Electronic Device for Providing an Integrated Service for Non-Face-to-Face Insurance Subscription and Enrollment

Abstract

The present disclosure comprises at least one processor including a communication interface, a memory for storing instructions, and a processing circuit, wherein when the instructions are executed by the at least one processor, the electronic device obtains from an insurance company database contract data including at least one of the insurance product name, contract number, insurance period, payment period, premium, and surrender value according to the insurance product subscribed to by the user, and coverage data including at least one of the coverage scope, coverage amount, coverage start date, and maturity date; obtains from a public database medical treatment and medication history including major disease codes and medication details for the user, and health checkup results including body mass index (BMI), blood pressure, blood sugar, and cholesterol; obtains from a MyData API financial asset data including deposit and savings account balances, investment product holding details, and tax payment history for the user; compares the coverage scope included in the coverage data with predefined items to identify non-covered items among the predefined items that are not covered by the subscribed insurance product, and based on the medical treatment and medication history and the health checkup results, the necessity of the non-covered items The existence of such items is identified, and if the aforementioned uninsured items are identified as necessary for the user, among multiple insurance products, an insurance product that includes the aforementioned uninsured items within its coverage scope is identified as a candidate insurance product, the ability to pay the premiums of the candidate insurance product is identified based on the financial asset data, and if the ability to pay is identified, a non-face-to-face subscription procedure for the candidate insurance product is provided.

Description

Technology Field

[0001] The present disclosure relates to an electronic device that supports non-face-to-face insurance product subscription and enrollment.

[0002] In particular, the invention relates to an electronic device that collects and refines financial data corresponding to a user based on different, i.e., heterogeneous and multiple financial data such as insurance company databases, public databases, and MyData APIs, provides coverage analysis and interactive guidance using a Large Language Model (LLM), and provides integrated non-face-to-face subscription, fee calculation, and reporting to regulatory authorities. Background Technology

[0003] Traditional insurance sales have often been centered around face-to-face agents and General Agency (GA) organizations, making it difficult for customers to consistently receive information on coverage analysis, product comparison, application, and settlement / commission details through a single channel. Furthermore, despite the expanding trend of non-face-to-face channels, many systems are focused on simple application functions. Consequently, there is a technical requirement to analyze coverage gaps by combining customers' existing contract and coverage status with financial and medical information based on public and MyData sources, to present the basis for analysis in an explainable manner, and to pre-check for risks of disclosure violations during the non-face-to-face application process. In addition, there was a technical requirement to ensure transparency in commission calculation, installment payments, and reporting to regulatory authorities. means of solving the problem

[0004] An electronic device according to an embodiment of the present disclosure comprises at least one processor including a communication interface, a memory for storing instructions, and a processing circuit, wherein when the instructions are executed by the at least one processor, the electronic device obtains from an insurance company database contract data including at least one of an insurance product name, contract number, insurance period, payment period, premium, and surrender value according to an insurance product subscribed to by a user, and coverage data including at least one of a coverage scope, coverage amount, coverage start date, and maturity date; obtains from a public database medical treatment and medication history including major disease codes and medication details for the user, and health checkup results including body mass index (BMI), blood pressure, blood sugar, and cholesterol; obtains from a MyData API financial asset data including deposit and savings account balances, investment product holding details, and tax payment history for the user; identifies non-covered items among the predefined items that are not covered by the subscribed insurance product by comparing the coverage scope included in the coverage data with predefined items; and based on the medical treatment and medication history and the health checkup results The necessity of the aforementioned uninsured items is identified, and if the aforementioned uninsured items are identified as necessary for the user, among a plurality of insurance products, an insurance product that includes the aforementioned uninsured items within its coverage scope is identified as a candidate insurance product, the ability to pay the premium of the candidate insurance product is identified based on the financial asset data, and if the ability to pay is identified, a non-face-to-face subscription procedure for the candidate insurance product is provided. Brief explanation of the drawing

[0005] In relation to the description of the drawings, the same or similar reference numerals may be used for identical or similar components. FIG. 1 is a block diagram of an electronic device providing an insurance analysis and subscription procedure according to one embodiment of the present disclosure. FIG. 2 is a flowchart illustrating the process of an electronic device according to one embodiment of the present invention identifying whether there is a need for non-covered items based on health checkup results. FIG. 3 is a flowchart illustrating the process of an electronic device according to one embodiment of the present invention calculating available assets and identifying payment ability based on financial asset data. FIG. 4 is a flowchart illustrating the process of an electronic device according to an embodiment of the present invention providing a non-face-to-face insurance subscription procedure through user identification information verification and face matching. Specific details for implementing the invention

[0006] The present disclosure will be described in detail below with reference to the attached drawings.

