Insurance product presentation device and program

Abstract

To utilize information which has been already acquired at the time of contract from a contracted contractor of an insurance when a product or a service is related to the insurance.SOLUTION: An insurance product presenting device includes: a storage section for storing information on a contractor in association with an insurance policy number and an insurance policy number before renewal; a read-out section for reading out information stored in association with a specific insurance policy number and information stored in association with the insurance policy number before renewal which is associated with the specific insurance policy number, from the storage section; and a presenting section for presenting an insurance product with respect to the information read out by the read-out section using a machine learning model that has learned a relation between the information on the contractor and the contracted insurance product.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an insurance product presentation device and a program.

Background Art

[0002] There is a computer system that receives answers to questions from customers and determines products and services to be proposed to the customers based on the answers (see, for example, Patent Document 1). [Prior Art Document] [Patent Document] [Patent Document 1] Japanese Patent No. 6326538

Summary of the Invention

Problems to be Solved by the Invention

[0003] However, the above computer system requires customers to answer questions, and it cannot be said to be customer-friendly. In particular, when the products and services relate to insurance, since information has already been obtained from existing insurance policyholders at the time of contract, it is required to utilize this information.

Means for Solving the Problems

[0004] In order to solve the above problems, in a first aspect of the present invention, there is provided an insurance product presentation device including: a storage unit that stores information about a policyholder and a pre-renewal insurance policy number in association with an insurance policy number; a reading unit that reads out information stored in association with a specific insurance policy number, and information stored in association with a pre-renewal insurance policy number associated with the specific insurance policy number, from the storage unit; and a presentation unit that presents an insurance product with respect to the information read out by the reading unit, using a machine learning model that has learned the relationship between the information about the policyholder and the insurance products with which the policyholder has a contract.

[0005] In a second aspect of the present invention, a program is provided that causes a computer to implement a storage function for storing information about a policyholder and a policy number before renewal in a storage unit in association with the policy number, a reading function for reading from the storage unit the information stored in association with a specific policy number, and the information stored in association with the policy number before renewal associated with the specific policy number, and a presentation function for presenting an insurance product for the information read by the reading function using a machine learning model that has learned the relationship between the information about the policyholder and the insurance product with which the policyholder has a contract.

[0006] Note that the above summary of the invention does not list all the necessary features of the present invention. Also, sub-combinations of these feature groups can also be inventions.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Mode for Carrying Out the Invention

[0008] Hereinafter, the present invention will be described through embodiments of the invention. However, the following embodiments do not limit the invention according to the claims. Also, not all combinations of features described in the embodiments are essential for the solution means of the invention.

[0009] FIG. 1 shows a functional block of an insurance product presentation device 10 according to a first embodiment. The insurance product presentation device 10 is, for example, a computer managed by an insurance company. The insurance product presentation device 10 communicates with a terminal 20 used by a recruiter of an agency via a communication network such as the Internet. The recruiter is a salesperson of an agency who conducts insurance recruitment.

[0010] The insurance product presentation device 10 includes a policyholder information DB 130 that stores policyholder information regarding a policyholder, a complaint information DB 132 that stores complaint information regarding complaints from the policyholder, and an accident information DB 134 that stores accident information regarding accidents in which the policyholder was involved. These policyholder information, complaint information, and accident information are stored in their respective databases directly by employees of the insurance company or from the terminal 20 of the recruiter of the agency.

[0011] The insurance product presentation device 10 further includes an integrated information storage unit 100, a reading unit 110, an estimation unit 112, and a presentation unit 114. The presentation unit 114 includes a machine learning model 120.

[0012] FIG. 2 shows an example of the policyholder information stored in the policyholder information DB 130. The policyholder information in FIG. 2 exemplifies information regarding a policyholder of automobile insurance.

[0013] In the contractor information DB 130, contractor information is stored for each insurance policy number, that is, associated with the insurance policy number. Further, when the insurance contract is a renewal due to the expiration of the contract period of a previous insurance, etc., the insurance policy number before renewal is stored in association with the current insurance policy number. Note that in the example of FIG. 2, when the insurance contract is not due to renewal, an invalid value "*" is stored in the field of the insurance policy number before renewal.

