JP7090268B2 - Insurance claim calculation device, insurance claim calculation method, and program - Google Patents

Description

Application of Article 30, Paragraph 2 of the Patent Act On December 30, 1991, Mitsui Sumitomo Insurance Co., Ltd. held MS & AD Mitsui Sumitomo News Release, Takashi Nakano, Seiji Hattori, Tomohiro Maruyama, Toshiyuki Araki. Invented "Insurance claim calculation device and method for calculating the amount of insurance claims paid for the subject property affected by flood damage". On March 23, 2nd year of Reiwa, Arithmer Inc. published AERA, Vol. 33, No. 14, Vol. 1790, pp. 17-18, Asahi Shimbun Publishing, Takashi Nakano, Seiji Hattori, Tomohiro Maruyama, Araki. Toshiyuki's invented "Insurance claim calculation device and method for calculating the amount of insurance claims paid for a property damaged by flooding" has been released.

The present invention relates to an insurance claim calculation device for calculating an insurance claim payment amount for a subject property suffered from flood damage, an insurance claim calculation method, and a program.

There is an insurance contract that pays insurance money for flood damage to a building caused by a flood caused by a typhoon or heavy rain. In the past, the amount of insurance payment was determined by a researcher visiting the site to measure the inundation height of the target property and referring to a quick reference table based on the measurement results. However, the inundation height must be measured for each of the multiple target properties. If the flooded area is widespread, there are problems such as increased man-hours and a long period of time to pay the insurance money. For example, Patent Document 1 discloses a contractor specifying device that acquires an aerial image, identifies a flooded area based on the features included in the aerial image, and identifies a contractor in the area.
Patent Document 1 Japanese Unexamined Patent Publication No. 2020-042640

However, the above-mentioned contractor identification device does not specify the degree of inundation. Therefore, it cannot always be said that the amount of insurance payment can be determined quickly.

In the first aspect of the present invention, it is an insurance money calculation device that calculates the amount of insurance money paid to the target property suffered from flood damage, and the actual measurement address and the obtained water depth at the time of flood damage are measured. An input unit that accepts input of water depth actual measurement information including a set of actual measurement values and the address of the target property, and based on multiple sets of actual measurement addresses and actual measurement values included in the water depth actual measurement information, at the time of flood damage at the address of the target property An insurance money calculation device including an estimation unit for estimating the water depth and a calculation unit for calculating the amount of insurance money paid for the target property based on the estimation result of the water depth is provided.

In the second aspect of the present invention, there is an insurance money calculation method for calculating the amount of insurance money paid for the target property suffering from flood damage, and the actual measurement address and the obtained water depth at the time of flood damage are measured. Based on the stage of accepting input of water depth actual measurement information including a set of actual measurement values and the address of the target property, and the actual measurement addresses and actual measurement values of multiple sets included in the actual measurement information of the water depth, the water depth at the time of flood damage at the address of the target property An insurance claim calculation method is provided that includes a step of estimating the amount of insurance claims and a step of calculating the amount of insurance claims paid for the target property based on the estimation result of the water depth.

In the third aspect of the present invention, in order to calculate the payment amount of the insurance money for the target property suffering from the inundation damage, the measured address and the actually measured value of the obtained water depth at the time of the inundation damage are measured on the computer. Estimate the water depth at the time of flood damage at the address of the target property based on the procedure for accepting the input of the actual measurement information of the water depth including the set of A program is provided to execute the procedure for calculating the amount of insurance payment for the target property based on the estimation result of the water depth.

The outline of the above invention does not list all the features of the present invention. A subcombination of these feature groups can also be an invention.

The configuration of the insurance money calculation device according to this embodiment is shown. The functional configuration of the insurance money calculation device according to this embodiment is shown. An example of water depth measurement information is shown. An example of target property information is shown. The flow of the insurance money calculation method according to this embodiment is shown. An example of map data is shown. An example of setting the analysis area is shown. The machine learning flow of the estimation model is shown. An example of training data generation is shown. The flow of water depth analysis by the estimation unit is shown. An example of the boundary condition estimated based on the measured water depth information is shown. An example of the estimation result of the water depth at the address of the target property based on the boundary conditions is shown. An example of a conversion table from water depth to inundation height is shown. An example of a conversion table from the amount of inundation to the amount of insurance payment is shown. An example of the configuration of the computer according to this embodiment is shown.

