with the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy and the original payment amount. Since the user's behavior does not involve compensation, the above steps do not involve the original compensation amount.

[0085] S201. The server establishes a time interval classification parameter based on the time interval of the user's access behavior and the time interval of the original purchase of the insurance policy in the behavior information.

[0086] The server uses the behavior information to establish time interval classification parameters, including establishing time interval classification parameters based on the time interval of the user's access behavior in the behavior information and the time interval of the original purchase of the insurance policy.

[0087] Specifically, the time interval of user access behavior is the time interval of users searching and / or browsing insurance-related information. Compared with the time interval of purchasing insurance policies, the time interval of user access behavior is shorter.

[0088] Then, the time interval of the user's access behavior can be used as a time interval classification parameter. That is, the time interval classification parameter includes: the time interval of the most recent purchase of the insurance policy, the average time interval of the purchase of the insurance policy, and the time interval of the user's access behavior.

[0089] In one embodiment of the present invention, the time interval of the user's access behavior can also be divided into multiple parameters according to the access object. As an example, the access object includes APP1 and web page 1, and the time interval of the user's access behavior includes time interval 1 and time interval 2. Time interval 1 is used to characterize the time interval of the user's access to APP1; time interval 2 is used to characterize the time interval of the user's access to web page 1.

[0090] It is understandable that the time interval classification parameter includes not only the time interval for purchasing the insurance policy, but also the time interval for the access behavior.

[0091] S202. The server establishes frequency classification parameters according to the number of insurance policies involved in the user's access behavior and the frequency of the original purchase of insurance policies in the behavior information.

[0092] The server uses the behavior information to establish frequency classification parameters, including establishing frequency classification parameters based on the number of insurance policies involved in the user's access behavior in the behavior information and the frequency of the original purchase of insurance policies.

[0093] Then, the number of insurance policies involved in the user's access behavior can be used as a frequency classification parameter. In other words, the frequency classification parameters include: the number of insurance policies purchased in a preset period, the ratio of the number of insurance policies purchased in a preset period to the total number of insurance policies purchased by the user, the ratio of the total number of insurance policies purchased by the user to the average total number of insurance policies purchased by all users, and the number of insurance policies involved in the user's access behavior.

[0094] In an embodiment of the present invention, the number of insurance policies involved in the user's access behavior includes the number of visited pages. As an example, a user visits insurance page 1, insurance page 2, and insurance page 3 through an APP. Insurance page 1 involves auto insurance, insurance page 2 involves auto insurance, and insurance page 3 involves life insurance, then the number of insurance policies involved in the user's access behavior is 3. It can be seen that the visited page involves insurance, and if the visited page does not involve insurance, there is no need to record the number of insurance policies. Specifically, the web pages in the preset APP and / or preset website can be preset as insurance pages.

[0095] S203. The server establishes payment amount classification parameters according to the policy amount and original payment amount involved in the user's access behavior in the behavior information.

[0096] The server uses the behavior information to establish payment amount classification parameters, including establishing payment amount classification parameters based on the policy amount and original payment amount involved in the user's access behavior in the behavior information.

[0097] Then, the insurance policy amount involved in the user's access behavior can be used as a payment amount classification parameter. That is, the payment amount classification parameter includes: the payment amount within a preset period, the ratio of the payment amount within the preset period to the user's total payment amount, the ratio of the user's total payment amount to the average total payment amount of all users, and the insurance policy amount involved in the user's access behavior.

[0098] In an embodiment of the present invention, the insurance policy amount involved in the user's access behavior specifically includes the insurance policy amount involved in the page accessed by the user. As an example, the user's access behavior includes accessing page 1 and page 2. The user accesses page 1, and page 1 does not involve the insurance policy amount; the user accesses page 2, and the insurance policy amount indicated in page 2 is 10,000 yuan, then the insurance policy amount involved in the user's access behavior is 10,000 yuan.

[0099] In the specific practice process, on the APP or web page, the user can fill in information to obtain the policy amount, and then the policy amount can be recorded on the above APP or web page.

[0100] exist Figure 2 In the embodiment, classification parameters are established according to the user's behavior information, and the steps of establishing the classification parameters are not in any order.

[0101] S103. The server classifies the users into multiple categories based on the time interval classification parameter, the frequency classification parameter, the payment amount classification parameter and the original compensation amount.

