KR20190017105A - Method for matching insurances with a person who wants to have new insurances - Google Patents

Abstract

According to one embodiment of the present invention, a method for matching individuals desiring to subscribe to insurance and a recommended insurance product can comprise: a step of acquiring information on an individual desiring to subscribe to an insurance; a step of generating a first feature vector for the individual desiring to subscribe to the insurance on the basis of the information; a step of determining at least one recommended insurance product on the basis of the first feature vector and an insurance matcher; and a step of providing the recommended insurance product to the individual desiring to subscribe to the insurance. The insurance product matching part may be a data set expressing a correlation between a first feature vector on the basis of each plurality of insurance subscriber information and an insurance product to which each of the plurality of insured subscribers subscribes.

Description

[0001] METHOD FOR MATCHING INSURANCES WITH A PERSON WHO WANTS TO HAVE NEW INSURANCES [0002]

The present invention relates to a method of matching an insurance applicant with a recommended insurance product.

Today, with the development of information and communication technology, the way of purchasing products is also changing. The range of products that can be purchased through online shopping is increasing day by day. In recent years, financial products and insurance products have also become available online.

Currently, there are more than hundred kinds of insurance products and financial products that are sold, and these products reflect the insurance (financial) terms, insurance (financial) It is difficult to select the most optimal product for their purposes.

As a result, there have been attempts to sell insurance (financial) products on-line with a brief explanation. However, currently, online shopping malls of insurance (financial) products are merely categorized into various categories of products, It is entirely dependent on the discretion of the insurance planner to recommend appropriate insurance products.

Korean Patent No. 1,738,845

SUMMARY OF THE INVENTION The present invention is directed to provide a method of matching an insurance applicant and a recommendation insurance product that can match an appropriate insurance product to a desired insurer by learning insurance tendency of a plurality of insured subscribers do.

In addition to the recommendation of an objective insurance product for a person who wants to insure, a method of matching a person who wants to insure and a recommendation insurance product that can recommend an insurance product considering specific feasibility is provided.

Also, we want to provide a method of matching the insured applicant and the recommendation insurance product, which makes it easier to compare multiple recommended insurance products.

In addition, we want to provide a method of matching the insurance claimant with the recommended insurance product that can provide all the procedures from the recommendation to the subscription of the insurance product.

In addition, we want to provide a method of matching the applicant who wants to join the insurance product with the recommendation insurance product that can easily proceed to join the insurance product according to the simplified procedure by providing the insurance planner with the information without having to provide their information once again.

A method of matching an insurance applicant with one or more recommended insurance products according to an embodiment of the present invention includes: acquiring information on the insurance applicant; Generating a first feature vector for the insured person based on the information; Determining at least one recommendation insurance product based on the first feature vector and an insurance matcher; And providing the recommendation insurance commodity to the insured applicant.

In this case, the insurance product matching unit may be a data set expressing a correlation between a first feature vector based on each of a plurality of insurance subscriber information and an insurance product to which each of the plurality of insured subscribers subscribes.

The method of matching an insurance applicant and one or more recommended insurance products according to an embodiment of the present invention further includes training the insurance product matching machine before acquiring information on the insurance applicant . At this time, the step of tracing the insurance product matching machine includes: obtaining one or more labeled member information of a registered insurance product; Generating a second feature vector for each of the one or more subscriber information; And training the insurance product matching machine based on the second feature vector and the labeled insurance product.

The information on the insurance enrollee includes information on the identity of the insurance enrollee, age and gender, medical information including the disease history and the medical history of the insurance enrollee, information collected by the terminal of the insurance enrollee Biometric information of the insured person, and location information of the insured person.

The step of acquiring the information on the applicant for insurance includes the step of acquiring the insurance condition including the range of the amount of insurance product desired by the insured applicant, the guarantee item of the insurance product, and the type of the insurance product .

The method of matching an insurance applicant with at least one recommended insurance product according to an embodiment of the present invention is characterized in that an insurance product that does not satisfy the insurance condition among the recommended insurance products is excluded from the recommended insurance product The method comprising the steps of:

A method of matching an insurance applicant with one or more recommended insurance products according to an embodiment of the present invention includes the steps of obtaining information on the insurance applicant, And insuring the insured person having the first relationship with the insured person.

Wherein the step of determining the recommendation insurance product further comprises the step of adding the insurance commodity to which the insured member belongs by the first insured member to the recommendation insurance commodity, As shown in FIG. Wherein the first relationship may be a blood relationship.

Wherein the recommendation insurance product includes a plurality of recommended insurance products, and the providing step includes the steps of: classifying items that are different from items common to the recommended insurance products; And determining that the common items are displayed in accordance with the first display scheme, and determining that the different items are displayed according to the second display scheme.

