Insurance underwriting method and device using data preprocessing

Abstract

The present disclosure relates to an insurance underwriting method and device using data preprocessing. The insurance underwriting method comprises: a step for receiving medical history data related to a medical history of a customer; a step for generating structured data by preprocessing the medical history data; and a step for generating, on the basis of the structured data, injury-and-illness examination information for each type of injury and illness of the customer, wherein the structured data can include information related to at least one among the type of injury and illness, the presence or absence of notice of injury and illness, or a treatment history.

Description

Insurance underwriting method and device using data preprocessing

[0001] The present disclosure relates to an insurance underwriting method and apparatus, and specifically to an insurance underwriting method and apparatus using data preprocessing.

[0002]

[0003] Insurance companies approve insurance coverage for individuals who express an intention to purchase it through underwriting. Underwriting refers to the process in which an insurance company classifies the risk level of a target customer based on physical, environmental, moral, and financial criteria—such as occupation, age, income, health status, and purpose of enrollment—limits coverage appropriate to the degree of risk, and determines the final approval of insurance coverage.

[0004] Insurance underwriting has traditionally been based on expert experience and statistical data. Underwriting based on expert experience and statistical data is time-consuming and costly. Recently, driven by advancements in big data and AI technologies, the introduction of AI is being attempted as a precise and rapid evaluation technique.

[0005] Data utilized in the insurance industry possesses diverse formats and characteristics, and data incompleteness, noise, and bias can negatively impact the training and predictive performance of AI models. Furthermore, the opacity of the AI ​​model's decision-making process may lead to a lack of explainability regarding the results. Consequently, this can cause difficulties in meeting the requirements of insurance companies' internal management systems and government regulations.

[0006]

[0007] The present disclosure provides an insurance underwriting method, a computer program, and an apparatus for solving the above-mentioned problems.

[0008] The technical problem of the present disclosure is to provide an insurance underwriting method, a computer program, and an apparatus capable of providing a technology for preprocessing data used in insurance so that an AI model can learn and predict.

[0009] The technical problem of the present disclosure is to provide an insurance underwriting method, a computer program, and an apparatus that reduce the time and cost required for underwriting by utilizing an AI model in underwriting.

[0010]

[0011] The present disclosure may be implemented in various ways, including methods, devices, or computer programs stored on a readable storage medium.

[0012] According to one embodiment of the present disclosure, an insurance screening method comprises the steps of receiving medical history data associated with a customer's medical history, generating structured data by preprocessing the medical history data, and generating disease screening information for a customer by disease type based on the structured data, wherein the structured data may include information associated with at least one of the disease type, the presence or absence of disclosure of the disease, or treatment history.

[0013] According to one embodiment of the present disclosure, medical history data includes accident history data associated with a customer's accident history and notification data associated with a medical history notified by the customer, and the accident history data includes first accident history data classified into accident history units, and the step of generating structured data may include the step of generating second accident history data in which at least a portion of the first accident history data is aggregated based on the first accident history data, and the step of generating structured data based on the second accident history data and notification data.

[0014] According to one embodiment of the present disclosure, the first thinking ability data includes a first_1 thinking ability data including information associated with a first disease type and a first_2 thinking ability data including information associated with a second disease type, and the step of generating the second thinking ability data may include the step of calculating the association between the first disease type and the second disease type, and the step of generating at least a portion of the second thinking ability data based on the association.

[0015] According to one embodiment of the present disclosure, the first thinking ability data includes a first_3 thinking ability data including information associated with a first time point as information associated with a first category, and a first_4 thinking ability data including information associated with a second time point as information associated with a first category, and the step of generating the second thinking ability data may include generating at least a portion of the second thinking ability data based on the first_3 thinking ability data and the first_4 thinking ability data in response to a determination that the difference between the first time point and the second time point is smaller than a threshold period.

[0016] According to one embodiment of the present disclosure, information associated with the first category may include information associated with at least one of the time of the accident or the time of treatment.

[0017] According to one embodiment of the present disclosure, the first thinking ability data includes a first_5 thinking ability data including information associated with a first numerical value as information associated with a second category, and a first_6 thinking ability data including information associated with a second numerical value as information associated with a second category, and the step of generating the second thinking ability data may include the step of generating at least a portion of the second thinking ability data based on at least one of the first numerical value or the second numerical value.

[0018] According to one embodiment of the present disclosure, information associated with the second category may include information associated with at least one of the number of days of hospitalization, the number of days of outpatient treatment, or the number of surgeries.

[0019] According to one embodiment of the present disclosure, the step of generating structured data based on second thinking ability data and notification data may include determining whether at least a part of the second thinking ability data, which is at least a part of the second_1 thinking ability data, and at least a part of the notification data are related to each other, and generating at least a part of the structured data, which is at least a part of the first structured data, based on at least a part of the second_1 thinking ability data and notification data.

[0020] According to one embodiment of the present disclosure, the second thinking ability data includes second_2 thinking ability data that is different from second_1 thinking ability data, and the step of generating structured data based on the second thinking ability data and notification data may further include the step of generating second structured data, which is at least a part of the structured data, based on the second_2 thinking ability data.

[0021] According to one embodiment of the present disclosure, structured data includes information classified into a third category associated with the presence or absence of notification of a disease, the first structured data includes information associated with notification of a disease as information of the third category, and the second structured data may include information associated with non-notification of a disease as information of the third category.

[0022] According to one embodiment of the present disclosure, the method may further include the step of requesting additional notification data associated with a disease notification in response to some of the information included in the structured data satisfying a reference condition.

[0023] According to one embodiment of the present disclosure, an electronic device comprises a communication module, a memory, and at least one processor connected to the memory and configured to execute at least one computer-readable program included in the memory, and may have at least one program. It includes instructions for receiving medical history data associated with a customer's medical history, generating structured data classified by disease type by preprocessing the medical history data, and generating disease screening information for a customer by disease type based on the structured data, and the structured data may include information associated with at least one of the disease type, the presence or absence of notification of the disease, or treatment history.

[0024]

[0025] According to one embodiment of the present disclosure, an insurance review performed by an insurance review device can be carried out quickly and with reduced time and cost compared to an insurance review performed based on expert experience and statistical models.

[0026] According to one embodiment of the present disclosure, while there may be differences in judgment among examiners in insurance reviews, the insurance review device can make consistent judgments, thereby improving the reliability of the insurance review.

[0027] According to one embodiment of the present disclosure, structured data can be generated by structuring amorphous notification data and thinking ability data. The structured data can be optimized for use with machine learning models, etc.

[0028] According to one embodiment of the present disclosure, the convenience of insurance underwriting can be increased by conducting insurance underwriting through structured data.

[0029] The effects of the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art to which the present disclosure pertains (hereinafter referred to as "person skilled in the art") from the description in the claims.

[0030]

[0031] Embodiments of the present disclosure will be described with reference to the accompanying drawings described below, wherein similar reference numerals indicate similar elements, but are not limited thereto.

[0032] FIG. 1 is a schematic diagram showing an insurance screening device according to one embodiment of the present disclosure.

[0033] FIG. 2 is a schematic diagram showing a configuration in which an information processing device is connected to communicate with a plurality of user terminals to perform insurance screening according to one embodiment of the present disclosure.

[0034] FIG. 3 is a block diagram showing the internal configuration of a user terminal and an information processing device according to one embodiment of the present disclosure.

[0035] FIG. 4 is a drawing for explaining an example of a data preprocessing unit according to one embodiment of the present disclosure.

[0036] FIG. 5 is a drawing for explaining thinking ability data according to one embodiment of the present disclosure.

[0037] FIG. 6 is a drawing for explaining structured data according to one embodiment of the present disclosure.

[0038] FIG. 7 is a drawing for explaining an example of a disease examination unit according to one embodiment of the present disclosure.

[0039] FIG. 8 is a block diagram of a disease examination unit according to one embodiment of the present disclosure.

[0040] FIG. 9 is a block diagram of a disease examination unit according to one embodiment of the present disclosure.

[0041] FIG. 10 is a drawing for explaining an example of a score calculation model according to one embodiment of the present disclosure.

[0042] FIG. 11 is a drawing for explaining a collateral examination unit according to one embodiment of the present disclosure.

[0043] FIG. 12 is a flowchart illustrating an example of an insurance screening method according to one embodiment of the present disclosure.

[0044] FIG. 13 is a flowchart illustrating an example of an insurance screening method according to one embodiment of the present disclosure.

[0045]

[0046] Hereinafter, specific details for implementing the present disclosure will be described in detail with reference to the attached drawings. However, in the following description, specific descriptions regarding widely known functions or configurations will be omitted if there is a risk that the gist of the present disclosure may be unnecessarily obscured.

[0047] In the attached drawings, identical or corresponding components are assigned the same reference numerals. Additionally, in the description of the following embodiments, the description of identical or corresponding components may be omitted. However, even if a description of a component is omitted, it is not intended that such component is not included in any embodiment.

[0048] The advantages and features of the disclosed embodiments and the methods for achieving them will become clear by referring to the embodiments described below in conjunction with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below but may be implemented in various different forms, and the embodiments provided are merely to make the present disclosure complete and to fully inform those skilled in the art of the scope of the invention.

[0049] The terms used in this specification will be briefly explained, and the disclosed embodiments will be described in detail. The terms used in this specification have been selected to be as generally used as possible, taking into account their functions in this disclosure; however, these terms may vary depending on the intent of those skilled in the art, case law, the emergence of new technologies, etc. Additionally, in specific cases, terms may be arbitrarily selected by the applicant, and in such cases, their meanings will be described in detail in the relevant description of the invention. Therefore, the terms used in this disclosure should be defined not merely by their names, but based on their meanings and the content throughout this disclosure.