[0014] The contractor information includes the contract period, contractor name, contractor age, contractor gender, contractor address, vehicle type, vehicle name, and the color of the driver's license. These information are essential information at the time of contract. Note that the vehicle name includes information indicating whether it is a domestic vehicle or a foreign vehicle. In the example of FIG. 2, in the feed of the vehicle name, if it is a domestic vehicle, the notation "(domestic)" is attached after the vehicle name, and if it is a foreign vehicle, the notation "(foreign)" is attached.

[0015] The contractor information also includes the insurance type that distinguishes automobile insurance, fire insurance, life insurance, etc., and the insurance product ID that identifies the insurance product. In the example shown in FIG. 2, the insurance type and the insurance product ID are included in the insurance policy number. The first alphabetic character of the insurance policy number represents the insurance type. For example, automobile insurance is "J", fire insurance is "K", life insurance is "S", etc. Further, the three alphabetic characters from the second to the fourth of the insurance policy number represent the insurance product ID. Therefore, in the example of FIG. 2, "JBCD0001" and "JBCD0002" are automobile insurance and the same insurance product, and "JBCX0195" is automobile insurance but a different insurance product from them.

[0016] The contractor information may further include optional information that is not mandatory at the time of contract. Examples of optional information in automobile insurance shown in FIG. 2 are the presence or absence of a spouse and the difference between owning a house and renting. Optional information in automobile insurance may include the color of the car body, the presence or absence of living with children, the age of the children, the presence or absence of living with parents, the age of the parents, etc. The optional information may be information obtained by the recruiter from the contractor, or may be obtained through a questionnaire to the contractor attached to the contract. In the case where the insurance type is fire insurance, information on the value of assets such as the area, location, whether it is a corner room, the distance from the station, and the number of floors may be included.

[0017] Although illustration is omitted, in the complaint information DB 132, the content of the complaint filed by the contractor of the insurance certificate number with respect to the insurance with respect to the insurance certificate number is stored as complaint information in association with the insurance certificate number. If no complaint has been filed, information indicating that fact, for example, an invalid value "*", is stored in the field. The complaint information may include information indicating the category obtained by categorizing the content of the complaint and information indicating the rank of the degree of the complaint.

[0018] Similarly, in the accident information DB 134, the content of the accident in which the contractor of the insurance certificate number was involved is stored as accident information in association with the insurance certificate number. In particular, if the contract is automobile insurance, information on accidents related to the automobile is stored, and if the contract is fire insurance, information on accidents related to fire is stored. If there is no accident, information indicating that fact, for example, an invalid value "*", is stored in the field. The matter information may include information indicating the category obtained by categorizing the content of the accident and information indicating the rank of the degree of the accident.

[0019] Furthermore, the insurance product presentation device 10 may store, in association with the insurance certificate number, the log of the call from the contractor to the contact center of the insurance company as contact center incoming call information. The insurance product presentation device 10 may further be connected to an external DB in which information associated with the insurance certificate number is stored.

[0020] Figure 3 shows an example of the operation flow of the insurance product presentation device 10. The insurance product presentation device 10 integrates the policyholder information such as the policyholder information DB 130 (S10), analyzes each insurance product using a decision tree with the integrated policyholder information, etc., to create a machine learning model (S20), and presents insurance products to the terminal 20 using the machine learning model (S30).

[0021] Figure 4 shows an example of the operation flow of step S10 for integrating policyholder information, etc. This operation flow is started either by a direct instruction to the insurance product presentation device 10 or periodically, such as quarterly.

[0022] The reading unit 110 reads out the insurance policy number and the policyholder information stored in association with the insurance policy number from the policyholder information DB 130 (S101). The reading unit 110 further reads out the complaint information stored in the complaint information DB 132 and the accident information stored in the accident information DB 134 in association with the same insurance policy number (same step).

[0023] The reading unit 110 determines whether a pre-renewal insurance policy number is stored in association with the insurance policy number read in step S101 (S103). If a pre-renewal insurance policy number is stored (S103: Yes), the reading unit 110 reads out the policyholder information associated with this pre-renewal insurance policy number from the policyholder information DB (S105). Further, the reading unit 110 reads out the complaint information and accident information associated with this pre-renewal insurance policy number from the complaint information DB 132 and the accident information DB 134 (same step).

[0024] In the example shown in FIG. 2, the insurance certificate number before renewal, "JBCD0002", is stored in association with the insurance certificate number "JBCD0571". Therefore, the reading unit 110 reads the contract information, complaint information, and accident information of the insurance certificate number "JBCD0571" in step S103, and also reads the contract information, complaint information, and accident information of the insurance certificate number before renewal, "JBCD0002", in S105. The contact center incoming call information associated with the insurance certificate number and the external data when an external DB is connected are also read. Note that the contract information, complaint information, accident information, and other information related to the contract may be collectively referred to as contract information, etc.