Hereinafter, the present invention will be described through embodiments of the invention, but the following embodiments do not limit the invention within the scope of the claims. Also, not all combinations of features described in the embodiments are essential to the means of solving the invention.

FIG. 1 shows the configuration of the insurance money calculation device 1 according to the present embodiment. The insurance money calculation device 1 is a computer device that calculates the amount of insurance money paid for the target property that has suffered flood damage. The insurance money calculation device 1 according to the present embodiment further generates an estimation model 7 for estimating the boundary conditions for the analysis area of the fluid analysis. However, a computer device different from the insurance claim calculation device 1 may generate the estimation model 7. The insurance money calculation device 1 includes a processor 2, an input device 3, a main storage device 4, an auxiliary storage device 5, and a communication module 8.

The processor 2 is one or more central processing units (CPUs), microprocessors (MPUs), and graphics processors (GPUs), and by executing program 6, the amount of insurance money paid to the computer device is calculated. The function of generating the estimation model 7 and the function of generating the estimation model 7 are expressed. The functional configuration of the insurance claim calculation device 1 that expresses these functions will be described later.

The input device 3 is a device that receives input of water depth actual measurement information and target property information. The input device 3 reads the water depth actual measurement information via a keyboard, a CD-ROM drive, or the like, and reads the target property information possessed by the manager who uses the insurance claim calculation device 1. The read information is stored in the main storage device 4. When the estimation model 7 is generated by another computer device, the input device 3 reads the estimation model 7 stored in the storage device and expands it to the auxiliary storage device 5.

The main memory device 4 is a training used when the insurance money calculation device 1 (processor 2) generates data such as water depth actual measurement information and target property information used when calculating the insurance money payment amount, and an estimation model 7. It is a device that temporarily stores data such as data, and may be a temporary storage device such as one or a plurality of static random access memories (SRAMs) and dynamic random access memories (DRAMs).

The auxiliary storage device 5 includes a storage device such as a hard disk drive (HDD) and stores the program 6 and the estimation model 7. The auxiliary storage device 5 may store training data for generating the estimation model 7 and map data used in the fluid analysis.

The communication module 8 is a device that communicates with an external server via a network. With the communication module 8, for example, map data for fluid analysis can be obtained from an external server.

FIG. 2 shows the functional configuration of the insurance claim calculation device 1 according to the present embodiment. The insurance money calculation device 1 expresses the functions of the input unit 11, the estimation unit 12, the learning unit 13, the comparison unit 14, and the calculation unit 15 by executing the program 6 by the processor 2.

The input unit 11 receives the water depth actual measurement information and the target property information input via the input device 3.

FIG. 3 shows an example of water depth actual measurement information. The water depth actual measurement information is the information obtained by the investigator going to the site affected by the _inundation and actually measuring the water depth (the height of the water surface from the ground) at the time of the inundation damage. Includes the measured value Hi ( _i = 1 to N) of the water depth at Y _i and its address. The number of sets N is an arbitrary integer of 1 or more, and N ≧ 3 in this embodiment. In this example, the measured address is read as longitude X _i and latitude Y _i (i = 1 to N).

FIG. 4 shows an example of the target property information. The target property information includes the contract number, the name of the insured person, the address _Xk , _Yk of the property covered by the insurance contract, the insurance target, the building information, the report of flood damage, etc. Includes information about insurance transfer accounts. The target property information is not limited to one set, and may include information on a plurality of sets of target properties. In this example, the address of the target property is read as longitude X _k and latitude Y _k . When representing the address or the like of another target property, the subscript k is replaced with another symbol l or the like.

Insurance coverage includes the distinction between "buildings only or buildings and household goods" or "household goods only". Since the amount of insurance payment differs depending on the insurance target even if the inundation height (the height of the water surface from the floor) is the same, the insurance payment amount is calculated from the estimation result (or inundation height) of the water depth based on this information. Change the conversion table used at the time.

Building information includes the number of floors and the type of detached house or condominium. Since the floor height differs depending on each building, the conversion from the estimation result of the water depth to the inundation height also differs. In this example, the conversion is made uniformly for each of the detached houses and condominiums. Therefore, based on this information, the conversion table used when converting the estimation result of the water depth to the inundation height is changed.

