Method and related products for configuring insurance demand based on prediction model

Abstract

The present application discloses a method for configuring insurance demand based on a prediction model and related products, the method is applied to electronic devices, the method comprising: obtaining comprehensive information of any user from a user database of an insurance company; inputting the comprehensive information of the user into a pre-trained health prediction model to obtain a health score of the user; inputting the health score into an insurance database of the insurance company, configuring insurance demand corresponding to the health score in the insurance database; and sending the insurance demand to a terminal device of the user. The embodiments of the present application are conducive to improving the success rate of insurance marketing.

Description

Technical Field

[0001] The present application relates to the field of electronic technology, and in particular to a method for configuring insurance demand based on a prediction model and related products. Background Art

[0002] With the development of economy and the improvement of people's living standards, insurance services, a special "commodity", like most commodities, have bid farewell to the era of shortage. Fierce market competition has begun. The previous marketing ideas that focused on "production" and "providing" products can no longer adapt to the changing business environment of the times. Market sales, as a new theory and method of business management, has gradually attracted the attention of the insurance industry and has been introduced into this new field.

[0003] At present, various insurance companies have felt the pressure of market competition and have tried their best to actively recommend insurance services to users from the aspects of business diversification (group operations such as property insurance, life insurance, and investment), channel diversification (for example, expanding institutional networks, vigorously developing agents, bank insurance, and online marketing), and modern means (for example, TV advertising, public welfare activities, and the Internet).

[0004] At present, the method of recommending insurance services to users is blind, not targeted and has a low success rate. Summary of the invention

[0005] The embodiments of the present application provide a method and related products for configuring insurance needs based on a predictive model, in order to match insurance needs that are suitable for the user in the insurance database based on the user's comprehensive information, thereby improving the success rate of reimbursement marketing.

[0006] In a first aspect, an embodiment of the present application provides a method for configuring insurance demand based on a prediction model, the method comprising:

[0007] Obtain comprehensive information of any user from the insurance company's user database;

[0008] Inputting the comprehensive information of the user into a pre-trained health prediction model to obtain a health score for the user;

[0009] inputting the health score into an insurance database of the insurance company, and configuring insurance requirements corresponding to the health score in the insurance database;

[0010] The insurance demand is sent to the terminal device of the user.

[0011] In a second aspect, an embodiment of the present application provides a device for configuring insurance demand based on a prediction model, the device comprising:

[0012] An acquisition unit, used for acquiring comprehensive information of any user from a user database of the insurance company;

[0013] An input unit, used to input the comprehensive information of the user into a pre-trained health prediction model to obtain a health score for the user;

[0014] a configuration unit, configured to input the health score into an insurance database of the insurance company, and configure insurance requirements corresponding to the health score in the insurance database;

[0015] A sending unit is used to send the insurance demand to the terminal device of the user.

[0016] In a third aspect, an embodiment of the present application provides an electronic device, comprising one or more processors, one or more memories, one or more transceivers, and one or more programs, wherein the one or more programs are stored in the memories and are configured to be executed by the one or more processors, and the programs include instructions for executing the steps in the method described in the first aspect.

[0017] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the method described in the first aspect.

[0018] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer is operable to cause the computer to execute the method described in the first aspect.

[0019] Implementing the embodiments of the present application has the following beneficial effects:

[0020] It can be seen that in the embodiment of the present application, comprehensive information of any user is obtained from the user database of the insurance company, a health score corresponding to the comprehensive information of the user is obtained based on the health prediction model, and then the insurance demand corresponding to the health score is configured in the insurance database, and the insurance demand of the user is determined based on the health score, so that the configured insurance demand is targeted to the user, and the insurance demand is sent to the user's terminal device, thereby improving the success rate of recommending insurance needs and improving the persuasiveness of insurance marketing. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 A flowchart of a method for configuring insurance demand based on a prediction model provided in an embodiment of the present application;

[0023] Figure 1A A schematic diagram of a process of training a health prediction model to obtain a preset trained health prediction model provided in an embodiment of the present application;

[0024] Figure 1B A schematic diagram of configuring insurance requirements corresponding to user health scores provided in an embodiment of the present application;

[0025] Figure 2 A flowchart of another method for configuring insurance demand based on a prediction model provided in an embodiment of the present application;

[0026] Figure 3 A flowchart of another method for configuring insurance demand based on a prediction model provided in an embodiment of the present application;

[0027] Figure 4 A schematic diagram of the structure of a device for configuring insurance demand based on a prediction model provided in an embodiment of the present application;

[0028] Figure 5 It is a block diagram of the functional units of a device for configuring insurance needs based on a prediction model provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0030] The terms "first", "second", "third" and "fourth" etc. in the specification and claims of the present application and the drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0031] Reference to "embodiments" herein means that a particular feature, result, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0032] The electronic devices in this application may include smart phones (such as Android phones, iOS phones, Windows Phone phones, etc.), tablet computers, PDAs, laptops, mobile Internet devices MID (Mobile Internet Devices, MID for short) or wearable devices, etc. The above electronic devices are only examples, not exhaustive, and include but are not limited to the above electronic devices. For the convenience of description, the above electronic devices are referred to as user equipment UE (User equipment, UE for short) in the following embodiments. Of course, in actual applications, the above user equipment is not limited to the above realization forms, for example, it can also include: smart vehicle terminals, computer equipment, etc.