[0025] Next, the estimation unit 112 compares the contract information, etc. of the insurance certificate number with the contract information, etc. of the insurance certificate number before renewal, and determines whether there are any changes other than the age and contract period (S107). Here, the age and contract period are excluded because it is natural that the age and contract period are different before and after renewal. Note that the age here includes not only the age of the contract holder but also the ages of children and parents as arbitrary information.

[0026] If there is a change between the contract information, etc. of the insurance certificate number and the contract information, etc. of the insurance certificate number before renewal (S107: Yes), the estimation unit 112 estimates the life event of the contract holder (S109). The estimated life event becomes new information regarding the insurance certificate number.

[0027] In the example shown in FIG. 2, there is a change between the contract holder's address of the insurance certificate number "JBCD0571" and the contract holder's address of the insurance certificate number before renewal, "JBCD0002", associated with the insurance number. Therefore, the estimation unit 112 estimates that the contract holder has had a life event of "moving".

[0028] The life event is estimated using a lookup table in which the types of information that have changed and the life events are associated in advance. Examples of the association are as described above, such as "moving" if "the contractor's address has changed". Other examples include "giving birth" if "the number of children has increased", and "replacing a car" if "the car name has changed". Instead of or in addition to this, the life event may be estimated using a learning model that has learned the relationship between the types of information that have changed and the life events.

[0029] Next to step S109, or when the determination in either of steps S103 and S107 is No, the estimation unit 112 integrates the read information and the estimated life event and stores them in the integrated information storage unit 100 (S111). As a result, information at the contractor unit level is obtained.

[0030] FIG. 5 shows an example of contractor information and the like stored in the integrated information storage unit 100. In the integrated information storage unit 100, the latest insurance security number for the contractor name and contractor information and the like for the latest insurance security number are stored in association with the contractor name.

[0031] Furthermore, contractor information and the like that were not stored in association with the latest insurance security number but were stored in association with the insurance security number before renewal are also stored. In the example shown in FIG. 5, the information on whether the property is owner-occupied or rented, which is associated with the latest insurance security number "JBCD0570" of the contractor name "Taro Mitsui", is not stored. However, "rented" is stored in association with the insurance security number "JBCD0001" before the renewal of the insurance security number "JBCD0570". Furthermore, there is no change in the contractor address between these insurance security numbers. Therefore, "rented" is stored in the integrated information storage unit 100 in association with the contractor name "Taro Mitsui".

[0032] Furthermore, the integrated information storage unit 100 also stores the life events estimated by the estimation unit 112. In the example shown in FIG. 5, corresponding to the estimation in step S109 above that there was a life event of "moving" for the contractor name "Hanako Sumitomo", "moving" is stored in the field of the life event.

[0033] Thus, step S10 of integrating information ends. The contractors stored in the integrated information storage unit 100 are both existing policyholders of insurance products corresponding to their respective insurance policy numbers and also candidates for contracts for other insurance products. Next, the presentation unit 114 analyzes the policyholders of the insurance products using a decision tree (S20).

[0034] FIG. 6 is an example of a decision tree for analyzing the policyholders of an insurance product. The analysis using the decision tree is performed by machine learning. The decision tree constructed by the analysis becomes a machine learning model 120 that has learned the relationship between policyholder information and insurance products.

[0035] The target variable of the decision tree is the policyholder for each insurance product. In the example of FIG. 6, 200 policyholders who have subscribed to the insurance product "Automobile Insurance JBCD" are the target variables.

[0036] As explanatory variables, the policyholder information and the like stored in the integrated information storage unit 100 are used. In the example of FIG. 6, "age" with "35 years old" as the threshold, "difference between foreign cars and domestic cars", "presence or absence of moving", etc. are used as explanatory variables. Among these, for example, "age" is directly stored in the policyholder information DB130 and is information directly carried over to the integrated information storage unit 100. On the other hand, the "presence or absence of moving" is a so-called composite variable estimated as a life event by the estimation unit 112 from the "address" information directly stored in the policyholder information DB130 and stored in the integrated information storage unit 100.

[0037] Thus, step S20 of analyzing using the decision tree ends. Next, the presentation unit 114 presents insurance products using this decision tree (S30).