The declaration of inundation damage includes the situation of inundation damage that the insured declares by himself / herself. In this example, it is used to confirm the validity of the estimation result of the water depth by the estimation unit 12. If the estimated water depth is unreasonable, the amount of insurance payment may be determined based on the inundation damage report.

The insurance transfer account is information about the insured's account for paying insurance, including the account name, financial institution number, and account number.

The estimation unit 12 estimates the water depth at the time of flood damage at the address of the target property based on the water depth actual measurement information. Here, the estimation unit 12 uses the estimation model 7 described later to execute the fluid analysis using the measured addresses of N sets (for example, 3 sets) included in the water depth actual measurement information and the boundary conditions based on the actual measurement values. Estimate the water depth at the time of flood damage at the address of the target property. The details of the estimation of the water depth by the estimation unit 12 will be described later.

The learning unit 13 generates an estimation model 7 based on the boundary conditions regarding the water flow flowing in and out at the boundary of the analysis area and the training data including a plurality of sets of the water depth distribution in the analysis area for the boundary conditions. Here, the learning unit 13 inputs the water depth distribution included in the training data into the machine learning model, and uses the boundary conditions corresponding to the water depth distribution as correct answer data to generate the estimation model 7. The details of machine learning of the estimation model 7 by the learning unit 13 will be described later. The boundary condition is a parameter relating to the water flow on the boundary surface forming the unit section, and is, for example, the flow velocity when the water flow flows in and out of the boundary surface. However, the boundary condition is not limited to the flow velocity, and may be, for example, a water flow rate.

The comparison unit 14 compares the estimation result of the water depth by the estimation unit 12 with the inundation height reported by the insured person. As a result of the comparison, the comparison unit 14 outputs an error when the estimation result of the water depth and the declared inundation height are not within a predetermined range.

The calculation unit 15 calculates the amount of insurance payment for the target property based on the estimation result of the water depth by the estimation unit 12. At that time, the calculation unit 15 may convert the estimation result of the water depth based on the building information of the target property into the inundation height of the target property, and calculate the insurance payment amount based on the inundation height. Details of the calculation of the payment amount by the calculation unit 15 will be described later.

FIG. 5 shows a flow of the insurance money calculation method S100 executed by the insurance money calculation device 1 according to the present embodiment.

In step S102, the input unit 11 receives the input of the map data used in the fluid analysis. Map data includes elevation maps of flooded disaster areas, as shown in FIG. 6, with maps measured using satellites, maps measured using drones, or a combination thereof. It may be, or it may be an elevation map including buildings. The input unit 11 obtains the map data from the external server or reads the map data stored in the auxiliary storage device 5 in advance and expands the map data to the main storage device 4.

In step S104, the input unit 11 receives the input of the water depth actual measurement information. The water depth actual measurement information includes the actual measurement addresses Xi and _Yi of N sets and the actual measurement values _Hi ( _i = 1 to N) of the water depth at those addresses (see FIG. 3). In this example, N is a numerical value of 3 or more. The water depth actual measurement information is input by the administrator via the input device 3, and the processor 2 expands this to the main storage device 4.

In step S108, the estimation unit 12 selects a plurality of sets of actually measured addresses and actually measured values included in the water depth actual measurement information. In this embodiment, three sets (here, N = 3) of actually measured addresses X _i and Y _i and actually measured values _Hi (i = 1 to 3) are selected. However, the number selected is not limited to three sets.

In step S109, the estimation unit 12 sets the analysis area 99. The analysis area 99 is defined as a rectangular area as shown in FIG. 7, and is set to include at least the measured address selected in step S108 and the addresses _Xk and _Yk of the target property described later. In the analysis area 99, the measured addresses X _i , Y _i (i = 1 to N) of all the sets included in the water depth actual measurement information and the addresses of all selectable target properties (for example, X _l , Y _l ) are used. It may be set to include.

In step S110, the learning unit 13 uses three sets (here, N = 3) of actually measured addresses Xi and _Yi ( _i = 1 to 3) to calculate the water depth at an arbitrary address in the fluid analysis. Generate an estimation model 7 that estimates the boundary conditions for the purpose. The boundary condition is a condition relating to the amount of water flow flowing in and out at the boundary of the analysis area 99. By inputting the boundary requirement into the fluid analysis model, the water depth distribution within the analysis area 99 can be calculated.