The method of matching an insured applicant with at least one recommended insurance product according to an embodiment of the present invention includes: acquiring selection information of the insured applicant for the provided recommended insurance product after the providing step; And providing the subscription interface of the insurance product selected by the insurance subscriber with reference to the selection information.

Wherein providing the subscription interface comprises providing at least one insurance agent-specific benefit information for the selected insurance product; And transmitting a message including at least a part of information on the insured applicant to the insurance planner selected by the insurance inserter among the one or more insurance planners.

According to the embodiments of the present invention, it is possible to implement a method of matching an insured applicant with a recommended insurance product that can match an appropriate insurance product to an insured applicant by learning insurance tendency of a plurality of insured subscribers.

In addition, it is possible to implement a method of matching the prospective insurer and the recommendation insurance product which can recommend the insurance product considering the specific feasibility, in addition to the recommendation of the objective insurance product for the prospective insurer.

Also, it is possible to implement a method of matching the insured applicant with the recommended insurance product, which makes it easier to compare the plurality of recommended insurance products with each other.

In addition, it is possible to implement a method of matching a prospective insurer and a recommendation insurance product that can provide all procedures from recommendation to subscription of the insurance product.

In addition, it is possible to implement a method of easily matching the recommendation insurance product with the applicant who can proceed with the insurance product purchase in accordance with the simplified procedure by providing the insurance planer with the information of the insurance person without providing the information once again .

1 is a diagram illustrating an insurance product matching system according to embodiments of the present invention.
FIG. 2 illustrates an insurance product matching apparatus according to embodiments of the present invention. Referring to FIG.
3 is a view for explaining a method of generating an insurance product matching device by the insurance product matching device of FIG.
FIG. 4 is a diagram illustrating a method for the insurance product matching apparatus of FIG. 2 to determine a recommended insurance product for an insured person using an insurance product matching machine.
FIG. 5 is a view showing an example of a screen in which a plurality of recommended insurance products are displayed on a user terminal included in the insurance product matching system of FIG. 1;
6 is a flowchart illustrating an insurance product matching method performed by the insurance product matching apparatus of FIG.

BRIEF DESCRIPTION OF THE DRAWINGS The present invention is capable of various modifications and various embodiments, and specific embodiments are illustrated in the drawings and described in detail in the detailed description. It is to be understood, however, that the invention is not to be limited to the specific embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

The terms first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the terms "comprises" or "having" and the like are used to specify that there is a feature, a number, a step, an operation, an element, a component or a combination thereof described in the specification, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof. Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 schematically shows an insurance product matching system according to an embodiment of the present invention.

Referring to FIG. 1, an insurance product matching system according to an embodiment of the present invention may include a server 100, a user terminal 200, an external device 300, and a communication network 400 connecting them.

The insurance product matching system according to an embodiment of the present invention may be configured such that the server 100 receives information on the insured applicant from the user terminal 200 and / or the external device 300, Can be determined.

In addition, the insurance product matching system may be configured such that the server 100 acquires one or more insurance member information on which the insurance product subscribed from the user terminal 200 and / or the external device 300 is marked, . A more detailed description will be given later.

In the present invention, the term 'insured person' may mean a person who intends to join at least one insurance product. In this case, the 'insurance product' is to collect a certain amount of money from those who want to avoid the threat of common accidents in case of economic damages in the event of a disaster or various accidents, It can mean a financial instrument that compensates. The insurance product may be an insurance product of the present invention regardless of its kind. Accordingly, the insurance product of the present invention may be a concept that includes both flat-rate insurance, casualty insurance, protection-type insurance, and savings-type insurance.

In the present invention, the user terminal 200 may refer to various devices capable of transmitting and receiving the information on the insurance enrollee to the server 100. In this case, the terminal may be the portable terminal 201 or the personal computer 202. 1, the portable terminal 201 is shown as a smart phone, but the present invention is not limited thereto.

On the other hand, the user terminal 200 may include display means for displaying a description of the insurance product or the like, and input means for obtaining the input of the user. At this time, the input means and the display means can be configured in various ways. For example, the input means may be any one of a keyboard, a mouse, a trackball, a microphone, a button, and a touch panel, but is not limited thereto.

The external device 300 may refer to various devices that transmit and receive data to and from the server 100 and / or the user terminal 200 via the communication network 400. [

According to an embodiment of the present invention, the external device 300 may be an apparatus for providing insurance subscriber information for training an insurance product matching machine provided in the server 100. For example, the external device 300 may be a server of an insurance company, a server of the National Health Insurance Corporation, or an IRS server that stores information on an insurance payment amount.

The external device 300 may be a single number or a plurality. However, it should be understood that the present invention is not limited thereto.

According to another embodiment of the present invention, the external device 300 may be a device that provides a recommendation insurance product among the insurance products provided by the operating entity of the external device 300 to the user of the service provided by the external device 300. In this case, the external device 300 may acquire user information from the user terminal 200 and transmit the acquired information to the server 100, and may receive the recommended insurance product from the server 100 and provide it to the user terminal 200.

