A smart city medical insurance data evaluation method and system based on the Internet of Things

Abstract

The embodiments of this specification provide a smart city medical insurance data assessment method and system based on the Internet of Things, which is executed by a medical management platform, including: obtaining a user's risk query request through a user platform based on a service platform, and the risk query request is used to conduct a risk assessment on the insurance risk of the assessment object; obtaining the associated persons of the assessment object based on a population information platform; obtaining the medical characteristics and insurance characteristics of the assessment object and the associated persons based on a medical information platform; determining target medical characteristics and target insurance characteristics based on the medical characteristics and insurance characteristics of the assessment object and the associated persons; determining an assessment value of the insurance risk based on the target medical characteristics and target insurance characteristics; and feeding back the assessment value to the user through a user platform based on the service platform.

Description

Technical Field

[0001] This specification relates to the field of smart cities, and in particular to a smart city medical insurance data evaluation method and system based on the Internet of Things. Background Art

[0002] Nowadays, there are more and more insurance companies and commercial insurance types, and different insurance companies have different ways of reviewing different types of insurance. In order to control risks, insurance companies need to review the insurance application information of insured customers before insurance is taken out.

[0003] Therefore, it is hoped to provide a smart city medical insurance data evaluation method and system based on the Internet of Things, which can accurately and effectively review insured customers. Summary of the invention

[0004] One of the embodiments of the present specification provides a smart city medical insurance data assessment method based on the Internet of Things, which is executed by a medical management platform, including: obtaining a user's risk query request based on a service platform and a user platform, the risk query request is used to conduct a risk assessment on the insurance risk of the assessment object; obtaining the associated persons of the assessment object based on a population information platform; obtaining the medical characteristics and insurance characteristics of the assessment object and the associated persons based on a medical information platform; determining target medical characteristics and target insurance characteristics based on the medical characteristics and insurance characteristics of the assessment object and the associated persons; determining an assessment value of the insurance risk based on the target medical characteristics and the target insurance characteristics; and feeding back the assessment value to the user through the user platform based on the service platform.

[0005] One of the embodiments of the present specification provides a smart city medical insurance data assessment system based on the Internet of Things, including a service platform and a medical management platform, wherein the medical management platform is configured to perform the following operations: obtain a user's risk query request based on a user platform through the service platform, wherein the risk query request is used to conduct a risk assessment on the insurance risk of the assessment object; obtain the associated persons of the assessment object based on a population information platform; obtain the medical characteristics and insurance characteristics of the assessment object and the associated persons based on a medical information platform; determine target medical characteristics and target insurance characteristics based on the medical characteristics and insurance characteristics of the assessment object and the associated persons; determine an assessment value of the insurance risk based on the target medical characteristics and target insurance characteristics; and feed back the assessment value to the user based on the user platform through the service platform.

[0006] One of the embodiments of this specification provides a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the above-mentioned smart city medical insurance data evaluation method based on the Internet of Things. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0008] Figure 1 It is a schematic diagram of an application scenario of a smart city medical insurance data evaluation system based on the Internet of Things according to some embodiments of this specification;

[0009] Figure 2 is an exemplary module diagram of a smart city medical insurance data evaluation system based on the Internet of Things according to some embodiments of this specification;

[0010] Figure 3 is an exemplary flow chart of a smart city medical insurance data evaluation method based on the Internet of Things shown in some embodiments of this specification;

[0011] Figure 4 is an exemplary schematic diagram of obtaining target medical features according to some embodiments of this specification;

[0012] Figure 5 is an exemplary schematic diagram of obtaining target insurance characteristics according to some embodiments of this specification;

[0013] Figure 6 An exemplary flow chart of determining an assessment value of an insurance risk based on collaborative features according to some embodiments of this specification;

[0014] Figure 7 It is an exemplary schematic diagram of determining the assessment value of insurance risk according to some embodiments of this specification.

[0015] Among them, 100, application scenario; 110, processor; 120, network; 130, memory; 140, terminal; 150, cloud platform; 200, smart city medical insurance data evaluation system based on the Internet of Things; 210, user platform; 220, service platform; 230, medical management platform; 410, medical knowledge graph; 420, evaluation object; 430, first associated person; 440, second associated person; 430-1, first medical feature; 440-1, second medical feature; 420-1, first medical feature; 420-2, second medical feature; 450, weighted first medical feature; 460, weighted second medical feature; 47 0. Target medical characteristics; 510. Medical knowledge graph; 530. First associated person; 540. Second associated person; 530-1. First insurance characteristics; 540-1. Second medical characteristics; 520. Evaluation object; 520-1. First insurance characteristics; 520-2. Second insurance characteristics; 550. Weighted first insurance characteristics; 560. Weighted second insurance characteristics; 570. Target insurance characteristics; 720. Security calculation model; 710-1. Target medical characteristics; 710-2. Target insurance characteristics; 730-1. Target medical characteristic vector; 730-2. Characteristic vector; 740. Risk assessment model; 750. Assessment value of insurance risk. DETAILED DESCRIPTION

[0016] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0017] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0018] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0019] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0020] Figure 1 It is a schematic diagram of an application scenario of a smart city medical insurance data evaluation system based on the Internet of Things according to some embodiments of this specification.

[0021] like Figure 1 As shown, the application scenario 100 of the smart city medical insurance data evaluation system based on the Internet of Things may include a processor 110, a network 120, a memory 130, a terminal 140, and an off-network cloud platform 150. In some embodiments, the components in the application scenario 100 may be connected and / or communicated with each other via the network 120 (e.g., wireless connection, wired connection, or a combination thereof). For example, the processor 110 may be connected to the memory 130 via the network 120.

[0022] The smart city medical insurance data assessment system based on the Internet of Things can determine the assessment value of the insurance risk of the assessment object by implementing the methods and / or processes disclosed in this specification. Specifically, when the assessment object is willing to participate in the insurance, the insurance company can request the smart city medical insurance data assessment system based on the Internet of Things to determine the assessment value of the insurance risk of the assessment object based on the medical characteristics and insurance characteristics of the assessment object and its associated persons, so that the insurance company can perform subsequent processing based on the assessment value. For example, when the assessment value of the insurance risk of the assessment object is high, the insurance company may increase the premium or even refuse the assessment object to participate in the insurance.

[0023] The processor 110 may process data and / or information related to the smart city medical insurance data evaluation system based on the Internet of Things. In some embodiments, the processor 110 accesses information and / or data from the off-network cloud platform 150, the memory 130, and / or the terminal 140. For example, the processor 110 may obtain the medical characteristics, insurance characteristics, and collaborative characteristics of the evaluation object and the associated person from the off-network cloud platform 150 and / or from the memory 130. In some embodiments, the processor 110 may process the information and / or data obtained from the off-network cloud platform 150 and / or the memory 130. For example, the processor 110 may process the medical characteristics and insurance characteristics of the evaluation object and the associated person obtained from the off-network cloud platform 150 to determine the evaluation value of the insurance risk of the evaluation object. In some embodiments, the processor 110 may include one or more processing engines (e.g., a single-chip processing engine or a multi-chip processing engine). By way of example only, the processor 110 may include a central processing unit (CPU). The processor 110 may process data, information and / or processing results obtained from other devices or system components, and execute program instructions based on the data, information and / or processing results to perform one or more functions described in this specification.

