KR102068896B1 - Method for recommending customized insurance, and computer program recorded on record-medium for executing method therefor - Google Patents

Abstract

The present invention proposes a customized insurance recommendation method. The method includes dividing an object corresponding to each of the plurality of insurance products into a plurality of virtual bins; Creating a virtual container based on the customer's personal information and the monthly payment amount of the customer; Loading at least one box into the container such that a ratio of the total volume of the box loaded to the container to the volume of the container is maximum; Classifying one or more boxes loaded in the container according to the type of insurance product; And recommending an insurance product corresponding to the sorted box to the customer. Through this, the present invention can recommend the best insurance products to customers without having to prepare all insurance products of all insurance companies.

Description

Method for recommending customized insurance, and computer program recorded on record-medium for executing method therefor}

The present invention relates to a computing algorithm. More specifically, the present invention relates to a customized insurance recommendation method using an algorithm for solving a 3D bin packing problem, and a computer program recorded on a recording medium to execute the same.

The 3D bin packing problem deals with ways to maximize the volumetric efficiency of a container by loading one or more three-dimensional cube bins into a container of three-dimensional cubes. It is a problem. Here, the volume ratio means the ratio of the total volume of the loaded box to the volume of the container.

This three-dimensional box filling problem can be classified into two types according to the number of containers that can be loaded. The single container loading problem is a problem that deals with a method for loading as many boxes as possible with a minimum amount of unusable space when one container cannot load all boxes. In addition, the multiple container loading problem is a problem dealing with a method for minimizing the number of containers for loading all given boxes.

Alternatively, the three-dimensional box filling problem can be classified into two types according to the type of box to be loaded. The homogeneous loading problem deals with how to efficiently load boxes of the same size into a container. In addition, the heterogeneous loading problem is a problem dealing with a method for efficiently loading several boxes of different sizes into a container. The mixed loading problem is a strongly heterogeneous loading problem with a large number of boxes but a small number of boxes of each kind, and a heterogeneous loading problem with a small number of boxes but a large number of boxes. may be reclassified as a loading problem.

Insurance, on the other hand, is a system in which those at risk of accidents of the same kind form a common property in advance, and in the event of an accident, benefits are provided from the common property. As such, insurers providing insurance services and insurance products provided by each insurer are very large in number and variety. In addition, the insurance planner who designs the insurance plan required by the customer receives a fee set by the insurance company differently for each insurance product.

Therefore, an insurance planner who has a large number and a great variety of insurance products cannot realistically know the insurance plan of the customer. . In other words, the conventional insurance plan is not designed to maximize the range that the customer can receive from the premium paid by the customer, but is designed to maximize the fee that the insurance agent can receive from the insurance company.

Therefore, there is a demand for a solution that can design an insurance plan so that the maximum coverage that can be guaranteed by the customer compared to the premium paid by the customer.

Republic of Korea Patent Registration No. 10-1867241, 'Insurance Information Processing Device and Method', (August 12, 2018 notification)

One disclosure of the present specification is to provide a method for recommending a customized insurance.

It is another object of the present invention to provide a computer program recorded on a recording medium for executing a customized insurance recommendation method.

Technical problems of the present invention are not limited to the aforementioned technical problems, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description.

In order to achieve the above technical problem, the present invention proposes a customized insurance recommendation method. The method includes dividing an object corresponding to each of the plurality of insurance products into a plurality of virtual bins; Creating a virtual container based on the customer's personal information and the monthly payment amount of the customer; Loading at least one box into the container such that a ratio of the total volume of the box loaded to the container to the volume of the container is maximum; Classifying one or more boxes loaded in the container according to the type of insurance product; And recommending an insurance product corresponding to the sorted box to the customer. Here, the box may be a unit configuration having a volume corresponding to a unit insurance premium per preset guaranteed unit with respect to the insurance product.

The generating of the container may include: a container having a volume corresponding to a 2-dimensional width value of the container calculated based on the personal information of the customer and a height value of the container corresponding to the monthly payable amount of the customer; Can be generated. The 2D width value of the container may be a value derived by inputting a risk value assigned according to a combination of age, gender, and occupation of the customer as a key value in a hash table.

The loading of the boxes into the container may include arranging the divided list of the plurality of boxes according to a preset order; Selecting one of the spaces existing inside the container as a space for loading the box; Selecting one box from the sorted list to remove from the list, and loading the selected box into the selected space; And dividing a space excluding the space in which the box is loaded from the selected space into a plurality of sub-spaces. Herein, each of the divided plurality of sub-spaces may be recursively selected as a space to load the box, loading into the selected space, and dividing into a plurality of sub-spaces. .

In the loading of the selected space, if the selected box cannot be loaded in the selected space, a third space existing inside the container and having a proximate surface adjacent to the selected space may be selected. After merging, the selected box may be loaded in the merged space.

In particular, the sorting may include arranging a list of templates consisting of a combination of the plurality of boxes in the order, and loading the space into the space by selecting one template from the list of templates and selecting the templates. The plurality of boxes constituting the selected template may be removed from the list at the same time.

The sorting may include sorting the boxes of the list according to a descending order of the brand value of insurance products corresponding to the boxes, or an order of decreasing monthly premiums of insurance products corresponding to the boxes. Can be.

In order to achieve the above technical problem, the present invention proposes a computer program recorded on a recording medium in order to execute the store arrangement method. The program includes a memory; A processor processing an instruction loaded in the memory; And a transceiver configured to transmit and receive data under control of the processor, wherein the processor includes a plurality of virtual bins for objects corresponding to each of a plurality of insurance products. Dividing into; the processor generating a virtual container based on the customer's personal information and the monthly payable amount of the customer; the processor loading the container into the container relative to the volume of the container Loading the at least one box into the container so that the ratio of the total volume of the boxes is at a maximum, the processor sorting the at least one box loaded into the container by the type of insurance product, and the processor Controlling the transceiver to provide insurance products corresponding to the classified boxes to the customer. Web pages can be recommended to execute the step of transmitting.

Specific details of other embodiments are included in the detailed description and the drawings.

According to embodiments of the present invention, by determining an insurance product to be recommended based on an algorithm for solving the 3D box filling problem, it is possible to recommend an optimal insurance product to a customer without preparing for all insurance products of all insurance companies. Will be. Through this, it is possible to design an insurance plan optimized for each customer based on the customer's information and the customer's needs (needs) without designing the insurance plan around the insurance company or the insurance product.