[0007] The terms used in the embodiments of this disclosure have been selected to be as widely used as possible, taking into account their functions within 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 have been arbitrarily selected by the applicant, and in such cases, their meanings will be described in detail in the relevant explanatory section of this disclosure. Therefore, terms used in this disclosure should be defined not merely by their names, but based on their meanings and the overall content of this disclosure.

[0008] In this specification, expressions such as “have,” “may have,” “include,” or “may include” indicate the presence of such features (e.g., numerical values, functions, operations, or components such as parts) and do not exclude the presence of additional features.

[0009] The expression "at least one of A and / or B" should be understood as representing either "A" and "B" or "A or B".

[0010] Expressions such as "first," "second," "first," or "second" used in this specification may modify various components regardless of order and / or importance, and are used only to distinguish one component from another and do not limit said components.

[0011] Where it is stated that a component (e.g., Component 1) is "(operatively or communicatively) coupled with / to" or "connected to" another component (e.g., Component 2), it should be understood that the component may be directly connected to the other component or connected through the other component (e.g., Component 3).

[0012] Singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, terms such as "comprising" or "consisting of" are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0013] In the present disclosure, the term "user" may refer to a person using an electronic device or a device using an electronic device (e.g., an artificial intelligence electronic device).

[0014] Embodiments of the present disclosure will be described in more detail below with reference to the attached drawings.

[0016] FIG. 1 is a block diagram of an electronic device providing an insurance analysis and subscription procedure according to one embodiment of the present disclosure.

[0017] An electronic device (100) according to an embodiment of the present invention may include various types of intelligent computing devices that collect and analyze user data to propose an optimal insurance product and induce subscription. For example, the electronic device (100) may include not only a server-type computing device, but also a user's smartphone, tablet PC, desktop, laptop, or wearable device.

[0018] According to an embodiment, the electronic device (100) includes a communication interface (110), a memory (120), and a processor (130).

[0019] According to an embodiment, the communication interface (110) may be a module that transmits and receives data with an external entity according to wired or wireless communication standards. For example, it may be linked with an insurance company server, a public institution server, and a MyData platform via mobile communication networks such as LTE and 5G, as well as Wi-Fi, Bluetooth, or near-field communication (NFC).

[0020] According to an embodiment, the memory (120) may store instructions in a non-volatile or volatile manner so that the process of the present disclosure can be performed. Source data obtained from a database, intermediate analysis data, and insurance product recommendation algorithms, etc., may be stored according to the present disclosure.

[0021] According to an embodiment, the processor (130) includes at least one processing circuitry and can perform complex operations by executing instructions stored in memory (120). For example, it may include a central processing unit (CPU), a graphics processing unit (GPU), or a neural network processing unit (NPU) specialized for artificial intelligence operations.

[0022] According to an embodiment, the electronic device (100) can obtain information from three different data sources for reliable insurance analysis.

[0023] In an embodiment of the present disclosure, the electronic device (100) may obtain explicit consent from the user in advance when collecting and using personal information (including sensitive information) including insurance contract information, health information, and financial asset information. Additionally, the electronic device (100) may collect data only to the minimum extent necessary for identifying uninsured items, identifying necessity, and identifying payment ability, and may store identification information that is unnecessary for achieving the purpose by masking or tokenizing it, or process it in a de-identified form. Furthermore, the electronic device (100) may provide the user terminal with the data storage period, purpose of use, whether to provide to a third party, and method of withdrawal, and may delete the relevant data or switch it to an inaccessible state upon the user's withdrawal of consent.

[0024] 1. Insurance company database and contract / coverage data: According to the embodiment, the processor (130) may retrieve contract data from the insurance company system.

[0025] For example, the processor (130) can access the insurance company system in accordance with the user's consent (e.g., login, identity verification, etc.) and download contract data according to the insurance product the user has subscribed to.

[0026] For example, contract data may include product name (e.g., OO Indemnity Medical Expense Insurance), contract number, insurance period (e.g., maturity at age 80), payment period (e.g., 20-year payment), monthly premium, and surrender value information received upon cancellation.