[0024] The network 120 may include any suitable network that provides information and / or data exchange between various components in the application scenario 100 of the smart city medical insurance data evaluation system based on the Internet of Things. One or more components (e.g., the processor 110, the memory 130, the terminal 140, and the off-network cloud platform 150) in the application scenario 100 of the smart city medical insurance data evaluation system based on the Internet of Things can exchange information and / or data through the network 120. For example, the network 120 can send the medical characteristics, insurance characteristics, and collaborative characteristics of the evaluation object and the associated person obtained from the off-network cloud platform 150 to the processor 110. In some embodiments, the network 120 can be any one or more of a wired network or a wireless network. In some embodiments, the network 120 may include one or more network access points. For example, the network 120 may include a wired or wireless network access point. In some embodiments, the network may be a point-to-point, shared, centralized, or other topological structure or a combination of multiple topological structures.

[0025] The memory 130 may be used to store data, instructions and / or any other information. In some embodiments, the memory 130 may store data and / or information obtained from, for example, the processor 110, the off-network cloud platform 150, etc. For example, the memory 130 may store the medical characteristics, insurance characteristics and collaborative characteristics of the evaluation object and the associated person, as well as the medical knowledge graph, etc. In some embodiments, the memory 130 may be set in the processor 110. In some embodiments, the memory 130 may include a large-capacity memory, a removable memory, etc., or any combination thereof.

[0026] The terminal 140 may refer to one or more terminal devices or software used by a user. In some embodiments, the terminal 140 may be a mobile device, a tablet computer, a laptop computer, etc. or any combination thereof. In some embodiments, the terminal 140 may interact with other components in the application scenario 100 of the smart city medical insurance data evaluation system based on the Internet of Things through the network 120. In some embodiments, the terminal 140 may be a terminal device or software used by an insurance personnel.

[0027] The off-network cloud platform 150 may be a cloud computing platform for data storage and processing that is communicatively connected to the smart city medical insurance data evaluation system based on the Internet of Things. In some embodiments, the off-network cloud platform 150 may include a population information platform, a medical information platform, a collaborative platform, etc. The population information platform may refer to a cloud platform or an external database that records resident-related information (such as resident identity information, address information, etc.). In some embodiments, the processor 110 may determine the associated person of the evaluation object based on the population information platform. The medical information platform may refer to a cloud platform or an external database that records the relevant medical information of the residents (such as the residents' disease records, treatment records, etc.).

[0028] In some embodiments, the processor 110 can obtain the medical characteristics and insurance characteristics of the assessment object and the associated person through the medical information platform. The collaborative platform may refer to one or more cloud platforms or external databases that record the collaborative information related to residents. In some embodiments, the processor 110 can obtain the collaborative characteristics of the assessment object and the associated person through the collaborative platform. In some embodiments, the network cloud platform 150 can communicate and exchange data with the processor 110 memory 130 and the terminal 140 through the network 120. For example, the network cloud platform 150 can send the acquired medical characteristics and insurance characteristics of the assessment object and the associated person to the processor 110 for processing.

[0029] It should be noted that the application scenario 100 of the smart city medical insurance data evaluation system based on the Internet of Things is provided only for illustrative purposes and is not intended to limit the scope of this specification. For those of ordinary skill in the art, various modifications or changes can be made according to the description of this specification. For example, the application scenario may also include a database. For another example, the application scenario 100 may be implemented on other devices to achieve similar or different functions. However, changes and modifications will not deviate from the scope of this specification.

[0030] The Internet of Things system is an information processing system that includes some or all of the management platform, service platform, and user platform. The management platform can realize the overall planning and coordination of the connection and collaboration between the functional platforms. The management platform gathers the information of the Internet of Things operation system and can provide perception management and control management functions for the Internet of Things operation system. The service platform refers to a platform that can provide input and output services to users. The management platform can realize the overall planning and coordination of the connection and collaboration between the functional platforms, gathers the information of the Internet of Things operation system, and can provide perception management and control management functions for the Internet of Things operation system. The user platform is a functional platform that generates perception information and executes control information.

[0031] The information processing in the IoT system can be divided into the processing flow of perception information and the processing flow of control information. Control information can be information generated based on perception information. Among them, the processing of perception information is that the user platform obtains the perception information and transmits it to the management platform. The control information is sent from the management platform to the user platform to achieve control over the corresponding users.

[0032] In some embodiments, when the Internet of Things system is applied to city management, it can be called a smart city Internet of Things system.

[0033] Figure 2 1 is an exemplary schematic diagram of a smart city medical insurance data evaluation system based on the Internet of Things according to some embodiments of this specification. Figure 2 As shown, the smart city medical insurance data evaluation system 200 based on the Internet of Things includes a user platform 210, a service platform 220, and a medical management platform 230. In some embodiments, the smart city medical insurance data evaluation system 200 based on the Internet of Things can be a part of the processor 110 or implemented by the processor 110.

[0034] The user platform 210 may be a platform for interacting with a user. In some embodiments, the user platform may be configured as a terminal device, for example, the terminal device may include a mobile device, a tablet computer, etc., or any combination thereof. In some embodiments, the user platform may be used to receive requests and / or instructions input by a user. For example, the user platform may obtain a user's risk query request through a terminal (e.g., terminal 140). In some embodiments, the user platform 210 may be connected in communication with (i.e., interact with) the service platform 220, send the input instructions to the medical management platform 230 via the service platform 220, and receive the data and / or information required by the user platform 210 extracted from the medical management platform 230 via the service platform 220.

[0035] The service platform 220 may be a platform for receiving and transmitting data and / or information. For example, the medical insurance service platform 220 may obtain a risk query request from the user platform 210. For another example, the service platform 220 may feed back the assessment value of the assessment object's insurance risk to the user through the user platform 210.

[0036] The medical management platform 230 may refer to a platform that coordinates and coordinates the connections and collaborations between various functional platforms, gathers all the information of the smart city medical insurance data assessment system 200 based on the Internet of Things, and provides perception management and control management functions for the operation system of the smart city medical insurance data assessment system 200 based on the Internet of Things. For example, the medical management platform 230 may obtain the user's risk query request based on the user platform 210 through the service platform 220, and the risk query request is used to conduct a risk assessment on the insurance risk of the assessment object; obtain the associated persons of the assessment object based on the population information platform; obtain the medical characteristics and insurance characteristics of the assessment object and the associated persons based on the medical information platform; determine the target medical characteristics and target insurance characteristics based on the medical characteristics and insurance characteristics of the assessment object and the associated persons; determine the assessment value of the insurance risk based on the target medical characteristics and target insurance characteristics; and feed back the assessment value to the user based on the user platform 210 through the service platform 220. The medical management platform 230 may include Figure 1 In some embodiments, the medical management platform 230 may be a remote platform controlled by a manager, artificial intelligence, or preset rules.

[0037] In some embodiments, the medical management platform 230 can also communicate with the off-network cloud platform 150 (e.g., population information platform, medical information platform, collaborative platform, etc.) to obtain data and / or information. For more information about the population information platform, medical information platform, and collaborative platform, please refer to Figure 3-5 Related instructions.

[0038] In some embodiments, the smart city medical insurance data evaluation system 200 based on the Internet of Things can be applied to various scenarios of medical insurance data evaluation. For example, scenarios of new user insurance, scenarios of old user renewal, etc. In some embodiments, the smart city medical insurance data evaluation system 200 based on the Internet of Things can obtain the medical characteristics and insurance characteristics of the evaluation object and its associated persons in various scenarios, respectively, to obtain the evaluation value of the insurance risk of the evaluation object, and further determine the insurance strategy of the evaluation object.