[0033] See also Figure 1 , Figure 1 A flowchart of a method for configuring insurance demand based on a prediction model provided in an embodiment of the present application is provided. The method is applied to an electronic device. The method includes the contents shown in steps S101 to S104:

[0034] Step S101: Obtain comprehensive information of any user from the user database of the insurance company.

[0035] Optionally, the user's comprehensive information may come from comprehensive information that is pre-entered into the insurance company's user database or comprehensive information that is temporarily entered into the user database.

[0036] Optionally, before retrieving the comprehensive information of any user from the user database of the insurance company, the insurance push platform first obtains access rights, and retrieves the comprehensive information of the user after access is allowed.

[0037] Among them, the user's comprehensive information specifically includes: the user's demographic information and the user's medical information. The demographic information specifically includes: personal information, insurance information, claims information, eating habits information, behavioral habits information. The personal information includes the user's gender, age, occupation, place of residence, family structure information, etc.; the insurance information includes information on insurance products that the user has purchased from an insurance company, etc.; the claims information includes information on diseases for which the user has already made claims from an insurance company; the eating habits information includes information on sleep, smoking, drinking, and the amount of fruits and vegetables consumed, etc.; the behavioral habits information includes exercise information, etc.; the medical information specifically includes: physical examination information and medical history information.

[0038] Step S102: input the comprehensive information of the user into a pre-trained health prediction model to obtain a health score of the user.

[0039] Among them, the health score can be 50, 60, 70, 80 or other values.

[0040] Optionally, obtaining the health score of the user specifically includes: extracting characteristic information from the demographic information used to calculate the health score, such as exercise information and eating habit information; inputting the characteristic information as input data into a pre-trained health prediction model, and outputting a first health score corresponding to the characteristic information at the output end of the pre-trained health prediction model.

[0041] Optionally, the health prediction model needs to be trained first to obtain a preset trained health prediction model. The training process is as follows: Figure 1A The content shown in:

[0042] Step 10: Obtain a preset number (e.g., 5000) of information samples from the database of the health center, each of which includes the user's demographic information, the user's identification information (e.g., ID card number, mobile phone number), and the health score result of the user based on the user's demographic information;

[0043] Step 11: Divide the acquired preset number of information samples into a training set of a first proportion (e.g., 80%) and a test set of a second proportion (e.g., 20%);

[0044] Step 12: Use the demographic information of each user in the training set to train a predetermined health prediction model to obtain a preset trained health prediction model, and use the demographic information of each user in the test set to test the preset trained health prediction model. If the test passes, the training ends. If the test fails, increase the number of information samples from the database of the health center, and re-execute steps 11 and 12.

[0045] Optionally, testing the preset trained health prediction model using the demographic information of each user in the test set specifically includes: using the preset trained health prediction model to analyze the demographic information of each user in the test set to obtain a health score for each user; using the identification information of each user to query the health score of each user in the database of the health center, and determining the difference between the health score obtained using the preset trained health prediction model and the health score of the health center to obtain an accuracy test result of the preset trained health prediction model, the output result of which is binary data, i.e., binary data of 0 and 1, 0 represents that the accuracy test result is wrong, and 1 represents The accuracy test result of the table is correct, specifically, if the difference falls within the preset interval [-a, a], the accuracy test result is 1, if the difference falls outside the preset interval [-a, a], the accuracy test result is 0, determine the percentage of the accuracy test result of 1 in all accuracy test results, if the percentage is greater than the percentage threshold (for example, 80%), then it is determined that the test of the preset trained health prediction model has passed, or, if the percentage is less than or equal to the percentage threshold, it is determined that the test of the preset trained health prediction model has failed, and the number of information samples needs to be increased from the database of the health center, and steps 11 and 12 are re-executed.