Effects of the present invention are not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the claims.

1 is a block diagram of an insurance recommendation system according to an embodiment of the present invention.
2 is a logical diagram of an insurance recommendation server according to an embodiment of the present invention.
3 is a hardware configuration diagram of the insurance recommendation server according to an embodiment of the present invention.
4 is an exemplary view of an input screen of a user device according to an embodiment of the present invention.
5 is an exemplary view of an output screen of a user device according to an embodiment of the present invention.
6 is an exemplary view for explaining the concept of a box according to an embodiment of the present invention.
7 is an exemplary view for explaining the concept of a container according to an embodiment of the present invention.
8 is an exemplary diagram of a three-dimensional box filling problem algorithm according to an embodiment of the present invention.
9 is an exemplary view for explaining merging of spaces according to an embodiment of the present invention.
10 is an exemplary diagram for describing division of a space according to an embodiment of the present invention.
11 is an exemplary view for explaining the classification of boxes according to an embodiment of the present invention.
12 is a flowchart illustrating an insurance recommendation method according to an embodiment of the present invention.
13 is a flowchart of an algorithm for solving a 3D box filling problem according to an embodiment of the present invention.

It is to be noted that the technical terms used herein are merely used to describe particular embodiments and are not intended to limit the present invention. In addition, the technical terms used in the present specification should be interpreted as meanings generally understood by those skilled in the art to which the present invention belongs, unless specifically defined otherwise in the present specification, and are overly inclusive. It shall not be construed in the sense of or in the sense of being excessively reduced. In addition, when the technical terms used herein are incorrect technical terms that do not accurately express the spirit of the present invention, they should be replaced with technical terms that can be properly understood by those skilled in the art. In addition, the general terms used in the present invention should be interpreted as defined in the dictionary or according to the context before and after, and should not be interpreted in an excessively reduced sense.

Also, the singular forms used herein include the plural forms unless the context clearly indicates otherwise. In the present application, terms such as “consisting of” or “having” should not be construed as necessarily including all of the various components, or the various steps described in the specification, and some of the components or some steps are included. It should be construed that it may not be, or may further include additional components or steps.

In addition, terms including ordinal numbers, such as first and second, as used herein 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. For example, without departing from the scope of the present invention, the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component.

When a component is said to be "connected" or "connected" to another component, it may be directly connected to or connected to that other component, but other components may be present in between. On the other hand, when a component is said to be "directly connected" or "directly connected" to another component, it should be understood that there is no other component in between.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings, and the same or similar components will be given the same reference numerals regardless of the reference numerals and redundant description thereof will be omitted. In addition, in describing the present invention, when it is determined that the detailed description of the related known technology may obscure the gist of the present invention, the detailed description thereof will be omitted. In addition, it should be noted that the accompanying drawings are only for easily understanding the spirit of the present invention and should not be construed as limiting the spirit of the present invention by the accompanying drawings. The spirit of the invention should be construed as being extended to all changes, equivalents, and substitutes in addition to the accompanying drawings.

As described above, insurers providing insurance services and insurance products provided by each insurer are very large in number and variety. In addition, the insurance planner who designs the insurance plan required by the customer receives a fee set by the insurance company differently for each insurance product.

Therefore, an insurance planner who has a large number and a great variety of insurance products cannot realistically know the insurance plan of the customer. . In other words, the conventional insurance plan is not designed to maximize the range that the customer can receive from the premium paid by the customer, but is designed to maximize the fee that the insurance agent can receive from the insurance company.

This problem is due to the large number of insurers that provide insurance services, and the variety of insurance products provided by each insurer. In particular, even if the insurance products provided by the same insurer, the relationship between the premiums to be paid compared to the coverage can be different for each insurance product. For example, an insurance company called 'AA Cancer Insurance' provided by an insurance company called 'SS Fire' should pay a premium of 100,000 won per month to be guaranteed 30 million won, while an insurance product called 'BB Cancer Insurance' is 30 million won. It may be configured to pay a premium of 90,000 won to 5,000 won per month in order to receive the guarantee.

In addition, even if the same insurance product provided by the same insurer, the relationship of the coverage range according to the premium to be paid is not linearly. For example, an insurance company called 'CC Cancer Insurance' provided by an insurance company called 'AB Insurance' can receive 30 million won if you pay a premium of 100,000 won a month, but 15 million won if you pay a premium of 60,000 won a month. It can be configured to be guaranteed.

Therefore, in order to recommend the optimal customized insurance products required by the customer, all insurance companies should basically prepare for all insurance products, and thus requires a lot of time and money.

In order to solve such a difficulty, the present invention proposes a method of recommending an optimal customized insurance product required by a customer by modifying and applying an algorithm for solving a 3D bin packing problem.

The present invention determines an insurance product to be recommended based on an algorithm for solving the 3D box filling problem, so that it is possible to recommend an optimal insurance product to a customer without preparing for all insurance products of all insurance companies. Through this, it is possible to design an insurance plan optimized for each customer based on the customer's information and the customer's needs (needs) without designing the insurance plan around the insurance company or the insurance product.

Hereinafter, with reference to the accompanying drawings will be described in more detail with respect to the configuration for implementing the features of the present invention as described above.

1 is one of the present invention Example  The insurance recommendation system according to the configuration.

As shown in FIG. 1, an insurance recommendation system according to an embodiment of the present invention includes one or more user devices 100a, 100b,..., 100n; 100, an insurance recommendation server 200, and an insurance company server 300. Can be configured. As such, the components of the insurance recommendation system merely represent functionally distinct elements, and any one or more components may be integrated with each other in an actual physical environment.

Referring to each component, the user device 100 is a device that can be used by a customer who wants to purchase insurance or an insurance planner who connects the customer and the insurance company.

First, the user device 100 may provide insurance product recommendation information to a customer who wants to purchase insurance. In detail, the user device 100 may receive an insurance recommendation initial webpage from the insurance recommendation server 200 according to an input of a user (ie, a customer). The user device 100 may output the received insurance recommendation initial web page and receive input of personal information and monthly payment amount from the user. Here, the personal information may include a user's age, gender, and occupation, but is not limited thereto. The user device 100 may request the recommendation of the insurance product by transmitting the personal information input from the user and the monthly payable amount to the insurance recommendation server 200.