[0039] The various scenarios of the smart city medical insurance data evaluation system 200 based on the Internet of Things may include new user insurance scenarios, old user renewal scenarios, etc. It should be noted that the above scenarios are only examples and do not limit the specific application scenarios of the smart city medical insurance data evaluation system 200 based on the Internet of Things. Those skilled in the art can apply the smart city medical insurance data evaluation system 200 based on the Internet of Things to any other suitable scenarios based on the content disclosed in this embodiment.

[0040] For example, in the scenario of new user insurance, relevant personnel of the insurance company can evaluate the insurance risk of the new user (i.e., the subject of evaluation) and determine the insurance strategy of the new user based on the evaluation value. In the process of evaluating the insurance risk of the new user, the new user's associated persons can be obtained, and the medical characteristics and insurance characteristics of the new user and its associated persons can be determined based on the medical data (age, number of illnesses, treatment costs, etc.) and insurance data (for example, historical insurance data) of the new user and its associated persons, and the evaluation value of the insurance risk of the subject of evaluation (i.e., the new user) can be determined based on the medical characteristics and insurance characteristics. The evaluation value of the insurance risk can be used to determine the risk of the insurance company paying compensation due to an accident after the subject of evaluation participates in the insurance. If the compensation risk is high, the insurance company may increase the premium or reject the new user's insurance request.

[0041] For example, in the scenario of renewal of old users, relevant personnel of the insurance company can evaluate the renewal risk of the old users (i.e., the evaluation object) and determine the renewal strategy of the old users based on the evaluation value. In the process of evaluating the renewal risk of old users, relevant data of the old users' historical insurance participation in the insurance company can be obtained, and further medical data and insurance data of the old users and their related persons during the historical insurance period can be obtained to determine the evaluation value of the renewal risk of the old users.

[0042] In some embodiments, the smart city medical insurance data evaluation system 200 based on the Internet of Things can be composed of multiple medical insurance data evaluation subsystems, and each subsystem can be applied to a scenario. The smart city medical insurance data evaluation system 200 based on the Internet of Things can comprehensively manage and process the data acquired and output by each subsystem, and then obtain relevant policies or instructions for assisting the medical insurance data evaluation. For example, the smart city medical insurance data evaluation system 200 based on the Internet of Things may include subsystems applied to the insurance scenarios of new users and subsystems applied to the renewal of old users. The smart city medical insurance data evaluation system 200 based on the Internet of Things serves as the superior system of each subsystem.

[0043] For those skilled in the art, after understanding the principle of the system, it is possible to transfer the system to any other suitable scenario without deviating from the principle.

[0044] In some embodiments, the medical management platform 230 can be configured to: obtain the user's risk query request based on the user platform through the service platform, and the risk query request is used to perform a risk assessment on the insurance risk of the assessment object; obtain the associated persons of the assessment object based on the population information platform; obtain the medical characteristics and insurance characteristics of the assessment object and the associated persons based on the medical information platform; determine the target medical characteristics and target insurance characteristics based on the medical characteristics and insurance characteristics of the assessment object and the associated persons; determine the assessment value of the insurance risk based on the target medical characteristics and target insurance characteristics; and feed back the assessment value to the user based on the user platform through the service platform.

[0045] In some embodiments, the medical management platform 230 may be configured to further perform the following operations: obtain a medical knowledge graph based on the medical platform; obtain medical characteristics and insurance characteristics of the evaluation object and associated persons based on the medical knowledge graph. For more details about the medical knowledge graph, the medical characteristics and insurance characteristics of the evaluation object and associated persons, please refer to Figure 3 and Figure 4 and its related description.

[0046] In some embodiments, the medical management platform 230 may be configured to further perform the following operations: obtaining collaborative features of the evaluation object and the associated person based on the collaborative platform; determining the assessment value of the insurance risk based on the target medical features, the target insurance features, and the collaborative features. For more details on the collaborative features of the evaluation object and the associated person, see Figure 5 and its related description.

[0047] In some embodiments, the medical management platform 230 may be configured to further perform the following operations: based on the risk assessment model, the target medical characteristics and the target insurance characteristics are processed to determine the assessment value of the insurance risk. For more details on the assessment value of the insurance risk, please refer to Figure 6 and its related description.

[0048] It should be noted that the above description of the system and its components is only for convenience of description and does not limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the various components, or form a subsystem connected to other components without deviating from this principle. For example, the various components can share a storage device, or each component can have its own storage device. Such variations are all within the scope of protection of this specification.

[0049] Figure 3 This is an exemplary flow chart of a smart city medical insurance data evaluation method based on the Internet of Things according to some embodiments of this specification. Figure 3As shown, the process 300 includes the following steps: In some embodiments, the process 300 may be executed by the medical management platform 230 .

[0050] Step 310, based on the service platform, the user's risk query request is obtained through the user platform, and the risk query request is used to conduct a risk assessment on the insurance risk of the assessment object.

[0051] In some embodiments, users may include relevant operating personnel of the insurance company, relevant personnel who have been insured or are going to be insured, etc.

[0052] The assessment object may refer to a person whose insurance risk needs to be assessed. For example, when user A intends to purchase major disease insurance, the insurance risk of user A can be assessed, and user A is the assessment object.

[0053] The insurance risk may be the risk that may lead to insurance claims after the subject of the assessment participates in the insurance. In some embodiments, the insurance risk may be the risk that the subject of the assessment is unable to pay subsequent premiums due to poor economic conditions.

[0054] The risk query request may be an operation instruction for conducting a risk assessment on the insurance risk of the assessment object. In some embodiments, the risk query request may include the assessment object and the type of insurance that the assessment object has insured or intends to insure. For example, the risk query request may be a risk assessment of the major disease insurance insured by the assessment object A. The assessment object in the risk query request may be identified by identification information. For example, the risk query request may include the identity document (ID), name, etc. of the assessment object.

[0055] In some embodiments, the user platform 210 can generate a risk query request based on the identification information and insurance type of the assessment object input by the user on the user platform. In some embodiments, the medical management platform 230 can obtain the risk query request input by the user platform 210 via the service platform 220. For example, relevant operators in an insurance company can input a risk query request on the user platform 210. After receiving the risk query request, the user platform 210 sends the risk query request to the service platform 220. The service platform 220 can parse the risk query request and send it to the medical management platform 230, so that the medical management platform 230 executes the smart city medical insurance data assessment method based on the Internet of Things provided in this specification according to the risk query request. For more information about the user platform 210, the service platform 220 and the medical management platform 230, please refer to Figure 2 and its related description.

[0056] Step 320: Acquire the associated persons of the evaluation object based on the population information platform.

[0057] The population information platform may refer to a cloud platform or an external database that records information related to residents (such as resident identity information, address information, etc.). For example, the population information platform may include a household registration database of the public security system.

[0058] In some embodiments, the medical management platform 230 may communicate with the population information platform and obtain the associated persons of the assessment subject in response to the risk query request.

[0059] An associated person may refer to a person who has an associated relationship with the subject of evaluation. In some embodiments, an associated person may be a person who has a family relationship with the subject of evaluation. For example, an associated person may be the wife or husband, parents, siblings, etc. of the subject of evaluation. In some embodiments, an associated person may also be a person who has a certain relationship with the address, disease record, treatment record, or insurance record of the subject of evaluation. For example, an associated person may be a person who has the same type of insurance as the subject of evaluation. For another example, an associated person may be a person who has the same residential address as the subject of evaluation.

