Claim settlement method and device, storage medium and computer equipment
The intelligent life insurance claims method, which combines blockchain and wearable devices, solves the problem of low efficiency in traditional underwriting, realizes dynamic premium calculation and real-time claims decision-making, improves the automation rate of underwriting and data credibility, saves premiums, and increases user activity.
Patent Information
- Application Number
- CN202511062633.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-30
- Publication Date
- 2025-11-14
AI Technical Summary
Traditional insurance underwriting processes rely on manual review, which is inefficient and susceptible to subjective factors. Furthermore, existing technologies have failed to deeply integrate wearable device data for dynamic risk assessment and lack real-time data-driven intelligent decision-making capabilities.
By using a blockchain-based smart life insurance claims method, health data is collected in real time using medical-grade wearable devices and encrypted and uploaded to the blockchain. Combined with zero-knowledge proof technology, dynamic premium calculation and federated learning models are realized to automate the underwriting process and make real-time claims decisions.
It improved the accuracy of health data tampering detection, increased the automation rate of underwriting, shortened decision-making delays, and enabled health-compliant users to save on premiums through the dynamic premium model, thereby increasing user activity in health management services.
Smart Images
Figure CN120952975A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent life insurance claims technology, and can be applied to the fields of financial technology business and medical and health care and elderly care business. In particular, it relates to a claims method, device, storage medium and computer equipment. Background Technology
[0002] In the traditional insurance underwriting field, the underwriting process mainly relies on manual review of paper medical examination reports and historical medical records, which is inefficient and poses a risk of information asymmetry. For example, many life insurance companies use electronic questionnaire systems to collect user health information, but this still requires manual intervention, resulting in long underwriting cycles and susceptibility to subjective factors. In recent years, some insurance companies have attempted to introduce wearable device data to assist underwriting, such as collecting user health indicators like heart rate and sleep through smartwatches and wristbands. However, this data is currently only used for premium discount incentives and has not yet been deeply integrated into underwriting risk control models, making dynamic risk assessment impossible. Fintech business platforms support functions such as shopping, social networking, interactive games, and resource transfer, and have functions such as applying for loans, credit cards, or purchasing insurance and wealth management products. Systems applying the methods described in this application can be medical, health, and elderly care business systems, which support functions such as disease auxiliary diagnosis, health management, and remote consultation. The application of blockchain technology in the insurance industry has been initially explored, for example, using medical data storage chains to ensure the immutability of data. However, existing solutions mostly focus on post-event evidence preservation (such as data verification during the claims stage), failing to connect the entire process of underwriting, insurance, and claims, and lacking real-time data-driven intelligent decision-making capabilities. Summary of the Invention
[0003] In view of this, the present invention provides a claims settlement method, apparatus, storage medium, and computer equipment, the main purpose of which is to solve the problem of low efficiency in the current claims settlement process due to manual intervention.
[0004] To address the aforementioned issues, this application provides a claims settlement method, including:
[0005] Based on the policyholder's wallet address, a preset mapping table is queried to obtain the first health data and medical data corresponding to the policyholder;
[0006] When the first health data and the medical data meet the preset timeliness conditions, dynamic premium calculation is performed based on the first health data and the medical data to obtain the target premium.
[0007] Real-time monitoring and acquisition of the policyholder's second health data and the policyholder's medical records on the blockchain;
[0008] When the second health data and the medical record meet the preset claim triggering conditions, the compensation amount is calculated based on the target premium.
[0009] The insured will receive compensation based on the stated amount.
[0010] Optionally, before collecting the policyholder's initial health data and the policyholder's medical records on the blockchain, the method further includes:
[0011] Real-time acquisition of the insured's original health data collected using certified medical devices;
[0012] The original health data is encrypted using a symmetric encryption method to obtain encrypted health data;
[0013] The encrypted health data is hashed to obtain a first hash value;
[0014] The first hash value representing the original health data is stored in the target area of the preset mapping table corresponding to the wallet address of the policyholder in chronological order using a preset structure template.
[0015] The raw health data includes heart rate, blood pressure, blood oxygen, and sleep quality.
[0016] Optionally, when the first health data and the medical data meet preset timeliness conditions, dynamic premium calculation is performed based on the first health data and the medical data to obtain the target premium, specifically including:
[0017] When the first health data and the treatment data meet the preset timeliness conditions, the target risk index is obtained by calculating and processing based on the first health data and the treatment data using risk assessment rules corresponding to different data dimensions.
[0018] The target premium is obtained by calculation based on the preset base rate, the target risk indicator, and the predetermined Laplace noise.
[0019] Optionally, the step of calculating and processing the target risk indicator based on the first health data and the medical data using risk assessment rules corresponding to different data dimensions specifically includes:
[0020] Based on the heart rate parameters in the first health data, a first function is used to calculate and process the heart rate risk index.