FIG. 8 shows the flow of machine learning S110 of the estimation model 7 by the learning unit 13.

For convenience of explanation, as shown in FIG. 9, two of the four boundary surfaces (left side surface and upper side surface) are used as the inflow surface of the water flow, and the other two boundary surfaces (right side surface and lower side surface) are used. The outflow surface. For the outflow surface, the spatial gradient of physical quantities (flow velocity, water depth, etc.) is set to zero, and the outflow is free. Further, if the _inflow amount is the same, it is considered that the distribution of the entire water depth does not change so much. Only the flow velocity _UBC on the surface (upper side surface) is variable. The surface on which the flow velocity is fixed or variable may be the reverse of the above. The above-mentioned method for setting the boundary condition is an example, and the present embodiment is not limited to this. For example, both of the two inflow surfaces may be variable, and other boundary conditions may be set for the outflow surface. Further, the inflow surface may be one surface or three surfaces.

In step S112, the learning unit 13 generates training data. First, the learning unit 13 sets the flow velocity of the above-mentioned variable boundary surface as a boundary condition.

Next, the learning unit 13 executes the fluid analysis for the boundary condition (flow velocity _UBC ) given above. That is, the learning unit 13 substitutes the boundary conditions into the fluid analysis model given by the shallow water equation described later, and calculates the water depth distribution h in the analysis area 99. The water depth distribution h is given as a set of water depth values in each of the plurality of sections obtained by dividing the analysis area. The learning unit 13 stores the boundary condition (flow velocity _UBC ) and the calculated water depth distribution h in the analysis area 99 as a set.

Then, the learning unit 13 changes the value of the boundary condition and repeats the above procedure a plurality of times to create training data including a plurality of sets of boundary conditions and the water depth distribution h in the analysis area 99.

In this way, the training data is created by the same analysis as the fluid analysis used when estimating the water depth at the address of the target property. Thereby, it is possible to generate an estimation model 7 that appropriately estimates the boundary conditions for analyzing the water depth distribution by fluid analysis.

In step S114, the learning unit 13 generates the estimation model 7 using the training data created in step S112. The learning unit 13 extracts the water depth value h _i (= h (X _i , Y _i )) at the actually measured address (X _i , Y _i ) selected in step S108 from the water depth distribution h included in the training data. These are input to the machine learning model, and the estimation model 7 is generated by using the boundary condition _UBC corresponding to the water depth distribution h as the correct answer data. As the machine learning model, for example, a neural network can be adopted.

In step S120, the estimation unit 12 determines any of the measured values in the analysis area 99 based on the measured values _Hi (i = 1 to 3) at the measured addresses X _i and Y _i of three sets (here, N = 3). Estimate the water depth at the time of flood at the address.

FIG. 10 shows the flow of the water depth analysis S120 by the estimation unit 12.

In step S122, the estimation unit 12 estimates the boundary conditions (flow velocity _UBC ) for the analysis area 99 using the estimation model 7. As shown in FIG. 11, the boundary conditions for the analysis area 99 are estimated by inputting the measured values _Hi (i = 1 to 3) at the measured addresses X _i and Y _i of the three sets into the estimation model 7.

ここで、ｕは流速ベクトル（ただし、位置の関数）であり、ｈは水深、ｈ_０は標高、ｇは重力加速度である。式（１）の右辺第１項は水流に加わる重力を表し、第２項τ^ωは水流が流れる表面の粗さを表し、第３項τ^ｂｌｄは建物による抵抗を表す。推定部１２は、流体解析モデルに境界条件を代入し、数値解法により２つの方程式を連立して解く。それにより、図１２に示すように、解析エリア９９内での水深分布ｈが算出され、これに基づいて解析エリア９９内の任意の住所での浸水害時の水深が得られる。 In step S124, the estimation unit 12 executes the fluid analysis based on the boundary condition (flow velocity _UBC ) estimated in step S122. As a fluid analysis model (also called a shallow water equation), the equation of motion of equation (1) and the continuity equation of equation (2) are used.