[0060] In some embodiments, the medical management platform 230 can query the population information platform to find people who have a family relationship with the evaluation object or have a certain relationship with the evaluation object in terms of address, disease record, treatment record or insurance record, and identify these people as associated persons of the evaluation object.

[0061] In some embodiments, the medical management platform 230 can call the relevant information of the evaluation object from the population information platform according to the identification information of the evaluation object, and determine the associated person according to the relevant information of the evaluation object. For example, the person with the same residential address as the evaluation object can be used as the associated person of the evaluation object according to the residential address of the evaluation object. In some embodiments, in order to ensure the privacy security of the evaluation object and the associated person, the evaluation object and the associated person fed back by the population information platform can be represented by identification information that does not expose private information (such as resident ID).

[0062] Step 330, obtaining the medical characteristics and insurance characteristics of the assessment subject and related persons based on the medical information platform.

[0063] The medical information platform may refer to a cloud platform or an external database that records the relevant medical information of residents. In some embodiments, the medical information platform may include information such as residents' disease records, treatment records, insurance records (including the types of insurance purchased by commercial medical insurance, claims, etc.).

[0064] Medical characteristics may be characteristics that describe the health status of an object (i.e., the evaluation object and the associated person). In some embodiments, the medical characteristics may include the number of treatments for a disease, the cost of treatment, etc. In some embodiments, the medical characteristics may include a first medical characteristic and a second medical characteristic. The first medical characteristic may be a medical characteristic related to a genetic disease (such as asthma, congenital heart disease, etc.), and the second medical characteristic may be a medical characteristic related to a disease caused by an unhealthy lifestyle (such as hypertension, diabetes, etc.). In some embodiments, medical characteristics may also include medical characteristics related to common diseases (such as colds, fevers, etc.). For more information about the first medical characteristic and the second medical characteristic, see Figure 4 and its related description.

[0065] The insurance characteristics may be characteristics describing the types of insurance and claims of the medical insurance purchased by the subject (such as the assessment subject and the associated person). In some embodiments, the insurance characteristics may include the type of insurance purchased by the subject, the number of insurance purchases, the total insurance premium, the number of claims, and the total amount of claims.

[0066] In some embodiments, the medical management platform 230 may send a data call request to the medical information platform to obtain the medical characteristics and insurance characteristics of the evaluation object and the associated person. The data call request may include the identification information of the object (such as the identity ID of the object), the type of data called (such as medical characteristics or insurance characteristics), etc. In some embodiments, the medical information platform may parse the corresponding data call request, determine the identity ID of the evaluation object and the associated person, and call the corresponding data according to the identity ID and send it to the medical management platform 230.

[0067] In some embodiments, when the medical management platform 230 obtains the medical characteristics and insurance characteristics of the evaluation object and related persons based on the medical information platform, it can obtain the medical knowledge graph based on the medical information platform, and obtain the medical characteristics and insurance characteristics of the evaluation object and related persons based on the medical knowledge graph.

[0068] The medical knowledge graph may refer to a semantic network constructed based on residents' medical data and insurance data, and the medical knowledge graph may include node data and edge data.

[0069] Node data may include resident nodes and institution nodes, where a resident node corresponds to a resident, and the node attributes corresponding to the resident node may include the resident's age information, address information, etc.; an institution node corresponds to an institution, and the institution node may include a medical institution node and an insurance institution node, and the node attributes corresponding to the institution node may include the institution's name, address information, etc.

[0070] Edge data includes edge types and edge attributes. The edge types between resident nodes may include edges indicating the existence of one-generation direct family relationships (hereinafter referred to as first-type edges) and edges indicating the same address (hereinafter referred to as second-type edges). The edge types between resident nodes and institution nodes may include edges indicating the existence of an insurance relationship with a corresponding insurance institution (hereinafter referred to as third-type edges) and edges indicating a treatment relationship with a corresponding medical institution (hereinafter referred to as fourth-type edges).

[0071] The first type of edge is used to indicate that there is a first-generation direct kinship relationship between the residents corresponding to the resident nodes, and the first-generation direct kinship relationship may include a father-son relationship, a mother-daughter relationship, etc. Based on the attributes of the first type of edge, it can be determined what the first-generation direct kinship relationship is between the two connected nodes.

[0072] The second type of edge is used to indicate that the residents' addresses corresponding to the resident nodes are the same. For example, there is a second type of edge between the resident nodes corresponding to the residents living in the Lotus Community. Based on the attributes of the second type of edge, the specific address information of the two connected nodes can be determined.

[0073] The third type of edge is used to indicate that there is an insurance relationship between the resident and the insurance institution, which is used to reflect that the resident has bought insurance from the insurance institution. In some embodiments, the edge attributes of the third type of edge may include the number of times the resident has been insured, the total insurance premium, the number of claims, and the total amount of claims. In some embodiments, the edge attributes of the third type of edge can be represented by a vector, for example, the edge attributes of the third type of edge can be (a, b, c, d), where a represents the number of insurances, b represents the total insurance premium, c represents the number of claims, and d represents the total amount of claims.

[0074] The fourth type of edge is used to indicate that there is a treatment relationship between a resident and a medical institution, and is used to reflect that the resident has been treated in the medical institution. In some embodiments, the edge attributes of the fourth type of edge may include a treatment frequency vector, a treatment cost vector, and the like. In some embodiments, the treatment frequency vector and the treatment cost vector may be three-dimensional vectors, and their three dimensions are respectively related to the first medical feature, the second medical feature, and the third medical feature. For example, there is an edge between resident a and medical institution b, and the treatment frequency vector is (0,0,5) and the treatment cost vector is (0,0,500), indicating that resident a has been treated for common diseases 5 times in medical institution b at a cost of 500 yuan.

[0075] In some embodiments, the medical management platform 230 can search for the corresponding resident node from the medical knowledge graph according to the identification information of the evaluation object and the associated person, and determine the nodes and edges associated with the resident node, and determine the medical characteristics and insurance characteristics of the evaluation object and the associated person according to the node attributes and edge attributes. In some embodiments, the insurance characteristics of the evaluation object can be determined according to the edge attributes of the third type of edge between the resident node corresponding to the evaluation object and the medical institution node. For example, the edge attribute of the third type of edge can be (2,6000,1,20000), and the corresponding insurance characteristics are: the number of insurances is 2 times, the total insurance premium is 6,000 yuan, the number of claims is 1 time, and the total claim amount is 20,000 yuan.

[0076] In some embodiments, the medical characteristics of the evaluation object can be determined based on the edge attributes of the fourth type of edge between the resident node and the medical institution node corresponding to the evaluation object. The edge attributes of the fourth type of edge may include a treatment frequency vector, a treatment cost vector, and the like. In some embodiments, the treatment frequency vector and the treatment cost vector may be three-dimensional vectors, whose three dimensions are respectively related to the first medical characteristic, the second medical characteristic, and the third medical characteristic. For example, the edge attributes of the fourth type of edge are a treatment frequency vector (0,0,5) and a treatment cost vector (0,0,500), indicating that the medical characteristics of the corresponding resident are that the common disease has been treated 5 times in the corresponding medical institution, and the cost is 500 yuan. In some embodiments, the treatment frequency vector and the treatment cost vector included in the edge attributes of the fourth type of edge can be determined as the medical characteristics of the evaluation object.