[0021] The first risk index is obtained by calculating and processing the preset initial value of the risk coefficient and the heart rate risk index.
[0022] Blood pressure risk indicators are determined based on the blood pressure parameters in the first health data and each preset blood pressure danger zone.
[0023] A second risk indicator is obtained by calculating and processing based on the first risk indicator and the blood pressure risk indicator.
[0024] Based on the sleep quality parameters in the first health data, a second function is used to calculate and process the sleep quality risk parameters.
[0025] The target risk index is obtained by calculation based on the second risk index and the sleep quality risk parameter.
[0026] Optionally, the calculation process based on the preset base rate, the target risk indicator, and the predetermined Laplace noise to obtain the target premium specifically includes:
[0027] A comprehensive risk index is obtained by performing an addition operation based on the target risk index and the predetermined Laplace noise.
[0028] The target premium is obtained by calculating based on the base premium rate and the comprehensive risk index.
[0029] Optionally, when the second health data and the medical record meet the preset claim triggering conditions, the compensation amount is calculated based on the target premium, specifically including:
[0030] When the heart rate parameter in the second health data is greater than the first preset threshold, a preset timer is used to record the duration for which the heart rate parameter is greater than the first preset threshold;
[0031] When the duration exceeds a preset duration threshold, a federated learning method is used to verify the second health data and the medical record.
[0032] When the verification is successful, it is determined that the second health data and the medical record meet the preset claim triggering conditions;
[0033] The compensation amount is obtained by calculating based on the target premium.
[0034] Optionally, the step of using a federated learning method to verify the second health data and the medical evidence specifically includes:
[0035] The associated data is obtained by concatenating the second health data, the medical evidence, and the version number of the current federated learning model.
[0036] The associated data is subjected to hash calculation to obtain a second hash value;
[0037] Based on the current federated learning model, query the smart contract to obtain the third hash value corresponding to the current federated learning model;
[0038] When the second hash value is the same as the third hash value, it is determined that the second health data and the medical evidence meet the preset claim triggering conditions.
[0039] To address the aforementioned problems, this application provides a claims processing device, comprising:
[0040] The query module is used to query a preset mapping table based on the policyholder's wallet address to obtain the first health data and medical data corresponding to the policyholder;
[0041] The dynamic premium calculation module is used to perform dynamic premium calculation processing based on the first health data and the medical data when the first health data and the medical data meet the preset timeliness conditions, so as to obtain the target premium.
[0042] The acquisition module is used to respond to the policyholder's claim application operation by acquiring the policyholder's second health data and the policyholder's medical records on the blockchain in real time.
[0043] The compensation calculation module is used to calculate the compensation amount based on the target premium when the second health data and the medical evidence meet the preset claim triggering conditions.
[0044] The claims module is used to process claims for the insured based on the compensation amount.
[0045] To address the aforementioned problems, this application provides a storage medium storing a computer program that, when executed by a processor, implements the steps of the claims settlement method described above.
[0046] To address the aforementioned problems, this application provides a computer device, comprising at least a memory and a processor. The memory stores a computer program, and the processor, when executing the computer program in the memory, implements the steps of the aforementioned claims settlement method.
[0047] The beneficial effects of this application are as follows: This application achieves a complete revolution in the life insurance underwriting and claims process through blockchain and dynamic health data assessment technology. Regarding data credibility, medical-grade wearable devices collect vital sign data in real time and encrypt it via hashing before uploading it to the blockchain. Combined with zero-knowledge proof technology, this improves the accuracy of detecting health data tampering and completely solves the problem of assessment distortion caused by traditional underwriting relying on static medical examination reports. Regarding underwriting efficiency, smart contracts automatically retrieve continuous health data within a predetermined timeframe to generate dynamic premiums. Federated learning models integrate medical records from multiple institutions, improving the automation rate of underwriting and reducing decision-making delays. Through intelligent analysis of medical images stored on the blockchain and cross-verified by multiple nodes, the time required for critical illness claims is shortened. The dynamic premium model allows users who meet health standards to save on premiums and increases user activity in health management services.
[0048] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description
[0049] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:
[0050] Figure 1 This illustration shows an application environment diagram of a claims settlement method provided in an embodiment of this application;
[0051] Figure 2 A flowchart illustrating a claims settlement method provided in an embodiment of this application is shown;
[0052] Figure 3 A flowchart illustrating a claims settlement method provided in another application embodiment is shown;
[0053] Figure 4 A structural block diagram of a claims processing device according to another embodiment of this application is shown;
[0054] Figure 5 A schematic diagram of the structure of a computer device according to an embodiment of this application is shown;
[0055] Figure 6 Another structural schematic diagram of a computer device according to one embodiment of this application is shown. Detailed Implementation
[0056] Various embodiments and features of this application are described herein with reference to the accompanying drawings.