[0102] In the embodiment of the present invention, user classification involves time interval classification parameters, frequency classification parameters, payment amount classification parameters and original compensation amount.

[0103] Each of the above parameters has multiple sub-parameters. For example, the time interval classification parameter includes the following interval parameters: the time interval of the most recent insurance policy purchase, the average time interval of insurance policy purchase, and the time interval of user access behavior.

[0104] In the embodiment of the present invention, a weight is set for a sub-parameter of each parameter, that is, a weight is set for each sub-parameter, so as to calculate and obtain a corresponding score.

[0105] See also Figure 3 , Figure 3 The flowchart of classifying users into multiple categories based on classification parameters according to an embodiment of the present invention specifically includes the following steps:

[0106] S301. The server determines a time interval score according to the interval parameter and the weight of the interval parameter in the time interval classification parameter.

[0107] Specifically, the time interval classification parameters include the following interval parameters: the time interval to the most recent purchase of an insurance policy, the average time interval to purchase an insurance policy, and the time interval of user access behaviors.

[0108] The server presets the weights of the above interval parameters, namely, the weight of the time interval for the most recent insurance policy purchase, the weight of the average time interval for insurance policy purchases, and the weight of the time interval for user access behaviors.

[0109] The server multiplies the interval parameter by the weight of the interval parameter to determine the time interval score. That is, the server determines the time interval score according to the interval parameter and the weight of the interval parameter in the time interval classification parameter.

[0110] S302: The server determines a frequency score according to the frequency parameters and the weights of the frequency parameters in the frequency classification parameters.

[0111] The frequency classification parameters include the following frequency parameters: the number of times insurance policies are purchased in a preset period, the ratio of the number of times insurance policies are purchased in a preset period to the total number of times users purchase insurance policies, the ratio of the total number of times users purchase insurance policies to the average total number of times all users purchase insurance policies, and the number of insurance policies involved in the user's access behavior.

[0112] The server presets the weights of the above-mentioned frequency parameters, namely, the weight of the preset number of times insurance policies are purchased in a preset period, the weight of the ratio of the preset number of times insurance policies are purchased in the preset period to the total number of times users purchase insurance policies, the weight of the ratio of the total number of times a user purchases insurance policies to the average total number of times all users purchase insurance policies, and the weight of the number of insurance policies involved in the preset user's access behavior.

[0113] The server multiplies the frequency parameter by the weight of the frequency parameter to obtain the frequency score. That is, the server determines the frequency score according to the frequency parameter and the weight of the frequency parameter in the frequency classification parameter.

[0114] S303. The server determines the payment score according to the payment parameters in the payment amount classification parameters and the weights of the payment parameters.

[0115] The payment amount classification parameters include the following payment parameters: the payment amount within a preset period, the ratio of the payment amount within the preset period to the total payment amount of the user, the ratio of the total payment amount of the user to the average total payment amount of all users, and the policy amount involved in the user's access behavior.

[0116] The server presets the weights of payment parameters, namely, the weight of the payment amount within a preset period, the weight of the ratio of the payment amount of the preset period to the total payment amount of the user, the weight of the ratio of the total payment amount of the preset user to the average total payment amount of all users, and the weight of the policy amount involved in the user's access behavior.

[0117] The server multiplies the payment parameter by the weight of the payment parameter to obtain the payment score. That is, the server determines the payment score according to the payment parameter in the payment amount classification parameter and the weight of the payment parameter.

[0118] S304. The server determines the compensation score according to the compensation parameters in the original compensation amount and the weights of the compensation parameters.

[0119] The original compensation amount includes the following compensation parameters: the compensation amount within a preset period, the ratio of the compensation amount within the preset period to the total compensation amount of the user, and the ratio of the total compensation amount of the user to the average total compensation amount of all users.

[0120] The server presets the weights of the compensation parameters, i.e., the weight of the compensation amount within a preset period, the weight of the ratio of the compensation amount within the preset period to the total compensation amount of the user, and the weight of the ratio of the total compensation amount of the preset user to the average total compensation amount of all users.

[0121] The server multiplies the compensation parameter and the weight of the compensation parameter to obtain the compensation score. That is, the server determines the compensation score according to the compensation parameter in the original compensation amount and the weight of the compensation parameter.

[0122] S305. The server divides the users into multiple categories according to the time interval score, frequency score, payment score and compensation score.