[0077] In some embodiments, the associated person of the evaluation object can be determined based on the first type of edge and the second type of edge connected to the resident node corresponding to the evaluation object, and then the insurance characteristics and medical characteristics of the associated person can be determined based on the third type of edge and the fourth type of edge connected to the resident node corresponding to the associated person. Similarly, the insurance characteristics and medical characteristics of the associated person are determined in the same way as the insurance characteristics and medical characteristics of the evaluation object.

[0078] In some embodiments, considering that the medical characteristics and insurance characteristics may involve the private information of the subject, the medical information platform may encrypt the medical characteristics and insurance characteristics of the assessment subject and the associated person before sending them to the medical management platform 230 through a secure computing model to generate a medical characteristic vector and an insurance characteristic vector that do not expose the private information of the subject. For more information about the secure computing model, see Figure 7 and its related description.

[0079] Step 340, determining target medical characteristics and target insurance characteristics based on the medical characteristics and insurance characteristics of the assessment subject and the associated persons.

[0080] The target medical feature may reflect the influence of the associated person on the medical feature of the subject to be evaluated. In some embodiments, the target medical feature may be a weighted result of the medical feature of the subject to be evaluated and the medical feature of the associated person. Similarly, the target insurance feature may reflect the influence of the associated person on the insurance feature of the subject to be evaluated. In some embodiments, the target insurance feature may be a weighted result of the insurance feature of the subject to be evaluated and the insurance feature of the associated person.

[0081] In some embodiments, the medical management platform 230 can weight the medical characteristics of the evaluation subject and the medical characteristics of the associated persons to determine the target medical characteristics; and weight the insurance characteristics of the evaluation subject and the insurance characteristics of the associated persons to determine the target insurance characteristics.

[0082] In some embodiments, the medical management platform 230 may assign different weights to the medical characteristics of the evaluation object and the medical characteristics of the associated person and perform weighted processing to determine the target medical characteristics. For example, the weight of the medical characteristics of the evaluation object may be set to 0.8, the weight of the medical characteristics of associated person a may be set to 0.08, the weight of the medical characteristics of associated person b may be set to 0.1, and the weight of the medical characteristics of associated person c may be set to 0.02 to determine the target medical characteristics. Similarly, different weights may be assigned to the insurance characteristics of the evaluation object and the insurance characteristics of the associated person and perform weighted processing to determine the target insurance characteristics.

[0083] In some embodiments, the medical management platform 230 may assign different weights to the first medical characteristic of the evaluation object and the first medical characteristic of the associated person, and then perform weighted processing to determine the weighted first medical characteristic; assign different weights to the second medical characteristic of the evaluation object and the second medical characteristic of the associated person, and then perform weighted processing to determine the weighted second medical characteristic, and finally determine the target medical characteristic based on the weighted first medical characteristic and the weighted second medical characteristic. Exemplarily, the number of treatments and the cost in the first medical characteristic of the associated person may be weighted to the first medical characteristic of the evaluation object; the number of treatments and the cost in the second medical characteristic of the second associated person may be weighted to the second medical characteristic of the evaluation object, thereby obtaining the target medical characteristic of the evaluation object. For more information about the weighted first medical characteristic and the weighted second medical characteristic, see Figure 4 and its related description.

[0084] In some embodiments, the weight may be related to the degree of proximity between the resident node corresponding to the associated person and the resident node corresponding to the evaluation object. The smaller the degree of proximity, the higher the weight. The degree of proximity is related to the number of edges involved in the shortest path between two nodes. A degree of proximity of 1 means that the shortest path between two nodes is one edge. For more information about proximity, see Figure 4 and its related description.

[0085] In some embodiments, the weights of the evaluation object and the associated person can reflect the influence of the associated person on the evaluation object. For example, the larger the neighbor degree value of the relative, the greater the difference between the relative's gene and the associated person's gene, and the relative's weight is lower. When a relative with a smaller neighbor degree value suffers from a gene-related disease, the probability that the evaluation object suffers from the gene-related disease is lower. In some embodiments, the weight of the evaluation object can be greater than the weight of the associated person. In some embodiments, the weight can also be preset in advance. For example, when the neighbor degree is 1, the weight is set to 0.3, and when the neighbor degree is 2, the weight is set to 0.2.

[0086] In some embodiments, the medical management platform 230 can determine the first associated person and the second associated person based on the medical knowledge graph, and determine the first medical feature of the first associated person and the second medical feature of the second associated person; weight the first medical feature of the first associated person and the first medical feature of the evaluation object to obtain the weighted first medical feature; weight the second medical feature of the second associated person and the second medical feature of the evaluation object to obtain the weighted second medical feature; and finally determine the target medical feature based on the weighted first medical feature and the weighted second medical feature. For more information on determining the target medical feature, see Figure 4 and its related description.

[0087] In some embodiments, the medical management platform 230 can determine the first associated person and the second associated person based on the medical knowledge graph, and determine the insurance characteristics of the first associated person and the insurance characteristics of the second associated person; then perform weighted processing on the insurance characteristics of the first associated person, the insurance characteristics of the second associated person, and the insurance characteristics of the evaluation object to determine the target insurance characteristics. For more information on determining the target insurance characteristics, see Figure 5 and its related description.

[0088] Step 350, determining an assessment value of the insurance risk based on the target medical characteristics and the target insurance characteristics.

[0089] The assessment value can be used to indicate the size of the insurance risk. The higher the assessment value, the higher the insurance risk of the assessed object, and the higher the probability of making a claim for the assessed object. In some embodiments, the form of the assessment value can be determined according to actual needs. For example, the assessment value can be a percentage or a risk level (such as 1-3 risk levels, the higher the value, the higher the risk level).

[0090] In some embodiments, the medical management platform 230 can process the target medical features and the target insurance features based on the security calculation model to determine the target medical feature vector and the target insurance feature vector, and process the target medical feature vector and the target insurance feature vector based on the risk assessment model to determine the assessment value of the insurance risk. In some embodiments, the security calculation model and the risk assessment model can be obtained through joint training. For more information about the risk assessment model, please refer to Figure 7 and its related description.

[0091] Considering that the target medical characteristics and target insurance characteristics may involve the private information of the subject, the medical management platform 230 can encrypt the target medical characteristics and target insurance characteristics through the secure computing model before obtaining the target medical characteristics and target insurance characteristics of the evaluation subject and the associated person from the medical information platform, and generate a target medical characteristic vector and a target insurance characteristic vector that do not expose the private information of the subject. For more information about the secure computing model and risk assessment model, please refer to Figure 7 and its related description.

[0092] Step 360: Feedback the evaluation value to the user through the user platform based on the service platform.

[0093] In some embodiments, after the medical management platform 230 determines the evaluation value, the evaluation value can be sent to the user platform through the service platform, and the evaluation value can be fed back to the user through the user platform.

[0094] In some embodiments, the user can perform subsequent processing based on the obtained evaluation value. In some embodiments, the user can adjust the insurance premium of the evaluation object based on the evaluation value, or reject the insurance request of the evaluation object. For example, the premium of the insurance project with a higher evaluation value can be increased, or the evaluation object can be rejected from participating in the insurance project. In some embodiments, the user can arrange a more detailed examination for the evaluation object based on the evaluation value. For example, the insurance company can further arrange for the evaluation object to go to its designated medical institution for a physical examination, so as to obtain more detailed medical data.