[0057] It should be understood that various modifications can be made to the embodiments described herein. Therefore, the above description should not be considered as limiting, but merely as an example of embodiments. Other modifications within the scope and spirit of this application will be apparent to those skilled in the art.
[0058] The accompanying drawings, which are included in and form part of this specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.
[0059] These and other features of this application will become apparent from the following description of preferred forms of embodiments given as non-limiting examples, with reference to the accompanying drawings.
[0060] It should also be understood that although this application has been described with reference to some specific examples, those skilled in the art can certainly implement many other equivalent forms of this application.
[0061] The above and other aspects, features and advantages of this application will become more apparent when taken in conjunction with the accompanying drawings and in view of the following detailed description.
[0062] Specific embodiments of this application are described thereafter with reference to the accompanying drawings; however, it should be understood that the claimed embodiments are merely examples of this application, which can be implemented in various ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that could obscure the application. Therefore, the specific structural and functional details claimed herein are not intended to be limiting, but merely serve as the basis and representative basis for the claims to teach those skilled in the art to use this application in a variety of substantially any suitable detailed structures.
[0063] This specification may use the phrases “in one embodiment,” “in another embodiment,” “in yet another embodiment,” or “in other embodiments,” all of which may refer to one or more of the same or different embodiments according to this application.
[0064] The claims settlement method provided in this application embodiment can be applied to, for example, Figure 1 In this application environment, the client communicates with the server via a network. The server can query a preset mapping table based on the policyholder's wallet address to obtain the first health data and medical data corresponding to the policyholder. When the first health data and the medical data meet preset timeliness conditions, dynamic premium calculation is performed based on the first health data and the medical data to obtain the target premium. In response to the policyholder's claim application, the server obtains the policyholder's second health data and the policyholder's medical records on the blockchain in real time. When the second health data and the medical records meet preset claim trigger conditions, calculation is performed based on the target premium to obtain the compensation amount. The policyholder is then compensated based on the compensation amount. This intelligent life insurance claims method, based on blockchain and dynamic health data assessment, can save manpower and resources and improve claims efficiency.
[0065] This application provides a claims settlement method, such as... Figure 2 As shown, it includes:
[0066] Step S101: Based on the policyholder's wallet address, query the preset mapping table to obtain the first health data and medical data corresponding to the policyholder;
[0067] In the specific implementation of this step, the data types of the first health data include health data of different dimensions such as heart rate, blood pressure, blood oxygen, and sleep quality; the medical data includes medical record data stored on the blockchain of medical institutions, including patient basic information, clinical medical data, medical operation metadata, etc.; the patient basic information includes de-identified identity identifiers and basic statistical information; the de-identified identity identifiers include blockchain hash IDs and decentralized identity identifiers, etc.; the basic statistical information includes non-sensitive fields such as age and gender, as well as encrypted stored data such as blood type and allergy history; the clinical medical data includes medical record summaries, examination and test reports, prescriptions, and treatments, etc.; the medical operation metadata includes data such as responsible entity authentication and data permission marking, etc.; the responsible entity authentication includes data such as doctor digital signatures, medical institution digital signatures, and operation timestamps, etc.; the data permission marking includes data such as access control lists and patient authorization records, etc.
[0068] Step S102: When the first health data and the medical data meet the preset timeliness conditions, perform dynamic premium calculation based on the first health data and the medical data to obtain the target premium;
[0069] In the specific implementation process of this step, when the first health data and the medical data meet the preset timeliness conditions, the target risk index is obtained by calculating and processing the first health data and the medical data using risk assessment rules corresponding to different data dimensions; the target premium is obtained by calculating and processing the preset basic premium rate, the target risk index and the predetermined Laplace noise.
[0070] Step S103: Real-time monitoring to obtain the policyholder's second health data and the policyholder's medical records on the blockchain;
[0071] In the specific implementation process of this step, after the policyholder takes out insurance, the second health data of the policyholder and the medical records of the policyholder on the blockchain are monitored and obtained in real time. The second health data and the medical records of the policyholder on the blockchain can be obtained by querying a preset mapping table based on the policyholder's wallet address.
[0072] Step S104: When the second health data and the medical record meet the preset claim triggering conditions, the compensation amount is calculated based on the target premium.
[0073] In this step, when the heart rate parameter in the second health data exceeds a first preset threshold, a preset timer records the duration for which the heart rate parameter exceeds the first preset threshold. When the duration exceeds a preset duration threshold, a federated learning method is used to verify the second health data and the medical record. When the verification is successful, it is determined that the second health data and the medical record meet the preset claim triggering conditions. The compensation amount is calculated based on the target premium. Specifically, the compensation amount can be obtained by multiplying the target premium and a predetermined coefficient. The predetermined coefficient can be 80%, etc., and can be set according to actual needs.
[0074] Step S105: Provide compensation to the policyholder based on the compensation amount.