[0046] Furthermore, after obtaining the first health score of the user, the medical information in the comprehensive information is extracted, and the medical information is processed to obtain the probability of a serious illness corresponding to the medical information, and the probability of a serious illness is input into the output end of the preset trained health prediction model, and the first health score is adjusted to obtain the health score of the user. Wherein, obtaining the probability of a serious illness corresponding to the medical information specifically includes: comparing the medical information with the disease sample database to determine multiple disease influencing factors that affect the disease in the medical information; extracting the autoregressive coefficient of each of the multiple disease influencing factors from the disease sample database; and calculating the probability of a serious illness corresponding to the medical information according to the serious illness probability calculation formula, the disease influencing factor and the autoregressive coefficient.

[0047] in,

[0048] Where P is the probability of serious illness of the user, X i is the value of the i-th disease influencing factor in the medical information, β i is the autoregression coefficient of the i-th disease influencing factor, is the average value of the i-th disease influencing factor in the disease sample database, S0(t) is the survival rate of the population suffering from the disease related to the i-th disease influencing factor in the disease sample database at time t, t is the time when the comprehensive information of the user is input, and n is the total number of disease influencing factors.

[0049] Optionally, the probability of serious illness is input into the output end of the preset trained health prediction model, and the first health score is adjusted to obtain the health score of the user, including: increasing or decreasing the first health score accordingly based on the probability of serious illness, because the probability of serious illness is an important criterion for measuring the user's physical health. Therefore, the probability of serious illness can be used as a compensation value for the health score, so the user's health score = first health score + compensation value. When the probability of serious illness is too high, the corresponding compensation value is a negative value. Specifically, when the probability of serious illness is in the first probability interval [0, P1], the corresponding compensation value is σ1, when the probability of serious illness is in the second probability interval [P1, P2], the corresponding compensation value is σ2, and when the probability of serious illness is in the third probability interval [P2, 1], the corresponding compensation value is σ3, σ1>σ2>σ3, among which, of course, more probability intervals can be divided, and the three probability intervals here are only examples and are not the only limitation.

[0050] For example, if the first health score is 90 and the probability of serious illness is 0<P<P1, the user's health score can be obtained as (90+σ1).

[0051] Step S103: input the health score into the insurance database of the insurance company, and configure the insurance demand corresponding to the health score in the insurance database.

[0052] Optionally, the insurance type corresponding to the health score is matched in the insurance database of the insurance company according to the mapping relationship between the health score and the insurance type; the pre-set claim ratio of the insurance type is adjusted according to the health score to obtain the claim ratio of the user for the insurance type; the economic information of the user is extracted from the comprehensive information of the user, and the insured amount of the insurance type is determined according to the economic information; and the insurance needs of the user are configured according to the insurance type, claim ratio and insured amount.

[0053] It is understandable that in the contracts of existing insurance companies, insurance types and claim ratios appear in pairs and are all pre-set. In this application, after the insurance type is determined, the pre-set claim ratio is dynamically adjusted according to the health score. This is because the user's future health status can be predicted based on the health score. If the user's current health score is high, a higher claim ratio can be set. Since the user's probability of illness is low, the user can obtain a higher claim ratio if he or she becomes ill. Therefore, by dynamically adjusting the claim ratio, the user's enthusiasm for insurance can be stimulated, further improving the success rate of insurance marketing.

[0054] Optionally, a first mapping relationship between the health score, insurance type, and claim ratio is established in advance, and the insurance type and claim ratio corresponding to the user's health score can be determined based on the mapping relationship. Then, a second mapping relationship between economic information and the insured amount is established in advance to obtain the insurance type, claim ratio, and insured amount corresponding to the user's health score, and the user's insurance policy information, i.e., insurance demand, is generated based on the insurance type, claim ratio, and insured amount.

[0055] For example, Figure 1B An example is shown of a schematic diagram of configuring the insurance requirements corresponding to the user health score, Figure 1B The left side shows an example of the first mapping relationship between health score, insurance type, and claim ratio. Figure 1B The second mapping relationship between economic information and insurance coverage is shown on the right. Figure 1B The user's insurance needs can be determined.

[0056] Of course, after obtaining the insurance type, the insurance information of the user can be queried in the insurance database based on the identification information of the user to inquire whether the insurance type has been insured in the insurance information of the user. If so, extract the insurance amount that has been invested in the insurance type from the insurance information to determine whether the invested insurance amount matches the above insurance amount. If not, the insurance policy information in the insurance information can be used as a standard to increase the insurance amount for the user, generate new policy information, and mark the policy information as the insurance need of the user.

[0057] Step S104: Send the insurance demand to the user's terminal device.

[0058] Optionally, the number of the user's terminal device is queried in a user database, and the insurance demand is sent to the terminal device of the number.