[0095] Based on the smart city medical insurance data assessment method based on the Internet of Things provided in some embodiments of this specification, it is possible to provide users (such as insurance assessors) with an assessment value of the insurance risk of the assessment object while ensuring that the privacy information of the assessment object is not leaked, and then adjust the insurance strategy of the assessment object based on the assessment value of the insurance risk (for example, adjust the insurance cost of the assessment object, or reject the insurance request of the assessment object). At the same time, the insurance risk of the assessment object can be determined based on the relevant conditions of the associated persons of the assessment object (such as insurance conditions, illness conditions), so as to reasonably arrange the insurance price, items, etc. of the assessment object, thereby reducing the economic cost of medical insurance.

[0096] It should be noted that the above description of process 300 is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 300 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification. For example, the above steps 330 and 340 can be performed by the medical information platform or its related processing equipment.

[0097] Figure 4 is an exemplary schematic diagram of obtaining target medical features according to some embodiments of the present specification.

[0098] like Figure 4 As shown, the node data of the medical knowledge graph 410 may include resident node A, resident node B, resident node C, resident node D, medical institution node A, medical institution node B, insurance institution node C, etc.; the edge data of the medical knowledge graph 410 includes first-class edge a, first-class edge b, second-class edge a, fourth-class edge a, fourth-class edge b, fourth-class edge c, third-class edge d, etc. For more information about resident nodes, medical institution nodes, first-class edges, second-class edges, third-class edges, and fourth-class edges, see Figure 3 and its related description.

[0099] In some embodiments, a first associated person 430 and a second associated person 440 of the evaluation object 420 may be determined based on the medical knowledge graph 410 , and a first medical feature 430 - 1 of the first associated person 430 and a second medical feature 440 - 1 of the second associated person 440 may be determined.

[0100] The first associated person may be a person corresponding to a resident node with which there is a first-type edge between the resident node corresponding to the evaluation object, that is, the first associated person may be a person who has a direct family relationship with the evaluation object. Figure 4 As shown, there is a first type edge a between resident node A and resident node B. When the resident corresponding to resident node A is the evaluation object, the resident corresponding to resident node B is the first associated person of the evaluation object.

[0101] The second associated person may be a person corresponding to a resident node with which there is a second type of edge between the resident node corresponding to the evaluation object, that is, the second associated person may be a person with the same address as the evaluation object. Figure 4 As shown, there is a second type edge a between resident node A and resident node D. When the resident corresponding to resident node A is the evaluation object, the resident corresponding to resident node D is the second associated person of the evaluation object.

[0102] In some embodiments, the first associated person 430 of the evaluation object 420 can be determined according to a preset neighbor degree condition. The neighbor degree is related to the number of edges involved in the shortest path between two nodes. A neighbor degree of 0 indicates that there is no edge between the two nodes, a neighbor degree of 1 indicates that the shortest path between the two nodes is one edge, and a neighbor degree of 2 indicates that the shortest path between the two nodes is two edges. For example, resident node A is connected to resident node B through a first-class edge a, and resident node B is connected to resident node C through a first-class edge b, that is, there are two first-class edges between resident node A and resident node C. The preset neighbor degree condition can be a condition that the neighbor degree between two nodes needs to meet, such as a preset neighbor degree value not exceeding 2.

[0103] It is worth noting that in the embodiment of determining the first associated person, when the neighbor degree is greater than or equal to 2, the edges between the two nodes must be of the same type. For example, when the neighbor degree is 2, the two edges between the two nodes can both be first-type edges or second-type edges, but cannot be one first-type edge and one second-type edge.

[0104] In some embodiments, when the edge type is a first-class edge, the resident corresponding to the resident node whose neighbor degree between the resident node corresponding to the evaluation object satisfies the preset neighbor degree condition can be determined as the first associated person of the evaluation object. Exemplarily, the preset neighbor degree condition is a neighbor degree of 2. When the resident node corresponding to the evaluation object 420 in the medical knowledge graph 410 is resident node A, the residents corresponding to the resident nodes with one or two first-class edges between the resident node A and the resident node C with the first-class edge b between the resident node B and the resident node B can be determined as the first associated person 430.

[0105] In some embodiments, the resident corresponding to the resident node having a second type of edge between the resident node corresponding to the evaluation object can be determined as the second associated person of the evaluation object. Exemplarily, when the resident node corresponding to the evaluation object 420 in the medical knowledge graph 410 is resident node A, the resident corresponding to the resident node having a second type of edge between the resident node A and the evaluation object 420 can be determined as the second associated person 440, that is, the resident corresponding to the resident node D having a second type of edge a between the resident node A and the evaluation object can be determined as the second associated person 440.

[0106] In some embodiments, after determining the first associated person 430 and the second associated person 440 , the medical management platform 230 may determine the first medical feature 430 - 1 of the first associated person 430 and the second medical feature 440 - 1 of the second associated person 440 according to the edge attributes of the medical knowledge graph 410 .

[0107] In some embodiments, the first medical feature 430-1 of the first associated person 430 and the second medical feature 440-1 of the second associated person 440 can be determined respectively according to the edge attributes of the fourth type of edge between the resident node and the medical institution node corresponding to the first associated person 430 and the second associated person 440, respectively. For example, the relevant data of the gene-related disease in the medical features of the first associated person 430 can be determined as the first medical feature 430-1 of the first associated person 430. For another example, the relevant data of the disease caused by an unhealthy lifestyle in the medical features of the second associated person 440 can be determined as the second medical feature 440-1 of the second associated person 440. For more information about obtaining medical features, please refer to step 330 and its related description, which will not be repeated here.

[0108] In some embodiments, the first medical feature 420-1 and the second medical feature 420-2 of the evaluation object 420 can be directly determined based on the medical features of the evaluation object 420. For example, the data related to the gene-related diseases in the medical features of the evaluation object 420 can be determined as the first medical feature 420-1 of the evaluation object 420, and the data related to the diseases caused by unhealthy lifestyles in the medical features of the evaluation object 420 can be determined as the second medical feature 420-2 of the evaluation object 420. For more information about obtaining the medical features of the evaluation object, please refer to step 330 and its related description, which will not be repeated here.

[0109] In some embodiments, the medical management platform 230 can weight the first medical feature 430-1 of the first associated person 430 and the first medical feature 420-1 of the evaluation object 420 to obtain a weighted first medical feature 450; and weight the second medical feature 440-1 of the second associated person 440 and the second medical feature 420-2 of the evaluation object 420 to obtain a weighted second medical feature 460; finally, based on the weighted first medical feature 450 and the weighted second medical feature 460, determine the target medical feature 470.