However, both of the above-described cases are exemplary and the present invention is not limited thereto.

In the present invention, the communication network 400 connects the server 100, the user terminal 200, and the external device 300. For example, the communication network 400 provides a connection path so that the user terminal 200 can transmit and receive packet data after connecting to the server 100.

The communication network 400 may be a wired network such as LANs (Local Area Networks), WANs (Wide Area Networks), MANs (Metropolitan Area Networks), ISDNs (Integrated Service Digital Networks), wireless LANs, CDMA, Bluetooth, But the scope of the present invention is not limited thereto.

In the present invention, the server 100 may receive information on an insurance applicant who wants to receive an insurance product from the user terminal 200 and / or the external device 300, and may determine a recommended insurance product for the applicant. In addition, the server 100 may acquire one or more insurance subscriber information marked with the insurance product subscribed from the user terminal 200 and / or the external device 300, and train the insurance product matching machine based on the information.

FIG. 2 schematically shows a configuration of an insurance product matching apparatus 110 according to an embodiment of the present invention.

Referring to FIG. 2, an insurance product matching apparatus 110 according to an embodiment of the present invention may include a communication unit 111, a control unit 112, and a memory 113. Also, although not shown in the figure, the insurance product matching apparatus 110 according to the present embodiment may further include an input / output unit, a program storage unit, and the like.

The communication unit 111 is connected to the network 110 through the network 110. The communication unit 111 includes hardware necessary for the insurance product matching apparatus 110 to transmit and receive signals such as a control signal or a data signal through a wired connection with another network apparatus such as the user terminal 200 and / And software.

The control unit 112 may include any kind of device capable of processing data, such as a processor. Herein, the term " processor " may refer to a data processing apparatus embedded in hardware, for example, having a circuit physically structured to perform a function represented by a code or an instruction contained in the program. As an example of the data processing apparatus built in hardware, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an ASIC (Application-Specific Integrated Circuit, and an FPGA (Field Programmable Gate Array), but the scope of the present invention is not limited thereto.

The memory 113 performs a function of temporarily or permanently storing data processed by the insurance product matching apparatus 110. [ The memory may include a magnetic storage medium or a flash storage medium, but the scope of the present invention is not limited thereto.

Although the insurance product matching apparatus 110 is provided in the server 100 in the following description, the insurance product matching apparatus 110 may be provided separately from the server 100 according to the role allocation.

Meanwhile, as described above, the server 100, that is, the insurance product matching device 110 determines the recommended insurance product for the insured person, or the insurance product matching device 110 based on the insured person information, .

Hereinafter, a method for generating and / or updating an insurance commodity matching device from one or more insurance subscriber information will be described first, and a recommendation insurance commodity for the insured is determined based on the generated insurance commodity matching device We will explain how to decide later.

<Method of Generating Insurance Product Matching Machine for Insurance Product Matching Device 110>

In the present invention, the 'insurance matcher' may be a data set expressing a correlation between a feature vector based on each of a plurality of insurance subscriber information and an insurance product to which a plurality of insured subscribers subscribe.

In this case, the insurance product matching machine may be generated by a machine learning technique. In other words, the insurance product matching unit may be the mapping information between the feature vector based on each of the plurality of insurance subscriber information and the insurance product to which each of the plurality of insured subscribers belongs.

The insurance product matching device 110 may use various machine learning techniques to train and / or learn such an insurance product matching machine. For example, the insurance product matching apparatus 110 may include an algorithm such as a Logistic regression, a decision tree, a nearest-neighbor classifier, a kernel discriminate analysis, a neural network, a support vector machine, a random forest, Or techniques (techniques) can be used. However, it should be understood that the present invention is not limited thereto.

Meanwhile, the insurance product matching unit may be a data set as described above. For example, the insurance product matching unit may be a data set comprising a plurality of numbers such as a matrix. However, it should be understood that the present invention is not limited thereto.

FIG. 3 is a diagram illustrating a method of generating an insurance product matching device by the insurance product matching device 110 according to an embodiment of the present invention.

Referring to FIG. 3, the controller 112 of the insurance product matching apparatus 110 according to an exemplary embodiment of the present invention may acquire one or more insurance information items 310 on which a registered insurance product is marked. At this time, the insurance subscriber information 310 includes information on the subscriber's personal information (such as identification information, age and sex), medical information (such as a disease history and a medical history), biometric information (e.g., Biometric information) and location information.

On the other hand, 'marked' of the insured item may mean that the identification information of the insured item to which the insured person belongs is related to the insured's information.

For example, in the case of the first subscriber information 311, the insurance product 311-1 to which the subscriber is subscribed may be marked. Of course, the subscriber information 311 may include personal information of the subscriber, medical information, biometric information, and location information. However, it should be understood that the present invention is not limited thereto.