[0075] In the specific implementation of this step, when the second health data and the medical evidence meet the preset claim triggering conditions, a smart contract is used to call the Gnosis Safe contract to initiate a transfer request. At least two of the preset claim settlement parties (such as insurance companies, hospitals, and regulatory agencies) sign the request, and the funds are automatically transferred to the beneficiary's wallet. The insured is then compensated based on the compensation amount.
[0076] This application revolutionizes the entire life insurance underwriting and claims process through blockchain and dynamic health data assessment technology. Regarding data credibility, medical-grade wearable devices collect vital signs data in real time and encrypt it via hashing before uploading it to the blockchain. Combined with zero-knowledge proof technology, this improves the accuracy of detecting health data tampering and completely solves the assessment distortion problem caused by traditional underwriting relying on static medical examination reports. In terms of underwriting efficiency, smart contracts automatically retrieve continuous health data within a predetermined timeframe to generate dynamic premiums. Federated learning models integrate medical records from multiple institutions, improving underwriting automation and reducing decision-making delays. Intelligent analysis of medical images stored on the blockchain and cross-verified by multiple nodes shortens the time required for critical illness claims. The dynamic premium model allows users who meet health standards to save on premiums and increases user activity in health management services.
[0077] Another embodiment of this application provides an alternative claims settlement method, such as... Figure 3 As shown, it includes:
[0078] Step S201: Construct a preset mapping table;
[0079] In the specific implementation process of this step, a health data structure template is constructed: a data package named HealthData is created, containing four key pieces of information: average heart rate (heart rate per minute), blood pressure (systolic blood pressure value), sleep quality score (0-100 points, the higher the better), and update time (the time the data is uploaded); the health data structure template avgHeartRate is obtained; and the health data structure template is used to store the health data of the insured user in real time. A medical data structure template is constructed, and the construction method of the medical data structure template is the same as that of the health data structure template. The medical data includes key data information such as patient basic information, clinical medical data, and medical operation metadata, to construct the medical data structure template. A federated learning model is constructed: First, the parameters of the federated learning model are set. Specifically, an FLParams data package is created to store the model parameters of the federated learning model. The model parameters include the model version number (modelVersion), used to distinguish different algorithm versions; the data fingerprint (dataHash), a byte hash value, used to generate a unique identifier through a hash algorithm; and the validators list, i.e., the address list, used to store the server addresses participating in the computation, thus obtaining the federated learning model. A mapping relationship is constructed between the user's wallet address and the health data structure and the medical data structure to obtain the preset mapping table. The system acquires the insured's original health data in real time using certified medical devices; encrypts the original health data using a symmetric encryption method to obtain encrypted health data; performs hash calculation on the encrypted health data to obtain a first hash value; and stores the first hash value representing the original health data in the target area of the preset mapping table corresponding to the insured's wallet address in chronological order using a preset structure template; wherein the original health data includes heart rate, blood pressure, blood oxygen, and sleep quality.
[0080] Step S202: Query the preset mapping table based on the policyholder's wallet address to obtain the first health data and medical data corresponding to the policyholder;
[0081] In this step, the process involves querying the mapping relationships in a preset mapping table based on the policyholder's wallet address to obtain the target mapping relationship corresponding to the policyholder's wallet address. This yields the first health data and treatment data corresponding to the policyholder's wallet address. The first health data includes different dimensions of health data such as heart rate, blood pressure, blood oxygen, and sleep quality. The treatment data includes treatment records stored on the blockchain of medical institutions, including patient basic information, clinical treatment data, and medical operation metadata. The patient basic information includes desensitized identity identifiers and basic statistical information. The desensitized identity identifiers include blockchain hash IDs and decentralized identity identifiers. The basic statistical information includes non-sensitive fields such as age and gender, as well as encrypted data such as blood type and allergy history. The clinical treatment data includes medical record summaries, examination and test reports, prescriptions, and treatments. The medical operation metadata includes data such as responsible entity authentication and data permission marking. The responsible entity authentication includes data such as doctor digital signatures, medical institution digital signatures, and operation timestamps. The data permission marking includes access control lists and patient authorization records.
[0082] Step S203: Based on the heart rate parameters in the first health data, a first function is used to calculate and process the heart rate risk index;
[0083] In this step, when the first health data and the treatment data meet the preset timeliness conditions, a heart rate risk index is obtained by calculating the heart rate parameter in the first health data using a first function. The method for determining whether the first health data and the treatment data meet the preset timeliness conditions is as follows: Check whether the first health data and the treatment data are updated within a predetermined time period; the preset time period can be 24 hours. The data update time is obtained by subtracting the current time from the data update time. When the data update time is less than or equal to the preset time period, it is determined that the first health data and the treatment data meet the preset timeliness conditions. When the data update time is greater than the preset time period, it is determined that the first health data and the treatment data do not meet the preset timeliness conditions. The first function can be `_calcHeartRisk`; the calculation logic formula is: `risk Factor += _calcHeartRisk(data.avg Heart Rate)`. For example, when the heart rate is 75, the heart rate risk index calculated using the calculation logic formula is 8.