[0110] Exemplarily, when the resident corresponding to resident node A is the evaluation object 420, the medical characteristics of the evaluation object 420 at the medical institution node B can be determined according to the edge attributes of the fourth type of edge c between the resident node A and the medical institution node B, that is, the treatment frequency vector and the treatment cost vector are (0,0,10) and (0,0,5000) respectively, and the corresponding weight of the evaluation object 420 is 0.5; according to the edge attributes of the fourth type of edge b between the resident node B and the medical institution B, the treatment frequency vector and the treatment cost vector of the corresponding first associated person 430 can be determined to be (1,0,0) and (10000,0,0) respectively, and the corresponding weight of the first associated person 430 corresponding to the resident node B is 0.2; according to the edge attributes of the fourth type of edge d between the resident node D and the medical institution B, the treatment frequency vector and the treatment cost vector of the corresponding second associated person 440 can be determined to be (0,2,0) and (0, 20000,0), the weight of the second associated person 440 corresponding to resident node D is 0.3, the treatment frequency vector and treatment cost vector between the second associated person 440 corresponding to resident node D and medical institution B are (0,0,10) and (0,0,5000) respectively, and the weight is 0.5. The weighted medical characteristics of the evaluation object can be determined, that is, the weighted treatment frequency vector and the weighted treatment cost vector are (0.2,0.6,5) and (2000,6000,2500) respectively, that is, the weighted first medical characteristic 450 can be determined to be (0.2,2000), where 0.2 represents the treatment frequency of the first medical characteristic and 2000 represents the treatment cost of the first medical characteristic; the weighted second medical characteristic 460 is (0.6,6000), where 0.6 represents the treatment frequency of the second medical characteristic and 6000 represents the treatment cost of the second medical characteristic.

[0111] The target medical characteristics determination method provided in some embodiments of the present specification can comprehensively consider the impact of family health status, family genetic diseases, and the lifestyle of co-residents on the insurance risk of the assessment object by obtaining the weighted results of the medical characteristics of the assessment object and the medical characteristics of related persons, and more accurately conduct risk assessment on the target object.

[0112] Figure 5 It is an exemplary schematic diagram of obtaining target insurance characteristics according to some embodiments of this specification.

[0113] like Figure 5As shown, the node data of the medical knowledge graph 510 may include resident node A, resident node B, resident node C, resident node D, medical institution node A, medical institution node B, insurance institution node C, etc.; the edge data of the medical knowledge graph 510 includes first-class edge a, first-class edge b, second-class edge a, third-class edge a, third-class edge b, third-class edge c, fourth-class edge d, etc. For more information about resident nodes, medical institution nodes, first-class edges, second-class edges, third-class edges, and fourth-class edges, see Figure 3 and its related description.

[0114] like Figure 5 As shown, there is a first type of edge a between resident node A and resident node B. When the resident corresponding to resident node A is the evaluation object, the resident corresponding to resident node B is the first associated person of the evaluation object. There is a second type of edge a between resident node A and resident node D. When the resident corresponding to resident node A is the evaluation object, the resident corresponding to resident node D is the second associated person of the evaluation object.

[0115] In some embodiments, when the edge type is a first-class edge, the resident corresponding to the resident node whose neighbor degree with the resident node corresponding to the evaluation object meets the preset neighbor degree condition can be determined as the first associated person of the evaluation object. In some embodiments, the resident corresponding to the resident node with a second-class edge between the resident node corresponding to the evaluation object can be determined as the second associated person of the evaluation object. For more information on determining the first associated person and the second associated person, see Figure 4 and its related description.

[0116] In some embodiments, after determining the first associated person 530 and the second associated person 540 , the medical management platform 230 may determine the insurance features 530 - 1 of the first associated person 530 and the insurance features 540 - 1 of the second associated person 540 according to the edge attributes of the medical knowledge graph 510 .

[0117] In some embodiments, the insurance characteristics 530-1 of the first associated person 530 and the insurance characteristics 540-1 of the second associated person 540 can be determined respectively according to the edge attributes of the third type of edge between the resident node and the insurance institution node corresponding to the first associated person 530 and the second associated person 540 respectively.

[0118] In some embodiments, the insurance characteristics 520-1 and the insurance characteristics 520-2 of the evaluation object 520 can be directly determined based on the insurance characteristics of the evaluation object 520. The insurance characteristics are determined in a similar manner to the first medical characteristics and the second medical characteristics. For more information, please refer to Figure 4 and its related description.

[0119] In some embodiments, the medical management platform 230 may perform weighted processing on the insurance characteristics 530-1 of the first associated person 530, the insurance characteristics 540-1 of the second associated person 540, and the insurance characteristics 520-1 of the evaluation object 520 to obtain the target insurance characteristics 550. The determination method of the target insurance characteristics 570 is similar to the determination method of the target medical characteristics 470. For more information, please refer to Figure 4 and its related description.

[0120] The target insurance characteristics determination method provided in some embodiments of this specification can comprehensively consider the historical commercial medical insurance purchased and claims situation by obtaining the weighted results of the insurance characteristics of the evaluation object and the insurance characteristics of the related persons, and more accurately conduct risk assessment on the target object.

[0121] Figure 6 According to an exemplary flow chart of determining the assessment value of insurance risk based on collaborative features in some embodiments of this specification. In some embodiments, process 600 can be executed by the medical management platform 230. Figure 6 As shown, process 600 may include the following steps.

[0122] Step 610: Acquire collaborative features of the evaluation object based on the collaborative platform.

[0123] The collaborative feature may refer to other feature data that can be used to determine the insurance risk assessment value of the assessment object. In some embodiments, the collaborative feature may include a financial collaborative feature that can reflect the asset status of the assessment object, a social assistance collaborative feature that reflects the assessment object's application for or enjoyment of social assistance, and a vehicle accident feature that reflects the assessment object's vehicle accident status.

[0124] The collaborative platform refers to one or more cloud platforms or external databases that record the collaborative information related to residents. In some embodiments, the collaborative platform may include a financial platform, a social assistance platform, a traffic management platform, etc., wherein the financial platform may refer to a cloud platform or an external database that records the financial information of residents (such as deposits, loans, credit card usage, etc.). For example, the financial platform may include the resident database of the central bank. The social assistance platform may refer to a cloud platform or an external database that records the social assistance information of residents (such as the application for relief funds, the application for relief materials, etc.). For example, the social assistance platform may include the relief distribution database of the civil affairs system. The traffic management platform may refer to a cloud platform or an external database that records the car insurance information of residents (such as vehicle insurance conditions, vehicle insurance accident conditions, etc.). For example, the traffic management platform may include the vehicle database of the vehicle management system.

[0125] In some embodiments, the medical management platform 230 can obtain collaborative features of the evaluation object and the associated person based on the collaborative platform. For example, the medical management platform 230 can retrieve the corresponding collaborative features from the collaborative platform based on the identification information (such as the identity ID) of the evaluation object. In some embodiments, considering that the collaborative features may involve the privacy information of the object, the collaborative platform can encrypt the collaborative information through the secure computing model before sending the collaborative features of the evaluation object and the associated person to the medical management platform 230 to generate collaborative features that do not expose the privacy information of the object. For more information about the secure computing model, please refer to Figure 7 and its related description.

[0126] In some embodiments, the medical management platform 230 may obtain the financial characteristics of the evaluation object and its associated persons based on the financial knowledge graph.

[0127] Financial characteristics may be characteristics that describe financial information of an object (such as an evaluation object and an associated person). In some embodiments, financial characteristics may include the total number of credit card overdue payments, the total amount of credit card overdue payments, etc. of the object.

[0128] The financial knowledge graph can refer to a semantic network built based on residents' financial information, including node data and edge data.

[0129] The node data of the financial knowledge graph may include resident nodes and financial institution nodes, where a resident node corresponds to a resident, and the node attributes corresponding to the resident node may include the resident's age information, address information, etc.; a financial institution node corresponds to a financial institution, and a financial institution may refer to an institution that provides financial services (such as a bank), and the node attributes corresponding to the financial institution node may include the address information of the financial institution, etc.