[0123] In the embodiment of the present invention, for each user, four scores can be obtained according to the above steps, which are divided into: time interval score, frequency score, payment score and compensation score. That is to say, the user is described from the above four aspects. Furthermore, the user can be divided into multiple categories according to the time interval score, frequency score, payment score and the compensation score.

[0124] As an example, a classification threshold of a preset time interval score, a classification threshold of a preset frequency score, a classification threshold of a preset payment score, and a classification threshold of a preset compensation score.

[0125] Furthermore: the server divides the users into two categories of time interval users according to the time interval score and the classification threshold of the time interval score;

[0126] The server classifies the users into two types of frequency users according to the frequency scores and the classification thresholds of the frequency scores;

[0127] The server classifies the users into two types of payment users according to the payment scores and the classification thresholds of the payment scores;

[0128] The server divides the users into two categories of compensation users according to the compensation scores and the classification thresholds of the compensation scores;

[0129] The server classifies users into multiple categories by combining time interval users, frequency users, payment users, and compensation users.

[0130] It should be noted that the solution in the embodiment of the present invention can be applied to the application (APP) and / or web page of the mobile terminal. In other words, the technical solution in the embodiment of the present invention is implemented through the mobile terminal and / or computer, so as to realize the classification of users involved in the insurance policy. Among them, the server is specifically a mobile terminal and / or a computer.

[0131] In one embodiment of the present invention, the purpose of user classification is to provide targeted services according to different user characteristics.

[0132] As an example, for the category to which the user belongs, the server sends the recommended information of the category to the user. The user can visit the insurance website through the APP or web page to obtain information related to the insurance policy. Then, although the user has not purchased the insurance policy at present, based on the time interval of the user's original purchase of the insurance policy, the frequency of the original purchase of the insurance policy, the original payment amount, the original compensation amount, and the behavior information, the recommended information can be sent according to the user classification to improve the pertinence of the recommended information.

[0133] In addition, in order to help the insurance agent understand the user and improve the pertinence of the service, the server pushes the user's category and / or recommendation information of the category to which the user belongs to the insurance agent.

[0134] In one embodiment of the present invention, the user includes multiple members of a family. It is understandable that the classification of the family is implemented based on the family as a unit, and then the recommendation information is sent to the members of the family. This is because the insurance policy includes three roles: the insured, the insured, and the beneficiary. In a family, different family members are divided into the insured, the insured, and the beneficiary. For family insurance policies, if one user is used as the classification object, the insurance policy information is less; while if one family is used as the classification object, the accuracy of user classification can be improved due to the increase of insurance policy information.

[0135] Specifically, in the case where the user includes multiple family members, the time interval for the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy, the original payment amount and the original compensation amount are determined based on the insurance policy information of the multiple family members. That is, based on the insurance policy information of the multiple members, the time interval for the original purchase of the insurance policy of the multiple members, the frequency of the original purchase of the insurance policy of the multiple members, the original payment amount and the original compensation amount of the multiple members are determined. In other words, the multiple family members are considered as a whole.

[0136] Accordingly, the user's behavior information includes the behavior information of the multiple members.

[0137] In the above embodiment, the server determines the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy, the original payment amount and the original compensation amount based on the user's insurance policy information; the server establishes the time interval classification parameter, the frequency classification parameter and the payment amount classification parameter according to the user's behavior information, combined with the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy and the original payment amount; the server classifies the user into multiple categories based on the time interval classification parameter, the frequency classification parameter and the payment amount classification parameter. Establishing classification parameters based on the user's behavior information can improve the accuracy of classification by classifying users based on the established classification parameters, because the behavior information can represent the user's recent actual behavior.

[0138] The following is an illustrative description with reference to specific embodiments.

[0139] See also Figure 4 , Figure 4 It is a schematic diagram of information of an original purchased insurance policy according to an embodiment of the present invention. Figure 4 The parameters in are divided into four groups: R, F, M, and C. R represents the time interval of the original purchase of the policy, F represents the frequency of the original purchase of the policy, M represents the original payment amount, and C represents the original compensation amount.

[0140] From the four dimensions of R, F, M and C, multiple indicators are selected in each dimension to calculate the score. And each indicator is weighted and summed to obtain the total score of the four dimensions. In one embodiment of the present invention, the weight w can be obtained by using the entropy method.