[0084] Step S204: Calculate and process the first risk index based on the preset initial value of the risk coefficient and the heart rate risk index;
[0085] In this step, the initial value of the preset risk coefficient is a pre-set starting point for the risk coefficient. This starting point can be set using `uint256riskFactor = 100`. A starting point of 100 represents a 100% baseline risk, meaning the baseline risk value for healthy individuals. Based on the initial value of the preset risk coefficient and the heart rate risk indicator, a first risk indicator is obtained. For example, if the heart rate risk indicator calculated using the formula is 8, then an addition operation is performed between the initial value of the preset risk coefficient and the heart rate risk indicator to obtain a first risk indicator of 108.
[0086] Step S205: Determine blood pressure risk indicators based on the blood pressure parameters in the first health data and each preset blood pressure danger zone;
[0087] In this step, the blood pressure parameters in the first health data are compared with each preset blood pressure threshold; the target blood pressure risk period of the blood pressure parameter is determined; for example: when the blood pressure value is greater than or equal to 130 and less than 140, the target blood pressure risk period of the blood pressure parameter is determined to be prehypertension; when the blood pressure value is greater than or equal to 140 and less than 150, the target blood pressure risk period of the blood pressure parameter is determined to be stage one hypertension, etc.; when the blood pressure parameter falls into the prehypertension stage, the blood pressure risk index is determined to be 15; when the blood pressure parameter falls into the prehypertension stage, the blood pressure risk index is determined to be 30.
[0088] Step S206: Calculate and process the second risk indicator based on the first risk indicator and the blood pressure risk indicator;
[0089] In this step, the second risk indicator is obtained by adding the first risk indicator and the blood pressure risk indicator. For example, when the blood pressure parameter falls into the prehypertension range and the blood pressure risk indicator is determined to be 15, the second risk indicator is 108 + 15 = 123; when the blood pressure parameter falls into the hypertension range and the blood pressure risk indicator is determined to be 30, the second risk indicator is 108 + 30 = 138.
[0090] Step S207: Based on the sleep quality parameters in the first health data, the second function is used to calculate and process the sleep quality risk parameters;
[0091] In this step, calculations are performed based on sleep quality parameters to obtain a discount rate. Specifically, the square of the sleep quality score is calculated to obtain an indirect parameter; the percentage of the indirect parameter is then calculated to obtain the discount rate. Based on the discount rate, a sleep quality risk parameter is obtained; the sleep quality risk parameter = (100 - discount rate) / 100.
[0092] Step S208: Calculate and process the target risk index based on the second risk index and the sleep quality risk parameter;
[0093] In the specific implementation process, this step involves multiplying the second risk indicator and the sleep quality risk parameter to obtain the target risk indicator.
[0094] Step S209: Calculate the target premium based on the preset base rate, the target risk indicator, and the predetermined Laplace noise.
[0095] In this step, an additive operation is performed based on the target risk indicator and the predetermined Laplace noise to obtain a comprehensive risk indicator. The predetermined Laplace noise is a Laplace distributed random number with a value greater than or equal to -5 and less than or equal to 5. The value of the Laplace noise can be set according to actual needs. Using Laplace noise prevents hackers from deducing real health data from insurance premiums, protecting user privacy. The mathematical formula for calculating the target premium is: Comprehensive Risk Indicator = Target Risk Indicator + Laplace Noise. The target premium is obtained by calculating based on the base rate and the comprehensive risk indicator. The mathematical formula for calculating the target premium is: Target Premium = (Base Rate × Comprehensive Risk Indicator) / 100.
[0096] Step S210: Real-time monitoring to obtain the policyholder's second health data and the policyholder's medical records on the blockchain;
[0097] In the specific implementation process of this step, after the policyholder takes out insurance, the second health data of the policyholder and the medical records of the policyholder on the blockchain are monitored and obtained in real time. The second health data and the medical records of the policyholder on the blockchain can be obtained by querying a preset mapping table based on the policyholder's wallet address.
[0098] Step S211: When the second health data and the medical record meet the preset claim triggering conditions, the compensation amount is calculated based on the target premium.
[0099] In this step, when the heart rate parameter in the second health data exceeds a first preset threshold, a preset timer records the duration for which the heart rate parameter exceeds the first preset threshold. When the duration exceeds a preset duration threshold, a federated learning method is used to verify the second health data and the medical record. When the verification is successful, it is determined that the second health data and the medical record meet the preset claim triggering conditions. The compensation amount is calculated based on the target premium. Specifically, the compensation amount can be obtained by multiplying the target premium and a predetermined coefficient. The predetermined coefficient can be 80%, etc., and can be set according to actual needs.