[0050] In this specification, singular expressions include plural expressions unless the context clearly specifies them as singular. Additionally, plural expressions include singular expressions unless the context clearly specifies them as plural. Throughout the specification, when a part is described as including a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0051] Additionally, the terms "module" or "part" as used in the specification refer to software or hardware components, and the "module" or "part" performs certain roles. However, the meaning of "module" or "part" is not limited to software or hardware. The "module" or "part" may be configured to reside in an addressable storage medium or configured to operate one or more processors. Thus, as an example, the "module" or "part" may include components such as software components, object-oriented software components, class components, and task components, and at least one of processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, or variables. The components and the functions provided within the "module" or "part" may be combined into a smaller number of components and "modules" or "parts," or further separated into additional components and "modules" or "parts."

[0052] According to one embodiment of the present disclosure, a “module” or “part” may be implemented as a processor and memory. The term “processor” should be broadly interpreted to include a general-purpose processor, a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a controller, a microcontroller, a state machine, etc. In some contexts, the term “processor” may refer to an application-specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), etc. The term “processor” may also refer to a combination of processing devices, such as, for example, a combination of a DSP and a microprocessor, a combination of multiple microprocessors, a combination of one or more microprocessors combined with a DSP core, or any other combination of such configurations. Additionally, the term “memory” should be broadly interpreted to include any electronic component capable of storing electronic information. "Memory" may refer to various types of processor-readable media, such as Random Access Memory (RAM), Read-Only Memory (ROM), Non-Volatile Random Access Memory (NVRAM), Programmable Read-Only Memory (PROM), Erasable-Programmable Read-Only Memory (EPROM), Electrically Erasable PROM (EEPROM), Flash Memory, Magnetic or Optical Data Storage Devices, Registers, etc. If a processor can read information from memory and / or write information to memory, the memory is said to be in an electronic communication state with the processor. Memory integrated into a processor is in an electronic communication state with the processor.

[0053] In the present disclosure, the "system" may include at least one of a server device and a cloud device, but is not limited thereto. For example, the system may be composed of one or more server devices. As another example, the system may be composed of one or more cloud devices. As yet another example, the system may be configured and operated with both a server device and a cloud device.

[0054] In the present disclosure, a “machine learning model” may include any model used to infer an answer to a given input. According to one embodiment, a machine learning model may include an artificial neural network model comprising an input layer, a plurality of hidden layers, and an output layer. Each layer may include a plurality of nodes. In the present disclosure, each of the plurality of machine learning models is described as a separate machine learning model, but is not limited thereto, and some or all of the plurality of machine learning models may be implemented as a single machine learning model. Additionally, a single machine learning model may include a plurality of machine learning models. In the present disclosure, the terms machine learning model and artificial neural network model may be used interchangeably to refer to the same or similar models.

[0055] In the present disclosure, "accident history" may refer to information related to the history of accidents experienced by a customer. An accident may include cases where a disease or the like occurred. For example, the accident history may include information regarding the time of the accident, the type of illness, the number of days of hospitalization, the number of days of outpatient treatment, the number of surgeries, whether surgery was performed, whether the disease recurred, etc.

[0056] In the present disclosure, "treatment history" may refer to information related to treatment performed for an accident. Treatment history may be included in accident history. For example, treatment history may include information regarding the number of days of hospitalization, number of outpatient visits, number of surgeries, whether surgery was performed, etc.

[0057] FIG. 1 is a schematic diagram showing an insurance screening device (100) according to one embodiment of the present disclosure.

[0058] An insurance contract may refer to a contract entered into between an insurance company and its customers. An insurance contract may refer to a contract that becomes effective when one party pays an agreed-upon premium and the other party agrees to pay a certain insurance amount or other benefits in the event of an uncertain accident involving property, life, or body. In one embodiment, an insurance contract may include personal insurance. Personal insurance may include life insurance, health insurance, accident insurance, etc.

[0059] An insurance company may conduct an examination regarding an insurance product for a customer who wishes to enter into an insurance contract. For example, the insurance company may examine the customer's past medical history, etc., to determine whether the customer is eligible to subscribe to the insurance product. The insurance company may use an insurance examination device (100) to examine the customer's insurance subscription.

[0060] In one embodiment, the insurance screening device (100) may receive medical history data (110) associated with a customer's medical history for the purpose of screening the customer's insurance application. The insurance screening device (100) may receive insurance product information (120) associated with an insurance product that the customer wishes to subscribe to. Based on the medical history data (110) and the insurance product information (120), the insurance screening device (100) may output insurance screening information (130) associated with the results of the insurance screening for the customer.

[0061] In one embodiment, the insurance underwriting device (100) may include a data preprocessing unit (102), a disease underwriting unit (104), and a coverage underwriting unit (106). The data preprocessing unit (102) of the insurance underwriting device (100) may receive medical history data (110) associated with a customer's medical history. By preprocessing the medical history data, the data preprocessing unit (102) may generate structured data classified by disease type. The method by which the data preprocessing unit (102) generates structured data will be described in detail with reference to FIGS. 4 to 6.

[0062] In one embodiment, the medical history data (110) may include accident history data associated with the customer's accident history. For example, the accident history data may include information regarding the time of the accident, type of disease, number of days of hospitalization, number of days of outpatient treatment, number of surgeries, treatment history, etc. The accident history data may include information regarding the customer's name, gender, time of birth, time of the accident, number of days of hospitalization, number of days of outpatient treatment, time of hospitalization, time of discharge, whether surgery was performed, number of hospitalizations, number of outpatient treatments, number of surgeries, type of disease, etc. The type of disease may be expressed as an ICD code, KCD code, etc.

[0063] In one embodiment, accident history data may be obtained from the insurance company's database, the database of the insurance company's related organizations (e.g., Health Insurance Review & Assessment Service, National Health Insurance Service, Korea Credit Information Service, etc.). The accident history data may include information regarding points in time, periods, etc., associated with the customer's accident history. For example, the accident history data may include information regarding the time of the accident, the time of the insurance claim, the duration of the illness, the time of hospitalization, etc.

[0064] In one embodiment, the medical history data (110) may include disclosure data associated with the medical history disclosed by the customer. The disclosure data may include information regarding the time of the accident, the type of illness, the number of days of hospitalization, the number of days of outpatient treatment, the number of surgeries, treatment history, etc. The disclosure data may be obtained by the insurance company requesting it from the customer. For example, the insurance company may provide the customer with a questionnaire in a prescribed form, and the insurance company may obtain the disclosure data by having the customer answer the questionnaire.

[0065] In one embodiment, the disease screening unit (104) may receive structured data transmitted from the data preprocessing unit (102). The disease screening unit (104) may extract information regarding at least one disease type associated with the structured data. Then, the disease screening unit (104) may generate disease screening information for each disease type based on the information regarding at least one disease type and the structured data.

[0066] In one embodiment, the disease screening unit (104) may further receive insurance product information (120) associated with the insurance product that the customer intends to subscribe to. For example, the insurance product information (120) may include information regarding a predetermined insurance product, such as information regarding the insurance product that the customer intends to subscribe to. Based on the insurance product information (120) and structured data, the disease screening unit (104) may generate disease screening information for each type of disease. The method by which the disease screening unit (104) generates disease screening information is described in detail with reference to FIGS. 7 through 10.

[0067] In one embodiment, the insurance product information (120) may include information regarding the type of insurance product. The insurance product may be associated with multiple types. The first type of the insurance product may be associated with coverage limitation. The second type of the insurance product may be a standard type of insurance product and may differ from the first type. In the first type of the insurance product, an insurance screening result that limits at least one of the multiple coverages may be generated. However, insurance screening results such as acceptance with a premium surcharge, conditional acceptance, etc., may be omitted or not generated. Conditional acceptance may refer to accepting insurance under the condition that it does not provide coverage for the occurrence of a specific accident. On the other hand, in the second type, various types of insurance screening results may be generated, such as acceptance determined to limit at least one of the multiple coverages, acceptance with a premium surcharge, conditional acceptance, etc.

[0068] In Type 1 of insurance products, an insurance application screening may be conducted by the customer answering specific questions (e.g., recent medical history, history of hospitalization, history of surgery, etc.). The screening results for Type 1 insurance products may include decisions to approve the underwriting of the insurance product, to approve the underwriting of an insurance product with limited coverage, or to reject the underwriting of the insurance product. Due to the relatively simple insurance application process, the premiums for Type 1 insurance products may be set higher than those for other types.

[0069] In Type 2 insurance products, the underwriting process may be conducted by comprehensively reviewing the customer's accident history, medical history, and other factors. The results of the review for Type 2 insurance products may include decisions such as the approval of the insurance product, the approval of an insurance product with exclusion conditions, or the approval of an insurance product with a surcharge. The review of Type 2 insurance products requires a relatively complex insurance application process, and depending on the review results, it may allow for the subscription to insurance products with various conditions.

[0070] In one embodiment, the coverage review unit (106) receives disease examination information and can perform coverage examination by classifying the type of insurance product. Based on the disease examination information, the coverage review unit (106) can generate coverage examination results related to the customer by applying different processing logic for each type of insurance product. Afterward, the coverage review unit (106) can generate insurance examination information (130) including coverage examination results. The method by which the coverage review unit (106) generates insurance examination information (130) will be described in detail with reference to FIG. 12.

[0071] In one embodiment, the insurance screening device (100) may output insurance screening information (130) for a customer. The insurance screening information (130) may include information regarding an insurance product that the customer wishes to subscribe to, such as acceptance of underwriting, rejection of underwriting, requirement for notification of illness, rejection of coverage, acceptance of underwriting under the condition of premium surcharge, or acceptance of underwriting under the condition of exclusion of coverage. The insurance company may review an insurance contract with the customer based on the insurance screening information (130).