[0141]

[0142] After calculating the scores of the four dimensions through weighted summation, the classification threshold is selected according to the data distribution, and the A / B grade is divided into two categories, with A being good and B being relatively bad.

[0143] Afterwards, by analyzing each user group based on the user portrait, we can get the characteristics of each user. Combined with the scores on the four dimensions of the user grouping, we can name and score the importance of each user group.

[0144] See Table 1, which is a user classification table based on the actual user's insurance policy information. In theory, users can be divided into 16 categories. In the above practical application, users are divided into 12 categories.

[0145] Table 1

[0146]

[0147]

[0148] Table 1 includes 12 categories of users. A category name is set for each category of users, and the importance is evaluated in the form of scoring. Each category of users has a corresponding strategy.

[0149] See also Figure 5 , Figure 5 is an information schematic diagram of determining user classification using behavior information according to an embodiment of the present invention. Figure 4 In addition to the indicators under the four dimensions of R, F, M and C, three indicators R3, F4 and M4 are added. Among them, the three indicators R3, F4 and M4 are indicators added based on the user's behavior information. In addition, users can also include multiple members in the family, that is, classification is considered from the perspective of the family.

[0150] It should be noted that, in addition to using the entropy method to preliminarily determine the weights of each parameter, the weights determined above can also be fine-tuned based on empirical values.

[0151] Analyzing the insurance policy and behavior information from the perspective of the family can better reflect the family's interest in insurance products and changes in interest. In addition, in order to obtain family relationships in real time, family relationships, i.e., relationships between family members, can also be stored in a relational database and / or a graph database.

[0152] By applying the technical solution in the embodiment of the present invention, after classifying the users, two types of high-value sleep users can be screened out, namely: high-value sleep potential users and high-value sleep loyal users. Afterwards, we will work with the business department to explain the characteristics of such users, so as to facilitate the design of solutions to promote them to insurance agents.

[0153] Since most of these users are historical users who have not purchased insurance from the company in recent years and may have lost contact with their previous insurance agents, external assistance is needed to retrieve the lost users. At the same time, because they are all historical old users, it is necessary to review the insurance products sold that year so that insurance agents can be fully prepared before communicating with users. Therefore, we extracted the historical insurance products purchased by this batch of users, selected the insurance products with the highest number, and organized insurance agents to learn.

[0154] When insurance agents start visiting users, they need to provide conversion rate reports for these insurance agents and users, so that the management team can track the conversion effect and provide supervision. Currently, only some branches have been selected for the pilot project, which has converted 88 million yuan in premiums, with significant results.

[0155] In the embodiment of the present invention, the problem of low differentiation caused by only using sparse policy purchase and claim settlement behaviors to describe each dimension is solved. Using user behavior information can more comprehensively display the characteristics of users, and the grouping can also be closer to the users.

[0156] After adding family relationship and behavior information, the calculation of user scores in various dimensions becomes more diversified, not limited to sparse values, and the differences between users become larger, which is also convenient for refined classification. After adding more behavior information, users can be distinguished by their interactions on the APP and / or web pages: some users only purchase one insurance product, but browse other products on the official website many times, check their own insurance policy information, etc. The solution in the embodiment of the present invention can capture the above behavior information and show it in the F value.

[0157] In the above embodiments of the present invention, it can be applied to the management of users during the renewal period to help the business department screen out high-value sleep users, such as issuing a list for intervention, thereby improving the conversion of high-value sleep users.

[0158] In addition to the above-mentioned embodiments of the present invention, business strategies can be set for the overall customers, and different types of users can be grouped for management. Different strategies can be adopted for each group of users, and existing users can be deeply explored, with a focus on intervening in high-value users, thereby improving the efficiency of intervention.

[0159] Specifically, the channel has accumulated a large number of historical users and cannot intervene in all users. Different types of users are managed in different groups. Different strategies are adopted for each group of users, and existing users are deeply explored and high-value users are intervened to improve the efficiency of intervention.

[0160] As an example, users can be divided into the following categories: loyal high-value users (with / without risk); loyal general users (with / without risk); sleeping loyal high-value users (with / without risk); sleeping general users (with / without risk); sleeping potential high-value users (with / without risk); sleeping worthless users (with / without risk).

[0161] Active users, risky users, and valuable users can also be further merged and divided, and different marketing methods can be adopted for different user groups.