[0027] Additionally, the processor (130) can obtain (download) coverage data based on the insurance product subscribed to by the user. For example, the coverage data may include specific coverage scope of the insurance product (e.g., diagnosis of cancer, diagnosis of fracture), coverage amount (e.g., 50 million won), coverage start date and maturity date, etc.

[0029] 2. Public database and health data: The electronic device (100) can obtain data from public institutions such as the National Health Insurance Service.

[0030] For example, the processor (130) can access a public institution / public data provision system based on the user's consent (e.g., login, identity verification, etc.) to obtain a 'medical treatment and medication history' including major disease codes and medication history for the user.

[0031] For example, 'medical treatment and medication history' may include major disease codes according to the Korean Standard Classification of Diseases and Causes of Death (KCD) (e.g., I10-Hypertension) (diagnosis) and the ingredients and details of prescribed medications. Depending on the embodiment, the medication history may include the types and duration of medications continuously taken for the treatment of a specific disease.

[0032] However, this is merely an example and is not limited thereto. For instance, it may include various forms of identification information capable of identifying the user's disease or the medication prescribed to the user.

[0033] According to an embodiment, the processor (130) may obtain the user's health checkup results. For example, the health checkup results may include various forms of numerical information that objectively represent the user's current health status, such as body mass index (BMI), which is physical measurement data, and biological signals such as blood pressure, blood sugar, and blood cholesterol levels.

[0035] 3. MyData API-based financial asset data: The processor (130) can identify the user's financial asset status through a standard API, obtain the balance of savings and deposits, and the details of holding investment products such as stocks and bonds from securities companies, and can obtain tax payment history by accessing the National Tax Service system.

[0036] According to an embodiment, the processor (130) can identify whether the user has the ability to pay the insurance premium (determining the sustainability of future premium payments) based on the user's net worth, income level, and fixed expenditure level.

[0037] A processor (130) according to an embodiment of the present disclosure can fuse contract / coverage data, health data (e.g., medical treatment and medication history, health checkup results), and financial asset data to perform user-customized product recommendations rather than a simple listing of insurance products.

[0039] A processor (130) according to an embodiment of the present disclosure can identify a coverage gap in an insurance product subscribed to by the user and recommend a customized insurance product to the user so that no gap occurs in coverage items of high necessity based on the user's health data.

[0040] According to an embodiment, the processor (130) derives a guarantee gap by comparing the acquired guarantee data with predefined items stored in the system memory (120) (or received from the server).

[0041] For example, the processor (130) compares the 'predefined items,' which are a standard coverage list recommended by the system, with the 'coverage scope' actually subscribed to by the user. According to an embodiment, the processor (130) may identify an item as an uninsured item if a specific coverage (e.g., diagnosis benefit for cerebrovascular disease) does not exist in the subscription history, or if, even if it exists, the coverage amount is below the statistically required level.

[0042] According to an embodiment, for identified non-covered items, the processor (130) combines medical treatment and medication history and health checkup results obtained from a public database as filtering conditions.

[0043] For example, if an uninsured item is coverage related to 'cardiovascular disease,' and the user's blood pressure or cholesterol levels exceed a threshold or there is a history of taking related medication, the necessity of that item is defined as 'high risk / necessary.'

[0045] According to an embodiment, the 'predefined items' that are compared with the coverage scope when determining the coverage gap may not be fixed constants, but may be a dynamic data set that is reconfigured in real time according to the user's human characteristics.

[0046] For example, the predefined items include diagnostic fees corresponding to each specific disease code (e.g., KCD code). This may refer to agreed amounts paid upon confirmed diagnosis of conditions ranging from major severe diseases such as cancer, cerebrovascular disease, and heart disease to chronic diseases such as diabetes and hypertension.

[0048] According to an embodiment, the processor (130) changes the type and importance of predefined disease codes based on the user's personal information. That is, the processor (130) can optimize or dynamically reconfigure predefined items based on gender and age.

[0049] For example, if the user is female, disease codes related to female-specific conditions, such as breast cancer (C50) and cervical cancer (C53), can be placed above predefined items to prioritize the calculation of the necessity for the corresponding diagnosis fee. Accordingly, if the coverage scope included in the user's coverage data does not include breast cancer, breast cancer can be identified as a coverage gap. As another example, when the user is male, even if the coverage scope included in the coverage data does not include breast cancer, breast cancer may not be identified as a coverage gap.