[0072] Referring to FIG. 1, the disease examination unit (104) is depicted as receiving insurance product information (120), but the disease examination unit (104) may not directly receive the insurance product information (120). For example, the data preprocessing unit (102) may receive the insurance product information (120) and transmit it to the disease examination unit (104). As another example, the disease examination unit (104) may receive information regarding the type of insurance product instead of the insurance product information (120). As yet another example, the notification data included in the medical history data may have a different data format depending on the type of insurance product. That is, the notification data includes information regarding the type of insurance product, and the insurance examination device (100) may receive the notification data and process the information regarding the type of insurance product.

[0073] Insurance screening performed by the insurance screening device (100) can be performed quickly and with reduced time and cost compared to insurance screening based on expert experience and statistical models. In addition, while there may be differences in judgment among screening experts, the insurance screening device (100) can make consistent judgments, thereby improving the reliability of the insurance screening.

[0074] FIG. 2 is a schematic diagram showing a configuration in which an information processing device (230) is connected to communicate with a plurality of user terminals (210_1, 210_2, 210_3) for insurance screening according to one embodiment of the present disclosure. As illustrated, the plurality of user terminals (210_1, 210_2, 210_3) may be connected to an information processing device (230) capable of providing insurance screening services through a network (220). The plurality of user terminals (210_1, 210_2, 210_3) may include a user terminal receiving insurance screening services. In the present disclosure, the information processing device may correspond to the information processing device (230) or include the information processing device (230). In the present disclosure, the information processing device may correspond to the insurance screening device (100) of FIG. 1 or include the insurance screening device (100).

[0075] In one embodiment, the information processing device (230) may include one or more server devices and / or databases capable of storing, providing, and executing computer-executable programs (e.g., downloadable applications) and data associated with providing insurance screening services, etc., or one or more distributed computing devices and / or distributed databases based on cloud computing services.

[0076] The insurance screening service provided by the information processing device (230) may be provided to the user through an insurance screening service application, a web browser, a web browser extension, etc. installed on each of the multiple user terminals (210_1, 210_2, 210_3). For example, the information processing device (230) may provide information corresponding to an insurance screening request, etc. received from the user terminals (210_1, 210_2, 210_3) through the insurance screening service application, etc., or perform corresponding processing.

[0077] Multiple user terminals (210_1, 210_2, 210_3) can communicate with an information processing device (230) through a network (220). The network (220) can be configured to enable communication between the multiple user terminals (210_1, 210_2, 210_3) and the information processing device (230). Depending on the installation environment, the network (220) may be configured as a wired network such as Ethernet, Power Line Communication, telephone line communication device and RS-serial communication, a mobile communication network, a Wireless LAN (WLAN), Wi-Fi, Bluetooth and ZigBee, or a combination thereof. The communication method is not limited and may include not only communication methods utilizing communication networks that the network (220) may include (e.g., mobile communication network, wired internet, wireless internet, broadcasting network, satellite network, etc.) but also short-range wireless communication between user terminals (210_1, 210_2, 210_3).

[0078] In FIG. 2, a mobile phone terminal (210_1), a tablet terminal (210_2), and a PC terminal (210_3) are illustrated as examples of user terminals, but are not limited thereto. The user terminals (210_1, 210_2, 210_3) may be any computing device capable of wired and / or wireless communication and capable of installing and running an insurance underwriting service application or a web browser, etc. For example, user terminals may include an AI speaker, a smartphone, a mobile phone, a navigation system, a computer, a laptop, a digital broadcasting terminal, a PDA (Personal Digital Assistants), a PMP (Portable Multimedia Player), a tablet PC, a game console, a wearable device, an IoT (Internet of Things) device, a VR (Virtual Reality) device, an AR (Augmented Reality) device, a set-top box, etc. Additionally, FIG. 2 illustrates three user terminals (210_1, 210_2, 210_3) communicating with an information processing device (230) through a network (220), but is not limited thereto, and may be configured so that a different number of user terminals communicate with an information processing device (230) through a network (220).

[0079] In FIG. 2, a configuration in which a user's request (e.g., an insurance review request, etc.) is transmitted to an information processing device (230) through a user terminal (210_1, 210_2, 210_3) is illustrated as an example, but is not limited thereto. A user's request may be provided to an information processing device (230) through an input device associated with the information processing device (230) without passing through the user terminal (210_1, 210_2, 210_3), and a result of processing the user's request (e.g., insurance review information, etc.) may be provided to the user through an output device (e.g., a display, etc.) associated with the information processing device (230).

[0080] FIG. 3 is a block diagram showing the internal configuration of a user terminal (210) and an information processing device (230) according to an embodiment of the present disclosure. The user terminal (210) may refer to any computing device capable of executing applications, web browsers, etc., and capable of wired / wireless communication, and may include, for example, the mobile phone terminal (210_1), tablet terminal (210_2), PC terminal (210_3) of FIG. 2. As shown in FIG. 3, the user terminal (210) may include a memory (312), a processor (314), a communication module (316), and an input / output interface (318). Similarly, the information processing device (230) may include a memory (332), a processor (334), a communication module (336), and an input / output interface (338). As illustrated in FIG. 3, the user terminal (210) and the information processing device (230) may be configured to communicate information and / or data through the network (220) using their respective communication modules (316, 336). Additionally, the input / output device (320) may be configured to input information and / or data to the user terminal (210) or output information and / or data generated from the user terminal (210) through the input / output interface (318).

[0081] The memory (312, 332) may include any non-transient computer-readable recording medium. According to one embodiment, the memory (312, 332) may include a permanent mass storage device such as ROM (read-only memory), a disk drive, a solid-state drive (SSD), or flash memory. As another example, a permanent mass storage device such as ROM, an SSD, flash memory, or a disk drive may be included in the user terminal (210) or information processing device (230) as a separate permanent storage device distinct from the memory. Additionally, an operating system and at least one program code may be stored in the memory (312, 332).

[0082] These software components may be loaded from a computer-readable recording medium separate from memory (312, 332). This separate computer-readable recording medium may include a recording medium that can be directly connected to the user terminal (210) and the information processing device (230), for example, a computer-readable recording medium such as a floppy drive, disk, tape, DVD / CD-ROM drive, or memory card. As another example, the software components may be loaded into memory (312, 332) via a communication module (316, 336) rather than a computer-readable recording medium. For example, at least one program may be loaded into memory (312, 332) based on a computer program installed by files provided through a network (220) by developers or a file distribution system that distributes installation files for the application.

[0083] The processor (314, 334) may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to the processor (314, 334) by memory (312, 332) or a communication module (316, 336). For example, the processor (314, 334) may be configured to execute instructions received according to program code stored in a recording device such as memory (312, 332). The processor (314, 334) may be configured to execute a program for providing insurance underwriting services.

[0084] The communication module (316, 336) may provide a configuration or function for the user terminal (210) and the information processing device (230) to communicate with each other via the network (220), and may provide a configuration or function for the user terminal (210) and / or the information processing device (230) to communicate with another user terminal or another system (e.g., a separate cloud system). For example, a request or data (e.g., medical history information of a target customer) generated by the processor (314) of the user terminal (210) according to program code stored in a recording device such as memory (312) may be transmitted to the information processing device (230) via the network (220) under the control of the communication module (316). Conversely, a control signal or command provided under the control of the processor (334) of the information processing device (230) can be received by the user terminal (210) through the communication module (336) and the network (220) via the communication module (316) of the user terminal (210).

[0085] The input / output interface (318) may be a means for interfacing with an input / output device (320). As an example, the input device may include a device such as a camera including an audio sensor and / or an image sensor, a keyboard, a microphone, or a mouse, and the output device may include a device such as a display, a speaker, or a haptic feedback device. As another example, the input / output interface (318) may be a means for interfacing with a device in which the configuration or function for performing input and output is integrated into one, such as a touchscreen. For example, when the processor (314) of the user terminal (210) processes instructions of a computer program loaded in memory (312), a service screen configured using information and / or data provided by an information processing device (230) or another user terminal may be displayed on a display through the input / output interface (318). In FIG. 3, the input / output device (320) is depicted as not being included in the user terminal (210), but is not limited thereto and may be configured as a single device with the user terminal (210). Additionally, the input / output interface (338) of the information processing device (230) may be a means for interfacing with a device (not shown) for input or output that is connected to the information processing device (230) or that the information processing device (230) may include. In FIG. 3, the input / output interface (318, 338) is shown as an element configured separately from the processor (314, 334), but is not limited thereto, and the input / output interface (318, 338) may be configured to be included in the processor (314, 334).

[0086] The user terminal (210) and the information processing device (230) may include more components than those of FIG. 3. In one embodiment, the user terminal (210) may be implemented to include at least some of the input / output devices (320) described above. Additionally, the user terminal (210) may include other components such as a transceiver, a GPS (Global Positioning System) module, a camera, various sensors, a database, etc. For example, if the user terminal (210) is a smartphone, it may include components that are generally included in a smartphone, and may be implemented to include various components such as an accelerometer, a gyroscope, a microphone module, a camera module, various physical buttons, buttons using a touch panel, input / output ports, and a vibrator for vibration.

[0087] While a program or application is running, the processor (314) can receive text, images, video, voice and / or actions, etc. that are input or selected through an input device such as a touch screen, keyboard, audio sensor and / or image sensor, camera, microphone, etc. connected to an input / output interface (318), and can store the received text, images, video, voice and / or actions, etc. in memory (312) or provide them to an information processing device (230) through a communication module (316) and a network (220).