Meanwhile, the control unit 112 may acquire insurance subscriber information 310 for training the insurance product matching machine from the external device 300 or may acquire the insurance subscriber information 310 from the memory 113 of the insurance product matching device 110.

For example, the control unit 112 may obtain information on the insured person information 310 and the insurance product to which the insured person subscribes from the server of the health insurance corporation, and the past control unit 112 may obtain the recommended insurance product The insurance subscriber information 310 may be obtained from the determined history.

Also, when the insurance product matching apparatus 110 is provided in a server of an insurance company that sells insurance products, the control unit 112 may utilize the insurance subscriber information 310 stored in its database.

However, it should be understood that the present invention is not limited thereto.

The controller 112 according to an embodiment of the present invention may generate a second feature vector 321 for each of the one or more insurance subscriber information obtained by the above-described process. At this time, the controller 112 may generate the second feature vector 321 based on any one of the personal information, medical information, biometric information, and location information of the insured person according to the system configuration, , The second feature vector 321 based on both the medical information, the biometric information, and the positional information. In other words, the control unit 112 can generate the second feature vector 321 based on various information of the insured subscriber.

The control unit 112 according to an embodiment of the present invention further includes an insurance product matching unit 330 based on the second feature vector 321 generated by the above process and the insurance product 311-1 to which the insured member subscribes, Can be updated. At this time, the insurance product 311-1 may be converted into the form of the vector 322 and used for updating the insurance product matching unit 330.

As described above, the insurance product matching unit 330 may be a correlation between the subscriber information generated by the machine learning technique and the insurance product, that is, the mapping information between the insurance product and the insurance product

The control unit 112 according to an embodiment of the present invention performs insurance product matching so that the second feature vector 321 generated by the process described above may be mapped to the associated insurance product 311-1, The insurance product matching unit 330 may be updated in such a manner as to update the data set of the insurance company 330.

For example, when the data set of the insurance product matching unit 330 is composed of a plurality of weights as shown in FIG. 3, the control unit 112 stores the second feature vector 321, And may adjust the coefficients constituting the insurance product matching unit 330 based on the vector 322.

The control unit 112 according to an embodiment of the present invention repeatedly generates the second feature vector 321 from a plurality of insurance subscriber information and repeatedly acquires information on the insurance product to which a plurality of insured subscribers subscribe Based on which the coefficients of the insurance product matching unit 330 are repeatedly updated, thereby obtaining the insurance product matching unit 330 with improved accuracy.

Thus, the present invention can learn the insurance tendency of a large number of insured subscribers and match an appropriate insurance product to the insured subscribers.

<How to decide the recommended insurance products for the insured>

In the foregoing, a method of generating the insurance product matching unit 330 by the insurance product matching apparatus 110 has been described with reference to FIG. Hereinafter, a method of determining the recommended insurance product for the insured person by the insurance product matching apparatus 110 generated by the above-described process will be described with reference to FIG.

Hereinafter, for convenience of explanation, it is assumed that the insurance product matching unit 330 is generated by the insurance product matching apparatus 110 by the above-described process.

4 is a diagram for explaining a method for the insurance product matching apparatus 110 according to an embodiment of the present invention to determine a recommended insurance product for an insured applicant by using the insurance product matching unit 330. Referring to FIG.

Referring to FIG. 4, the controller 112 of the insurance product matching apparatus 110 according to an embodiment of the present invention can acquire the information 411 about the insured applicant. At this time, the information 411 of the applicant for insurance is information (such as identification information, age and sex) of the applicant for insurance, medical information (such as disease history and treatment history), biometric information Biometric information of an insured person) and location information. However, it should be understood that the present invention is not limited thereto.

According to another embodiment of the present invention, the control unit 112 can acquire the insurance condition in addition to the information 411 on the insurance applicant. In this case, the insurance condition may include the amount of payment of the insurance product desired by the insured person, the guarantee item of the insurance product, and the kind of the insurance product. The insurance conditions obtained can be used to determine the nominated insurance product, which will be described later.

The controller 112 according to an embodiment of the present invention may generate the first feature vector 421 for the insured. 3, the controller 112 generates the first feature vector 421 from the information 411 of the insured person in the same manner as the method in which the controller 112 generates the second feature vector from the insured subscriber information .

The controller 112 according to an embodiment of the present invention may determine at least one recommended insurance product based on the first feature vector 421 and the previously learned insurance product matching unit 330. [

As described above, the insurance product matching unit 330 may be a correlation between a plurality of insurance products and a feature vector based on a plurality of subscriber information generated by a machine learning technique, that is, mapping information.

Therefore, the control unit 112 according to an embodiment of the present invention can refer to the insurance product matching unit 330 to determine insurance products having a high degree of correlation with the subscriber information 411 as the recommended insurance product.