[0162] For example, for loyal general user groups, users have formed certain consumption habits, with high purchase frequency, but low value. Most users are non-high-end customer groups. The company should increase promotion efforts and publicize preferential policies to enhance user value.

[0163] In addition, the business model of each channel is different. Due to the large number of channel users, it is difficult to fully cover and intervene. Users are also one of the pain points of the business. Different strategies are adopted for different customer groups. Specifically:

[0164] (1) Supplementary information

[0165] Although we have a relatively good understanding of the information about users purchasing insurance policies, it is more difficult to perceive the user's behavior information. For example, a user purchased an insurance policy three years ago and is inactive in terms of the policy, but the user's behavior information in the past week includes a large amount of browsing behavior, so the user can be considered an active user.

[0166] In addition, the classification from the family dimension greatly makes up for the fact that insurance policy information is relatively sparse. Since the frequency of purchasing insurance policies is much lower than the frequency of purchasing e-commerce products, the user's family information increases the frequency of behavior and makes up for this shortcoming.

[0167] (2) Large number of users

[0168] New customers, old customers, lost users, returning users, high-value users, potential users. It is difficult to adopt appropriate strategies for different types of users. Unified classification of users can better intervene. For example: only send SMS reminders to some users, focus on intervention when there are major discounts for certain customer groups, intervene when there are equity activities for certain customer groups, and frequently intervene and visit certain customer groups.

[0169] By adopting the solution in the embodiment of the present invention, the problem of users' scores being too homogeneous and difficult to distinguish in a certain dimension will no longer occur. The behavior information of users is diverse and the values ​​are relatively continuous, which is different from variables with sparse values ​​such as the number of insurance policies purchased. Therefore, it provides help for subsequent user classification.

[0170] See also Figure 6 , Figure 6 is a schematic diagram of the main structure of a user classification device according to an embodiment of the present invention. The user classification device can implement a user classification method, such as Figure 6 As shown, the user classification device specifically includes:

[0171] The insurance policy module 601 is used to determine the time interval of the original insurance policy purchase, the frequency of the original insurance policy purchase, the original payment amount and the original compensation amount based on the user's insurance policy information;

[0172] Establishing module 602, for establishing time interval classification parameters, frequency classification parameters and payment amount classification parameters according to the user's behavior information, combined with the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy and the original payment amount;

[0173] The classification module 603 is used to classify users into multiple categories based on the time interval classification parameter, the frequency classification parameter, the payment amount classification parameter and the original compensation amount.

[0174] In one embodiment of the present invention, the user includes multiple members of a family;

[0175] Establishing module 602, specifically for determining the time interval of original purchase of insurance policies of the multiple members, the frequency of original purchase of insurance policies of the multiple members, the original payment amount and the original compensation amount of the multiple members based on the insurance policy information of the multiple members;

[0176] The user's behavior information includes behavior information of the multiple members.

[0177] In one embodiment of the present invention, the time interval of the original purchase of the insurance policy includes: the time interval of the most recent purchase of the insurance policy and the average time interval of the purchase of the insurance policy;

[0178] The frequency of original policy purchases includes: the number of policy purchases in a preset period, the ratio of the number of policy purchases in a preset period to the total number of policy purchases by the user, and the ratio of the total number of policy purchases by the user to the average total number of policy purchases by all users;

[0179] The original payment amount includes: the payment amount within a preset period, the ratio of the payment amount within the preset period to the total payment amount of the user, and the ratio of the total payment amount of the user to the average total payment amount of all users;

[0180] The original compensation amount includes: the compensation amount within a preset period, the ratio of the compensation amount within the preset period to the total compensation amount of the user, and the ratio of the total compensation amount of the user to the average total compensation amount of all users.

[0181] In one embodiment of the present invention, the establishing module 602 is specifically used to establish a time interval classification parameter according to the time interval of the user's access behavior in the behavior information and the time interval of the original purchase of the insurance policy;

[0182] Establishing the frequency classification parameter according to the number of insurance policies involved in the user's access behavior in the behavior information and the frequency of the original purchase of insurance policies;

[0183] The payment amount classification parameter is established based on the policy amount involved in the user access behavior in the behavior information and the original payment amount.

[0184] In one embodiment of the present invention, the user's behavior information includes searching and / or browsing insurance-related information, and the insurance-related information is determined by multiple keywords.