The user device 100 may receive an insurance recommendation result web page from the insurance recommendation server 200. The user device 100 may output the insurance recommendation result web page. If the user device 100 receives a request for joining the recommended insurance product from the user, the user device 100 may transmit a request for joining the recommended insurance product to the insurance recommendation server 200.

In addition, the user device 100 may provide the insurance agent with information of a customer who wants to purchase insurance. In detail, the user device 100 may receive the personal information of the customer and the information about the recommended insurance product from the insurance recommendation server 200. The user device 100 may output the personal information of the customer and the information about the recommended insurance product to induce the insurance of the customer by the insurance agent.

As such, the user device 100 may transmit / receive data with the insurance recommendation server 200, and any device may be accepted as long as it is a computing device capable of performing an operation based on the received data.

Preferably, the user device 100 can be either a mobile computing device or a fixed computing device. Here, the mobile computing device includes a smart phone (100a), a laptop (laptaop), a tablet (tablet, 100n), a phablet, a portable multimedia player (PMP), a personal portable terminal (Personal) Digital assistants (PDAs), or e-book readers, but are not limited thereto. In addition, the stationary computing device may include a desktop 100b, a workstation, or a server, but is not limited thereto.

In addition, the user device 100 may be implemented as any one of a wearable device, such as a smart wristband (smart band), smart watch (smart watch), smart ring (smart ring) or smart glasses (smart glasses, etc.) It will be obvious in this technical field.

Next, the insurance recommendation server 200 is a device that can recommend an insurance product based on the information of the customer, and induce the subscription of the recommended insurance product. In brief, the insurance recommendation server 200 may collect information on the insurance product from the insurance company server 300. The insurance recommendation server 200 may determine and provide an insurance product to be recommended based on information received from the user device 100 used by a customer who wants to purchase insurance. When the insurance recommendation server 200 receives a request for subscription of a recommended insurance product from a user device 100 used by a customer who wants to purchase insurance, the insurance recommendation server 200 requests a user's insurance subscription from the user device 100 used by an insurance agent. Can be.

As such, the insurance recommendation server 200 may exchange data with the user device 100 and the insurance company server 300, and any device may be allowed as long as it is a computing device capable of performing an operation based on the received data. have. Preferably, it may be any one of a fixed computing device such as a desktop, a workstation or a server, but is not limited thereto.

In particular, the insurance recommendation server 200 according to an embodiment of the present invention may determine an insurance product tailored to a customer by applying an algorithm for solving a 3D box filling problem. The specific configuration and operation of the insurance recommendation server 200 having such a feature will be described in detail later with reference to FIGS. 2 to 13.

Next, the insurance company server 300 is operated by an insurance company that provides insurance services, and is a device that can inquire information about insurance products. As such, the insurer server 300 may be a plurality of devices that each insurer operates independently, or may be a single device that the insurers operate integrally.

In detail, the insurance company server 300 may be requested to provide information on the insurance product from the insurance recommendation server 200. The insurance company server 300 may transmit the insurance product information to the insurance recommendation server 300 in response to the request. In this case, the insurance company server 300 may transmit only the information of the insurance product, the product information is updated, or may transmit the information of the requested insurance product regardless of whether the product information is updated.

The network for the user device 100, the insurance recommendation server 200, and the insurance company server 300 to transmit and receive data to each other may be either a mobile communication network or a public wired communication network. The mobile communication network may include code division multiple access (CDMA), wide band code division multiple access (WCDMA), high speed packet access (HSPA), long term evolution (Long Term Evolution). LTE) may be included, but is not limited thereto. The public wired network may include Ethernet, x Digital Subscriber Line (xDSL), Hybrid Fiber Coax (HFC), and Fiber To The Home (FTTH). It is not limited to this.

In addition, the user device 100 and the insurance recommendation server 200 may include Radio Frequency Identification (RFID), Near Field Communication (NFC), Bluetooth, Bluetooth Low Energy (BLE), or ZigBee. It will be apparent to those skilled in the art that data can be communicated using the same short range wireless communication.

Hereinafter, the configuration of the insurance recommendation server 200 as described above will be described in more detail.

2 is one of the present invention Example  According to the insurance recommendation server 200 according to the logical configuration.

As shown in FIG. 2, the insurance recommendation server 200 includes a communication unit 205, an input / output unit 210, an insurance product management unit 215, a customer management unit 220, a recommendation product determination unit 225, and a contract support unit ( 230). As such, the components of the insurance recommendation server 200 merely represent functionally distinct elements, and any one or more components may be integrated with each other in an actual physical environment.

Referring to each component, the communication unit 205 may transmit and receive data with the user device 100 or the insurance company server 300. In detail, the communication unit 205 may transmit the insurance recommendation initial web page to the user device 100 according to a request of the user device 100. The communication unit 205 may receive the customer's personal information and the monthly payment amount from the user device 100. Here, the personal information of the customer may include the age, gender and occupation of the user, but is not limited thereto.

The communication unit 205 may further receive a weight that is a reference when determining the recommended insurance product from the user device 100. Here, the weight is the importance considered in selecting a box or template to be loaded into a container. For example, the weight may be any one of the brand value ranking of the insurance product, the monthly premium of the insurance product, or the ratio of the brand value ranking and the monthly premium, but is not limited thereto.

The communication unit 205 may transmit the insurance recommendation result web page including the information about the recommended insurance product determined by the recommendation product determination unit 225 to the user device 100. The communication unit 205 may receive a request for subscription of a recommended insurance product from the user device 100. In addition, the communication unit 205 may transmit the personal information of the customer and the information about the recommended insurance product to the user device 100.

The communicator 205 may transmit a request for providing insurance product information to the insurance company server 300. The communication unit 205 may receive insurance product information from the insurance company server 300.

In the following configuration, the input / output unit 210 may input and output data necessary for the operation of the insurance recommendation server 200 from the user through the user interface. In detail, the input / output unit 210 may receive a reference volume, a reference amount, or a reference guarantee unit for dividing an object corresponding to the insurance product into a plurality of boxes. As such, the input reference volume, reference amount, or reference guarantee unit may be used by the insurance product management unit 215 to divide the object corresponding to each of the plurality of insurance products into a plurality of boxes.