[0059] It can be seen that in the embodiment of the present application, the comprehensive information of any user is obtained from the user database of the insurance company, the demographic information in the comprehensive information is extracted, the demographic information is input into the health prediction model to obtain the first health score of the user, the medical information in the comprehensive information is processed to obtain the probability of serious illness of the user, the first health score is adjusted according to the probability of serious illness, and the health score of the user is obtained. Therefore, adjusting the health score according to the probability of serious illness makes the health score of the user more objective and more accurate, and then the insurance type corresponding to the health score is configured in the insurance database in the insurance database, and the insurance type of the user is determined according to the health score, so that the configured insurance type is more targeted to the user. Finally, the insurance amount of the user is determined in combination with the economic information of the user, and the insurance demand of the user is configured. The insurance demand configured according to the insurance amount is more in line with the needs of the user and is more targeted. Therefore, sending the insurance demand to the user's terminal device can improve the success rate of recommending insurance needs and improve the persuasiveness of insurance marketing.

[0060] In a possible example, cluster analysis is performed on the comprehensive information of users in the user database of the insurance company to obtain multiple families of users, and a first-level family portrait tag is established for multiple users in each family. The cluster analysis is performed based on the basic information of the user. After configuring the insurance needs of any user, the family tag of the user is parsed, and the insurance needs are simultaneously pushed to the terminal devices of multiple users belonging to the same family tag. It can be seen that in this example, by establishing a family portrait tag, insurance needs are pushed to users with the same needs simultaneously, thereby improving the efficiency of reimbursement marketing.

[0061] See also Figure 2 , Figure 2 A flowchart of another method for configuring insurance demand based on a prediction model provided in an embodiment of the present application is provided. The method is applied to an electronic device. The method includes the contents shown in steps S201 to S207:

[0062] Step S201: Establish an online insurance system.

[0063] Optionally, when the insurance push platform establishes an online insurance system, the pre-trained health prediction model is embedded in a hardware device supporting the online insurance system. The hardware device supporting the online insurance system maintains a communication connection with the user database of the insurance company to retrieve data from the user database.

[0064] Step S202: receiving comprehensive information input by any user in the user information input interface of the online insurance system.

[0065] Optionally, the online insurance system has multiple functional interfaces, such as a style display interface, a manual service interface, a user information input interface, a health score details interface, and the like.

[0066] Step S203: input the comprehensive information into the preset trained health prediction model to obtain the health score of the user.

[0067] Step S204: calling the insurance database of the insurance company, and configuring the insurance needs of the user in the database of the insurance company according to the health score.

[0068] Step S205: displaying the insurance demand on the web page interface of the online insurance system.

[0069] Optionally, the insurance demand is displayed on the web page interface in the form of text, or in the form of an image, or in the form of text and graphics.

[0070] Step S206: determining whether a preset operation is detected in the web page interface;

[0071] If yes, execute step S207;

[0072] If not, return to step S202.

[0073] Optionally, determining whether a preset operation is detected in the web page interface specifically includes: determining whether a click operation for a link button for detailed information is detected at the bottom of the web page interface, or whether the browsing time of the user on the web page interface is greater than a first threshold, wherein determining the browsing time of the user on the web page interface specifically includes: starting timing with the moment when the web page interface is displayed as the starting moment, detecting the moment when a data packet for closing the page is sent to the online system, taking the moment as the ending moment, and taking the time interval between the starting moment and the ending moment as the browsing time, or whether the user browses from the top to the bottom of the web page interface, or whether the number of times the user browses the web page interface is greater than a second threshold, wherein determining the number of times the user browses the web page interface specifically includes: when logging into the online system, obtaining the MAC address of the terminal device that logs into the online system, saving the MAC address when detecting that the web page interface is loaded, and counting the number of times the MAC address is saved, and taking the number of times the MAC address is saved as the number of times the user browses the web page interface.

[0074] The first threshold may be 3 minutes, 7 minutes, 10 minutes or other values.

[0075] The second threshold may be 5 times, 7 times, 10 times or other values.

[0076] Step S207: determining whether the online insurance application request of the user is received;

[0077] If yes, execute step S208;

[0078] If not, execute step S209.

[0079] Step S208: verify the user's online insurance request, configure the insurance policy information corresponding to the insurance request for the user, and display the insurance policy information on the web page interface for the user to confirm whether the insurance policy information is correct.

[0080] Step S210: Mark the user as an interested user, and send the comprehensive information of the interested user and the insurance requirements configured for the user in the online insurance system to the terminal device of the insurance company.

[0081] It can be seen that in the embodiment of the present application, an online insurance system is established to receive comprehensive information input by any user in the information input interface of the online insurance system, determine the health score of the user based on the comprehensive information, configure insurance requirements for the user based on the health score, and display the insurance requirements on the web page interface of the online insurance system. If the user's online insurance request is not received on the web page interface, the user's click operation on the web page interface is detected. If a preset operation is detected, the user is marked as an interested user, and the user's comprehensive information and the insurance requirements configured for the user by the online insurance system are sent to the terminal device of the insurance company to inform the insurance company that the user is interested in the insurance requirements, so as to delegate professionals to communicate with the user online or offline to improve the success rate of insurance marketing. Since the insurance requirements correspond to the user's health score, the insurance requirements configured in the present application are targeted, which increases the persuasiveness of insurance marketing.