[0185] In one embodiment of the present invention, the classification module 603 is specifically configured to determine the time interval score according to the interval parameter in the time interval classification parameter and the weight of the interval parameter;

[0186] Determining a frequency score according to the frequency parameters in the frequency classification parameters and the weights of the frequency parameters;

[0187] Determining a payment score according to the payment parameter in the payment amount classification parameter and the weight of the payment parameter;

[0188] Determining the compensation score according to the compensation parameters in the original compensation amount and the weights of the compensation parameters;

[0189] Users are classified into a plurality of categories according to the time interval score, the frequency score, the payment score and the compensation score.

[0190] In one embodiment of the present invention, the classification model 603 is further used to send recommendation information of the category to which the user belongs to the user;

[0191] and / or,

[0192] Push the category of the user and / or recommendation information of the category to which the user belongs to to the insurance agent.

[0193] Figure 7 An exemplary system architecture 700 is shown to which the method for user classification or the apparatus for user classification according to the embodiment of the present invention can be applied.

[0194] like Figure 7 As shown, system architecture 700 may include terminal devices 701, 702, 703, network 704 and server 705. Network 704 is used to provide a medium for communication links between terminal devices 701, 702, 703 and server 705. Network 704 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0195] Users can use terminal devices 701, 702, and 703 to interact with server 705 through network 704 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 701, 702, and 703, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).

[0196] The terminal devices 701 , 702 , and 703 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0197] The server 705 may be a server that provides various services, such as a backend management server (only for example) that supports shopping websites browsed by users using the terminal devices 701, 702, and 703. The backend management server may analyze and process the received data such as product information query requests, and feed back the processing results (such as target push information, product information - only for example) to the terminal device.

[0198] It should be noted that the user classification method provided in the embodiment of the present invention is generally executed by the server 705 , and accordingly, the user classification device is generally set in the server 705 .

[0199] It should be understood that Figure 7 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0200] Reference below Figure 8 , which shows a schematic diagram of the structure of a computer system 800 of a terminal device suitable for implementing an embodiment of the present invention. Figure 8 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0201] like Figure 8 As shown, the computer system 800 includes a central processing unit (CPU) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage part 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the system 800 are also stored. The CPU 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0202] The following components are connected to the I / O interface 805: an input section 806 including a keyboard, a mouse, etc.; an output section 807 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN card, a modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 810 as needed, so that a computer program read therefrom is installed into the storage section 808 as needed.

[0203] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 809, and / or installed from the removable medium 811. When the computer program is executed by the central processing unit (CPU) 801, the above-mentioned functions defined in the system of the present invention are executed.

[0204] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0205] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0206] The modules involved in the embodiments of the present invention may be implemented in software or hardware. The modules described may also be set in a processor, for example, it may be described as: a processor includes a policy module, a creation module and a classification module. The names of these modules do not constitute a limitation on the modules themselves in some cases, for example, the policy module may also be described as "used to determine the time interval for the original purchase of the policy, the frequency of the original purchase of the policy, the original payment amount and the original compensation amount based on the user's policy information".

[0207] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes:

[0208] The server determines the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy, the original payment amount and the original compensation amount based on the insurance policy information of the user;

[0209] The server establishes a time interval classification parameter, a frequency classification parameter and a payment amount classification parameter according to the user's behavior information, combined with the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy and the original payment amount;

[0210] The server classifies users into a plurality of categories based on the time interval classification parameter, the frequency classification parameter, the payment amount classification parameter and the original compensation amount.

[0211] According to the technical solution of the embodiment of the present invention, the server determines the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy, the original payment amount and the original compensation amount based on the user's insurance policy information; the server establishes time interval classification parameters, frequency classification parameters and payment amount classification parameters according to the user's behavior information, combined with the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy and the original payment amount; the server divides the user into multiple categories based on the time interval classification parameters, the frequency classification parameters, the payment amount classification parameters and the original compensation amount. The user's behavior information is combined with the parameters of the original purchase of the insurance policy. Since the behavior information can represent the user's actual recent behavior, the user is classified by the established parameters, which can improve the accuracy of the classification.