[0050] For example, if the user is a male in his 20s or 30s, the items may be organized around codes related to injury accidents or disease income coverage, and for middle-aged users in their 50s or 60s, codes for age-related diseases such as degenerative diseases, dementia (F00-F03), and cataracts may be included by assigning weights to predefined items. The examples described above are merely for convenience of explanation and are not limited thereto.

[0051] According to an embodiment, the processor (130) may change the priority or inclusion of predefined disease codes based on the user's age. For example, the processor (130) may include disease codes that show a relatively high incidence rate or risk level according to age ranges (e.g., 20s, 30s, 40s, 50s and older) in the predefined items or place them at the top. Additionally, the processor (130) may update the configuration of predefined items by referring to a pre-stored table of risk disease codes by age range or a weighting table based on insurance statistics. Accordingly, even with the same coverage data, the types of uninsured items identified as coverage gaps may change depending on the user's age.

[0052] If the processor (130) according to an embodiment of the present disclosure determines through analysis that an uninsured item is necessary for the user, the processor (130) can search a plurality of insurance product databases and select candidate insurance products that include the uninsured item.

[0053] According to an embodiment, the electronic device (100) may refer to an insurance product database in which coverage scope information corresponding to each of a plurality of insurance products is normalized and stored in units of disease codes to identify candidate insurance products. The processor (130) may filter candidate insurance products by matching non-covered items (disease codes or coverage codes) with coverage scopes for each insurance product, and may determine the priority of the filtered candidate insurance products based on at least one of premiums, payment periods, whether there is overlapping coverage with existing insurance, and whether there are exclusion / reduction conditions. At this time, the processor (130) may lower the priority of candidate insurance products that have excessive coverage overlapping with coverage included in the user's existing coverage data, and present candidate insurance products with a significant effect in resolving actual coverage gaps at the top.

[0054] For example, the processor (130) according to the present disclosure does not merely stop at finding coverage gaps, but can analyze whether the user's biometric indicators belong to a high-risk group for disease occurrence or are in a state requiring medical management, and identify whether the coverage item is 'necessary' to the user. The processor (130) can compare and calculate multiple biometric indicators (body mass index, blood pressure, blood sugar, cholesterol, etc.) included in health checkup results obtained from a public database with a preset threshold. According to an embodiment, if at least one indicator exceeds the threshold and is determined to have a statistically high risk of occurrence, the uninsured item covering the disease can be defined as an item that is absolutely necessary for the user, thereby selecting candidate insurance products.

[0056] Subsequently, the processor (130) identifies whether the user can afford the monthly premium of the product, i.e., the candidate insurance product, based on MyData-based financial asset data, and if the above-mentioned conditions are met, it can maximize the user's convenience of subscribing to the insurance product by providing a non-face-to-face subscription procedure.

[0057] According to an embodiment, the electronic device (100) may not provide a non-face-to-face subscription procedure for a candidate insurance product if the candidate insurance product is not identified as necessary for the user or if the ability to pay the premium for the candidate insurance product is not identified. In this case, the electronic device (100) may provide the reason for not providing the non-face-to-face subscription procedure to the user terminal, and may provide at least one of, for example, (i) grounds for determining that uninsured items are not necessary (e.g., health checkup values ​​are below a threshold), or (ii) grounds for not meeting the payment ability (e.g., the ratio of premiums to available assets exceeds the safety ratio). Additionally, after the user confirms the reason, the electronic device (100) may search for alternative candidate insurance products with lower premium levels or provide a procedure to update input data (e.g., latest checkup results) used for determining necessity.

[0059] FIG. 2 is a flowchart illustrating the process of an electronic device according to one embodiment of the present disclosure identifying whether there is a need for an uninsured item based on a health checkup result.

[0060] Referring to FIG. 2, an electronic device (100) according to one embodiment of the present disclosure can perform a process of determining whether a user's biometric indicator exceeds a preset threshold to identify the need for specific insurance coverage.

[0061] According to an embodiment, the processor (130) has a technical feature in that, through this process, it goes beyond the step of simply checking for coverage (i.e., going beyond the step of checking for coverage gaps) and calculates a personalized risk based on objective health data obtained from a public database.

[0062] According to an embodiment, the processor (130) can identify whether an uninsured item is necessary by inputting a plurality of numerical values ​​included in the acquired health checkup results into a predefined threshold algorithm as follows.