The control unit 112 can determine the recommended insurance product as the vector form 441. [ The vector may be, for example, a vector having 10 elements in the form of a row vector as shown in FIG. Assuming that the size of the first element and the fifth element is greater than the size of the other element, the controller 112 can determine the insurance product corresponding to the first element and the insurance product corresponding to the fifth element as the recommended insurance product have.

In other words, the control unit 112 can confirm the size of each element constituting the vector, and determine an insurance product corresponding to an element whose size is equal to or larger than a predetermined critical size, as a recommended insurance product. However, it should be understood that the present invention is not limited thereto.

Meanwhile, according to another embodiment of the present invention, the control unit 112 may exclude an insurance product that does not satisfy the insurance condition among the determined recommended insurance products, from the recommended insurance product. At this time, the insurance condition may include the range of the amount of the insurance product desired by the insurer, the guarantee item of the insurance product, the kind of the insurance product, and may be obtained from the user terminal 200 as described above.

Accordingly, the present invention can recommend the insurance product considering the specific feasibility, in addition to the recommendation of the objective insurance product to the insured person.

The control unit 112 according to another embodiment of the present invention can confirm the insured applicant and the first insured insured person based on the personal information of the insured person. Wherein the first relationship may be, for example, a blood relationship.

In general, the disease of the parent and the disease of the child are genetically correlated. Therefore, a person who wants to insure the insurance tends to want to join the same product as the insurance product to which the person in the blood relationship belongs.

Accordingly, the control unit 112 according to the embodiment of the present invention can add the insurance product to which the insured applicant joins the first insured member to the recommended insurance product. Further, in providing the recommended insurance product to the user terminal 200, the control unit 112 may provide the insurance product, which is insured by the first insured member, to be distinguished from the remaining recommended insurance products.

For example, the control unit 112 can highlight the insurance product to which the insured member of the first relationship is subscribed through visual processing such as emphasis processing and underline processing. In addition, the control unit 112 may display the identification information of the subscriber who is the first relation with the insurance product to which the subscriber belongs. However, it should be understood that the present invention is not limited thereto.

Thus, the present invention can provide the insurance product required by the insurance applicant.

As described above, the controller 112 according to the embodiment of the present invention can provide the determined recommendation insurance product to the user terminal 200. [ At this time, the user terminal 200 may be the terminal of the insurance subscriber.

Thus, the present invention can provide a recommendation insurance commodity that more closely matches the insured person. In particular, since the present invention determines the recommendation insurance product of the applicant for the subscription based on the subscriber information of the subscriber of the actual insurance product and the subscription product, more valid conclusions can be drawn.

Meanwhile, the controller 112 according to the embodiment of the present invention can classify items that are different from items common to the recommended insurance products when there are a plurality of recommended insurance products. Further, the control unit 112 may determine to display the common items according to the first display method, and to display the different items according to the second display method.

Further, the controller 112 according to an embodiment of the present invention may recommend complementary insurance products. In other words, the control unit 112 may recommend a combination of a plurality of insurance products in accordance with the determination conditions of the recommended insurance product.

Assuming that the applicant for insurance requires a total of 10 security items, A insurance covers only 1 to 6 security items, B insurance covers only 2 to 9 security items, and C insurance covers only 7 to 10 security items Let's do it.

In this case, the control unit 112 may recommend a combination of the A insurance and the C insurance as the first rank, and recommend the B insurance as the second rank.

FIG. 5 is an illustration of a screen 500 in which a plurality of recommended insurance products are displayed on the user terminal 200 according to an exemplary embodiment of the present invention.

For convenience of explanation, assume that the control unit 112 has determined a total of 12 insurance products as recommendation insurance products, and only three insurance products 510, 520, and 530 are displayed on the screen 500.

As described above, when there are a plurality of recommended insurance products, the control unit 112 can classify items that are different from items common to the recommended insurance products. At this time, the control unit 112 may determine to display the items with the difference according to the second display mode (e.g., a method of emphasizing the items in boxes 511, 512, 521, and 531 in FIG. 5). In addition, the controller 112 may determine to display the common items according to the first display method (e.g., a method of displaying the items other than 511, 512, 521, and 531 in Fig. 5).

Thus, the present invention can make it easier to compare a plurality of recommended insurance products.

The control unit 112 according to an embodiment of the present invention can acquire selection information on a recommended insurance product provided from the user terminal 200. [ In other words, the control unit 112 can receive selection information of the insurance product to which the insurance subscriber wishes to subscribe from the user terminal 200.

Then, the control unit 112 can refer to the received selection information and provide the subscription interface of the insurance product selected by the insurance subscriber.

Thus, the present invention can provide all procedures from recommendation to subscription of insurance products.

The control unit 112 according to an embodiment of the present invention may provide one or more insurance agent-specific benefit information on the insurance product selected by the insurance subscriber in providing the subscription interface of the insurance product. In addition, the control unit 112 may transmit a message including at least a part of information on the insured person to the insurance planner selected by the insurer among the one or more insurance planners.