[0082] See also Figure 3 , Figure 3 A flowchart of another method for configuring insurance demand based on a prediction model provided in an embodiment of the present application is provided. The method is applied to an electronic device. The method includes:

[0083] Step S301: Establish an online insurance system.

[0084] Step S302: receiving comprehensive information input by any user in the user information input interface of the online insurance system.

[0085] Step S303: input the comprehensive information into the preset trained health prediction model to obtain the health score of the user.

[0086] Step S304: call the insurance database of the insurance company, and configure the insurance needs of the user in the database of the insurance company according to the health score.

[0087] Step S305: display the insurance demand on the web page interface of the online insurance system.

[0088] Step S306: If a preset operation is detected in the web page interface and no online insurance request from the user is received, the user is marked as an interested user.

[0089] Step S307: Obtain the IP address of the terminal device used by the interested user to log into the online insurance system.

[0090] Optionally, before inputting the comprehensive information of the user, it is necessary to complete registration in the online insurance system. After registration, the online system can be logged in based on the registered account. Each time the terminal device logs in, it is necessary to send a login data packet to the online system. The online system parses the data packet and obtains the login account, login device, login time, and login IP address in the login data packet. When the login data packet is verified to be legal, the terminal device is allowed to log in to the online system, and the IP address is saved in the configuration file of the online insurance system. After determining that the user is an interested user, the IP address of the terminal device is obtained from the configuration file.

[0091] Step S308: Determine the location information of the terminal device according to the IP address.

[0092] Optionally, determining the location information of the terminal device according to the IP address specifically includes: obtaining the IP address type of the IP address. Specifically, the IP address type includes but is not limited to a fixed allocation single center point type (such as a campus of a school), a dynamically allocated single center point type (such as a single cell), a fixed allocation multiple center point type (such as multiple campuses of a school) and a dynamically allocated multiple center point type (such as multiple cells). If the IP address belongs to the fixed allocation single center point type or the dynamically allocated single center point type, the location information corresponding to the IP address is directly queried in the IP address information library. If the IP address belongs to the fixed allocation multiple center point type or the dynamically allocated multiple center point type, the IP address information library is queried for the stop location of the terminal device, and the location information corresponding to the IP address is obtained near the stop location of the terminal device.

[0093] Step S309: query the offline subsidiary insurance company that is closest to the location information among the insurance companies, and send the comprehensive information of the user and the insurance requirements configured for the user in the online insurance system to the terminal device of the offline subsidiary insurance company.

[0094] It can be seen that in the embodiment of the present application, an online insurance system is established, comprehensive information input by any user in the information input interface of the online insurance system is received, the health score of the user is determined based on the comprehensive information, the insurance demand is configured for the user based on the health score, and the insurance demand is displayed on the web page interface of the online insurance system. If the user's online insurance request is not received on the web page interface, the click operation of the user on the web page interface is detected. If a preset operation is detected, the user is marked as an interested user, and the IP address of the terminal device used by the user to log in to the online insurance system is obtained, and the location information of the terminal device is obtained according to the IP address. Then, an offline sub-insurance company of the insurance company closest to the location information is obtained, and the comprehensive information of the user and the insurance demand are sent to the terminal device of the offline sub-insurance company to inform the offline sub-insurance company that the user is interested in the insurance demand, so as to delegate professionals to conduct offline exchanges with the user to improve the success rate of insurance marketing. Since the insurance demand corresponds to the health score of the user, the insurance demand configured in the present application is targeted and increases the persuasiveness of insurance marketing.

[0095] With the above Figure 1 , Figure 2 , Figure 3 For details on the embodiments shown in the drawings, please refer to Figure 4 , Figure 4 A schematic diagram of a device 400 for configuring insurance demand based on a prediction model provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, the device 400 includes a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are different from the one or more application programs, and the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the following steps;

[0096] Obtain comprehensive information of any user from the insurance company's user database;

[0097] Inputting the comprehensive information of the user into a pre-trained health prediction model to obtain a health score of the user;

[0098] inputting the health score into an insurance database of the insurance company, and configuring insurance requirements corresponding to the health score in the insurance database;

[0099] The insurance demand is sent to the terminal device of the user.