The input / output unit 210 may receive a reference formula for creating a container. As such, the input reference formula may be used by the customer manager 220 to create a container based on the customer's personal information and the monthly payment amount of the customer.

The input / output unit 210 may receive information about a template from a user. Here, the template refers to a combination of one or more bins that can be loaded into the container at the same time. The input / output unit 210 may receive a weight that is a reference when loading a box. The input / output unit 210 may receive a division criterion for dividing the container into a plurality of sub-spaces. As such, the inputted information, weight, or division criteria may be used by the recommendation product determination unit 225 to solve the 3D box filling problem.

In the following configuration, the insurance product management unit 215 can manage and store the insurance product provided from the insurance company server 300, and can be processed to use for the three-dimensional box filling problem. In detail, the insurance product manager 215 may request the insurance company server 300 from the insurance company through the communication unit 215. The insurance product manager 215 may add the insurance product information received from the insurance company server 300 to the insurance product management list through the communication unit 205.

The insurance product manager 215 stores the received insurance product information in a database inside the insurance recommendation server 200 or a data warehouse existing outside the insurance recommendation server 200. Can be stored at

The insurance product management unit 215 divides an object corresponding to each of the plurality of insurance products received from the insurance company server 300 into a plurality of box units based on any one of a reference volume, a reference amount, and a standard guarantee unit. Can be. Here, the reference volume, the reference amount or the reference guarantee unit may be set through the input / output unit 210 or may be preset. The insurance product manager 215 may add the divided plurality of boxes to the box management list.

More specifically, the bin is a virtual unit configuration having a volume corresponding to the unit premium per standard guaranteed unit with respect to the insurance product. For example, suppose you have an AA insurance product that guarantees you 30 million won for a monthly payment of 100,000 won. In addition, it is assumed that the 'AA insurance product' has a linear relationship with the insurance premium, and the insurer that provides the 'AA insurance product' accepts from the guarantee unit of 100,000 won (ie, the guaranteed amount). In this case, the insurance product management unit may divide the 'AA insurance product' into 300 boxes. Thus, boxes divided from AA insurance products may have a volume corresponding to a premium of 334 won (333.33 ceil) per 100,000 won guaranteed units, respectively.

The volume corresponding to the unit premium per reference guaranteed unit may be managed by a separate matching table or hash table. Accordingly, the insurance product manager 215 may input a unit premium per reference guaranteed unit as a key value for the matching table or hash table, and derive a volume corresponding to the unit premium per reference guaranteed unit.

Thus, the boxes thus divided may have different volumes depending on the premium or coverage of the insurance product.

In addition, the insurance product management unit 215 may configure a template by combining a plurality of boxes. In this case, the insurance product manager 215 may configure a template by combining a plurality of boxes based on the information about the template input through the input / output unit 210. Alternatively, the insurance product manager 215 may configure a template by combining a plurality of boxes based on a preset combination rule. The insurance product manager 215 may add the configured template to the template management list.

In the following configuration, the customer management unit 220 may manage and store the information of the customer provided from the user device 100, and may be processed to use for the three-dimensional box filling problem. In detail, the customer manager 220 may transmit the insurance recommendation initial webpage to the user device 100 through the communication unit 205. The customer manager 220 may receive the customer's personal information and the monthly payment information from the user device 100 through the communication unit 205. In addition, the customer manager 220 may add the personal information of the customer received from the user device 100 through the communication unit 205 and the information of the monthly payment amount to the customer management list.

The customer management unit 220 stores the received customer's personal information and monthly payment information in a database inside the insurance recommendation server 200 or a data warehouse (external to the insurance recommendation server 200). Not shown).

The customer manager 220 may generate a container based on the customer's personal information and the monthly payment amount provided from the user device 100. Here, the container is a virtual unit space having a volume in which one or more boxes can be loaded. For example, a container having a volume of '1000' may be loaded with 100 boxes having a volume of '10'.

More specifically, the customer manager 220 may generate a container having a volume calculated by substituting the personal information of the customer and the monthly payable amount into the reference formula. Here, the reference formula may be set through the input / output unit 210 or may be preset.

For example, the customer manager 220 may identify an assigned risk value according to a combination of a customer's age, gender, and occupation of the customer's personal information. The customer manager 220 may determine the derived value as the 2D width x depth of the container by inputting the identified risk value as a key value of a pre-configured matching table or hash table. The customer manager 220 may identify the height value of the corresponding container according to the amount of the monthly payable amount of the customer. In addition, the customer manager 220 may generate a container having a volume (width x depth x height) corresponding to the two-dimensional width value of the container and the height value of the container.

In the following configuration, the recommendation product determination unit 225 may determine an insurance product to recommend to the customer by modifying and applying an algorithm for solving the 3D box filling problem. The algorithm for solving the box filling problem performed by the recommendation product determining unit 225 is largely performed by filling one or more boxes in a container, classifying boxes loaded in the container according to types of insurance products, and classifying boxes. The process of determining the corresponding insurance product as an insurance product to be recommended to the customer may be performed.

In detail, each process of filling one or more boxes into a container includes the recommendation product determination unit 225 as the customer management unit 220 such that the total volume ratio of the boxes loaded in the container is maximized relative to the volume of the container. It may be performed by loading one or more boxes divided by the insurance product management unit 215 in the container generated by the).

More specifically, the recommendation product determination unit 225 may sort the list of the plurality of boxes divided by the insurance product management unit 215 according to a set order. Here, the order of sorting the boxes in the list may be determined by the weight received by the communication unit 205 or input through the input / output unit 210. Here, the weight may be any one of the brand value ranking of the insurance product corresponding to the box, the monthly premium of the insurance product corresponding to the box, or the ratio of the brand value ranking and monthly premium on the box. It doesn't happen.

For example, the recommendation product determining unit 225 may sort the boxes included in the list according to a descending order of the brand value ranking of the insurance product corresponding to the box. Alternatively, the recommendation product determination unit 225 may sort the boxes included in the list in the order of decreasing the monthly premium of the insurance product corresponding to the boxes.

The recommended product determiner 225 may select one of the spaces existing in the container as a space for loading the box. The recommendation product determination unit 225 may select one box from the sorted list, remove the box from the list, and load the selected box in the selected space. In this case, the recommended product determiner 225 may designate one corner of the selected space as a reference point, and load the selected box in the selected space so that any one of the corners of the box touches the reference point.