[0100] Step S212: Provide compensation to the policyholder based on the compensation amount.
[0101] In the specific implementation of this step, when the second health data and the medical evidence meet the preset claim triggering conditions, a smart contract is used to call the Gnosis Safe contract to initiate a transfer request. At least two of the preset claim settlement parties (such as insurance companies, hospitals, and regulatory agencies) sign the request, and the funds are automatically transferred to the beneficiary's wallet. The insured is then compensated based on the compensation amount.
[0102] This application revolutionizes the entire life insurance underwriting and claims process through blockchain and dynamic health data assessment technology. Regarding data credibility, medical-grade wearable devices collect vital signs data in real time and encrypt it via hashing before uploading it to the blockchain. Combined with zero-knowledge proof technology, this improves the accuracy of detecting health data tampering and completely solves the assessment distortion problem caused by traditional underwriting relying on static medical examination reports. In terms of underwriting efficiency, smart contracts automatically retrieve continuous health data within a predetermined timeframe to generate dynamic premiums. Federated learning models integrate medical records from multiple institutions, improving underwriting automation and reducing decision-making delays. Intelligent analysis of medical images stored on the blockchain and cross-verified by multiple nodes shortens the time required for critical illness claims. The dynamic premium model allows users who meet health standards to save on premiums and increases user activity in health management services.
[0103] Another embodiment of this application provides a claims processing device, such as... Figure 4 As shown, it includes:
[0104] Query module 1 is used to query a preset mapping table based on the policyholder's wallet address to obtain the first health data and medical data corresponding to the policyholder;
[0105] The dynamic premium calculation module 2 is used to perform dynamic premium calculation processing based on the first health data and the medical data when the first health data and the medical data meet the preset timeliness conditions, so as to obtain the target premium.
[0106] Module 3 is used to respond to the policyholder's claim application operation by acquiring the policyholder's second health data and the policyholder's medical records on the blockchain in real time.
[0107] The compensation calculation module 4 is used to calculate the compensation amount based on the target premium when the second health data and the medical evidence meet the preset claim triggering conditions.
[0108] Claims module 5 is used to process claims for the insured based on the compensation amount.
[0109] In specific implementation, the device further includes a data storage module, which is specifically used to acquire the original health data of the insured person collected by certified medical equipment in real time; encrypt the original health data using a symmetric encryption method to obtain encrypted health data; perform hash calculation on the encrypted health data to obtain a first hash value; and store the first hash value representing the original health data in the target area of the preset mapping table corresponding to the wallet address of the insured person in chronological order using a preset structure template; wherein, the original health data includes heart rate, blood pressure, blood oxygen, and sleep quality.
[0110] In the specific implementation process, the dynamic premium calculation module 2 is specifically used to: when the first health data and the medical data meet the preset timeliness conditions, calculate and process the target risk index based on the risk assessment rules corresponding to different data dimensions of the first health data and the medical data; and calculate and process the target premium based on the preset basic premium rate, the target risk index and the predetermined Laplace noise.
[0111] In the specific implementation process, the dynamic premium calculation module 2 is further used to: calculate and process the heart rate parameter in the first health data using a first function to obtain a heart rate risk index; calculate and process the heart rate risk index based on a preset initial value of the risk coefficient to obtain a first risk index; determine a blood pressure risk index based on the blood pressure parameter in the first health data and each preset blood pressure danger interval; calculate and process the first risk index and the blood pressure risk index to obtain a second risk index; calculate and process the sleep quality parameter in the first health data using a second function to obtain a sleep quality risk parameter; and calculate and process the second risk index and the sleep quality risk parameter to obtain the target risk index.
[0112] In the specific implementation process, the dynamic premium calculation module 2 is also used to perform addition operations based on the target risk indicator and the predetermined Laplace noise to obtain a comprehensive risk indicator; and to perform calculations based on the base premium rate and the comprehensive risk indicator to obtain the target premium.
[0113] In the specific implementation process, the compensation calculation module 4 is specifically used for: when the heart rate parameter in the second health data is greater than the first preset threshold, using a preset timer to record the duration for which the heart rate parameter is greater than the first preset threshold; when the duration is greater than the preset duration threshold, using a federated learning method to verify the second health data and the medical evidence; when the verification is successful, determining that the second health data and the medical evidence meet the preset claim triggering conditions; and calculating the compensation amount based on the target premium.
[0114] In the specific implementation process, the compensation calculation module 4 is also used to: concatenate the second health data, the medical evidence, and the version number of the current federated learning model to obtain associated data; perform hash calculation on the associated data to obtain a second hash value; query the smart contract based on the current federated learning model to obtain a third hash value corresponding to the current federated learning model; when the second hash value is the same as the third hash value, determine that the second health data and the medical evidence meet the preset claim triggering conditions.