[0088] The processor (314) of the user terminal (210) may be configured to manage, process, and / or store information and / or data received from an input / output device (320), another user terminal, an information processing device (230), and / or a plurality of external systems. The information and / or data processed by the processor (314) may be provided to the information processing device (230) through a communication module (316) and a network (220). The processor (314) of the user terminal (210) may transmit information and / or data to the input / output device (320) through an input / output interface (318) to output it. For example, the processor (314) may output or display the received information and / or data on a screen associated with the user terminal (210).

[0089] The processor (334) of the information processing device (230) may be configured to manage, process, and / or store information and / or data received from a plurality of user terminals (210) and / or a plurality of external systems. The information and / or data processed by the processor (334) may be provided to the user terminals (210) through the communication module (336) and the network (220).

[0090] FIG. 4 is a diagram illustrating an example of a data preprocessing unit (102) according to one embodiment of the present disclosure. The data preprocessing unit (102) can receive medical history data associated with a customer's medical history (e.g., medical history data (110) of FIG. 1). The data preprocessing unit (102) can generate structured data (140) by preprocessing the medical history data.

[0091] In one embodiment, the medical history data may include accident history data (112) associated with the customer's accident history and notification data (114) associated with the medical history disclosed by the customer. For example, the accident history data (112) may include information regarding the time of the accident, type of illness, number of days of hospitalization, number of days of outpatient treatment, number of surgeries, treatment history, etc. Similarly, the notification data (114) may include information regarding the time of the accident, type of illness, number of days of hospitalization, number of outpatient treatment, number of surgeries, treatment history, etc.

[0092] In one embodiment, accident history data (112) may be obtained from the insurance company's database, the insurance company's related agency database, etc., and notification data (114) may be obtained by a customer notifying the insurance company. Due to their characteristics, accident history data (112) and notification data (114) may contain different accident history information even though they are accident history information regarding the same accident. The data preprocessing unit (102) may preprocess medical history data, such as by grouping related information in the accident history data (112) and notification data (114) and deleting unnecessary information. By preprocessing the medical history data, the data preprocessing unit (102) may generate structured data (140). A method for preprocessing accident history data (112) and notification data (114) will be described in detail with reference to FIGS. 5 and 6.

[0093] FIG. 5 is a diagram illustrating an example of thinking ability data according to one embodiment of the present disclosure. In one embodiment, the first thinking ability data (510) may include information associated with a customer's thinking history. The first thinking ability data (510) may include data divided into predetermined thinking ability units. Referring to FIG. 4, the first thinking ability data (510) may include first_1 thinking ability data (512), first_2 thinking ability data (514), first_3 thinking ability data (516), and first_4 thinking ability data (518) divided into predetermined thinking ability units.

[0094] In one embodiment, an accident unit may be used to distinguish the first accident data (510). The accident unit may be determined in various ways. In the database from which the first accident data (510) is retrieved, the accident unit may be substantially the same as the unit determined in the database. For example, the accident unit may be determined as the claim unit that a customer claims from an insurance company. As another example, the accident unit may be determined based on the time of the accident and the type of illness. Additionally, some of the first accident data (510) obtained from the first database and other parts of the first accident data (510) obtained from the second database may be distinguished as different accident units.

[0095] In one embodiment, the first accident history data (510) and the second accident history data (520) may include information associated with a plurality of categories (530). The plurality of categories (530) include categories regarding the time of accident occurrence, type of illness, number of days of hospitalization, number of days of outpatient treatment, number of surgeries, treatment history, etc. The first_n accident history data (e.g., first_1 accident history data (512), first_2 accident history data (514), first_3 accident history data (516), first_4 accident history data (518), etc.) may include information associated with at least one of the plurality of categories (530) (where n is a natural number). Referring to FIG. 1, the first accident history data (512) may include information corresponding to 'October 25, 2022' for the category of the time of the accident, information corresponding to 'herniated disc' for the category of the type of disease, information corresponding to '2 days' for the category of the number of days of hospitalization, and information corresponding to '0 times' for the category of the number of surgeries.

[0096] In one embodiment, a data preprocessing unit (e.g., the data preprocessing unit (102) of FIG. 1) may generate second thinking ability data (520) in which at least a portion of the first thinking ability data (510) is aggregated based on the first thinking ability data (510). The data preprocessing unit may calculate the association between a plurality of disease types. The data preprocessing unit may generate at least a portion (522) of the second thinking ability data using the association calculated based on the first thinking ability data (510). For example, the data preprocessing unit may calculate a primary-secondary relationship for a plurality of disease types based on the importance of the disease. For example, the primary disease may be the basis for treatment, and the secondary disease may not be the basis for treatment but may be the basis for drug prescription. The primary-secondary relationship may be calculated statistically based on insurance review data that has been previously reviewed by an insurance company. The data preprocessing unit may consider at least a portion of the first thinking ability data (510) having a primary-secondary relationship as being related to each other. Although it was explained that the data preprocessing unit calculates the correlation between multiple types of diseases, it may be calculated by an external device or external system and transmitted to the data preprocessing unit.

[0097] Referring to FIG. 5, the first_1 cognitive data (512) may include information corresponding to 'herniated disc' as information associated with the type of disease. The first_2 cognitive data (514) may include information corresponding to 'spinal stenosis' as information associated with the type of disease. The first_3 cognitive data (516) may include information corresponding to 'herniated disc' as information associated with the type of disease. The first_4 cognitive data (518) may include information corresponding to 'dizziness' as information associated with the type of disease. The data preprocessing unit can identify the relationship between 'herniated disc', 'spinal stenosis', and 'dizziness' in the association between multiple types of diseases. For example, in 'herniated disc' and 'spinal stenosis', 'herniated disc' may be the primary disease and 'spinal stenosis' may be the secondary disease. In 'herniated disc' and 'dizziness', 'herniated disc' may be the primary diagnosis and 'dizziness' may be the secondary diagnosis. In this case, the data preprocessing unit may consider the 1_1 thinking ability data (512) to the 1_4 thinking ability data (518) as being related to each other. The data preprocessing unit may generate at least a portion (522) of the 2 thinking ability data based on the 1_1 thinking ability data (512) to the 1_4 thinking ability data (518). At least a portion (522) of the 2 thinking ability data may include information regarding 'herniated disc' as information related to the type of diagnosis. 'Herniated disc' may correspond to the primary diagnosis among the types of diagnosis in the 1_1 thinking ability data (512) to the 1_4 thinking ability data (518), or may be the diagnosis closest to the primary diagnosis.

[0098] In one embodiment, a plurality of categories (530) may include a first category associated with a time point and a second category associated with a numerical value. For example, the first category may include 'time of accident occurrence', 'time of treatment', etc. 'Time of treatment' may indicate the time when the last treatment was received to treat the illness. The first category may be expressed as a date, such as 'year / month / day'. The second category may include 'number of days of hospitalization', 'number of days of outpatient treatment', 'number of surgeries', etc. The second category may be expressed as a numerical value, such as a number of times, days, etc.

[0099] In one embodiment, the data preprocessing unit may use information associated with the first category included in the first thinking ability data (510) to generate information associated with the first category included in the second thinking ability data (520). The first_1 thinking ability data (512) may include information associated with the first point in time as information associated with the first category, and the first_2 thinking ability data (514) may include information associated with the second point in time as information associated with the first category. In response to the determination that the difference between the first point in time and the second point in time is smaller than the threshold period, the data preprocessing unit may consider the first_1 thinking ability data (512) and the first_2 thinking ability data (514) to be associated with each other. The threshold period may be determined in advance. For example, the threshold period may be determined in various ways, such as 5 days, 7 days, 10 days, 15 days, 20 days, 35 days, etc. After that, the data preprocessing unit can generate at least a portion (522) of the second thinking ability data based on the first thinking ability data (512) and the first thinking ability data (514).

[0100] Referring to FIG. 5, the first_1 accident data (512) may include information corresponding to 'October 25, 2022' as information associated with the category at the time of the accident. The first_2 accident data (514) may include information corresponding to 'October 27, 2022' as information associated with the category at the time of the accident. The first_3 accident data (516) may include information corresponding to 'October 27, 2022' as information associated with the category at the time of the accident. The first_4 accident data (518) may include information corresponding to 'October 27, 2022' as information associated with the category at the time of the accident. The threshold period may be predetermined as 5 days. In this case, the data preprocessing unit may consider the first_1 accident data (512) to the first_4 accident data (518) as related to each other in response to the determination that the difference between the time points included in each of the first_1 accident data (512) to the first_4 accident data (518) as the category of the time point of the accident occurrence is smaller than a threshold period. The data preprocessing unit may generate at least a portion (522) of the second accident data based on the first_1 accident data (512) to the first_4 accident data (518). At least a portion (522) of the second accident data may include information regarding 'October 27, 2022' as information related to the time point of the accident occurrence. 'October 27, 2022' may be the latest time point among the time points of the accident occurrence of the first_1 accident data (512) to the first_4 accident data (518). However, not limited thereto, at least some (522) of the second accident data may be information related to the time of the accident, and may include one of the times of the accident of the first_1 accident data (512) to the first_4 accident data (518) (e.g., the earliest time of the time of the accident).

[0101] In one embodiment, the data preprocessing unit may use information associated with the second category included in the first thinking ability data (510) to generate information associated with the second category included in the second thinking ability data (520). The first_1 thinking ability data (512) may include information associated with the first numerical value as information associated with the second category, and the first_2 thinking ability data (514) may include information associated with the second numerical value as information associated with the second category. The data preprocessing unit may generate at least a portion (522) of the second thinking ability data based on one of the first numerical value and the second numerical value. For example, one of the first numerical value and the second numerical value may be selected as information associated with the second category included in at least a portion (522) of the second thinking ability data. For example, the larger of the first numerical value and the second numerical value may be selected.