[0100] In a possible example, when the comprehensive information includes demographic information and medical information, in inputting the comprehensive information of the user into a pre-trained health prediction model to obtain a health score for the user, the instructions in the above program are specifically used to perform the following operations:

[0101] Extracting characteristic information from the demographic information, inputting the characteristic information as input data into a pre-trained health prediction model, and outputting a first health score corresponding to the characteristic information at an output end of the pre-trained health prediction model;

[0102] Processing the medical information to obtain the probability of a serious illness corresponding to the medical information;

[0103] The critical illness probability is input into the output end of the preset trained health prediction model, the first health score is adjusted, and the health score of the user is obtained.

[0104] In a possible example, in processing the medical information to obtain the probability of a serious illness corresponding to the medical information, the instructions in the above program are specifically used to perform the following operations:

[0105] Comparing the medical information with a disease sample database to determine multiple disease influencing factors in the medical information that have an impact on the disease;

[0106] Extracting the autoregressive coefficient of each disease influencing factor among the multiple disease influencing factors from the disease sample database;

[0107] Calculate the probability of a serious illness corresponding to the medical information according to the serious illness probability calculation formula, disease influencing factors and autoregressive coefficients;

[0108]

[0109] Where P is the probability of serious illness of the user, X i is the value of the i-th disease influencing factor in the medical information, β i is the autoregression coefficient of the i-th disease influencing factor, is the average value of the i-th disease influencing factor in the disease sample database, S0(t) is the survival rate of the population suffering from the disease related to the i-th disease influencing factor in the disease sample database at time t, t is the time when the comprehensive information of the user is input, and n is the total number of disease influencing factors.

[0110] In a possible example, in inputting the health score into the insurance database of the insurance company, and configuring the insurance demand corresponding to the health score in the insurance database, the instructions in the above program are specifically used to perform the following operations:

[0111] Matching the insurance type corresponding to the health score in the insurance database of the insurance company according to the mapping relationship between the health score and the insurance type;

[0112] Adjusting the pre-set claim ratio of the insurance type according to the health score to obtain the claim ratio of the user for the insurance type;

[0113] Extracting the economic information of the user from the comprehensive information of the user, and determining the insured amount of the insurance type according to the economic information;

[0114] The user's insurance needs are configured according to the insurance type, claim ratio and insurance amount.

[0115] In a possible example, the instructions in the above program are also used to perform the following operations:

[0116] Establish an online insurance system;

[0117] Receive comprehensive information input by any user on the user information input interface of the online insurance system, input the comprehensive information into the preset trained health prediction model, obtain the health score of the user, call the insurance database of the insurance company, configure the insurance demand of the user in the database of the insurance company according to the health score, and display the insurance demand on the web page interface of the online insurance system;

[0118] If a preset operation is detected in the web page interface and no online insurance application request from the user is received, marking the user as an interested user;

[0119] The comprehensive information of the interested user and the insurance requirements configured for the user in the online insurance system are sent to the terminal device of the insurance company.

[0120] In a possible example, when a preset operation is detected on the web page interface and no online insurance application request from the user is received, in terms of marking the user as an interested user, the instructions in the above program are specifically used to perform the following operations:

[0121] If a click operation on the link button for detailed information is detected at the bottom of the web page interface, or if it is detected on the web page interface that the browsing time of the user is greater than a first threshold, or if it is detected that the user browses from the top to the bottom of the web page interface, or if it is detected that the number of times the user browses the web page interface is greater than a second threshold, and no online insurance request is received from the user, the user will be marked as an interested user.

[0122] In a possible example, the instructions in the above program are further used to perform the following operations:

[0123] After determining the interested user, obtain the IP address of the terminal device used by the interested user to log into the online insurance system, determine the location information of the terminal device based on the IP address, query the offline sub-insurance company in the insurance company that is closest to the location information, and send the comprehensive information of the user and the insurance requirements configured for the user in the online insurance system to the terminal device of the offline sub-insurance company.

[0124] See also Figure 5 , Figure 5 A possible functional unit composition block diagram of the device 500 for configuring insurance demand based on a prediction model involved in the above embodiment is shown, and the device 500 includes an acquisition unit 510, an input unit 520, a configuration unit 530, and a sending unit 540, wherein;

[0125] An acquisition unit 510 is used to acquire comprehensive information of any user from a user database of an insurance company;

[0126] An input unit 520, used to input the comprehensive information of the user into a pre-trained health prediction model to obtain a health score for the user;

[0127] A configuration unit 530, configured to input the health score into an insurance database of the insurance company, and configure an insurance requirement corresponding to the health score in the insurance database;

[0128] The sending unit 540 is used to send the insurance demand to the terminal device of the user.