This makes it possible for the prospective insurer to proceed with the process of joining the insurance product according to the simplified procedure by simply providing the insurance agent with his / her information without having to provide it once again.

6 is a flowchart illustrating an insurance product matching method performed by the insurance product matching apparatus 110 according to an embodiment of the present invention. Hereinafter, the description of the contents overlapping with those described with reference to FIGS. 1 to 5 will be omitted.

The insurance product matching apparatus 110 according to an embodiment of the present invention may train the insurance product matching machine (S610). Referring back to FIG. 3, the insurance product matching apparatus 110 will be described in detail.

The insurance product matching apparatus 110 according to an embodiment of the present invention may acquire one or more insurance information items 310 on which the insured insurance products are marked. At this time, the insurance subscriber information 310 includes information on the subscriber's personal information (such as identification information, age and sex), medical information (such as a disease history and a medical history), biometric information (e.g., Biometric information) and location information.

On the other hand, 'marked' of the insured item may mean that the identification information of the insured item to which the insured person belongs is related to the insured's information.

For example, in the case of the first subscriber information 311, the insurance product 311-1 to which the subscriber is subscribed may be marked. Of course, the subscriber information 311 may include personal information of the subscriber, medical information, biometric information, and location information. However, it should be understood that the present invention is not limited thereto.

The insurance product matching device 110 may acquire insurance subscriber information 310 for training the insurance product matching device from the external device 300 or may acquire from the memory 113 of the insurance product matching device 110 have.

For example, the insurance product matching apparatus 110 may obtain information on the insured person information 310 and the insurance product to which the insured person has subscribed from the server of the health insurance corporation, The insurance subscriber information 310 may be obtained from the history of the recommendation insurance commodity for the applicant.

Also, when the insurance product matching apparatus 110 is provided in a server of an insurance company that sells insurance products, the insurance product matching apparatus 110 may utilize the insurance subscriber information 310 stored in its database.

However, it should be understood that the present invention is not limited thereto.

The insurance product matching apparatus 110 according to an embodiment of the present invention may generate a second feature vector 321 for each of the one or more insurance information items acquired by the above-described process. At this time, the insurance product matching apparatus 110 may generate the second feature vector 321 based on any one of the personal information, medical information, biometric information, and location information of the insured person according to the configuration of the system, The second feature vector 321 may be generated based on both the personal information, medical information, biometric information, and positional information of the first feature vector 321. [ In other words, the insurance product matching apparatus 110 can generate the second feature vector 321 based on various information of the insured person.

Then, the insurance product matching apparatus 110 according to the embodiment of the present invention calculates insurance product matching based on the second feature vector 321 generated by the above-described process and the insurance product 311-1 to which the insured member subscribes, Gt; 330 &lt; / RTI &gt; At this time, the insurance product 311-1 may be converted into the form of the vector 322 and used for updating the insurance product matching unit 330. [

As described above, the insurance product matching unit 330 may be a correlation between the subscriber information generated by the machine learning technique and the insurance product, that is, the mapping information between the insurance product and the insurance product

The insurance product matching apparatus 110 according to an embodiment of the present invention may be configured to match the second feature vector 321 generated by the process described above with the associated insurance product 311-1, The insurance product matching unit 330 may be updated in such a manner that the data set of the insurance product matching unit 330 is updated.

For example, when the data set of the insurance product matching unit 330 is composed of a plurality of weights as shown in FIG. 3, the insurance product matching apparatus 110 calculates the second feature vector 321, Based on the vector (322) corresponding to the insurance product matching unit (330).

The insurance product matching apparatus 110 according to an embodiment of the present invention repeatedly generates a second feature vector 321 from a plurality of insurance subscriber information and repeats the information of the insurance product to which a plurality of insured subscribers subscribe And acquire the insurance product matching unit 330 with improved accuracy by repeatedly updating the coefficients of the insurance product matching unit 330 based on the acquired information.

Thus, the present invention can learn the insurance tendency of a large number of insured subscribers and match an appropriate insurance product to the insured subscribers.

In the following steps S620 to S650, a method for determining the recommended insurance product for the insured person by the insurance product matching apparatus 110 will be described with reference to FIG.

4, the insurance product matching apparatus 110 according to the embodiment of the present invention may acquire the information 411 about the insured applicant (S620). At this time, the information 411 of the insured applicant, (E.g., biometric information (e.g., biometric information of an insured person collected by a terminal of an insured person) and location information (e.g., biometric information) . &Lt; / RTI &gt; However, it should be understood that the present invention is not limited thereto.

According to another embodiment of the present invention, the insurance commodity matching apparatus 110 may obtain the insurance condition in addition to the information 411 on the insured applicant. In this case, the insurance condition may include the amount of payment of the insurance product desired by the insured person, the guarantee item of the insurance product, and the kind of the insurance product. The insurance conditions obtained may be used to determine the nominated insurance product.