[0102] Referring to FIG. 5, the 1_1 thinking ability data (512) may include information corresponding to '2 days' as information associated with the category of the number of days of hospitalization. The 1_2 thinking ability data (514) may include information corresponding to '2 days' as information associated with the category of the number of days of hospitalization. The 1_3 thinking ability data (516) may include information corresponding to '2 days' as information associated with the category of the number of days of hospitalization. The 1_4 thinking ability data (518) may include information corresponding to '1 day' as information associated with the category of the number of days of hospitalization. The 1_1 thinking ability data (512) to the 1_4 thinking ability data (518) may be considered to be related to each other. In this case, the data preprocessing unit may select '2 days', which is the largest value among the values ​​included in each of the 1_1 thinking ability data (512) to the 1_4 thinking ability data (518), as the category of the number of days of hospitalization. The data preprocessing unit can generate information corresponding to '2 days' as a category of hospitalization days as information included in at least part (522) of the second accident history data.

[0103] Similarly, regarding the category of the number of surgeries, '1 time' may be selected from '0 times' of the 1_1 accident data (512) and '1 time' of the 1_2 accident data (514). At least a portion (522) of the 2 accident data may include information corresponding to '1 time' as the category of the number of surgeries. Additionally, regarding the category of the number of outpatient days, '1 day' of the 1_3 accident data (516) may be selected, and at least a portion (522) of the 2 accident data may include information corresponding to '1 day' as the category of the number of outpatient days.

[0104] As described above, the data preprocessing unit may associate data that can be considered as a single thinking unit in the first thinking ability data (510) with one another, and then merge them to generate at least a portion (522) of the second thinking ability data. Referring to FIG. 5, the first_1 thinking ability data (512) to the first_4 thinking ability data (518) are aggregated to generate at least a portion (522) of the second thinking ability data, and at least a portion (522) of the second thinking ability data can be considered as a single thinking unit. Subsequently, the second thinking ability data (520) can be merged with notification data to obtain structured data. The process of obtaining structured data is explained in detail with reference to FIG. 6.

[0105] FIG. 6 is a drawing for explaining structured data (600) according to one embodiment of the present disclosure.

[0106] In one embodiment, structured data (600) may be generated by merging notification data associated with the medical history reported by the customer with the second accident history data (e.g., the second accident history data (520) of FIG. 2). The structured data (600) may include first structured data (612) to third structured data (616) classified by accident unit to primary disease (or classified by being considered as primary disease to accident unit).

[0107] In one embodiment, structured data (600) may include information associated with a plurality of categories (620). For example, the plurality of categories (620) may include a category of whether a disease has been notified (e.g., 'Notification Status' in FIG. 6). The first structured data (612) may be a category of whether a disease has been notified and may include information corresponding to the notification of the disease (e.g., the 'O' mark in FIG. 6). The second structured data (614) and the third structured data (616) may be categories of whether a disease has been notified and may include information corresponding to the non-notification of the disease (e.g., the 'X' mark in FIG. 6). That is, each structured data may be tagged regarding whether a disease has been notified.

[0108] Referring to FIG. 6, the first structured data (612) may be generated by aggregating at least some of the second thinking ability data, which are divided into one thinking unit, and at least some of the notification data. At least some of the notification data may be determined to be related to at least some of the second thinking ability data. For example, the notification data and the second thinking ability data may be considered to be related to each other in the same way that the first_1 thinking ability data (512) to the first_4 thinking ability data (518) described with reference to FIG. 5 are considered to be related to each other. For example, at least some of the notification data may include information related to the first disease type (e.g., spinal stenosis, herniated disc, etc.). At least some of the second thinking ability data may include information related to the second disease type (e.g., herniated disc). Based on the relationship between multiple disease types, the first disease type and the second disease type may be determined to be related to each other, and at least some of the notification data and at least some of the second thinking ability data may be considered to be related to each other. As another example, at least some of the notification data may include information associated with a first time point (e.g., time of accident occurrence, time of treatment). At least some of the second accident history data may include information associated with a second time point (e.g., time of accident occurrence, time of treatment). The first time point and the second time point may be close to each other (e.g., the difference between the first time point and the second time point is smaller than a critical period). In this case, at least some of the notification data and at least some of the second accident history data may be considered to be related to each other. At least some of the structured data (600) may be generated by merging at least some of the notification data and at least some of the second accident history data that are considered to be related to each other.In this way, the first structured data (612) generated by merging at least some of the notification data and at least some of the accident data may include information related to 'notification status' and information corresponding to the notification of illness (e.g., the 'O' mark in FIG. 6).

[0109] In one embodiment, at least some of the notification data may be determined not to be associated with the second cognitive data. In this case, at least some of the notification data may serve as the basis for at least some of the structured data. For example, at least some of the structured data may be generated by using the information included in at least some of the notification data as is, and / or by using information in which some of the information has been deleted or modified. In this case, at least some of the structured data may include information corresponding to the notification of a disease as a category of whether or not a disease has been notified.

[0110] In one embodiment, each of the second structured data (614) and the third structured data (616) may be generated based on at least a different part of the second thinking ability data divided into one thinking unit. For example, at least a different part of the second thinking ability data may not be associated with the notification data. In this case, the second structured data (614) is generated based only on at least a different part of the second thinking ability data, and the second structured data (614) may include information corresponding to the non-notification of a disease (e.g., the 'X' mark in FIG. 6) as information associated with 'notification status'.

[0111] In one embodiment, each of the second accident history data and the notification data may include information associated with a second category separated by unit period. The unit period may be a predetermined period calculated backward from the 'time of treatment'. For example, the second accident history data may include information associated with the second category for unit periods such as 3 years from the time of treatment, 2 years from the time of treatment, or 1 year from the time of treatment. Information associated with the second category may also be separated by unit period in the structured data (600) generated by merging the second accident history data and the notification data. Referring to FIG. 6, the first structured data (600) may include information corresponding to '2 days' as information associated with 'number of days of hospitalization' and information corresponding to '3 days' as information associated with 'number of days of outpatient treatment' for a period of 3 years from the time of treatment.

[0112] In one embodiment, the data preprocessing unit may determine whether some of the information included in the structured data (600) meets a standard condition (e.g., a predetermined standard condition). In response to the determination result, the data preprocessing unit may request additional notification data related to the disease notification. The additional notification data is information additionally provided by the customer and may include information related to medical history. In this case, the additional notification data may be received from an external system, an external device, the customer, etc.

[0113] In one example, the standard condition may include a condition regarding whether the disease type of the structured data (600) corresponds to the target disease type. If the disease type corresponds to the target disease type, the data preprocessing unit may request information regarding detailed diseases associated with the disease type as additional notification data. For example, if the target disease type includes gastritis, the data preprocessing unit may request detailed information regarding whether it is atrophic gastritis, whether it is chronic gastritis, etc.

[0114] In another example, the criteria condition may include a condition regarding whether a disease type in the structured data (600) (e.g., second structured data (614), third structured data (616), etc.) corresponds to a target disease type. For example, the target disease type may include severe diseases (e.g., breast cancer, colorectal cancer). If the disease type corresponds to a target disease type, the data preprocessing unit may request additional notification data for the corresponding disease type. Alternatively, the data preprocessing unit may stop the insurance review for the structured data (600) associated with the corresponding disease type. Afterward, the insurance review device (e.g., the insurance review device (100) of FIG. 1) may output information corresponding to 'rejection of coverage' as insurance review information (e.g., the insurance review information (130) of FIG. 1).

[0115] In another example, the criterion condition may include a condition regarding whether the number of surgeries in the structured data (600) is one or more. If the number of surgeries in the structured data (600) is one or more, the data preprocessing unit may request information regarding the surgery as additional notification data. For example, the information regarding the surgery may include information regarding the surgical method, the hospital where the surgery was performed, etc.

[0116] As described above, structured data (600) can be generated by standardizing unstructured notification data and thinking ability data. The structured data (600) can be optimized for use with machine learning models, etc. By conducting insurance screening through the structured data (600), the convenience of insurance screening can be increased.

[0117] FIG. 7 is a drawing for explaining an example of a disease examination unit (104) according to one embodiment of the present disclosure. The disease examination unit (104) receives structured data (140) and can output disease examination information (150) based on the structured data (140).

[0118] In one embodiment, the disease examination unit (104) can extract information regarding at least one type of disease associated with the structured data (140) based on the structured data (140). For example, the disease examination unit (104) can extract information regarding a first type of disease (e.g., herniated disc) included in the first structured data (e.g., the first structured data (612) of FIG. 6) classified by accident unit. The disease examination unit (104) can extract information regarding a second type of disease (e.g., upper respiratory tract infection) included in the second structured data (e.g., the second structured data (614) of FIG. 6) classified by accident unit.

[0119] In one embodiment, the disease screening unit (104) may generate disease screening information (150) for each disease type based on information and structured data (140) regarding at least one disease type. For example, the disease screening unit (104) may generate disease screening information (150) for a first disease type based on information and structured data (140) regarding a first disease type. The disease screening unit (104) may generate disease screening information (150) for a second disease type based on information and structured data (140) regarding a second disease type.

[0120] In one embodiment, the disease examination unit (104) may further receive insurance product information (120). For example, the insurance product information (120) may include information regarding the type of insurance product. The disease examination unit (104) may generate disease examination information by distinguishing the type of insurance product. When the type of insurance product is a first type, the disease examination of the disease examination unit (104) is described in detail through FIG. 8, and when the type of insurance product is a second type, the disease examination of the disease examination unit (104) is described in detail through FIG. 9.

[0121] FIG. 8 is a block diagram of a disease examination unit (104) according to one embodiment of the present disclosure.

[0122] In one embodiment, the disease screening unit (104) may include an insurance type determination unit (810), a score calculation model (820), and a screening decision model (830). The insurance type determination unit (810) receives insurance product information (120) and can determine whether the type of the insurance product is a first type associated with coverage limitations based on the insurance product information (120). FIG. 8 describes the case where the type of the insurance product is determined to be a first type.