[0063] According to an embodiment, the processor (130) can perform a threshold comparison after verifying the units and measurement conditions of the values ​​included in the health checkup results. For example, blood sugar levels can be compared based on fasting blood sugar measured in a fasting state, and blood pressure levels can be compared based on the measurement value from the same institution or the average value of multiple measurements within a certain period. Additionally, if the elapsed time from the measurement date of the health checkup results exceeds a preset period (e.g., one year), the processor (130) can lower the reliability of the threshold comparison result or request the user terminal to update the latest checkup information.

[0064] 1. Body Mass Index (BMI) based determination step: The processor (130) determines that the user's body mass index (BMI) is 30 kg / m² 2 You can check whether there is an abnormality.

[0065] As a result of the judgment, if the value is 30 or higher, it is considered that there is a high risk of complications due to severe obesity, and among the predefined items, the diabetes diagnosis fee may be determined as an uninsured item necessary for the user.

[0066] 2. Blood pressure value-based judgment step: The processor (130) can analyze whether the user's blood pressure corresponds to a systolic blood pressure of 140 mmHg or higher or a diastolic blood pressure of 90 mmHg or higher.

[0067] If the corresponding conditions are met, the risk of developing hypertension and cardiovascular and cerebrovascular diseases is identified as heightened, and at least one of the diagnosis benefit for hypertensive diseases and the diagnosis benefit for cerebrovascular diseases can be classified as an uninsured item required by the user.

[0068] 3. Blood glucose level-based judgment step: The processor (130) can check whether the fasting blood glucose level is 126 mg / dL or higher. If the fasting blood glucose is 126 mg / dL or higher, it can determine that a gap in diabetes coverage may cause a fatal economic risk to the user and identify the diabetes diagnosis fee as an uninsured item required by the user.

[0069] 4. Cholesterol level-based judgment step: The processor (130) can determine whether the total cholesterol level is 240 mg / dL or higher. If the level is 240 mg / dL or higher, it is classified as a risk group for ischemic heart disease due to lipid accumulation in blood vessels, and the corresponding ischemic heart disease diagnosis fee can be determined as an uninsured item required by the user.

[0070] As described above, the processor (130) can provide the user with precise insurance analysis results based on data by prioritizing coverage items directly related to the user's actual health status. This can be organically combined with the candidate insurance product identification and payment ability verification steps performed in subsequent stages to ultimately improve the reliability of the non-face-to-face subscription process.

[0072] FIG. 3 is a flowchart illustrating the process of an electronic device according to one embodiment of the present disclosure calculating available assets and identifying solvency based on financial asset data.

[0073] Referring to FIG. 3, an electronic device (100) according to one embodiment of the present disclosure can identify payment ability by analyzing financial asset data obtained from a MyData API to determine whether a user can stably maintain the insurance contract after a candidate insurance product has been identified.

[0074] According to an embodiment, the processor (130) can calculate available assets by executing an algorithm that uses the balance of a savings account, investment product holdings, and tax payment history as variables to quantify the user's economic capacity.

[0075] According to the embodiment, available assets refer to liquid assets that can be invested in actual premium payments, rather than the simple sum of assets, and can be calculated by the following formula.

[0076] V available = (B account + Σ (V invest * α)) - T expected

[0077] V available : User's final calculated available assets.

[0078] B account : Real-time sum of deposit and savings account balances obtained via MyData API.

[0079] V invest : Current valuation of investment products such as stocks, bonds, and funds.

[0080] α (Liquidity Coefficient): A weighting factor reflecting the potential for immediate liquidity based on the type of investment product (e.g., 0.8 for listed stocks, 0.3 for closed-end funds, etc.).

[0081] T expected : Deductible items such as estimated future taxes based on tax payment history and fixed debt repayments.

[0082] According to an embodiment, the processor (130) calculates available asset V through the formula described above. available The final ability to pay can be identified by comparing the premiums of the selected candidate insurance products.

[0083] According to an embodiment, the processor (130) can compare the monthly or annual premium figures of the candidate insurance product with the size of available assets. At this time, not only is it possible to make a one-time payment, but the possibility of maintaining the product over the entire payment period can also be evaluated by analyzing the trend of the user's average asset increase or decrease.

[0084] If available assets calculated according to the embodiment are identified as having the ability to pay by meeting the premium payment criteria (e.g., when the ratio of premiums to available assets is less than or equal to a pre-set safety ratio), the electronic device (100) can activate a non-face-to-face subscription procedure for the candidate insurance product and provide it to the user.