The insurance product matching apparatus 110 according to the embodiment of the present invention may generate the first feature vector 421 for the insured applicant (S630). At this time, the insurance product matching apparatus 110, in step S610, The first feature vector 421 may be generated from the information 411 of the insured person in the same manner as the insurance product matching apparatus 110 generates the second feature vector from the insured person information.

The insurance product matching apparatus 110 according to an embodiment of the present invention may determine at least one recommended insurance product based on the first feature vector 421 and the previously learned insurance product matching unit 330. S640)

As described above, the insurance product matching unit 330 may be a correlation between a plurality of insurance products and a feature vector based on a plurality of subscriber information generated by a machine learning technique, that is, mapping information.

Therefore, the insurance product matching apparatus 110 according to an embodiment of the present invention can refer to the insurance product matching unit 330 to determine insurance products having a high degree of correlation with the subscriber information 411 as the recommended insurance products .

The insurance product matching apparatus 110 can determine the recommended insurance product as the form of the vector 441. The vector may be, for example, a vector having 10 elements in the form of a row vector as shown in FIG. Assuming that the sizes of the first element and the fifth element are larger than those of the other elements, the insurance product matching apparatus 110 stores the insurance product corresponding to the first element and the insurance product corresponding to the fifth element as the recommended insurance product .

In other words, the insurance product matching apparatus 110 can check the size of each element constituting the vector, and determine an insurance product corresponding to an element whose size is equal to or larger than a predetermined critical size as a recommended insurance product. However, it should be understood that the present invention is not limited thereto.

Meanwhile, according to another embodiment of the present invention, the insurance product matching apparatus 110 may exclude an insurance product that does not satisfy the insurance condition among the determined recommended insurance products, from the recommended insurance product. At this time, the insurance condition may include the range of the amount of the insurance product desired by the insurer, the guarantee item of the insurance product, the kind of the insurance product, and may be obtained from the user terminal 200 as described above.

Accordingly, the present invention can recommend the insurance product considering the specific feasibility, in addition to the recommendation of the objective insurance product to the insured person.

The insurance product matching apparatus 110 according to another embodiment of the present invention can confirm the insured applicant and the first insured person based on the personal information of the insured applicant. Wherein the first relationship may be, for example, a blood relationship.

In general, the disease of the parent and the disease of the child are genetically correlated. Therefore, a person who wants to insure the insurance tends to want to join the same product as the insurance product to which the person in the blood relationship belongs.

Accordingly, the insurance product matching apparatus 110 according to an embodiment of the present invention can add the insurance product to which the insured applicant and the first insured member are subscribed to the recommended insurance product. Furthermore, in providing the recommended insurance product to the user terminal 200, the insurance product matching device 110 may provide the insurance product that the first insured member is subscribed to be distinguished from the remaining recommended insurance product.

For example, the insurance product matching apparatus 110 can highlight the insured products of the first insured member through visual processing such as emphasis processing and underlining processing. In addition, the insurance product matching apparatus 110 may display the identification information of the first related relation with the insurance product to which the subscriber belongs, together with the identification information of the first subscriber. However, it should be understood that the present invention is not limited thereto.

Thus, the present invention can provide the insurance product required by the insurance applicant.

As described above, the insurance product matching apparatus 110 according to the embodiment of the present invention can provide the determined recommended insurance product to the user terminal 200. (S650) At this time, As shown in FIG.

Thus, the present invention can provide a recommendation insurance commodity that more closely matches the insured person. In particular, since the present invention determines the recommendation insurance product of the applicant for the subscription based on the subscriber information of the subscriber of the actual insurance product and the subscription product, more valid conclusions can be drawn.

Meanwhile, the insurance product matching apparatus 110 according to the embodiment of the present invention can classify items that are different from items common to the recommended insurance products when there are a plurality of recommended insurance products. In addition, the insurance product matching apparatus 110 may determine to display the common items according to the first display method, and to display the different items according to the second display method.

In addition, the insurance product matching apparatus 110 according to an embodiment of the present invention may recommend complementary insurance products. In other words, the insurance product matching apparatus 110 may recommend a combination of a plurality of insurance products according to the determination conditions of the recommended insurance product.

Assuming that the applicant for insurance requires a total of 10 security items, A insurance covers only 1 to 6 security items, B insurance covers only 2 to 9 security items, and C insurance covers only 7 to 10 security items Let's do it.

In this case, the insurance product matching apparatus 110 may recommend a combination of the A insurance and the C insurance as the first rank, and recommend the B insurance as the second rank.