Here, u is a flow velocity vector (however, a function of position), h is water depth, h ₀ is altitude, and g is gravitational acceleration. The first term on the right side of the equation (1) represents the gravity applied to the water flow, the second term τ ^ω represents the roughness of the surface on which the water flow flows, and the third term τ ^blend represents the resistance due to the building. The estimation unit 12 substitutes the boundary conditions into the fluid analysis model, and solves the two equations simultaneously by the numerical solution method. As a result, as shown in FIG. 12, the water depth distribution h in the analysis area 99 is calculated, and based on this, the water depth at any address in the analysis area 99 at the time of flood damage can be obtained.

By executing the fluid analysis for the analysis area 99 in this way, it is possible to generate the estimation model 7 in which the information of the actually measured address is reflected. Then, by using the estimation model 7, the boundary conditions in the analysis area 99 can be easily determined. A fluid analysis is performed based on such estimated boundary conditions to analyze the water depth distribution in the analysis area 99.

In step S125, the input unit 11 accepts the input of the target property information. The target property information includes the address _{Xk, Yk ,} insurance target, building information, flood damage report, etc. of the property covered by the insurance contract (see Fig. 4). The target property information is input by the administrator via the input device 3 and transmitted to the estimation unit 12. In addition, not only one set of target property information but also a plurality of sets of target property information may be input. Alternatively, the estimation unit 12 may select one or a plurality of sets of target property information from the target property information stored in the main storage device 4 in advance. In this embodiment, one set of target property information (address X _k , Y _k of the target property) is selected.

The process of step S125 does not necessarily have to be performed at this timing, and may be performed at an arbitrary timing before step S130.

In step S130, the calculation unit 15 approves the inundation height of the target property based on the estimation result of the water depth and the building information of the target property.

FIG. 13 shows an example of a conversion table from water depth to inundation height. The calculation unit 15 reads the insurance coverage from the building information of the target property, and if the target is only a building or a building and household goods, the conversion table above FIG. 13, and if the target is only household goods, the conversion table below FIG. Is used. Further, the calculation unit 15 reads the classification of the detached house or the condominium and the number of floors from the building information of the target property, applies it to the conversion table, and converts the estimated result of the water depth into the inundation height of the target property. In this example, regardless of whether the target property is covered by insurance or whether the target property is a detached house or a condominium, if the target property is a one-story building (one-story), the floor height is regarded as 60 cm, and the target property is In the case of a two-story building, the floor height is regarded as 350 cm, and the water depth is uniformly converted to the inundation height. However, if the target property is 3 stories or more, if the insurance target is only household goods, the inundation height is certified as 0 cm (that is, inundation is not certified), and if the insurance target is only the building or the building and household goods. The floor height is regarded as 350 cm, and the water depth is uniformly converted into the inundation height.

Since the floor height is different for each building, the conversion from water depth to inundation height is also different. In this way, while changing the conversion table according to the insurance coverage, the water depth is uniformly changed to the inundation height according to the number of floors of the building. By converting, the inundation height can be certified in a short period of time and with a small number of man-hours. In this example, a common conversion table is used regardless of whether it is a detached house or a condominium, but a different conversion table may be used. In this way, by certifying the inundation height of the target property based on the building information of the target property in addition to the estimation result of the water depth, the insurance payment amount can be calculated more appropriately based on the inundation height.

In step S132, the comparison unit 14 confirms the validity of the estimation result of the water depth at the address of the target property. In the present embodiment, the validity of the inundation height of the target property converted from the estimation result of the water depth in step S130 is confirmed. The comparison unit 14 reads the report of inundation damage by the insured from the target property information, and compares it with the inundation height converted in step S130 based on the reported number of inundated top floors and the inundation height. When the difference between the declared inundation height and the converted inundation height is within the allowable range, the comparison unit 14 determines that the estimation result of the water depth is valid (OK), and proceeds to the next step S134. If the difference is out of the permissible range, the comparison unit 14 determines that the water depth estimation result or the declared value may be incorrect (NG), and outputs an error (step S135). The allowable range of the difference may be, for example, a range in which the payment amount of the insurance money does not change even if there is the difference.

In step S134, the calculation unit 15 calculates the amount of insurance payment based on the inundation height converted in step S130. The calculation unit 15 converts the amount of insurance payment from the inundation height using the conversion table shown in FIG. In this example, the amount of insurance payment is determined according to the number of inundated top floors and the inundation height of the top floor.