[0129] In a possible example, when the comprehensive information includes demographic information and medical information, when the comprehensive information of the user is input into a pre-trained health prediction model to obtain a health score for the user, the input unit 520 is specifically used to: extract feature information from the demographic information, input the feature information as input data into the pre-trained health prediction model, and output a first health score corresponding to the feature information at the output end of the preset trained health prediction model; and process the medical information to obtain the probability of a serious illness corresponding to the medical information; and input the probability of a serious illness into the output end of the preset trained health prediction model, adjust the first health score, and obtain the health score of the user.

[0130] In a possible example, when processing the medical information to obtain the probability of a serious illness corresponding to the medical information, the input unit 520 is specifically used to: compare the medical information with the disease sample database to determine multiple disease influencing factors that affect the disease in the medical information; and to extract the autoregressive coefficient of each disease influencing factor in the multiple disease influencing factors from the disease sample database; and to calculate the probability of a serious illness corresponding to the medical information according to the serious illness probability calculation formula, the disease influencing factor and the autoregressive coefficient;

[0131]

[0132] Where P is the probability of serious illness of the user, X i is the value of the i-th disease influencing factor in the medical information, β i is the autoregression coefficient of the i-th disease influencing factor, is the average value of the i-th disease influencing factor in the disease sample database, S0(t) is the survival rate of the population suffering from the disease related to the i-th disease influencing factor in the disease sample database at time t, t is the time when the comprehensive information of the user is input, and n is the total number of disease influencing factors.

[0133] In a possible example, when the health score is input into the insurance database of the insurance company and the insurance demand corresponding to the health score is configured in the insurance database, the configuration unit 530 is specifically used to: match the insurance type corresponding to the health score in the insurance database of the insurance company according to the mapping relationship between the health score and the insurance type; and to adjust the pre-set claim ratio of the insurance type according to the health score to obtain the claim ratio of the user in terms of the insurance type; and to extract the economic information of the user from the comprehensive information of the user, and determine the insured amount of the insurance type based on the economic information; and to configure the insurance demand of the user according to the insurance type, claim ratio and insured amount.

[0134] In a possible example, the apparatus 500 further includes a processing unit 550;

[0135] Among them, the processing unit 550 is used to: establish an online insurance system; and to receive comprehensive information input by any user in the user information input interface of the online insurance system, input the comprehensive information into the preset trained health prediction model, obtain the health score of the user, call the insurance database of the insurance company, configure the insurance needs of the user in the database of the insurance company according to the health score, and display the insurance needs on the web interface of the online insurance system; and to mark the user as an interested user if a preset operation is detected on the web interface and the online insurance request of the user is not received; and to send the comprehensive information of the interested user and the insurance needs configured for the user in the online insurance system to the terminal device of the insurance company.

[0136] In a possible example, when a preset operation is detected on the web page interface and no online insurance request from the user is received, the user is marked as an interested user, and the processing unit 550 is specifically used to: when a click operation on a link button for detailed information is detected at the bottom of the web page interface, or when it is detected on the web page interface that the browsing time of the user is greater than a first threshold, or when it is detected that the user browses from the top to the bottom of the web page interface, or when it is detected that the number of times the user browses the web page interface is greater than a second threshold, and no online insurance request from the user is received, mark the user as an interested user.

[0137] In a possible example, the processing unit 550 is further used to: after determining the interested user, obtain the IP address of the terminal device used by the interested user to log into the online insurance system, determine the location information of the terminal device based on the IP address, query the offline sub-insurance company in the insurance company that is closest to the location information, and send the comprehensive information of the user and the insurance requirements configured for the user in the online insurance system to the terminal device of the offline sub-insurance company.

[0138] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any method for configuring insurance needs based on a predictive model as recorded in the above method embodiments.

[0139] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any method for configuring insurance needs based on a predictive model as recorded in the above method embodiments.

[0140] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0141] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0142] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0143] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0144] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software program module.