If the selected box cannot be loaded in the selected space (that is, if the volume of the selected space is smaller than the volume of the selected box), the recommendation product determining unit 225 has a proximate surface adjacent to the selected space and has a container. The third space existing inside and the selected space can be merged with each other. In addition, the recommended product determiner 225 may attempt to load the selected box in the merged space.

If the selected box cannot be loaded in the merged space, or if there is no third space to merge with the selected space, the recommended product determining unit 225 cannot use the space to load the box. Can be determined.

After loading the selected box in the selected space, the recommended product determining unit 225 may divide the space excluding the space in which the box is loaded from the selected space into a plurality of sub-spaces. If one of the corners of the box loaded in the container is loaded to reach the reference point, the recommended product determiner 225 may divide the space except the space in which the box is loaded into three sub-spaces from the selected space. . In this case, the recommended product determiner 225 may divide the information into three lower spaces according to the division criteria set through the input / output unit 210 or preset. Here, the division criteria may be any one of Top-to-Front, Side-to-Top, and Side-to-Front.

In addition, the recommended product determining unit 225 may select a space for loading a box for each of the plurality of divided sub-spaces until there are no boxes to be loaded any more or there is no space for loading the boxes in the container. Selecting, selecting and loading one box in the selected space, and recursively or iteratively performing the process of dividing the box-loaded space into a plurality of sub-spaces, and loading the container into the container volume The crates can be loaded in containers so that the proportion of the total volume of the crates is maximum.

According to another embodiment of the present invention, the recommended product determiner 225 may load a template rather than a box in a container in order to solve the 3D box filling problem more quickly.

More specifically, the recommendation product determination unit 225 may sort the list of templates in which a plurality of boxes are combined by the insurance product management unit 215 in a set order. The recommended product determiner 225 may select one of the spaces existing in the container as a space to load the template. The recommendation product determination unit 225 may select one template from the list of the arranged templates, remove the template from the list of templates, and simultaneously load a plurality of boxes constituting the selected template in the selected space.

Therefore, by stacking a plurality of boxes at once in one stacking attempt, the recommended product determination unit 225 can solve the three-dimensional box filling problem more quickly.

In the process of classifying the boxes loaded in the container according to the type of insurance product, the recommendation product determination unit 225 classifies the boxes loaded in the container into groups of boxes having the same attributes. As described above, the box has different volumes depending on the premium or coverage of the insurance product in which the box is divided. Therefore, the recommendation product determination unit may classify the boxes according to the volume of the boxes or the classification code of the object corresponding to the boxes.

In the process of determining the classified insurance product as an insurance product to be recommended to the customer, the recommendation product determination unit 225 may determine an insurance product having a condition of combining the boxes classified into the same group from the container as the insurance product to be recommended to the customer. have. For example, when 300 boxes having a volume corresponding to a premium of 334 won per 100,000 won guaranteed units are classified from the container, the recommendation product determination unit 225 provides insurance with a premium of 100,000 won for a coverage range of 30 million won. The product can be decided as an insurance product to recommend to the customer.

In the following configuration, the contract support unit 230 may provide the insurance product to be recommended by the recommendation product determination unit 225 to the customer, and connect it with the insurance agent at the request of the customer. Specifically, the contract support unit 230 includes information on the recommended insurance product determined by the recommended product determination unit 225. Generate a insurance recommendation result web page. The contract supporter 230 may transmit the generated webpage to the user device 100 through the communication unit 205.

When the contract support unit 230 receives a request for joining the recommended insurance product from the user device 100, the contract supporter 230 may select one insurance agent from the insurance agent list based on the address of the customer's personal information. In addition, the contract support unit 230 may transmit the personal information of the customer and the information on the recommended insurance product to the user device 100 registered in the personal information of the selected insurance agent, thereby connecting the customer and the insurance agent.

Hereinafter, hardware for implementing the logical component of the insurance recommendation server 200 as described above will be described in more detail.

3 is one of the present invention Example  According to the insurance recommendation server 200 according to the hardware configuration.

As shown in FIG. 3, the insurance recommendation server 200 may include a processor 250, a memory 255, a transceiver 260, an input / output device 265, and a data bus. Bus, 270) and storage (Storage, 275).

The processor 250 may implement operations and functions related to the insurance recommendation method based on the instructions according to the software 280a in which the insurance recommendation method residing in the memory 255 is implemented. In the memory 255, software 280a in which the insurance recommendation method is implemented may be loaded. The transceiver 260 may transmit / receive data with the user device 100 or the insurance company server 300. The input / output device 265 may receive data necessary for executing the insurance recommendation method and output information of the recommended insurance product. The data bus 270 is connected to the processor 250, the memory 255, the transceiver 260, the input / output device 265, and the storage 275 so that each component of the movement path for transferring data to each other. Can play a role.

The storage 275 may store an application programming interface (API), a library file, a resource file, and the like necessary for executing the software 280a in which the insurance recommendation method is implemented. The storage 275 may store software 280b in which an insurance recommendation method is implemented. In addition, the storage 275 may store a database 285 necessary to perform the insurance recommendation method. The insurance product management list, the customer management list, the box list, or the template list may be stored in the database 285, but is not limited thereto.

The software 280a or 280b for implementing an insurance recommendation method residing in the memory 255 or stored in the storage 275 may include objects corresponding to each of the plurality of insurance products in units of a plurality of virtual bins. Dividing into; generating a virtual container based on the customer's personal information and the monthly payable amount of the customer; and the total volume of the boxes loaded in the container relative to the volume of the container. Loading the at least one box into the container, classifying the at least one box loaded into the container by type of the insurance product such that the ratio is maximum, and recommending the classified insurance product to the customer. In order to execute the step of transmitting the web page, it may be a computer program recorded on the recording medium.

More specifically, the processor 250 may include an application-specific integrated circuit (ASIC), another chipset, a logic circuit, and / or a data processing device. The memory 255 may include read-only memory (ROM), random access memory (RAM), flash memory, a memory card, a storage medium, and / or another storage device. The transceiver 260 may include a baseband circuit for processing wired and wireless signals. The input / output device 265 may be an input device such as a keyboard, a mouse, and / or a joystick, a liquid crystal display (LCD), a light emitting diode (LED), an organic device, and the like. And a printing device such as a printer, a plotter, or the like, such as an organic light emitting diode (OLED) and / or an active organic light emitting diode (AMOLED).