[0038] FIG. 7 shows an example of the operation flow of step S30 for presenting insurance products. The operation flow of step S30 starts according to the instruction of the recruiter via terminal 20.

[0039] The presentation unit 114 reads out the integrated policyholder information etc. for each policyholder from the integrated information storage unit 100 (S131). The presentation unit 114 fits the policyholder information etc. to the decision tree for a specific insurance product (S133). In this case, the insurance products that the policyholder has already subscribed to are excluded from the specific insurance product. This is because there is no need to judge the possibility of subscribing to the insurance products that the policyholder has already subscribed to.

[0040] That is, the policyholder information etc. of policyholder X who has subscribed to insurance product A is fitted to the decision tree of insurance product B. Thereby, it is possible to estimate the possibility that policyholder X will also subscribe to insurance product B.

[0041] For example, in the examples of FIGS. 5 and 6, when fitting the decision tree of insurance product "JBCD" to policyholder "Tokyo Jiro", it can be seen from the information of "age 35 or older", "domestic car", and "no relocation" that the profile of the policyholder information etc. only matches that of only 4% of the existing policyholders of insurance product "JBCD". Therefore, it is estimated that the possibility that policyholder "Tokyo Jiro" will subscribe to insurance product "JBCD" is low.

[0042] The presentation unit 114 performs fitting for all decision trees of insurance products except the insurance products that the policyholder has subscribed to for the policyholder (S135). As a result, the presentation unit 114 outputs to the terminal 20 the insurance products with many policyholders whose profiles match as the proposed insurance products (S137). In this case, among the multiple insurance products for which fitting has been performed, it is also possible to propose the top predetermined number of insurance products with a high percentage of existing policyholders whose profiles match, or insurance products with a percentage of existing policyholders whose profiles match of a certain value or more, for example, 50% or more.

[0043] Execute all of the above steps S131 to S137 for all the contractors stored in the integrated information storage unit 100 (S139). Thereby, the operation flow of step S30 ends.

[0044] As described above, according to the present embodiment, since the decision tree is analyzed using the integrated information, it is possible to select appropriate explanatory variables from more candidate explanatory variables for machine learning. Further, since the integrated information is used to fit the decision tree, it is possible to present an insurance product with a higher contract possibility.

[0045] FIG. 8 shows a functional block of the insurance product presentation device 12 according to the second embodiment. The same components as those of the insurance product presentation device 10 in the insurance product presentation device 12 are denoted by the same reference numerals and the description thereof is omitted.

[0046] In addition to the configuration of the insurance product presentation device 10, the insurance product presentation device 12 further includes a recruitment information DB 136 and a machine learning model 122 in the presentation unit 116. The presentation unit 116 of the insurance product presentation device 12 uses the machine learning model 122 that has learned the relationship between the insurance product and the information related to the recruitment to present the information related to the recruitment to the terminal 20.

[0047] FIG. 9 shows an example of recruitment information, which is information related to recruitment stored in the recruitment information DB 136. In the recruitment information DB 136, the name of the recruiter, the age of the recruiter, the gender of the recruiter, the affiliated agency ID, the skill level, the insurance policy number concluded by the recruiter, and the recruitment activities contributing to the conclusion are stored in association with the recruiter ID. These information are stored in the recruitment information DB 136 directly by the employees of the insurance company or from the terminal 20 of the recruiter of the agency.

[0048] FIG. 10 shows an example of the operation flow of the insurance product presentation device 12. The operation flow of the insurance product presentation device 12 includes, in addition to the operation flow of the insurance product presentation device 10, a step in which the presentation unit 116 reads out the recruitment information (S22), a step in which the recruitment information is analyzed by a decision tree using the recruitment information (S24), and a step in which a recruitment is proposed using the decision tree of the recruitment information (S40).

[0049] FIG. 11 is an example of a decision tree that analyzes insurance products using solicitation information as explanatory variables. The analysis by the decision tree is performed by machine learning in steps S22 and S24 described above. The decision tree constructed by the analysis becomes a machine learning model 122 that has learned the relationship between the solicitation information and the insurance products.

[0050] The target variable of the decision tree is the total number of contract cases for each insurance product. In the example of FIG. 11, the number of contract cases of 500 for the insurance product "Automobile Insurance JBCD" is the target variable. Here, the total number of cases is calculated from the insurance certificate numbers that the solicitor has successfully concluded and stored in the solicitation information DB 136. Therefore, unlike FIG. 6, even if it is the same contractor, if they have contracted for the insurance product multiple times due to renewal or the like, each can be counted as a separate case.