[0145] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0146] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0147] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for configuring insurance demand based on a prediction model, characterized in that: The method comprises: Obtain comprehensive information of any user from the user database of the insurance company. The comprehensive information includes the demographic information and medical information of the user. The demographic information includes: personal information, insurance information, claims information, dietary habits information, and behavioral habits information. Personal information includes the user's gender, age, occupation, place of residence, and family structure information; insurance information includes information on insurance products purchased by the user from the insurance company; claims information includes information on diseases for which the user has made claims from the insurance company; dietary habits information includes information on sleep, smoking, drinking, and the amount of fruits and vegetables consumed; behavioral habits information includes exercise information; medical information includes: physical examination information and medical history information; Inputting the comprehensive information of the user into a pre-trained health prediction model to obtain a health score of the user; Inputting the health score into the insurance database of the insurance company, and configuring the insurance requirements corresponding to the health score in the insurance database; comprising: Matching the insurance type corresponding to the health score in the insurance database of the insurance company according to the mapping relationship between the health score and the insurance type; adjusting the pre-set claim ratio of the insurance type according to the health score to obtain the claim ratio of the user in terms of the insurance type; extracting the economic information of the user from the comprehensive information of the user, and determining the insured amount of the insurance type according to the economic information; configuring the insurance demand of the user according to the insurance type, claim ratio and insured amount; Sending the insurance demand to the terminal device of the user; Establish an online insurance system; Receiving comprehensive information input by any user on the user information input interface of the online insurance system, inputting the comprehensive information into a pre-trained health prediction model to obtain the health score of the user, calling the insurance database of the insurance company, configuring the insurance demand of the user in the database of the insurance company according to the health score, and displaying the insurance demand on the web page interface of the online insurance system; If a click operation on a link button for detailed information is detected at the bottom of the webpage interface, or if it is detected on the webpage interface that the browsing time of the user is greater than a first threshold, or if it is detected that the user browses from the top to the bottom of the webpage interface, or if it is detected that the number of browsing times of the user on the webpage interface is greater than a second threshold, and no online insurance application request from the user is received, the user is marked as an interested user; After determining that the user is an interested user, obtain the IP address of the terminal device used by the interested user to log into the online insurance system, obtain the IP address type of the IP address, if the IP address is of a fixed allocation single center point type or a dynamically allocated single center point type, directly query the IP address information corresponding to the IP address in the IP address information library, if the IP address is of a fixed allocation multiple center point type or a dynamically allocated multiple center point type, query the IP address information library for the stay location of the terminal device, and obtain the location information corresponding to the IP address near the stay location of the terminal device; query the offline sub-insurance company in the insurance company that is closest to the location information, and send the comprehensive information of the user and the insurance needs configured for the user in the online insurance system to the terminal device of the offline sub-insurance company.

2. The method according to claim 1, characterized in that When the comprehensive information includes demographic information and medical information, inputting the comprehensive information of the user into a pre-trained health prediction model to obtain a health score for the user specifically includes: Extracting characteristic information from the demographic information, inputting the characteristic information as input data into a pre-trained health prediction model, and outputting a first health score corresponding to the characteristic information at an output end of the pre-trained health prediction model; Processing the medical information to obtain the probability of a serious illness corresponding to the medical information; The critical illness probability is input into the output end of the pre-trained health prediction model, and the first health score is adjusted to obtain the health score of the user.

3. The method according to claim 2, characterized in that The processing of the medical information to obtain the probability of a serious illness corresponding to the medical information specifically includes: Comparing the medical information with a disease sample database to determine multiple disease influencing factors in the medical information that have an impact on the disease; Extracting the autoregressive coefficient of each disease influencing factor among the multiple disease influencing factors from the disease sample database; Calculate the probability of a serious illness corresponding to the medical information according to the serious illness probability calculation formula, disease influencing factors and autoregressive coefficients; Wherein, P is the probability of serious illness of the user, Xi is the value of the i-th disease influencing factor in the medical information, βi is the autoregressive coefficient of the i-th disease influencing factor, is the average value of the i-th disease influencing factor in the disease sample database, S0(t) is the survival rate of the population suffering from the disease related to the i-th disease influencing factor in the disease sample database at time t, t is the time when the comprehensive information of the user is input, and n is the total number of disease influencing factors.

4. A device for configuring insurance demand based on a prediction model, characterized in that: The device is used to implement the method described in any one of claims 1 to 3; the device comprises: An acquisition unit, used for acquiring comprehensive information of any user from a user database of the insurance company; An input unit, used to input the comprehensive information of the user into a pre-trained health prediction model to obtain a health score for the user; a configuration unit, configured to input the health score into an insurance database of the insurance company, and configure insurance requirements corresponding to the health score in the insurance database; A sending unit, configured to send the insurance demand to a terminal device of the user; Establish an online insurance system; After determining that the user is an interested user, obtain the IP address of the terminal device used by the interested user to log into the online insurance system, obtain the IP address type of the IP address, if the IP address is of a fixed allocation single center point type or a dynamically allocated single center point type, directly query the IP address information corresponding to the IP address in the IP address information library, if the IP address is of a fixed allocation multiple center point type or a dynamically allocated multiple center point type, query the IP address information library for the stay location of the terminal device, and obtain the location information corresponding to the IP address near the stay location of the terminal device; query the offline sub-insurance company in the insurance company that is closest to the location information, and send the comprehensive information of the user and the insurance needs configured for the user in the online insurance system to the terminal device of the offline sub-insurance company.

5. An electronic device, characterized in that: The method comprises a processor, a memory, a communication interface and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for executing the steps in any one of the methods of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: It is used to store computer programs, wherein The computer program enables a computer to execute the method according to any one of claims 1 to 3.

Images