[0085] First, the processor (130) can verify whether the proportion of the insurance premium within the user's monthly available asset flow is within a pre-set safety ratio. For example, if the proportion of the monthly insurance premium relative to the calculated available assets is 10% to 15% or less, it can identify that the ability to pay is sufficient, and if it exceeds this range, it can determine that there is a high risk of early termination due to the burden of payment, and lower the priority of the product or provide a warning notification to the user.

[0086] Additionally, the processor (130) can analyze the trends in increases and decreases in deposits and investment assets and fluctuations in investment assets over a past period (e.g., the last year) obtained through the MyData API in a time series. Through this, it can determine whether the current available assets are due to temporary asset sales, etc., or are based on a stable income stream, thereby ensuring objectivity in the results of identifying solvency.

[0087] The payment ability identification process prevents the risk of early termination caused by users’ excessive insurance subscriptions in advance, and by combining financial MyData with insurance analysis logic, it can provide the technical effect of suggesting only the optimal products that are practically feasible to maintain.

[0089] FIG. 4 is a flowchart illustrating the process of an electronic device according to one embodiment of the present disclosure providing a non-face-to-face insurance subscription procedure through user identification information verification and face matching.

[0090] Referring to FIG. 4, an electronic device (100) according to one embodiment of the present disclosure can perform an advanced identity verification and subscription process using a user's identification card and real-time biometric information to provide a secure non-face-to-face subscription environment after the payment ability of a candidate insurance product has been identified.

[0091] According to an embodiment, the processor (130) can extract user identification information, such as name, resident registration number, date of issuance, and issuing agency, from an ID card image input through a communication interface (110) or a camera module.

[0092] For example, the processor (130) can convert text areas within an ID card image into digital data by utilizing optical character recognition (OCR) technology.

[0093] According to an embodiment, the processor (130) can verify the format validity of whether the extracted user identification information conforms to a pre-set data format (e.g., digit count and combination rules of a resident registration number, date format, etc.). If it is determined that the format is invalid or if missing information is identified, the processor (130) can stop the registration process and provide feedback to the user requesting re-photography or correction.

[0094] According to an embodiment, when the validity of the identification information is confirmed, the processor (130) may perform a biometric authentication step to verify whether the actual attempting to sign up is the same person as the person on the identification.

[0095] According to an embodiment, the processor (130) controls the camera to acquire a real-time face image of the user, and at the same time, can extract a face image area from the previously input ID image.

[0096] According to an embodiment, the processor (130) can execute an artificial intelligence-based feature point extraction algorithm to calculate the similarity between a real-time face image and an ID card face image and determine whether they match. At this time, to prevent fraudulent authentication using photos or videos, an anti-spoofing technology that detects the user's minute movements or eye blinking can be combined to enhance the security of the authentication.

[0097] If the format validity of the user identification information is verified through the steps described above and it is determined that the real-time face image and the ID card image match, the processor (130) can approve the final subscription authority.

[0098] According to an embodiment, the processor (130) can generate an individualized electronic application form by combining the user's insurance contract data and the detailed terms and conditions of the candidate insurance product.

[0099] According to an embodiment, the processor (130) can finally complete the non-face-to-face subscription procedure by requesting a review of the electronic subscription form through a user interface and requesting an electronic signature using a security token or private certificate.

[0100] This series of processes can provide technical benefits that minimize the risk of theft without physical face-to-face verification and simultaneously ensure the reliability of the insurance subscription process and user convenience by establishing a multi-security system that combines the accuracy of identification information with biometric information.

[0102] According to an embodiment of the present disclosure, the processor (130) can perform an intelligent consultation function using an artificial intelligence model to resolve information asymmetry and difficulties in understanding terms and conditions that may occur during the process of a user proceeding with a non-face-to-face subscription procedure. The processor (130) can provide product descriptions or terms and conditions data corresponding to identified candidate insurance products as input values ​​to the artificial intelligence model.

[0103] The product description input into the artificial intelligence model may include complex text information such as the coverage details of the insurance product, reasons for payment restrictions (exclusions), premium structure, and renewal cycle. The processor (130) vectorizes and stores the core content of the product description through an artificial intelligence model to which natural language processing (NLP) technology is applied, and can configure the context to understand the user's various question intentions.

[0104] The AI ​​model can receive natural language queries from users regarding candidate insurance products in real time while the non-face-to-face sign-up process is enabled and provided.