[0051] As the explanatory variables, the solicitation information stored in the solicitation information DB 136 is used. As explanatory variables, composite variables based on the solicitation information in the solicitation information DB 136 and the contractor information etc. in the integrated information storage unit 100 may also be used. In this case, the composite variable is generated from the contractor information etc. associated with the same insurance certificate number and the solicitation information. The generation procedure of the composite variable may be stored in the presentation unit 116 in advance.

[0052] In the example of FIG. 11, the explanatory variable "face-to-face, internet, or telephone" of the "solicitation activity" is the "solicitation activity that contributed to the conclusion" stored in the solicitation information DB 136. On the other hand, the explanatory variable "is the solicitor older or younger than the contractor" is a composite variable generated by comparing the "solicitor age" in the solicitation information DB 136 and the "contractor age" in the integrated information storage unit 100 for the same insurance certificate number. As another composite variable, the "closeness of the address" generated from the "contractor address" in the integrated information storage unit 100 and the "address of the agency" (not shown in FIG. 11) in the solicitation information DB 136 may be used.

[0053] In step S40 described above, the presenting unit 116 makes a recruitment proposal using the decision tree which is the machine learning model 122 that has learned the relationship between the recruitment information and the insurance products. In this case, the presenting unit 116 uses the decision tree that has analyzed the relationship between the insurance products presented in step S30 and the recruitment information. For example, when insurance product C is presented to the contractor Y in step S30, a recruitment proposal for the contractor Y is made using the decision tree of insurance product C.

[0054] In this case, it is possible to propose a predetermined number of top recruitment information with a high percentage of the number of existing contracts analyzed by the decision tree, or to propose recruitment information with a percentage of the number of existing contracts equal to or higher than a certain value, for example, 50% or more. In the example of FIG. 11, if the recruitment information with the highest percentage of the number of existing contracts is to be proposed, it is proposed to conduct "face-to-face" and "guide at the time of vehicle inspection" as recruitment activities for recruiters whose "recruiter age" is "older" than the "contractor age".

[0055] As described above, according to the present embodiment, in addition to the effects in the first embodiment, since a recruitment proposal is made using the decision tree analyzed with the recruitment information, the possibility of contract can be further increased. In addition, the information possessed by the insurance company can be utilized more effectively.

[0056] In any of the embodiments, instead of fitting all the decision trees of all the insurance products to each contractor in step S30, it is also possible to search for contractors who fit the profile with a high percentage of existing contractors in each decision tree, and present the insurance products corresponding to the decision trees to the contractors.

[0057] Furthermore, in any of the embodiments, the insurance type of the contractor analyzed by the decision tree and the insurance type of the contractor to which the decision tree is fitted may be the same or different. In the above examples, all are automobile insurance and the insurance types are the same. Among the same type of insurance products, among the insurance products extracted in step S30, those with a thicker compensation than the current insurance product may be selected and presented. Thereby, it is possible to propose a renewal to an insurance product with a thicker compensation.

[0058] As an example where the insurance types are different, a decision tree may be constructed for the policyholders of automobile insurance, and by fitting the policyholder information of the policyholders of fire insurance or life insurance to the decision tree, automobile insurance may be presented to the policyholders of fire insurance or life insurance. Thereby, insurance products can be efficiently cross-sold.

[0059] Also, in the second embodiment, instead of constructing a decision tree for the recruitment information for individual insurance products, a decision tree may be constructed for each insurance type. Thereby, appropriate recruitment can be proposed for each insurance type.

[0060] In any of the embodiments, although a decision tree has been described as the machine learning models 120, 122, machine learning models using other supervised learning may also be used. Examples of other machine learning models include support vector machines, neural networks, and deep learning.

[0061] In any of the embodiments, although an example of an individual has been described as the policyholder, it may also be applied when the policyholder is a corporation. When the policyholder is a corporation, the policyholder information may include information on the policyholder's business partners or affiliated companies. The information on business partners and affiliated companies may be, for example, information provided by a corporate investigation company such as Teikoku Databank, Ltd. These business partner information and affiliated company information may be used as explanatory variables of the decision tree, or may be the target to which an insurance product is presented as a candidate for an insurance contract.