When the embodiments included in the present specification are implemented in software, the above-described method may be implemented by a module (process, function, etc.) that performs the above-described function. The module resides in memory 255 and may be executed by processor 250. The memory 255 may be inside or outside the processor 250 and may be connected to the processor 250 by various well-known means.

Each component shown in FIG. 3 may be implemented by various means, for example, hardware, firmware, software, or a combination thereof. In the case of a hardware implementation, an embodiment of the present invention may include one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), FPGAs ( Field Programmable Gate Arrays), processors, controllers, microcontrollers, microprocessors, and the like.

In addition, in the case of the implementation by firmware or software, an embodiment of the present invention is implemented in the form of a module, procedure, function, etc. for performing the functions or operations described above, so that Can be recorded. Here, the recording medium may include a program command, a data file, a data structure, etc. alone or in combination. The program instructions recorded on the recording medium may be those specially designed and constructed for the present invention, or may be known and available to those skilled in computer software. For example, the recording medium may be a magnetic medium such as a hard disk, a floppy disk, or a magnetic tape, an optical media such as a compact disk read only memory (CD-ROM), a digital video disk (DVD), or a floppy. Magnetic-Optical Media, such as a Disk, and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, Flash Memory, and the like. Examples of program instructions may include high-level language code that can be executed by a computer using an interpreter, as well as machine code such as produced by a compiler. Such hardware devices may be configured to operate as one or more software to perform the operations of the present invention, and vice versa.

On the other hand, as described above, a customer who wishes to purchase insurance may be provided with an insurance recommendation service through a web page output to the user device 100. Hereinafter, a web page output to the user device 100 according to some embodiments of the present invention will be described in detail.

4 is one of the present invention Example  Of the input screen of the user device 100 according to It is an illustration . And  5 is one of the present invention Example  Of the output screen of the user device 100 according to It is an illustration .

As shown in FIG. 4, the user device 100 may correspond to a mobile computing device such as a smartphone. In addition, the user device 100 corresponding to the mobile computing device may output the insurance recommendation initial webpage 110 received from the insurance recommendation server 200 in a mobile version.

The insurance recommendation initial web page 110 may be included in the input objects 111 for receiving the customer's personal information and monthly payment amount from the user. Objects 111 for inputting customer's personal information and monthly payment amount include text box, scroll box, check box, radio box, modal dialog box. (modal dialog) or modals dialog may be included, but is not limited thereto.

In addition, the insurance recommendation initial web page 110 may include a button 113 for receiving an insurance product recommendation request from the user. When the button 113 included in the insurance recommendation initial webpage 110 is input, the user device 100 displays the personal information of the customer collected by the input objects 111 and the monthly payment amount that can be paid by the insurance recommendation server ( 200).

As shown in FIG. 5, the user device 100 may correspond to a stationary computing device such as a desktop. The user device 100 corresponding to the fixed computing device may output the recommended insurance result webpage 120 received from the insurance recommendation server 200 in a desktop version.

The insurance recommendation result webpage 120 may include information 121 about recommended insurance products. The information 121 regarding the recommended insurance product may be output in a structure such as a table or a tree.

The insurance recommendation result web page 120 may include an interface 123 for inputting a weight that is a reference when determining a recommended insurance product. The interface 123 to input the weight may be configured to include a bar graph to adjust the ratio of the index such as the brand value ranking of the insurance product or the monthly premium of the insurance product, but is not limited thereto.

In addition, the insurance recommendation result webpage 120 may include a button 125 for receiving a request for subscription of a recommended insurance product from a user. When the button 125 included in the insurance recommendation result webpage 120 is input, the user device 100 may transmit a request for joining the recommended insurance product to the insurance recommendation server 200.

Hereinafter, the concept of a box and a container for transforming and applying a problem of determining an insurance product to be recommended by the insurance recommendation server 200 according to an embodiment of the present invention into a 3D box filling problem will be described.

6 is one of the present invention Example  To explain the concept of a box 20 according to It is an illustration . And  7 is one of the present invention Example  To explain the concept of containers It is an illustration .

Referring to FIG. 6, boxes 20a, 20b, 20c,..., 20n; 20 are virtual unit configurations having a volume corresponding to a unit premium per standard guaranteed unit with respect to an insurance product.

As such, the box 20 may be generated by dividing it from the insurance product 10. In detail, the insurance recommendation server 200 may divide an object corresponding to the insurance product 10 into units of a plurality of boxes 20 based on one of a reference volume, a reference amount, and a standard guarantee unit. To this end, the volume corresponding to the unit premium per reference guaranteed unit may be managed by a separate matching table or hash table.

Referring to FIG. 7, the container 40 is a virtual unit space having a volume in which one or more boxes 20 may be loaded.

As such, the container 40 may be generated based on the customer's personal information and the monthly payment amount 30. For example, the insurance recommendation server 200 may identify an assigned risk value according to the combination of the age, gender, and occupation of the customer among the personal information of the customer. The insurance recommendation server 200 may determine the derived value as the two-dimensional width x depth of the container 40 by inputting the identified risk value as a key value of a pre-configured matching table or hash table. The insurance recommendation server 200 may identify a height of the container 40 corresponding to the amount of the monthly payable amount of the customer. The insurance recommendation server 200 may generate a container having a volume (width x depth x height) corresponding to the two-dimensional width value of the container 40 and the height value of the container.

Hereinafter, the insurance recommendation server 200 according to an embodiment of the present invention will be described a process of applying the three-dimensional box filling problem using the box 20 and the container 40.

8 is one of the present invention Example  Of 3D Box Fill Problem Algorithm It is an illustration . 9 is one of the present invention Example  To illustrate the merging of spaces along It is an illustration . 10 is one of the present invention Example  To explain the division of space according to It is an illustration . And  11 is one of the present invention Example  It is an illustration for explaining the classification of the box according.

Referring to FIG. 8, the insurance recommendation server 200 includes a plurality of boxes in the container 40 such that the total volume ratio of the boxes 20 loaded in the container 40 as compared with the volume of the container 40 is maximized. The fields 20-1, 20-2, and 20-3 can be loaded.