[0105] According to an embodiment, the artificial intelligence model can analyze the intent of a query entered by a user (e.g., "Does the insurance payout come out immediately upon cancer diagnosis?", "What is the exclusion period?").

[0106] According to an embodiment, the artificial intelligence model can extract accurate information corresponding to the analyzed intent from a pre-entered product description and provide an optimized response to the user. Through this, the user can immediately understand the key contents of the product without connecting to a separate agent.

[0107] The artificial intelligence model according to the present disclosure is based on a Large Language Model (LLM) and can operate by combining Retrieval-Augmented Generation (RAG) technology to maintain the accuracy and timeliness of information.

[0108] Specifically, the processor (130) vectorizes and stores product descriptions and terms and conditions data of candidate insurance products, and when a user's query is received, it retrieves the terms and conditions phrases with the highest similarity to the query in real time. Subsequently, the LLM generates a response by referencing the text of the actual retrieved terms and conditions as context, thereby preventing hallucinations of artificial intelligence and providing the user with accurate information based on the terms and conditions.

[0109] Through this process, the AI ​​model can derive and provide objective answers to highly personalized questions linked to the user's actual health status and financial data (e.g., "Will I face any disadvantages when signing up for this product based on my blood pressure levels?") based on disclosure obligations and disclaimers within the product description.

[0110] According to an embodiment, the artificial intelligence model can maximize the objective reliability of the subscription decision by answering customized questions linked to the user's actual data (health status, financial assets) based on the evidence in the product description.

[0112] Meanwhile, the methods according to the various embodiments of the present disclosure described above may be implemented in the form of an application installable on an existing electronic device. Alternatively, the methods according to the various embodiments of the present disclosure described above may be performed using a deep learning-based learned neural network (or deep learned neural network), that is, a learning network model. Furthermore, the methods according to the various embodiments of the present disclosure described above may be implemented solely through a software upgrade or a hardware upgrade of an existing display device. Additionally, the various embodiments of the present disclosure described above may also be performed through an embedded server equipped in the electronic device or an external server of the electronic device.

[0113] Meanwhile, according to one embodiment of the present disclosure, the various embodiments described above may be implemented as software comprising instructions stored on a machine-readable storage medium (e.g., a computer). The machine may include an electronic device according to the disclosed embodiments, which is a device capable of calling instructions stored from the storage medium and operating according to the called instructions. When instructions are executed by a processor, the processor may perform a function corresponding to the instructions directly or by using other components under the control of the processor. Instructions may include code provided or executed by a compiler or an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, "non-transitory" means only that the storage medium does not contain a signal and is tangible, and does not distinguish whether data is stored semi-permanently or temporarily in the storage medium.

[0114] Additionally, according to one embodiment, the method according to the various embodiments described above may be provided by being included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed online in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or through an application store (e.g., Play Store™). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or provided on a storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0115] Additionally, each component (e.g., module or program) according to the various embodiments described above may be composed of a singular or multiple entities, and some of the aforementioned sub-components may be omitted, or other sub-components may be further included in the various embodiments. Generally or additionally, some components (e.g., module or program) may be integrated into a single entity to perform the functions performed by each of the respective components prior to integration in the same or similar manner. The operations performed by the module, program, or other components according to the various embodiments may be executed sequentially, in parallel, iteratively, or heuristically, or at least some operations may be executed in a different order, omitted, or other operations added.

[0116] Although preferred embodiments of the present disclosure have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above. It is understood that various modifications can be made by those skilled in the art without departing from the essence of the present disclosure as claimed in the claims, and such modifications should not be understood individually from the technical spirit or perspective of the present disclosure. Explanation of the symbols

[0117] 100: Electronic device 110: Communication interface 120: Memory 130: Processor