[0115] This application revolutionizes the entire life insurance underwriting and claims process through blockchain and dynamic health data assessment technology. Regarding data credibility, medical-grade wearable devices collect vital signs data in real time and encrypt it via hashing before uploading it to the blockchain. Combined with zero-knowledge proof technology, this improves the accuracy of detecting health data tampering and completely solves the assessment distortion problem caused by traditional underwriting relying on static medical examination reports. In terms of underwriting efficiency, smart contracts automatically retrieve continuous health data within a predetermined timeframe to generate dynamic premiums. Federated learning models integrate medical records from multiple institutions, improving underwriting automation and reducing decision-making delays. Intelligent analysis of medical images stored on the blockchain and cross-verified by multiple nodes shortens the time required for critical illness claims. The dynamic premium model allows users who meet health standards to save on premiums and increases user activity in health management services.
[0116] Another embodiment of this application provides a storage medium storing a computer program, which, when executed by a processor, implements the following method steps:
[0117] Step 1: Based on the policyholder's wallet address, query the preset mapping table to obtain the first health data and medical data corresponding to the policyholder;
[0118] Step 2: When the first health data and the medical data meet the preset timeliness conditions, perform dynamic premium calculation based on the first health data and the medical data to obtain the target premium;
[0119] Step 3: Real-time monitoring to obtain the policyholder's second health data and the policyholder's medical records on the blockchain;
[0120] Step 4: When the second health data and the medical record meet the preset claim trigger conditions, the compensation amount is calculated based on the target premium.
[0121] Step 5: Settle the claim with the insured based on the compensation amount.
[0122] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0123] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.
[0124] For details on the implementation of the above methods and steps, please refer to the embodiments of the above claims methods. This embodiment will not be repeated here.
[0125] This application revolutionizes the entire life insurance underwriting and claims process through blockchain and dynamic health data assessment technology. Regarding data credibility, medical-grade wearable devices collect vital signs data in real time and encrypt it via hashing before uploading it to the blockchain. Combined with zero-knowledge proof technology, this improves the accuracy of detecting health data tampering and completely solves the assessment distortion problem caused by traditional underwriting relying on static medical examination reports. In terms of underwriting efficiency, smart contracts automatically retrieve continuous health data within a predetermined timeframe to generate dynamic premiums. Federated learning models integrate medical records from multiple institutions, improving underwriting automation and reducing decision-making delays. Intelligent analysis of medical images stored on the blockchain and cross-verified by multiple nodes shortens the time required for critical illness claims. The dynamic premium model allows users who meet health standards to save on premiums and increases user activity in health management services.
[0126] Another embodiment of this application provides a computer device, which may be a server, and its internal structure is shown in the figure below. Figure 5 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external clients via a network connection. When the computer device program is executed by the processor, it implements the functions or steps of a claims processing server.
[0127] In one embodiment, a computer device is provided, which may be a client. Its internal structure is illustrated below. Figure 6 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with an external server via a network connection. When the computer program is executed by the processor, it implements the functions or steps of a claims processing method on the client side.
[0128] Another embodiment of this application provides a computer device, including at least a memory and a processor. The memory stores a computer program, and the processor, when executing the computer program in the memory, performs the following method steps:
[0129] Step 1: Based on the policyholder's wallet address, query the preset mapping table to obtain the first health data and medical data corresponding to the policyholder;
[0130] Step 2: When the first health data and the medical data meet the preset timeliness conditions, perform dynamic premium calculation based on the first health data and the medical data to obtain the target premium;
[0131] Step 3: Real-time monitoring to obtain the policyholder's second health data and the policyholder's medical records on the blockchain;
[0132] Step 4: When the second health data and the medical record meet the preset claim trigger conditions, the compensation amount is calculated based on the target premium.
[0133] Step 5: Settle the claim with the insured based on the compensation amount.
[0134] For details on the implementation of the above methods and steps, please refer to the embodiments of the above claims methods. This embodiment will not be repeated here.
[0135] This application revolutionizes the entire life insurance underwriting and claims process through blockchain and dynamic health data assessment technology. Regarding data credibility, medical-grade wearable devices collect vital signs data in real time and encrypt it via hashing before uploading it to the blockchain. Combined with zero-knowledge proof technology, this improves the accuracy of detecting health data tampering and completely solves the assessment distortion problem caused by traditional underwriting relying on static medical examination reports. In terms of underwriting efficiency, smart contracts automatically retrieve continuous health data within a predetermined timeframe to generate dynamic premiums. Federated learning models integrate medical records from multiple institutions, improving underwriting automation and reducing decision-making delays. Intelligent analysis of medical images stored on the blockchain and cross-verified by multiple nodes shortens the time required for critical illness claims. The dynamic premium model allows users who meet health standards to save on premiums and increases user activity in health management services.