[0212] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for user classification, characterized in that: include: The server determines the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy, the original payment amount and the original compensation amount based on the insurance policy information of the user; The server establishes a time interval classification parameter, a frequency classification parameter and a payment amount classification parameter according to the user's behavior information, in combination with the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy and the original payment amount; the user's behavior information includes searching and / or browsing information related to insurance, and the insurance-related information is determined by multiple keywords; The server classifies the users into a plurality of categories based on the time interval classification parameter, the frequency classification parameter, the payment amount classification parameter and the original compensation amount; The server establishes a time interval classification parameter, a frequency classification parameter and a payment amount classification parameter according to the user's behavior information, in combination with the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy and the original payment amount, including: The server establishes a time interval classification parameter according to the time interval of the user's access behavior in the behavior information and the time interval of the original purchase of the insurance policy; the time interval of the user's access behavior is the time interval of the user searching and / or browsing insurance-related information; The server establishes the frequency classification parameter according to the number of insurance policies involved in the user's access behavior in the behavior information and the frequency of the original purchase of insurance policies; The server establishes the payment amount classification parameter according to the policy amount involved in the user access behavior in the behavior information and the original payment amount.

2. The method for user classification according to claim 1, characterized in that: The users include multiple members of a family; The server determines the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy, the original payment amount and the original compensation amount based on the insurance policy information of the user, including: The server determines, based on the policy information of the multiple members, the time intervals for originally purchasing the policies of the multiple members, the frequencies for originally purchasing the policies of the multiple members, the original payment amounts and the original compensation amounts of the multiple members; The user's behavior information includes behavior information of the multiple members.

3. The method for user classification according to claim 1, characterized in that: The time interval for originally purchasing insurance policies includes: the time interval for the most recent insurance policy purchase and the average time interval for purchasing insurance policies; The frequency of original policy purchases includes: the number of policy purchases in a preset period, the ratio of the number of policy purchases in a preset period to the total number of policy purchases by the user, and the ratio of the total number of policy purchases by the user to the average total number of policy purchases by all users; The original payment amount includes: the payment amount within a preset period, the ratio of the payment amount within the preset period to the total payment amount of the user, and the ratio of the total payment amount of the user to the average total payment amount of all users; The original compensation amount includes: the compensation amount within a preset period, the ratio of the compensation amount within the preset period to the total compensation amount of the user, and the ratio of the total compensation amount of the user to the average total compensation amount of all users.

4. The method for user classification according to claim 1, characterized in that: The server classifies the users into multiple categories based on the time interval classification parameter, the frequency classification parameter, the payment amount classification parameter and the original compensation amount, including: The server determines a time interval score according to the interval parameter in the time interval classification parameter and the weight of the interval parameter; The server determines a frequency score according to the frequency parameter in the frequency classification parameter and the weight of the frequency parameter; The server determines the payment score according to the payment parameter in the payment amount classification parameter and the weight of the payment parameter; The server determines the compensation score according to the compensation parameter in the original compensation amount and the weight of the compensation parameter; The server classifies users into multiple categories according to the time interval score, the frequency score, the payment score and the compensation score.

5. The method for user classification according to claim 1, characterized in that: After the users are divided into multiple categories, the method further includes: The server sends recommendation information of the category to which the user belongs to the user; and / or, The server pushes recommendation information of the category of the user and / or the category to which the user belongs to to the insurance agent.

6. A user classification device, characterized in that: include: The insurance policy module is used to determine the time interval of the original insurance policy purchase, the frequency of the original insurance policy purchase, the original payment amount and the original compensation amount based on the user's insurance policy information; An updating module is used to establish a time interval classification parameter, a frequency classification parameter and a payment amount classification parameter according to the user's behavior information, in combination with the time interval of the original purchase of the insurance policy, the frequency of the original purchase of the insurance policy and the original payment amount; and the server establishes the time interval classification parameter according to the time interval of the user's access behavior in the behavior information and the time interval of the original purchase of the insurance policy; the server establishes the frequency classification parameter according to the number of insurance policies involved in the user's access behavior in the behavior information and the frequency of the original purchase of the insurance policy; the server establishes the payment amount classification parameter according to the policy amount involved in the user's access behavior in the behavior information and the original payment amount; the user's behavior information includes searching and / or browsing information related to insurance, and the information related to insurance is determined by multiple keywords; the time interval of the user's access behavior is the time interval of the user searching and / or browsing information related to insurance; The classification module is used to classify users into multiple categories based on the time interval classification parameter, the frequency classification parameter, the payment amount classification parameter and the original compensation amount.

7. An electronic device for user classification, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 5.

8. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images