In step S136, the calculation unit 15 determines whether or not to continue the calculation. If the target property information still remains, the process returns to step S125 to continue the calculation, and if it does not remain, the flow ends. In this example, since the target property information (positions of other target properties X _l , Y _l ) remains, the process returns to step S125 and the calculation of the insurance payment amount for the target property information is continued.

According to the insurance money calculation device 1 according to the present embodiment, the input unit that accepts the input of the actual measurement address including the actual measurement address of the actual water depth at the time of flood damage, the actual measurement value of the obtained water depth, and the address of the target property. 11. Estimating unit that estimates the water depth at the time of flood damage at the address of the target property based on multiple sets of measured addresses and measured values included in the water depth actual measurement information 12. Insurance for the target property based on the estimation result of the water depth. A calculation unit 15 for calculating the amount of money to be paid is provided. By estimating the water depth at the time of flood damage at the address of the target property from the actual measurement values at the actual measurement addresses of multiple sets included in the actual measurement information of the water depth and the address of the target property, the insurance money for the target property can be obtained in a short period and with a small number of man-hours. It is possible to calculate the payment amount.

According to the insurance claim calculation method according to the present embodiment, the stage of accepting the input of the actual measurement address including the actual measurement address of the actual water depth at the time of flood damage, the actual measurement value of the obtained water depth, and the address of the target property, the water depth. At the stage of estimating the water depth at the time of flood damage at the address of the target property based on the actual measurement address and the actual measurement value of multiple sets included in the actual measurement information, the amount of insurance money paid to the target property based on the estimation result of the water depth Prepare for the calculation stage. By estimating the water depth at the time of flood damage at the address of the target property from the actual measurement values at the actual measurement addresses of multiple sets included in the actual measurement information of the water depth and the address of the target property, the insurance money for the target property can be obtained in a short period and with a small number of man-hours. It is possible to calculate the payment amount.

The insurance money calculation device 1 according to the present embodiment generates an estimation model 7 and executes a water depth analysis using the estimation model 7, but instead of this, another computer device generates an estimation model 7. However, the insurance money calculation device 1 may use this to analyze the water depth.

In this embodiment, when the estimation model 7 is generated, it is not necessary to generate the estimation model 7 by using all the actually measured addresses included in the water depth actual measurement information. For example, the learning unit 13 generates a plurality of estimation models 7 based on a part of a plurality of sets of actually measured addresses included in the water depth actual measurement information, and the estimation unit 12 estimates a plurality of boundary conditions from the plurality of estimation models 7. However, the water depth may be estimated by averaging the plurality of boundary conditions and substituting the averaged boundary conditions into the fluid analysis model.

Various embodiments of the present invention may be described with reference to flowcharts and block diagrams, wherein the block is (1) a stage of the process in which the operation is performed or (2) a device having a role of performing the operation. May represent a section of. Specific stages and sections are implemented by dedicated circuits, programmable circuits supplied with computer-readable instructions stored on computer-readable media, and / or processors supplied with computer-readable instructions stored on computer-readable media. It's okay. Dedicated circuits may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. A programmable circuit is a memory element such as logical AND, logical OR, logical XOR, logical NAND, logical NOR, and other logical operations, flip-flops, registers, field programmable gate arrays (FPGAs), programmable logic arrays (PLA), etc. May include reconfigurable hardware circuits, including, etc.

The computer readable medium may include any tangible device capable of storing instructions executed by the appropriate device, so that the computer readable medium having the instructions stored therein is specified in a flow chart or block diagram. It will be equipped with a product that contains instructions that can be executed to create means for performing the operation. Examples of computer-readable media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, and the like. More specific examples of computer-readable media include floppy (registered trademark) disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), Electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disc read-only memory (CD-ROM), digital versatile disc (DVD), Blu-ray (RTM) disc, memory stick, integrated A circuit card or the like may be included.

Computer-readable instructions are assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or object-oriented programming such as Smalltalk, JAVA®, C ++, etc. Includes either source code or object code written in any combination of one or more programming languages, including languages, and traditional procedural programming languages such as the "C" programming language or similar programming languages. good.