[0136] The above embodiments are merely exemplary embodiments of this application and are not intended to limit this application. The scope of protection of this application is defined by the claims. Those skilled in the art can make various modifications or equivalent substitutions to this application within its substance and scope of protection, and such modifications or equivalent substitutions should also be considered to fall within the scope of protection of this application.
Claims
1. A claims settlement method, characterized in that, include: Based on the policyholder's wallet address, a preset mapping table is queried to obtain the first health data and medical data corresponding to the policyholder; When the first health data and the medical data meet the preset timeliness conditions, dynamic premium calculation is performed based on the first health data and the medical data to obtain the target premium. Real-time monitoring and acquisition of the policyholder's second health data and the policyholder's medical records on the blockchain; When the second health data and the medical record meet the preset claim triggering conditions, the compensation amount is calculated based on the target premium. The insured will receive compensation based on the stated amount.
2. The method as described in claim 1, characterized in that, Before collecting the insured's initial health data and the insured's medical treatment data on the blockchain, the method further includes: Real-time acquisition of the insured's original health data collected using certified medical devices; The original health data is encrypted using a symmetric encryption method to obtain encrypted health data; The encrypted health data is hashed to obtain a first hash value; The first hash value representing the original health data is stored in the target area of the preset mapping table corresponding to the wallet address of the policyholder in chronological order using a preset structure template. The raw health data includes heart rate, blood pressure, blood oxygen, and sleep quality.
3. The method as described in claim 1, characterized in that, When the first health data and the medical data meet the preset timeliness conditions, dynamic premium calculation is performed based on the first health data and the medical data to obtain the target premium, specifically including: When the first health data and the treatment data meet the preset timeliness conditions, the target risk index is obtained by calculating and processing based on the first health data and the treatment data using risk assessment rules corresponding to different data dimensions. The target premium is obtained by calculation based on the preset base rate, the target risk indicator, and the predetermined Laplace noise.
4. The method as described in claim 3, characterized in that, The target risk indicator is calculated and processed based on the first health data and the medical data using risk assessment rules corresponding to different data dimensions, specifically including: Based on the heart rate parameters in the first health data, a first function is used to calculate and process the heart rate risk index. The first risk index is obtained by calculating and processing the preset initial value of the risk coefficient and the heart rate risk index. Blood pressure risk indicators are determined based on the blood pressure parameters in the first health data and each preset blood pressure danger zone. A second risk indicator is obtained by calculating and processing based on the first risk indicator and the blood pressure risk indicator. Based on the sleep quality parameters in the first health data, a second function is used to calculate and process the sleep quality risk parameters. The target risk index is obtained by calculation based on the second risk index and the sleep quality risk parameter.
5. The method as described in claim 3, characterized in that, The calculation process based on the preset base premium rate, the target risk indicator, and the predetermined Laplace noise to obtain the target premium specifically includes: A comprehensive risk index is obtained by performing an addition operation based on the target risk index and the predetermined Laplace noise. The target premium is obtained by calculating based on the base premium rate and the comprehensive risk index.
6. The method as described in claim 1, characterized in that, When the second health data and the medical record meet the preset claim trigger conditions, the compensation amount is calculated based on the target premium, specifically including: When the heart rate parameter in the second health data is greater than the first preset threshold, a preset timer is used to record the duration for which the heart rate parameter is greater than the first preset threshold; When the duration exceeds a preset duration threshold, a federated learning method is used to verify the second health data and the medical record. When the verification is successful, it is determined that the second health data and the medical record meet the preset claim triggering conditions; The compensation amount is obtained by calculating based on the target premium.
7. The method as described in claim 1, characterized in that, The verification of the second health data and the medical evidence using a federated learning method specifically includes: The associated data is obtained by concatenating the second health data, the medical evidence, and the version number of the current federated learning model. The associated data is subjected to hash calculation to obtain a second hash value; Based on the current federated learning model, query the smart contract to obtain the third hash value corresponding to the current federated learning model; When the second hash value is the same as the third hash value, it is determined that the second health data and the medical evidence meet the preset claim triggering conditions.
8. A claims processing device, characterized in that, include: The query module is used to query a preset mapping table based on the policyholder's wallet address to obtain the first health data and medical data corresponding to the policyholder; The dynamic premium calculation module is used to perform dynamic premium calculation processing based on the first health data and the medical data when the first health data and the medical data meet the preset timeliness conditions, so as to obtain the target premium. The acquisition module is used to respond to the policyholder's claim application operation by acquiring the policyholder's second health data and the policyholder's medical records on the blockchain in real time. The compensation calculation module is used to calculate the compensation amount based on the target premium when the second health data and the medical evidence meet the preset claim triggering conditions. The claims module is used to process claims for the insured based on the compensation amount.
9. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of the claims settlement method according to any one of claims 1-7.
10. A computer device, characterized in that, It includes at least a memory and a processor, wherein the memory stores a computer program, and the processor, when executing the computer program in the memory, implements the steps of the claims method according to any one of claims 1-7.