Referring again to FIG. 5, a screen 500 in which a plurality of recommended insurance products are displayed by the user terminal 200 according to an embodiment of the present invention will be described. For convenience of explanation, it is assumed that the insurance product matching apparatus 110 has determined 12 insurance products as recommendation insurance products, and only three insurance products 510, 520, and 530 are displayed on the screen 500 Let's see.

As described above, when there are a plurality of recommended insurance products, the insurance product matching device 110 can classify items that are different from items common to the recommended insurance products. At this time, the insurance product matching apparatus 110 can determine to display the items with the difference according to the second display method (for example, a method of emphasizing with square boxes 511, 512, 521, and 531 in FIG. 5). In addition, the insurance product matching apparatus 110 may determine to display common items according to a first display method (e.g., a method of displaying the remaining items except 511, 512, 521, and 531 in FIG. 5).

Thus, the present invention can make it easier to compare a plurality of recommended insurance products.

The insurance product matching apparatus 110 according to an embodiment of the present invention can acquire selection information on a recommended insurance product provided from the user terminal 200. [ In other words, the insurance product matching apparatus 110 can receive selection information of the insurance product to which the insured person wants to subscribe from the user terminal 200.

Subsequently, the insurance product matching apparatus 110 can provide the subscription interface of the insurance product selected by the insurance applicant with reference to the received selection information.

Thus, the present invention can provide all procedures from recommendation to subscription of insurance products.

The insurance product matching apparatus 110 according to an embodiment of the present invention may provide one or more insurance agent-specific benefit information on the insurance product selected by the insured applicant in providing the insurance product's subscription interface. In addition, the insurance product matching device 110 may send a message to the insurance planner selected by the insurer among at least one insurance planner, including at least a part of information on the insured.

This makes it possible for the prospective insurer to proceed with the process of joining the insurance product according to the simplified procedure by simply providing the insurance agent with his / her information without having to provide it once again.

The embodiments of the present invention described above can be embodied in the form of a computer program that can be executed on various components on a computer, and the computer program can be recorded on a computer-readable medium. At this time, the medium may be a computer-executable program. Examples of the medium include a magnetic medium such as a hard disk, a floppy disk and a magnetic tape, an optical recording medium such as CD-ROM and DVD, a magneto-optical medium such as a floptical disk, And program instructions including ROM, RAM, flash memory, and the like.

Meanwhile, the computer program may be designed and configured specifically for the present invention or may be known and used by those skilled in the computer software field. Examples of computer programs may include machine language code such as those produced by a compiler, as well as high-level language code that may be executed by a computer using an interpreter or the like.

The specific acts described in the present invention are, by way of example, not intended to limit the scope of the invention in any way. For brevity of description, descriptions of conventional electronic configurations, control systems, software, and other functional aspects of such systems may be omitted. Also, the connections or connecting members of the lines between the components shown in the figures are illustrative of functional connections and / or physical or circuit connections, which may be replaced or additionally provided by a variety of functional connections, physical Connection, or circuit connections. Also, unless explicitly mentioned, such as &quot; essential &quot;, &quot; importantly &quot;, etc., it may not be a necessary component for application of the present invention.

Accordingly, the spirit of the present invention should not be construed as being limited to the above-described embodiments, and all ranges that are equivalent to or equivalent to the claims of the present invention as well as the claims .

100: Server
110: Insurance product matching device
111:
112:
113: Memory
200: user terminal
300: External device
400: communication network

Claims (3)

In a method for matching an insurance applicant with one or more recommended insurance products,
Training the insurance product matching machine;
Acquiring information on the insurance applicant;
Generating a first feature vector for the insured person based on the information;
Determining at least one recommendation insurance product based on the first feature vector and an insurance matcher; And
And providing the insurance insurance commodity to the insured applicant,
Wherein the insurance commodity matching unit is a data set expressing a correlation between a first feature vector based on each of a plurality of insurance subscriber information and an insurance commodity to which each of the plurality of insured subscribers belongs,
Wherein the step of training the insurance product matching machine comprises:
Acquiring one or more registered member information of a registered insurance product;
Generating a second feature vector for each of the one or more subscriber information; And
And training the insurance product matching machine based on the second feature vector and the labeled insurance product.
The method of claim 3, wherein
Wherein the step of acquiring the information on the insured person includes the step of confirming the insured person having the first relationship with the insured person on the basis of the personal information of the insured person,
The step of determining the recommendation insurance product may include adding an insurance product to which the insured member of the first relationship is subscribed to the recommendation insurance product,
The step of providing the recommended insurance product may include providing the insurance product to which the insured member of the first relationship is subscribed so as to be distinguished from the remaining recommended insurance product,
Wherein the first relationship is a blood relationship, and the method of matching the insurance applicant with the recommendation insurance product.
The method of claim 1, wherein
The recommendation insurance product is plural,
The providing step
Classifying items that are different from items common to the recommended insurance products; And
And determining to display the common items according to the first display method and displaying the items having the differences according to the second display method. Matching method.

Images