[0123] Referring to FIG. 8, when the insurance type determination unit (810) determines that the type of insurance product is a first type associated with coverage limitations, the score calculation model (820) and the examination decision model (830) of the disease examination unit (104) may not be used. In FIG. 8, the score calculation model (820) and the examination decision model (830) are illustrated as the disease examination unit (104) to distinguish it from the process illustrated in FIG. 9. However, the fact that the score calculation model (820) and the examination decision model (830) are not used in FIG. 8 does not limit the roles, functions, etc. of the score calculation model (820) and the examination decision model (830).

[0124] In one embodiment, the insurance type determination unit (810) may receive first structured data (800) classified into one accident unit or primary disease. The insurance type determination unit (810) may obtain information regarding the first disease type for the first structured data (800). The insurance type determination unit (810) may determine whether a disease notification is required, whether acceptance is approved, or whether acceptance is rejected, according to predetermined disease acceptance conditions. The disease acceptance conditions may be determined based on information regarding accident history. For example, the disease acceptance conditions may include a condition determining acceptance rejection if the disease type of the first structured data (800) is a severe disease. The disease acceptance conditions may include a condition determining acceptance acceptance if the disease type of the first structured data (800) is a very mild disease. The disease acceptance conditions may include a condition determining that a disease notification is required if the disease notification status of the first structured data (800) is a non-disclosure of the disease. The condition acceptance criteria for a disease may include a condition for determining rejection of acceptance if the number of days of hospitalization, outpatient days, number of surgeries, etc., of the first structured data (800) is above a threshold value. The condition acceptance criteria for a disease may determine that coverage review is required if the presence or absence of a disease notification in the first structured data (800) is a disease notification and information related to accident history exists. The condition acceptance criteria for a disease may be determined in various ways by considering the conditions and circumstances of the insurance company.

[0125] For example, the first structured data (800) may include information regarding the type of disease, such as 'spinal stenosis', whether the disease was disclosed, such as 'disclosure of disease', the time of treatment, such as 'September 15, 2023', the number of days of hospitalization, such as '3 days', the number of days of outpatient treatment, such as '5 days', and the number of surgeries, such as '1 time'. In this case, the disease screening information (150) may include information regarding the need for coverage screening for the first structured data (800). As another example, the first structured data (800) may include information regarding the type of disease, such as 'breast cancer', whether the disease was disclosed, such as 'non-disclosure of disease', and the number of days of outpatient treatment, such as '3 days'. In this case, the type of disease in the first structured data (800) corresponds to a severe disease, so the disease screening information (150) may include information regarding rejection of coverage for the first structured data (800). As another example, the first structured data (800) may include information regarding the type of injury as 'fracture', whether the injury is disclosed as 'injury not disclosed', the number of days of hospitalization as '2 days', the number of surgeries as '1 time', etc. In this case, the injury screening information (150) may include information regarding the need to disclose the injury for the first structured data (800).

[0126] In one embodiment, the insurance type determination unit (810) may generate disease examination information (150) including information determined based on the first structured data (800). The insurance type determination unit (810) may generate disease examination information (150) for the entire structured data including the first structured data (e.g., the structured data (600) of FIG. 6). The disease examination information (150) may be transmitted to the coverage examination unit. Subsequently, the coverage examination unit may proceed with a coverage examination based on the disease examination information (150). The method of examining coverage by the coverage examination unit will be described in detail with reference to FIG. 12.

[0127] FIG. 9 is a block diagram of a disease examination unit (104) according to one embodiment of the present disclosure. In one embodiment, an insurance type determination unit (810) receives insurance product information (120) and can determine whether the type of the insurance product is a second type different from the first type based on the insurance product information (120). FIG. 9 describes the case where the type of the insurance product is determined to be a second type.

[0128] In one embodiment, the insurance type determination unit (810) may transmit information (812) related to treatment history included in the first structured data (800) to the score calculation model (820) in response to the determination that the type of insurance product is the second type. The score calculation model (820) may calculate a score (822) based on the information (812) related to treatment history. The score (822) may be related to whether coverage review is required for each type of disease. The score calculation model (820) may be generated to calculate a score (822) based on the information (812) related to treatment history. The method of generating the score calculation model (820) will be described in detail with reference to FIG. 10.

[0129] In one embodiment, the screening decision model (830) may receive a score (822) calculated by the score calculation model (820). The screening decision model (830) may generate disease screening information (150) based on the score (822). The screening decision model (830) may be configured to determine whether a collateral screening is necessary by comparing the score (822) with a score threshold. For example, the score (822) and the score threshold may be expressed as numerical values ​​between 0 and 100. If the score (822) is greater than the score threshold, the first structured data (800) may be determined to require a collateral screening. If the score (822) is less than or equal to the score threshold, the first structured data (800) may be determined to require no collateral screening.

[0130] In one embodiment, the score threshold may differ depending on the type of disease. For example, the score threshold for a first type of disease may differ from the score threshold for a second type of disease. The first type of disease and the second type of disease may differ from each other. When the screening decision model (830) determines whether a coverage screening is necessary, the score threshold may be weighted.

[0131] In one embodiment, the examination decision model (830) may generate additional examination information in addition to generating information regarding whether a collateral examination is necessary, according to additional examination conditions (e.g., predetermined additional examination conditions). For example, the additional examination conditions may include a condition determining that a collateral examination is necessary if the first disease type of the first structured data (800) is a specific disease, even if it is determined that a collateral examination is unnecessary. As another example, the additional examination conditions may include a condition determining that a collateral examination is necessary and additionally determining that a disease notification is necessary if the disease notification status of the first structured data (800) is a non-disclosure of the disease.

[0132] In one embodiment, the screening decision model (830) may generate disease screening information (150) that includes information regarding whether coverage screening is necessary, whether disease notification is necessary, etc. If the screening decision model (830) determines that disease notification is necessary, the screening decision model (830) may request additional notification data related to disease notification from an external system, external device, customer, etc. If the screening decision model (830) receives information regarding additional notification data as a response to the request, it may generate disease screening information (150) that further includes additional notification data. The additional notification data may be merged into the first structured data (800).

[0133] In one embodiment, the screening decision model (830) may select a first decision associated with the need for a collateral screening and / or a second decision associated with the unnecessary screening of a collateral screening. Then, the screening decision model (830) may generate disease screening information (150) based on the selected decision. Weights may be applied to the screening decision model (830) so that the screening decision model (830) selects the first decision more than the second decision. Weights may be applied to the score calculation model (820), which is a machine learning model, so that the screening decision model (830) selects the first decision more than the second decision. In this case, the score calculation model may produce a relatively higher score than when no weights are applied. In one example, the weights may differ by disease type. For example, the weight for the first disease type and the weight for the second disease type may be different.

[0134] Below, the disease screening information (150) generated by the screening decision model (830) based on the structured data (600) of FIG. 6 is described. The score calculation model (820) can calculate a score (822) of '53.1' based on information related to the treatment history of the first structured data (612). The score threshold for 'herniated disc' may be '40.0'. In this case, since the score (822) is greater than the score threshold, the first structured data (612) may be determined to require coverage screening.

[0135] The score calculation model (820) can calculate a score (822) of '9.8' based on information related to the treatment history of the second structured data (614). The score threshold for 'upper respiratory infection' may be '65.1'. In this case, since the score (822) is smaller than the score threshold, the second structured data (614) may be determined to be unnecessary for collateral review. Determining that collateral review is unnecessary may correspond to a decision of acceptance approval.

[0136] The score calculation model (820) can calculate a score (822) of '12.1' based on information related to the treatment history of the third structured data (616). The score threshold for 'gastritis' may be '55.3'. In this case, since the score (822) is smaller than the score threshold, the third structured data (616) may be determined to be unnecessary for coverage review. The third structured data (616) may include information regarding 'atrophic gastritis' as a type of disease (or detailed type of disease). Additional review conditions may include a condition determining that coverage review is required if the type of disease is 'atrophic gastritis'. The review decision model (830) may determine that coverage review is required for the third structured data (616) based on the additional review conditions. Additionally, the additional screening condition may include a condition for additionally determining the need for a diagnosis of

[0137] FIG. 10 is a diagram illustrating an example of a score calculation model (820) according to one embodiment of the present disclosure. In one embodiment, a processor (e.g., at least one processor included in the insurance screening device (100) of FIG. 1) may receive treatment history data (1010) for a plurality of customers and screening data (1020) associated with the insurance screening results for said customers. The treatment history data (1010) and screening data (1020) may be obtained from the insurance company's database, the insurance company's related agency database, etc.

[0138] In one embodiment, the treatment history data (1010) may include information regarding the number of days of hospitalization, number of outpatient visits, number of accidents, number of claims, insurance premiums paid, date of accident occurrence, date of initial hospitalization, date of final hospitalization, date of initial treatment, date of final treatment, date of surgery, medical expenses incurred, etc. The screening data (1020) may include information regarding the results of an insurance screening conducted based on the treatment history data (1010). For example, the screening data (1020) may include information regarding acceptance approval, rejection of acceptance, need for supplementation (e.g., need for additional notification), acceptance approval with a surcharge, acceptance approval with conditions of burden, etc. The screening data (1020) may include information corresponding to the insurance screening results as numerical values. For example, the screening data (1020) may include each of the following as probabilities: acceptance approval, rejection of acceptance, need for supplementation, acceptance approval with a surcharge, acceptance approval with burden, etc. As another example, acceptance approval, acceptance rejection, need for supplementation, acceptance with premium, acceptance with burden, etc., each are expressed as a first number, and the screening data (1020) may include one or more second numbers that represent the sum of the numbers.