Claims

Claim 1 In an electronic device, a communication interface; a memory for storing instructions; The electronic device comprises at least one processor including a processing circuit, wherein when the instructions are executed by the at least one processor, the electronic device obtains contract data from an insurance company database that includes at least one of an insurance product name, contract number, insurance period, payment period, premium, and surrender value according to an insurance product subscribed to by the user, and coverage data that includes at least one of a coverage scope, coverage amount, coverage start date, and maturity date; obtains medical treatment and medication history including major disease codes and medication details for the user from a public database, and health checkup results including body mass index (BMI), blood pressure, blood sugar, and cholesterol; obtains financial asset data from a MyData API that includes deposit and savings account balances, investment product holding details, tax payment history, and fixed debt repayment amounts for the user; identifies non-covered items among the predefined items that are not covered by the insurance product subscribed to by comparing the coverage scope included in the coverage data with predefined items; and determines the necessity of the non-covered items based on the medical treatment and medication history and the health checkup results. Identify whether there is a need for the user, and if the aforementioned uninsured item is identified as necessary for the user, identify an insurance product among multiple insurance products that includes the aforementioned uninsured item within its coverage scope as a candidate insurance product, calculate a sum by summing the real-time total of the deposit and savings account balance and the value obtained by applying a liquidity coefficient according to the type of investment product to the current valuation amount of the investment product, calculate available assets by deducting the fixed debt repayment amount and the estimated future tax amount based on the tax payment history from the sum, compare the available assets with the premium of the candidate insurance product, and identify whether the ratio of the premium of the candidate insurance product to the available assets is below a preset safety ratio.An electronic device that analyzes in a time series the trends of increases and decreases in deposits and savings and fluctuations in investment assets over a past certain period obtained through the above MyData API to identify the feasibility of maintaining the above candidate insurance product over the entire payment period, identifies the user's ability to pay based on the above premium proportion and the above feasibility of maintaining, provides a non-face-to-face subscription procedure for the above candidate insurance product if it is identified that the user has the ability to pay, does not provide a non-face-to-face subscription procedure for the above candidate insurance product if it is identified that the user does not have the ability to pay, provides grounds for non-satisfaction of the ability to pay to the user terminal, and after providing grounds for non-satisfaction of the ability to pay to the user terminal, provides a procedure to re-search for an alternative candidate insurance product with a lower premium level, wherein the grounds for non-satisfaction of the ability to pay include information that the above premium proportion exceeds the above-set safety ratio, and the liquidity coefficient is a weighting factor reflecting the possibility of immediate cash conversion according to the type of the above investment product, applies the liquidity coefficient as 0.8 if the above investment product is a listed stock, and applies the liquidity coefficient as 0.3 if the above investment product is a closed-end fund. Claim 2 In claim 1, the previously defined items include a diagnostic fee corresponding to each of the previously defined disease codes, and the previously defined disease codes are changed according to the user's gender and age, an electronic device. Claim 3 In claim 1, the electronic device identifies the non-covered item as necessary for the user when at least one of the body mass index (BMI), blood pressure, blood sugar, and cholesterol included in the health checkup results exceeds a preset threshold. Claim 4 In paragraph 3, the previously defined items further include at least one of diabetes diagnosis benefit, hypertensive disease diagnosis benefit, ischemic heart disease diagnosis benefit, and cerebrovascular disease diagnosis benefit, and the electronic device identifies the necessity of the above-mentioned uninsured items based on whether at least one of the body mass index (BMI), blood pressure, blood sugar, and cholesterol included in the health examination results exceeds a preset threshold; (i) if the body mass index (BMI) is 30 or higher, the diabetes diagnosis benefit among the above-mentioned uninsured items is determined to be necessary for the user; (ii) if the blood pressure is systolic blood pressure 140 mmHg or higher or diastolic blood pressure 90 mmHg or higher, at least one of the hypertensive disease diagnosis benefit and cerebrovascular disease diagnosis benefit among the above-mentioned uninsured items is determined to be necessary for the user; (iii) if the blood sugar is fasting blood sugar 126 mg / dL or higher, the diabetes diagnosis benefit among the above-mentioned uninsured items is determined to be necessary for the user; and (iv) if the cholesterol is total cholesterol 240 mg / dL or higher, among the above-mentioned uninsured items An electronic device that determines that ischemic heart disease diagnosis costs are necessary for the above user. Claim 5 delete Claim 6 In claim 1, the electronic device extracts user identification information from an ID card image, verifies the format validity of the extracted user identification information, acquires a face image of the user, extracts a face image from the ID card image, compares the face image with the face image to determine whether they match, and if the format validity is verified and the face image matches the face image, requests an electronic signature on an electronic application form for the candidate insurance product to provide the non-face-to-face subscription procedure. Claim 7 An electronic device according to claim 1, wherein the electronic device inputs a product description corresponding to the candidate insurance product into an artificial intelligence model, and provides a response corresponding to the user's query regarding the candidate insurance product while providing the non-face-to-face subscription procedure through the artificial intelligence model.

Images