[0062] Various embodiments of the present invention may be described with reference to flowcharts and block diagrams, where the blocks may represent (1) stages of a process in which operations are performed or (2) sections of a device having the role of performing the operations. Specific stages and sections may be implemented by dedicated circuits, programmable circuits supplied with computer-readable instructions stored on a computer-readable medium, and / or processors supplied with computer-readable instructions stored on a computer-readable medium. The dedicated circuits may include digital and / or analog hardware circuits, including integrated circuits (ICs) and / or discrete circuits. The programmable circuits may include reconfigurable hardware circuits including memory elements such as logical AND, logical OR, logical XOR, logical NAND, logical NOR, and other logical operations, flip-flops, registers, field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), etc.

[0063] A computer-readable medium may include any tangible device capable of storing instructions executable by a suitable device, such that a computer-readable medium having instructions stored therein will comprise a product including instructions executable to create means for performing the operations specified in the flowchart or block diagram. Examples of computer-readable media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer-readable media may include floppy (registered trademark) disks, diskettes, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), electrically erasable programmable read only memory (EEPROM), static random access memory (SRAM), compact disc read only memory (CD-ROM), digital versatile disc (DVD), Blu-ray (RTM) disc, memory stick, integrated circuit card, etc.

[0064] Computer-readable instructions may include any combination of one or more programming languages, including assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or source code or object code written in an object-oriented programming language such as Smalltalk, JAVA (registered trademark), C++, and a conventional procedural programming language such as the "C" programming language or a similar programming language.

[0065] Computer-readable instructions may be provided locally or via a wide area network (WAN) such as a local area network (LAN), the Internet, etc., to a processor or programmable circuit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, and the computer-readable instructions may be executed to create means for performing the operations specified in a flowchart or block diagram. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.

[0066] FIG. 12 shows an example of a computer 2200 in which multiple aspects of the present invention may be embodied, in whole or in part. Programs installed on the computer 2200 can cause the computer 2200 to function as an operation associated with the device according to an embodiment of the present invention or as one or more sections of the device, or can cause the operation or the one or more sections to be executed, and / or can cause the computer 2200 to execute a process according to an embodiment of the present invention or a stage of the process. Such a program may be executed by the CPU 2212 to cause the computer 2200 to perform specific operations associated with some or all of the blocks of the flowcharts and block diagrams described herein.

[0067] The computer 2200 according to this embodiment includes a CPU 2212, a RAM 2214, a graphic controller 2216, and a display device 2218, which are mutually connected by a host controller 2210. The computer 2200 also includes an input / output unit such as a communication interface 2222, a hard disk drive 2224, a DVD-ROM drive 2226, and an IC card drive, which are connected to the host controller 2210 via an input / output controller 2220. The computer also includes legacy input / output units such as a ROM 2230 and a keyboard 2242, which are connected to the input / output controller 2220 via an input / output chip 2240.

[0068] The CPU 2212 operates according to programs stored in the ROM 2230 and the RAM 2214, thereby controlling each unit. The graphic controller 2216 acquires image data generated by the CPU 2212 in a frame buffer or the like provided in the RAM 2214 or in itself, and the image data is displayed on the display device 2218.

[0069] The communication interface 2222 communicates with other electronic devices via a network. The hard disk drive 2224 stores programs and data used by the CPU 2212 in the computer 2200. The DVD-ROM drive 2226 reads a program or data from the DVD-ROM 2201 and provides the program or data to the hard disk drive 2224 via the RAM 2214. The IC card drive reads programs and data from an IC card and / or writes programs and data to the IC card.

[0070] The ROM 2230 stores therein a boot program or the like executed by the computer 2200 when activated and / or a program dependent on the hardware of the computer 2200. The input / output chip 2240 may also be connected to the input / output controller 2220 via various input / output units such as a parallel port, a serial port, a keyboard port, a mouse port, etc.

[0071] The program is provided by a computer-readable medium such as a DVD-ROM 2201 or an IC card. The program is read from the computer-readable medium, installed in the hard disk drive 2224, the RAM 2214, or the ROM 2230 which is also an example of a computer-readable medium, and executed by the CPU 2212. The information processing described in these programs is read by the computer 2200, resulting in the cooperation between the programs and the various types of hardware resources described above. The apparatus or method may be configured by realizing the operation or processing of information according to the use of the computer 2200.