[0139] In one embodiment, the processor may generate a score calculation model (820), which is a machine learning model trained on treatment history data (1010) and screening data (1020). For example, the machine learning model may include a logistic regression model. The score calculation model (820) may calculate a score (1040) based on information (1030) associated with treatment history. The score may represent numerically the probability determined as requiring a collateral screening or not requiring a collateral screening. The score calculation model (820) may learn the treatment history data (1010) and screening data (1020) to take information associated with treatment history included in the treatment history data (1010) as input and output a score associated with information regarding whether a collateral screening is required or not in the screening data (1020). The information associated with treatment history (1030) includes information regarding the type of disease, so the score calculation model (820) may also learn information regarding the type of disease. In addition, information (1030) related to treatment history may include information regarding the duration of the illness, days of hospitalization, days of outpatient treatment, number of surgeries, etc.

[0140] In one embodiment, the score calculation model (820) can learn human data together with treatment history data (1010) and screening data (1020). The human data is personal information of a customer and may include information regarding gender, age, height, weight, etc. In this case, the score calculation model (820) can receive the human information along with information related to treatment history (1030) and calculate a score (1040).

[0141] FIG. 11 is a drawing for explaining a coverage review unit (106) according to one embodiment of the present disclosure. The coverage review unit (106) may receive disease review information (150) from a disease review unit. The coverage review unit (106) may generate insurance review information (130) based on the disease review information (150).

[0142] In one embodiment, the coverage review unit (106) may perform a coverage review on structured data determined to require coverage review in the disease examination information (150). The coverage review unit (106) may suspend coverage review on structured data determined to require coverage review and disease notification. In this case, the coverage review unit (106) may perform coverage review after receiving additional notification data.

[0143] In one embodiment, the coverage review unit (106) may not perform coverage review for structured data determined in the disease review information (150) to be other than the need for coverage review. The insurance review information (130) may include the disease review information (150) as is for the structured data. For example, the insurance review information (130) may include information regarding decisions such as rejection of acceptance, acceptance approval, or the necessity of coverage review for the structured data.

[0144] In one embodiment, the coverage review unit (106) may process the disease review information (150) regarding the first type of insurance product and the disease review information (150) regarding the second type of insurance product separately. The first type of insurance product is associated with the presence or absence of coverage restrictions, and the second type may be different from the first type. The coverage review unit (106) may generate insurance review information (130) using a first logic based on the disease review information regarding the first type of insurance product. Additionally, the coverage review unit (106) may generate insurance review information (130) using a second logic based on the disease review information regarding the second type of insurance product.

[0145] First, the method of the coverage review department (106) to review coverage for a first type of insurance product using a first logic is explained. The first logic can be determined in advance in various ways by considering the conditions and circumstances of the insurance company. For example, the first logic may include a rule that determines that the first coverage is restricted if some of the information included in the structured data satisfies the first condition. The first logic may include a rule that determines that acceptance is rejected if some of the information included in the structured data satisfies the second condition. For example, the structured data (e.g., the first structured data (800) of FIG. 8) may include information regarding the type of disease as 'spinal stenosis', whether the disease is disclosed as 'disclosure of disease', the time of treatment as 'September 15, 2023', the number of days of hospitalization as '3 days', the number of days of outpatient treatment as '5 days', the number of surgeries as '1 time', etc. In this case, the disease review information (150) may include information regarding the need for coverage review for the first structured data. The collateral review department (106) may decide to limit coverage related to surgery costs because the type of sexually transmitted disease is ‘spinal stenosis’ and the number of surgeries is one or more.

[0146] Next, the collateral examination department (106) explains how to perform a collateral examination for a second type of insurance product using a second logic. The second logic can be configured to perform a collateral examination by classifying information regarding accident history into various cases.

[0147]

[0148] Type of Disease, Days Elapsed, Income Source, Days of Outpatient Treatment, Presence / Absence of Surgery, Presence / Absence of Recurrence, No Coverage Group, MINMAX, MINMAX, MINMAX, Disease Death, Disease Daily Benefit A, Disease 020, 300, 30YN12

[0149]

[0150] In one example, a coverage group may be determined for a case such as that shown in Table 1. For instance, information regarding the customer's accident history may include details such as the number of inpatient days for Disease A being 10 days, the number of outpatient days being 20 days, the number of surgeries being one or more, and that Disease A has not recurred. The structured data associated with the customer may be determined by the Disease Review Department to require coverage review. According to Table 1, the Coverage Review Department may determine '1' for the 'Death from Disease' coverage group and '2' for the 'Daily Benefit from Disease' coverage group regarding the structured data. '1' refers to acceptance approval, meaning that acceptance approval may be determined for Disease A and the 'Death from Disease' coverage group without further review. '2' refers to the need for disease disclosure, meaning that additional disclosure data may be required in relation to Disease A and the 'Daily Benefit from Disease' coverage group. Various other decisions may be made in addition to '1' and '2'. A coverage group may be a grouping of one or more coverages with similar characteristics. For example, the 'Daily Disease Allowance' coverage group may include coverages such as 'Daily Disease Hospitalization Allowance', 'Daily Disease Caregiver Hospitalization Allowance', and 'Daily Allowance for Single Room in a Tertiary General Hospital'.

[0151] As shown in Table 1 and the example above, the second logic can be configured to perform a collateral assessment by classifying the ability to think into various cases.

[0152] FIG. 12 is a flowchart illustrating an example of an insurance screening method (S1200) according to one embodiment of the present disclosure. In one embodiment, the insurance screening method (S1200) may be performed by at least one processor included in an insurance screening device (e.g., the insurance screening device (100) of FIG. 1).

[0153] First, the insurance screening method (S1200) can be initiated by receiving medical history data related to the customer's medical history (S1210).

[0154] In one embodiment, the processor can generate structured data by preprocessing medical history data (S1220). The structured data may include information associated with at least one of the type of disease, whether the disease was reported, or treatment history. Additionally, the structured data may be classified into at least one of the accident unit or the type of disease.

[0155] In one embodiment, medical history data may include accident history data associated with the customer's accident history and notification data associated with the medical history disclosed by the customer. The accident history data may include first accident history data classified by accident history units. Based on the first accident history data, the processor may generate second accident history data in which at least a portion of the first accident history data is aggregated. Based on the second accident history data and the notification data, the processor may generate structured data.

[0156] In one embodiment, the first thinking ability data may include 1_1 thinking ability data including information associated with a first disease type and 1_2 thinking ability data including information associated with a second disease type. The processor may calculate the association between the first disease type and the second disease type. Based on the association, the processor may generate at least a portion of the second thinking ability data.

[0157] In one embodiment, the first thinking ability data may include first_3 thinking ability data, which includes information associated with a first time point as information associated with a first category, and first_4 thinking ability data, which includes information associated with a second time point as information associated with a first category. In response to a determination that the difference between the first time point and the second time point is smaller than a predetermined threshold period, the processor may generate at least a portion of the second thinking ability data based on the first_3 thinking ability data and the first_4 thinking ability data. For example, the information associated with the first category may include information associated with at least one of the time of the accident occurrence or the time of treatment.

[0158] In one embodiment, the first thinking ability data may include 1_5 thinking ability data, which includes information associated with a first numerical value as information associated with a second category, and 1_6 thinking ability data, which includes information associated with a second numerical value as information associated with a second category. The processor may generate at least a portion of the second thinking ability data based on at least one of the first numerical value or the second numerical value. The information associated with the second category may include information associated with at least one of the number of days of hospitalization, the number of outpatient days, or the number of surgeries.

[0159] In one embodiment, the processor can determine whether at least a portion of the second thinking ability data, which is at least a portion of the second thinking ability data, and at least a portion of the notification data are related to each other. Based on at least a portion of the second thinking ability data and the notification data, the processor can generate at least a portion of the structured data, which is the first structured data.

[0160] In one embodiment, the second thinking ability data may include second_2 thinking ability data that is different from the second_1 thinking ability data. Based on the second_2 thinking ability data, the processor may generate second structured data, which is at least a part of the structured data.

[0161] In one embodiment, the structured data may include information classified into a third category associated with the notification of a disease. The first structured data may include information associated with the notification of a disease as information of the third category. The second structured data may include information associated with the non-notification of a disease as information of the third category.

[0162] In one embodiment, the processor may request additional notification data associated with the disease notification in response to some of the information included in the structured data satisfying a reference condition.

[0163] In one embodiment, the processor can generate disease screening information for a customer by disease type based on structured data (S1230).

[0164] FIG. 13 is a flowchart illustrating an example of an insurance screening method (S1300) according to one embodiment of the present disclosure. In one embodiment, the insurance screening method (S1300) may be performed by at least one processor included in an insurance screening device.

[0165] In one embodiment, the processor may obtain structured data generated by preprocessing medical history data associated with the customer's medical history (S1310). The structured data may include information associated with at least one of the notification of a disease or a history of accidents. The information associated with the history of accidents may include information associated with the history of treatment.

[0166] In one embodiment, the processor can extract information regarding at least one disease type associated with structured data (S1320).

[0167] In one embodiment, the processor can generate disease screening information for each disease type based on information and structured data regarding at least one disease type (S1330).

[0168] In one embodiment, the processor can calculate a score associated with whether coverage review is required for each type of disease based on information related to treatment history. Based on the calculated score, the processor can determine whether coverage review is required.

[0169] In one embodiment, the processor may calculate a score based on information related to treatment history using a score calculation model. The score calculation model may be configured to receive information related to treatment history as input and output a score by learning treatment history data for a plurality of customers and review data related to insurance review results for a plurality of customers. For example, information related to treatment history may include information related to at least one of the time of the accident, the time of treatment, the number of days elapsed since the illness, the number of days of hospitalization, the number of outpatient days, or the number of surgeries.