Computer-readable instructions are used locally or to a local area network (LAN), wide area network (WAN) such as the Internet, to a general purpose computer, a special purpose computer, or the processor or programmable circuit of another programmable data processing device. ) May execute computer-readable instructions to create means for performing the operations specified in the flowchart or block diagram. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, and the like.

FIG. 15 shows an example of a computer 2200 in which a plurality of aspects of the present invention may be embodied in whole or in part. The program installed on the computer 2200 can cause the computer 2200 to function as an operation associated with the device according to an embodiment of the present invention or as one or more sections of the device, or the operation or the one or more. Sections can be run and / or the computer 2200 can be run a process according to an embodiment of the invention or a stage of such process. Such a program may be run by the CPU 2212 to cause the computer 2200 to perform certain operations associated with some or all of the blocks of the flowcharts and block diagrams described herein.

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

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

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

The ROM 2230 contains a boot program or the like executed by the computer 2200 at the time of activation, and / or a program depending on the hardware of the computer 2200. The input / output chip 2240 may also connect various input / output units to the input / output controller 2220 via parallel ports, serial ports, keyboard ports, mouse ports, and the like.

The program is provided by a computer-readable medium such as a DVD-ROM 2201 or an IC card. The program is read from a computer-readable medium, installed in a hard disk drive 2224, RAM2214, or ROM2230, which is also an example of a computer-readable medium, and executed by the CPU 2212. The information processing described in these programs is read by the computer 2200 and provides a link between the program and the various types of hardware resources described above. The device or method may be configured to implement the manipulation or processing of information in accordance with the use of computer 2200.

For example, when communication is executed between the computer 2200 and an external device, the CPU 2212 executes a communication program loaded in the RAM 2214, and performs communication processing on the communication interface 2222 based on the processing described in the communication program. You may order. Under the control of the CPU 2212, the communication interface 2222 reads and reads transmission data stored in a transmission buffer processing area provided in a recording medium such as a RAM 2214, a hard disk drive 2224, a DVD-ROM 2201, or an IC card. The data is transmitted to the network, or the received data received from the network is written to the reception buffer processing area provided on the recording medium.

Further, the CPU 2212 makes the RAM 2214 read all or necessary parts of the file or the database stored in the external recording medium such as the hard disk drive 2224, the DVD-ROM drive 2226 (DVD-ROM2201), and the IC card. Various types of processing may be performed on the data on the RAM 2214. The CPU 2212 then writes back the processed data to an external recording medium.

Various types of information such as various types of programs, data, tables, and databases may be stored in recording media and processed. The CPU 2212 describes various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, and information retrieval described in various parts of the present disclosure with respect to the data read from the RAM 2214. Various types of processing may be performed, including / replacement, etc., and the results are written back to RAM 2214. Further, the CPU 2212 may search for information in a file, a database, or the like in the recording medium. For example, when a plurality of entries each having an attribute value of the first attribute associated with the attribute value of the second attribute are stored in the recording medium, the CPU 2212 specifies the attribute value of the first attribute. Search for an entry that matches the condition from the plurality of entries, read the attribute value of the second attribute stored in the entry, and associate it with the first attribute that satisfies the predetermined condition. The attribute value of the second attribute obtained may be acquired.

The program or software module described above may be stored on or near a computer 2200 on a computer-readable medium. Also, a recording medium such as a hard disk or RAM provided in a dedicated communication network or a server system connected to the Internet can be used as a computer readable medium, thereby providing the program to the computer 2200 over the network. do.

Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various changes or improvements can be made to the above embodiments. It is clear from the description of the claims that the form with such changes or improvements may be included in the technical scope of the present invention.

The order of execution of each process such as operation, procedure, step, and step in the apparatus, system, program, and method shown in the claims, specification, and drawings is particularly "before" and "prior to". It should be noted that it can be realized in any order unless the output of the previous process is used in the subsequent process. Even if the scope of claims, the specification, and the operation flow in the drawings are explained using "first", "next", etc. for convenience, it means that it is essential to carry out in this order. It's not a thing.