[0072] For example, when communication is executed between the computer 2200 and an external device, the CPU 2212 may execute a communication program loaded in the RAM 2214 and instruct the communication interface 2222 to perform communication processing based on the processing described in the communication program. The communication interface 2222 reads the transmission data stored in the transmission buffer processing area provided in a recording medium such as the RAM 2214, the hard disk drive 2224, the DVD-ROM 2201, or the IC card under the control of the CPU 2212, transmits the read transmission data to the network, or writes the received data received from the network to the reception buffer processing area or the like provided on the recording medium.

[0073] Further, the CPU 2212 may cause all or necessary parts of files or databases stored in external recording media such as a hard disk drive 2224, a DVD-ROM drive 2226 (DVD-ROM 2201), an IC card, etc. to be read into the RAM 2214, and execute various types of processing on the data on the RAM 2214. Next, the CPU 2212 writes back the processed data to the external recording media.

[0074] Various types of information such as various types of programs, data, tables, and databases may be stored in the recording media and may be subjected to information processing. The CPU 2212 may execute various types of processing on the data read from the RAM 2214, including various types of operations, information processing, condition judgment, conditional branch, unconditional branch, information search / replacement, etc. described throughout this disclosure and specified by the instruction sequence of the program, and write back the results to the RAM 2214. Also, the CPU 2212 may search for information in files, databases, etc. within the recording media. For example, when a plurality of entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored in the recording media, the CPU 2212 searches for an entry that matches the condition where the attribute value of the first attribute is specified from among the plurality of entries, reads the attribute value of the second attribute stored in the entry, and thereby may obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0075] The programs or software modules described above may be stored in a computer-readable medium on or near the computer 2200. Also, a recording medium such as a hard disk or RAM provided in a server system connected to a dedicated communication network or the Internet can be used as a computer-readable medium, and thereby provide the program to the computer 2200 via the network.

[0076] As described above, the present invention has been described using embodiments, but the technical scope of the present invention is not limited to the scope described in the above embodiments. It is obvious to those skilled in the art that various changes or improvements can be made to the above embodiments. It is clear from the description of the claims that forms with such changes or improvements can also be included in the technical scope of the present invention.

[0077] It should be noted that the execution order of each process such as operations, procedures, steps, and stages in the apparatuses, systems, programs, and methods shown in the claims, the specification, and the drawings is not explicitly stated as "earlier" or "preceding" etc., and can be realized in any order unless the output of the previous process is used in the subsequent process. Regarding the operation flows in the claims, the specification, and the drawings, even if "first," "next," etc. are used for convenience of explanation, it does not mean that it is essential to implement in this order.

Description of Reference Numerals

[0078] 10, 12 Insurance product presentation device, 20 Terminal, 100 Integrated information storage unit, 110 Reading unit, 112 Estimation unit, 114, 116 Presentation unit, 120, 122 Machine learning model, 130 Policyholder information DB, 132 Complaint information DB, 134 Accident information DB, 136 Recruitment information DB

Claims

1. A storage unit that stores information about a policyholder and a previous insurance policy number in association with an insurance policy number; A reading unit that reads from the storage unit the information stored in association with a specific insurance policy number and the information stored in association with the previous insurance policy number associated with the specific insurance policy number; A presentation unit that presents an insurance product for the information read from the integrated storage unit that integrates and stores the information read by the reading unit, using a first machine learning model that has learned the relationship between the information about the policyholder and the insurance product with which the policyholder has a contract; Comprising; The presentation unit further presents information related to recruitment for the presented insurance product, using a second machine learning model that has learned the relationship between the insurance product and the information related to recruitment; An insurance product presentation device, wherein the explanatory variable of the second machine learning model includes a composite variable based on information about the recruiter and information about the policyholder.

2. On a computer, A storage function that stores information about a policyholder and a previous insurance policy number in a storage unit in association with an insurance policy number; A reading function that reads from the storage unit the information stored in association with a specific insurance policy number and the information stored in association with the previous insurance policy number associated with the specific insurance policy number; A presentation function that presents an insurance product for the information read from the integrated storage unit that integrates and stores the information read by the reading function, using a first machine learning model that has learned the relationship between the information about the policyholder and the insurance product with which the policyholder has a contract; To be realized; The presentation function further presents information related to recruitment for the presented insurance product, using a second machine learning model that has learned the relationship between the insurance product and the information related to recruitment; A program, wherein the explanatory variable of the second machine learning model includes a composite variable based on information about the recruiter and information about the policyholder.

Images