[0170] In one embodiment, the processor may determine whether a collateral examination is necessary based on the calculated score by using an examination decision model configured to determine whether a collateral examination is necessary by comparing a score and a score threshold. The score threshold for a first disease type may be different from the score threshold for a second disease type that is different from the first disease type.

[0171] In one embodiment, the screening decision model may be configured to select a first decision associated with the need for a collateral screening or a second decision associated with the unnecessary nature of a collateral screening. Weights may be applied to the screening decision model so that the screening decision model selects the first decision more than the second decision. Additionally, or alternatively, the weight for the first disease type may be different from the weight for the second disease type.

[0172] In one embodiment, the processor may select a first decision related to the need for a collateral examination for the structured data in response to a determination that the score is greater than the score threshold. Alternatively, the processor may select a second decision related to the unnecessary need for a collateral examination for the structured data in response to a determination that the score is less than or equal to the score threshold.

[0173] In one embodiment, the processor may request additional notification data if at least part of the structured data is associated with a non-notification of a disease.

[0174] In one embodiment, the processor may select a first decision associated with the need for a collateral examination for at least some of the structured data associated with a predetermined specific disease.

[0175] In one embodiment, the processor may obtain information on the type of insurance product that a customer wishes to subscribe to. The type of insurance product may include a first type associated with the presence or absence of coverage limitations and a second type different from the first type.

[0176] In one embodiment, the insurance product may be associated with at least one coverage. In response to a determination that the type of the insurance product is of the first type, the processor may generate information associated with a limitation of the first coverage among the at least one coverage. In response to a determination that the type of the insurance product is of the second type, the processor may generate information associated with whether a coverage review is necessary.

[0177] The method described above may be provided as a computer program stored on a computer-readable recording medium for execution on a computer. The medium may continuously store a computer-executable program, or temporarily store it for execution or download. Additionally, the medium may be various recording or storage means in the form of a single or multiple hardware components, and may not be limited to a medium directly connected to a computer system but may exist distributed over a network. Examples of media may include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and media configured to store program instructions, including ROM, RAM, and flash memory. Furthermore, other examples of media may include recording or storage media managed by app stores that distribute applications or sites and servers that supply or distribute various other software.

[0178] The methods, operations, or techniques of the present disclosure may be implemented by various means. For example, these techniques may be implemented in hardware, firmware, software, or a combination thereof. Those skilled in the art will understand that the various exemplary logical blocks, modules, circuits, and algorithmic steps described in connection with the disclosure herein may be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate such interchangeability between hardware and software, various exemplary components, blocks, modules, circuits, and steps have been generally described above in terms of their functional aspects. Whether such functions are implemented in hardware or in software depends on the design requirements imposed on the specific application and the overall system. Those skilled in the art may implement the functions described in various ways for each specific application, but such implementations should not be construed as departing from the scope of the present disclosure.

[0179] In a hardware implementation, the processing units used to perform the techniques may be implemented in one or more ASICs, DSPs, GPUs, digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, electronic devices, other electronic units designed to perform the functions described in this disclosure, computers, or a combination thereof.

[0180] Accordingly, the various exemplary logic blocks, modules, and circuits described in connection with the present disclosure may be implemented or performed by any combination of general-purpose processors, DSPs, ASICs, FPGAs or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or those designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but alternatively, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, for example, a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors coupled with a DSP core, or any other combination of configurations.

[0181] In firmware and / or software implementations, techniques may be implemented as instructions stored on a computer-readable medium such as random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, compact disc (CD), magnetic or optical data storage devices, etc. The instructions may be executable by one or more processors, and may cause the processor(s) to perform specific aspects of the functions described in this disclosure.

[0182] When implemented in software, the techniques may be stored on a computer-readable medium as one or more instructions or code, or transmitted through a computer-readable medium. Computer-readable media include both computer storage media and communication media, including any medium that facilitates the transmission of a computer program from one place to another. Storage media may be any available medium that can be accessed by a computer. As a non-limiting example, such computer-readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to transfer or store desired program code in the form of instructions or data structures and can be accessed by a computer. Additionally, any connection is appropriately made to the computer-readable medium.

[0183] For example, if software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair cable, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, coaxial cable, fiber optic cable, twisted pair cable, digital subscriber line, or wireless technologies such as infrared, radio, and microwave are included within the definition of a medium. As used herein, disk and disc include CD, laser disc, optical disc, DVD (digital versatile disc), floppy disk, and Blu-ray disc, wherein disks usually play data magnetically, whereas discs play data optically using a laser. The above combinations should also be included within the scope of computer-readable media.

[0184] The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other known form of storage medium. An exemplary storage medium may be connected to a processor so that the processor can read information from the storage medium or write information to the storage medium. Alternatively, the storage medium may be integrated into the processor. The processor and the storage medium may exist within an ASIC. The ASIC may exist within a user terminal. Alternatively, the processor and the storage medium may exist as separate components within the user terminal.

[0185] Although the embodiments described above have been described as utilizing aspects of the subject matter disclosed herein in one or more standalone computer systems, the present disclosure is not limited thereto and may be implemented in conjunction with any computing environment, such as a network or a distributed computing environment. Furthermore, aspects of the subject matter in the present disclosure may be implemented in a plurality of processing chips or devices, and storage may be similarly affected across a plurality of devices. Such devices may include PCs, network servers, and portable devices.

[0186] Although the present disclosure has been described in relation to one embodiment, various modifications and changes may be made without departing from the scope of the present disclosure as understood by a person skilled in the art to which the invention of the present disclosure pertains. Furthermore, such modifications and changes should be considered to fall within the scope of the claims appended to this specification.

Claims

1. A step of receiving medical history data related to the customer's medical history; A step of generating structured data by preprocessing the above medical history data; and A step of generating disease screening information for the customer by disease type based on the above structured data Includes, The above structured data includes information associated with at least one of the type of disease, whether the disease was disclosed, or the history of treatment. An insurance screening method.

2. In Paragraph 1, The above medical history data includes accident history data related to the customer's accident history and notification data related to the medical history reported by the customer, and The above thinking ability data includes first thinking ability data classified into thinking ability units, and The step of generating the above structured data is, Based on the first thinking ability data, a step of generating second thinking ability data in which at least a portion of the first thinking ability data is aggregated; and A step of generating the structured data based on the second thinking ability data and the notification data. An insurance underwriting method including 3. In Paragraph 2, The above first thinking ability data includes 1_1 thinking ability data including information associated with a first disease type and 1_2 thinking ability data including information associated with a second disease type, and The step of generating the above second thinking ability data is, A step of calculating the relationship between the first disease type and the second disease type; and Based on the above association, the step of generating at least some of the second thinking ability data An insurance underwriting method including 4. In Paragraph 2, The above-mentioned first thinking ability data includes first_3 thinking ability data, which includes information associated with a first point in time as information associated with a first category, and first_4 thinking ability data, which includes information associated with a second point in time as information associated with the above-mentioned first category. The step of generating the above second thinking ability data is, In response to the determination that the difference between the first time point and the second time point is smaller than a critical period, the step of generating at least a portion of the second thinking ability data based on the first_3 thinking ability data and the first_4 thinking ability data. An insurance underwriting method including 5. In Paragraph 4, An insurance screening method in which information associated with the above-mentioned first category includes information associated with at least one of the time of occurrence of an accident or the time of treatment.

6. In Paragraph 2, The above-mentioned first thinking ability data includes 1_5 thinking ability data including information associated with a first numerical value as information associated with a second category, and 1_6 thinking ability data including information associated with a second numerical value as information associated with the above-mentioned second category. The step of generating the above second thinking ability data is, A step of generating at least a portion of the second thinking ability data based on at least one of the first numerical value or the second numerical value. An insurance underwriting method including 7. In Paragraph 6, An insurance screening method in which information associated with the above-mentioned second category includes information associated with at least one of the number of days of hospitalization, the number of days of outpatient treatment, or the number of surgeries.

8. In Paragraph 2, Based on the above second thinking ability data and the above notification data, the step of generating the structured data is: A step of determining whether at least a part of the second thinking ability data, which is 2_1 thinking ability data, and at least a part of the notification data are related to each other; and A step of generating a first structured data, which is at least a part of the structured data, based on at least a part of the above 2_1 thinking ability data and the above notification data. An insurance underwriting method including 9. In Paragraph 8, The above second thinking ability data includes second_2 thinking ability data that is different from the above second_1 thinking ability data, and Based on the above second thinking ability data and the above notification data, the step of generating the structured data is: Based on the above 2_2 thinking ability data, the step of generating a second structured data which is at least a part of the above structured data An insurance screening method that further includes 10. In Paragraph 9, The above structured data includes information classified into a third category related to the notification status of a disease, and The above-mentioned first structured data is information of the above-mentioned third category, and includes information related to disease notification, and The above second structured data is information of the above third category, and is an insurance screening method including information related to non-disclosure of disease.

11. In Paragraph 1, A step of requesting additional notification data associated with disease notification in response to some of the information included in the above structured data meeting the criteria conditions. An insurance screening method that further includes 12. A computer-readable, non-transient recording medium recording instructions for executing the method according to paragraph 1 on a computer.

13. As an information processing device, Communication module; Memory; and At least one processor connected to the memory and configured to execute at least one computer-readable program contained in the memory. Includes, The above at least one program is, Receive medical history data related to the customer's medical history, and By preprocessing the above medical history data, structured data classified by disease type is generated, and Based on the above structured data, it includes commands for generating disease screening information for the above customer according to the above disease type, and The above structured data is an information processing device comprising information associated with at least one of the type of disease, the presence or absence of notification of the disease, or the treatment history.

Images