The plurality of boxes 20-1, 20-2, and 20-3 may have different volumes depending on the premium or coverage of the insurance product 10. Therefore, the insurance recommendation server 200 may sort the list of the plurality of boxes 20-1, 20-2, and 20-3 in the order determined by the weight. The insurance recommendation server 200 may select one box 20 from the sorted list, remove it from the list, and load the selected box 20 in the space in the container 40.

Referring to FIG. 9, when the box 20 cannot be loaded in a space (ie, a container or divided space, 40) selected for loading the box 20, the insurance recommendation server 200 may store the box 20. The third space 40-b and the selected space 40-a existing inside the container 40 and having a surface adjacent to the selected space 40-a for loading the same, the volume is further increased. It is possible to create a large new space 40-c. The insurance recommendation server 200 may attempt to load the selected box 20 in the created new space 40-c.

Referring to FIG. 10, after loading the selected box 20 in the space in the container 40, the insurance recommendation server 200 divides the space except the space in which the box 20 is loaded into the plurality of sub-spaces 40-1. , 40-2, 40-3). If one of the corners of the box 20 is loaded to touch one of the corners of the container 40, the insurance recommendation server 200 divides three sub-spaces 40-1 into the space excluding the space in which the box is loaded. , 40-2, 40-3). In addition, the insurance recommendation server 200 divides three sub-spaces 40-1, 40-2, and 40-3, and selects one of Top-to-Front, Side-to-Top, and Side-to-Front. You can divide by one.

Then, the insurance recommendation server 200, for each of the three divided sub-spaces 40-1, 40-2, 40-3, spaces 40-1, 40-2, 40-3 for loading the boxes. , A box 20 is loaded in the selected space, and the process of dividing the space excluding the space in which the box 20 is loaded into a plurality of sub-spaces can be recursively performed.

If there is no box 20 to be loaded in the container 40 anymore, or if there is no space for loading the box in the container 40 anymore, loading the box 20 to the container 40. Will end.

Referring to FIG. 11, after the loading of the box 20 on the container 40 is finished, the insurance recommendation server 200 displays the boxes 20 having the same properties as the box 20 loaded on the container 40. -1, 20-2, 20-3). As described above, the boxes 20-1, 20-2, and 20-3 have different volumes depending on the premium or coverage of the insurance product in which the boxes are divided. Accordingly, the insurance recommendation server 200 may classify the boxes according to the volume of the boxes or the classification code of the object corresponding to the boxes.

Finally, the insurance recommendation server 200 may determine an insurance product having a condition of combining boxes classified into the same group as an insurance product to be recommended to a customer.

Hereinafter, the process of performing the insurance recommendation method by the insurance recommendation server 200 according to an embodiment of the present invention will be described.

12 is one of the present invention Example  To explain how to recommend insurance It is a flowchart .

In describing the insurance recommendation method, a description overlapping with that described with reference to FIGS. 2 to 11 will not be repeated. In addition, it is assumed that the insurance recommendation server 200 collects information on insurance products and manages a box 20 for each insurance product before receiving a request for insurance product recommendation from a customer.

Referring to FIG. 12, the insurance recommendation server 200 may receive personal information of a customer and information of a monthly payment amount from the user device 100 (S100). The insurance recommendation server 200 may generate the container 40 based on the received personal information of the customer and the monthly payment amount (S200).

The insurance recommendation server 200 may load one or more boxes 20 in the container 40 such that the total volume ratio of the boxes 20 loaded in the container 40 is maximized relative to the volume of the container 40. It may be (S300).

The insurance recommendation server 200 may classify the boxes 20 loaded in the container 40 according to the type of insurance product (S400). The insurance recommendation server 200 may determine a corresponding insurance product corresponding to the sorted box as an insurance product to recommend, and transmit a web page including information of the insurance product to be recommended to the user device 100 ( S500).

Thereafter, the insurance recommendation server 200 may wait to receive an insurance design request from the user device 100 during the waiting time. Here, the waiting time may be a session holding time, but is not limited thereto. The insurance recommendation server 200 may determine whether an insurance design request has been received from the user device 100 within a waiting time (S600).

As a result of the determination, when the insurance design request is not received from the user device 100 within the waiting time, the insurance recommendation server 200 may terminate without performing the following steps. On the contrary, when the insurance design request is received from the user device 100 within the waiting time, the insurance recommendation server 200 may select one insurance agent based on the address of the customer (S700).

In addition, the insurance recommendation server 200 may transmit the personal information of the customer and the information about the recommended insurance product to the user device 100 registered in the personal information of the selected insurance agent, and request the insurance design (S800).

Hereinafter, the insurance recommendation server 200 according to an embodiment of the present invention will be described how to apply the three-dimensional box filling problem.

13 is one of the present invention Example  Algorithm to solve the 3D box fill problem It is a flowchart .

Referring to FIG. 13, after generating the container 40 (S200), the insurance recommendation server 200 may sort the list of boxes according to a set order (S310). Here, the order of sorting the boxes in the list may be determined by the weight or input weight provided from the customer.

The insurance recommendation server 200 may select one of the spaces existing in the container 40 as a space for loading the box 20 (S320). The insurance recommendation server 200 may select one box 20 from the sorted list (S330).

The insurance recommendation server 200 may determine whether the selected box 20 can be loaded in the selected space (S340). As a result of the determination, when the selected box 20 can be loaded in the selected space, the insurance recommendation server 200 may load the selected box 20 in the selected space (S350). The insurance recommendation server 200 may divide a space excluding a space in which the box 20 is loaded from the selected space into a plurality of sub-spaces (S360).

On the contrary, when it is impossible to load the selected box 20 in the selected space, the insurance recommendation server 200 may merge the selected space with the third space existing inside the container 40 when the insurance recommendation server 200 has a surface adjacent to the selected space. It can be determined whether or not (S370). As a result of the determination, when it is possible to merge the third space and the selected space, the insurance recommendation server 200 merges the third space and the selected space (S380), and loading of the selected box 20 in the merged space is performed. You can determine if it is possible. On the contrary, if there is no third space to merge with the selected space, the insurance recommendation server 200 may determine the selected space as an unavailable space in which a box cannot be loaded.