1 ... insurance money calculation device, 2 ... processor, 3 ... input device, 4 ... main memory device, 5 ... auxiliary storage device, 6 ... program, 7 ... estimation model, 8 ... communication module, 11 ... input unit, 12 ... estimation Unit, 13 ... Learning unit, 14 ... Verification unit, 15 ... Calculation unit, 99 ... Analysis area, 2200 ... Computer, 2201 ... DVD-ROM, 2210 ... Host controller, 2214 ... RAM, 2216 ... Graphic controller, 2218 ... Display device 22,20 ... input / output controller, 2222 ... communication interface, 2224 ... hard disk drive, 2226 ... DVD-ROM drive, 2240 ... input / output chip, 2242 ... keyboard.

Claims (10)

It is an insurance money calculation device that calculates the amount of insurance money paid for the target property that has suffered flood damage.
An input unit that accepts input of the actual measurement address including the actual measurement address of the actual water depth at the time of flood damage, the actual measurement information of the obtained water depth, and the address of the target property.
An estimation unit that estimates the water depth at the time of the flood damage at the address of the target property based on a plurality of sets of measured addresses and measured values included in the water depth actual measurement information.
A calculation unit that calculates the amount of insurance payments for the target property based on the estimation result of the water depth.
Insurance claim calculation device equipped with. The insurance claim calculation device according to claim 1, wherein the estimation unit selects a plurality of sets of actual measurement addresses and actual measurement values from the water depth actual measurement information based on the address of the target property. The input unit further accepts the input of the self-report of the water depth by the customer.
Further, a comparison unit that compares the self-reported value of the water depth with the estimation result of the water depth and outputs an error when the difference between the self-reported value and the estimation result of the water depth is out of the allowable range. The insurance claim calculation device according to claim 1 or 2 , wherein the permissible range is a range in which the calculation result of the insurance claim payment amount does not change . The input unit further accepts input of building information of the target property.
From claim 1, the calculation unit recognizes the inundation height of the target property based on the estimation result of the water depth and the building information of the target property, and calculates the payment amount of the insurance money based on the inundation height. The insurance claim calculation device according to any one of 3. The estimation unit inputs actual measurement values into the estimation model corresponding to the plurality of sets of actual measurement addresses, estimates boundary conditions for the analysis area, and executes fluid analysis based on the boundary conditions in the analysis area. The insurance claim calculation device according to any one of claims 1 to 4, which analyzes the water depth distribution of the above. The insurance claim calculation device according to claim 5, wherein the estimation unit sets an analysis area so as to include the actual measurement address of the plurality of sets and the address of the target property. Machine learning by extracting the water depth values at the measured addresses of the plurality of sets from the training data including the boundary conditions regarding the water flow flowing in and out at the boundary of the analysis area and the training data including the plurality of sets of the water depth distribution in the analysis area for the boundary conditions. The insurance claim calculation device according to claim 5 or 6, further comprising a learning unit that inputs to a model and uses the boundary conditions corresponding to the water depth distribution as correct answer data to generate the estimation model. The learning unit determines a plurality of boundary conditions for the analysis area, performs the fluid analysis for each of the plurality of boundary conditions, calculates the water depth distribution in the analysis area, and creates the training data. , The insurance claim calculation device according to claim 7. This is an insurance claim calculation method that calculates the amount of insurance claims paid for a property that has suffered flood damage.
The stage of accepting the input of the actual measurement address including the actual measurement address of the actual water depth at the time of the inundation damage, the actual measurement information of the obtained water depth, and the address of the target property by the insurance money calculation device .
The stage of estimating the water depth at the time of the flood damage at the address of the target property based on the actual measurement addresses and the actual measurement values of a plurality of sets included in the water depth actual measurement information by the insurance money calculation device .
The stage of calculating the insurance payment amount for the target property based on the estimation result of the water depth by the insurance money calculation device, and
Insurance claim calculation method. To calculate the amount of insurance payment for the inundated property, use a computer
The procedure for accepting the input of the actual measurement address including the actual measurement address of the actual water depth at the time of the flood damage, the actual measurement information of the obtained water depth, and the address of the target property, and the procedure for accepting the input of the address of the target property.
A procedure for estimating the water depth at the time of the flood damage at the address of the target property based on a plurality of sets of measured addresses and measured values included in the water depth actual measurement information, and a procedure for estimating the water depth at the time of the inundation damage.
A procedure for calculating the amount of insurance payment for the target property based on the estimation result of the water depth, and
A program to execute.

Images