And, the insurance recommendation server 200 is each divided into a plurality of sub-spaces until there is no box 20 to be loaded anymore or there is no more space to load the box 20 in the container 40 For the step of selecting a space to load the box with respect to (S320) to divide the space (S360) can be performed recursively.

As described above, although the present specification and drawings disclose preferred embodiments of the present invention, in addition to the embodiments disclosed herein, other modifications based on the technical idea of the present invention may be implemented in the technical field to which the present invention belongs. It is self-evident to those of ordinary knowledge. In addition, although specific terms are used in the specification and the drawings, they are only used in a general sense to easily explain the technical contents of the present invention and to help the understanding of the present invention, and are not intended to limit the scope of the present invention. Accordingly, the above detailed description should not be construed as limiting in all respects but should be considered as illustrative. The scope of the invention should be selected by reasonable interpretation of the appended claims, and all changes within the equivalent scope of the invention are included in the scope of the invention.

In addition, the device or the terminal according to the present invention can be driven by a command to cause one or more processors to perform the functions and processes described above. For example, such instructions may include interpreted instructions, such as script instructions such as JavaScript or ECMAScript instructions, or executable instructions or other instructions stored on a computer readable medium. Furthermore, the device according to the present invention may be implemented in a distributed manner over a network, such as a server farm, or may be implemented in a single computer device.

Furthermore, a computer program (also known as a program, software, software application, script or code) mounted on an apparatus according to the invention and executing a method according to the invention comprises a compiled or interpreted language or a priori or procedural language. It can be written in any form of programming language, and can be deployed in any form, including stand-alone programs or modules, components, subroutines, or other units suitable for use in a computer environment. Computer programs do not necessarily correspond to files in the file system. A program may be in a single file provided to the requested program, in multiple interactive files (eg, a file that stores one or more modules, subprograms, or parts of code), or part of a file that holds other programs or data. (Eg, one or more scripts stored in a markup language document). The computer program may be deployed to run on a single computer or on multiple computers located at one site or distributed across multiple sites and interconnected by a communication network.

In addition, in describing the embodiments according to the present invention, although the operations are depicted in the drawings in a specific order, it is necessary to perform the operations in the specific order or the sequential order shown in order to obtain a desirable result or all the illustrated operations. Should not be understood as being performed. In certain cases, multitasking and parallel processing may be advantageous. In addition, the separation of the various system components of the above-described embodiments should not be understood as requiring such separation in all embodiments, and the described program components and systems will generally be integrated together into a single software product or packaged into multiple software products. It should be understood that it can.

User Devices: 100 Insurance Recommendation Servers: 200
Insurer server: 300
Communication unit: 205 Input / output unit: 210
Insurance Product Management Department: 215 Customer Management Department: 220
Recommended Product Decision: 225 Contract Support: 230

Claims (10)

The insurance recommendation server dividing an object corresponding to each of the plurality of insurance products into units of a plurality of virtual bins;
Generating, by the insurance recommendation server, a virtual container based on the personal information of the customer and the monthly payment amount of the customer;
Loading, by the insurance recommendation server, at least one box into the container such that a ratio of the total volume of the box loaded to the container to the volume of the container is maximized;
Classifying, by the insurance recommendation server, one or more boxes loaded in the container according to the type of insurance product; And
The insurance recommendation server recommending an insurance product corresponding to the classified box to the customer,
The box is a unit configuration having a volume corresponding to a unit premium per standard guaranteed unit with respect to the insurance product,
The container is a unit space having a volume corresponding to the two-dimensional width value of the container and the height value of the container, the two-dimensional width value of the container is identified according to the combination of the age, gender and occupation of the customer in the personal information of the customer And a height value of the container is a value corresponding to an amount of the monthly payable amount of the customer. The method of claim 1, wherein the step of loading the box in the container
Sorting the divided list of the plurality of boxes according to a preset order;
Selecting one of the spaces existing inside the container as a space for loading the box;
Selecting one box from the sorted list to remove from the list, and loading the selected box into the selected space; And
And dividing a space excluding the space in which the box is loaded from the selected space into a plurality of sub-spaces. The method of claim 2, wherein each of the divided plurality of sub-spaces
Wherein the step of selecting the box as a space to be loaded, loading into the selected space and dividing into the plurality of sub-spaces is performed recursively. The method of claim 2, wherein the step of loading in the selected space
If the selected box cannot be loaded in the selected space, after merging the selected space with the third space existing in the container and having a proximate surface adjacent to the selected space, Customized insurance recommendation method, characterized in that for loading the selected box in a merged space. The method of claim 2,
The sorting step includes sorting a list of templates consisting of a combination of the plurality of boxes in the order,
The loading of the space may include selecting one template from the list of templates, removing the template from the list of templates, and simultaneously loading the plurality of boxes constituting the selected template into the selected space. How to recommend a personalized insurance. The method of claim 2, wherein the aligning step
Characterized in that the boxes of the list are sorted in descending order of the brand value of the insurance products corresponding to the box, or in descending order of the monthly premium of the insurance products corresponding to the box. How to recommend customized insurance. delete delete The method of claim 1, wherein the two-dimensional width value of the container
And a value derived by inputting a risk value assigned according to a combination of the age, gender, and occupation of the customer as a key value in a hash table. Memory;
A processor processing an instruction loaded in the memory; And
In combination with a computing device configured to include a transceiver for transmitting and receiving data under control of the processor,
Dividing an object corresponding to each of the plurality of insurance products into units of a plurality of virtual bins by the processor;
Generating, by the processor, a virtual container based on the customer's personal information and the monthly payment amount of the customer;
Loading the at least one box into the container such that the processor has a maximum ratio of the total volume of the box loaded to the container to the volume of the container,
Classifying, by the processor, one or more boxes loaded in the container according to the type of insurance product; and
The processor controlling the transceiver to transmit a web page for recommending the insurance product corresponding to the classified box to the customer;
The box is a unit configuration having a volume corresponding to a unit premium per standard guaranteed unit with respect to the insurance product,
The container is a unit space having a volume corresponding to the two-dimensional width value of the container and the height value of the container, the two-dimensional width value of the container is identified according to the combination of the age, gender and occupation of the customer in the personal information of the customer And a height value of the container is a value corresponding to an amount of the monthly payable amount of the customer, wherein the height value of the container is a value corresponding to the risk value.

Images