[0130] The edge data of the financial knowledge graph includes the type of edge and the attributes of the edge, among which the type of edge between resident nodes includes edges indicating that residents have the same address (i.e., second-type edges), and the type of edge between resident nodes and financial institution nodes includes edges that have financial business with the corresponding financial institution (hereinafter referred to as fifth-type edges). The fifth-type edge is used to indicate that the credit card that the resident has applied for at the corresponding financial institution is overdue. In some embodiments, the edge attributes of the fifth-type edge may include the number of credit card overdues, the total amount of credit card overdue, etc. In some embodiments, when obtaining financial features, the person corresponding to the resident node with the second-type edge between the resident node corresponding to the evaluation object can be regarded as an associated person.

[0131] In some embodiments, the financial knowledge graph can determine the financial characteristics of the evaluation object based on the edge attributes of the fifth type of edge. For example, the total number of credit card overdues and the total amount of credit card overdues of the evaluation object in various financial institutions can be calculated and superimposed to determine the total number of credit card overdues and the total amount of credit card overdues as the financial characteristics of the evaluation object. In some embodiments, the associated person of the evaluation object can be determined based on the resident node corresponding to the evaluation object, and then the financial characteristics of the associated person can be determined in a similar manner to the determination of the financial characteristics of the evaluation object.

[0132] In some embodiments, the financial knowledge graph can perform weighted processing on the financial characteristics of the evaluation object and the associated persons to obtain financial collaboration information. For example, the total number of overdue credit card payments and the total overdue amount of credit card payments of the evaluation object and the associated persons living with the evaluation object can be weighted to determine the financial collaboration information of the evaluation object (i.e., the weighted result of the total number of overdue credit card payments and the weighted result of the total overdue amount of credit card payments).

[0133] In some embodiments, before sending the financial collaboration information to the medical management platform 230, the financial platform may process the financial collaboration information based on the security computing model to determine the financial collaboration characteristics. It is understood that the financial collaboration information can be encrypted through the security computing model to generate a financial collaboration feature vector (referred to as financial collaboration feature) that does not expose the privacy information of the object. For more information about the security computing model, please refer to Figure 7 and its related description.

[0134] Based on the financial platform shown in some embodiments of this specification as a collaborative platform, the collaborative characteristics can reflect the comprehensive financial capabilities of the evaluation object, so that the premium payment ability of the evaluation object can be further considered when determining the assessment value of the insurance risk, thereby improving the accuracy of the assessment value of the insurance risk.

[0135] In some embodiments, the medical management platform 230 can determine the social assistance characteristics of the assessment object and its associated persons through the social assistance knowledge graph.

[0136] Social assistance characteristics may be characteristics that describe the social assistance information of an object (such as an assessment object and an associated person). In some embodiments, the social assistance characteristics may include the frequency or number of times the object receives free food, the total value of food received, the frequency or number of assistance applications, the total amount of assistance applications, etc.

[0137] The social assistance knowledge graph may refer to a semantic network constructed based on residents' social assistance information, including node data and edge data.

[0138] The node data of the social assistance knowledge graph may include resident nodes and assistance agency nodes. A resident node corresponds to a resident, and the node attributes corresponding to the resident node may include the age information, address information, etc. of the resident; an assistance agency node corresponds to an assistance agency, and the assistance agency may refer to an agency that provides social assistance services (such as a free food collection point), and the node attributes corresponding to the assistance agency node may include the address information of the assistance agency, etc.

[0139] The edge data of the social assistance knowledge graph includes the edge type and edge attributes. The edge types between resident nodes include edges indicating that residents have the same address (i.e., the second type of edges), and the edge types between resident nodes and social assistance agency nodes include edges indicating that free food has been received at a social assistance agency (hereinafter referred to as the sixth type of edges) and edges indicating that an application for assistance has been submitted to a social assistance agency (hereinafter referred to as the seventh type of edges).

[0140] The sixth type of edge is used to indicate that a resident has received free food from a social assistance agency. In some embodiments, the edge attributes of the sixth type of edge include the frequency (or number of times) of receiving free food, the total value of receiving, etc. For example, resident A has been to free food collection point B to receive free food, and has also been to free food collection point C to receive free food, then there is a sixth type of edge between A and B, and between A and C. In some embodiments, if there are multiple sixth type edges for a resident node, and the corresponding frequency of receiving free food exceeds a certain threshold, it can be said that the resident has received free food everywhere, and this feature can be used as a social assistance feature of the resident node.

[0141] The seventh type of edge is used to indicate that a resident has applied for assistance from a social assistance agency. In some embodiments, the edge attributes of the seventh type of edge may include the frequency (or number of times) of assistance applications, the total amount, and the like.

[0142] In some embodiments, when obtaining rescue features, a person corresponding to a resident node having a second type of edge with a resident node corresponding to the evaluation object may be regarded as an associated person.

[0143] In some embodiments, the social assistance knowledge graph can determine the social assistance characteristics of the evaluation object based on the edge attributes of the sixth type of edge connected to the resident node corresponding to the evaluation object and the edge attributes of the seventh type of edge. For example, the total frequency or total number of free food collection, the total value of food collection, the total frequency or total number of assistance applications, and the total amount of assistance applications of the evaluation object in various social assistance institutions can be superimposed and calculated to determine the social assistance characteristics of the evaluation object as the evaluation object. In some embodiments, the associated person of the evaluation object can be determined based on the resident node corresponding to the evaluation object, and then the social assistance characteristics of the associated person can be determined in a similar manner to the determination of the social assistance characteristics of the evaluation object.

[0144] In some embodiments, the social assistance knowledge graph can perform weighted processing on the social assistance characteristics of the evaluation object and the associated persons to obtain social assistance collaborative information. For example, the total frequency or total number of free food collection, the total value of food collection, the total frequency or total number of assistance applications, and the total amount of assistance applications of the evaluation object and the associated persons living with the evaluation object can be weighted to determine the social assistance collaborative information of the evaluation object (i.e., the weighted result of the frequency or number of free food collection, the weighted result of the value of food collection, the weighted result of the frequency or number of assistance applications, and the weighted result of the amount of assistance applications).

[0145] In some embodiments, before sending the social assistance collaborative information to the medical management platform 230, the social assistance platform may process the social assistance collaborative information based on the security computing model to determine the social assistance collaborative features. It is understood that by encrypting the social assistance collaborative information through the security computing model, a social assistance collaborative feature vector (referred to as the social assistance collaborative feature) that does not expose the privacy information of the object can be generated. For more information about the security computing model, please refer to Figure 7 and its related description.

[0146] Based on the social assistance platform shown in some embodiments of this specification as a collaborative platform, the collaborative features can reflect the social assistance situation of the assessment object. Therefore, when determining the assessment value of the insurance risk, the social assistance situation of the assessment object can be further considered, thereby improving the accuracy of determining the assessment value of its insurance risk.

[0147] In some embodiments, the medical management platform 230 may obtain the vehicle accident characteristics of the assessment subject through the traffic management platform.

[0148] Vehicle accident characteristics may be characteristics that describe vehicle accident information of an object (such as an evaluation object and an associated person). In some embodiments, vehicle accident characteristics may include the number of vehicle accidents of the evaluation object, the average repair amount, the average claim amount, etc.

[0149] In some embodiments, the traffic management platform can call up vehicle accident information based on the identification information (such as identity ID) of the evaluation object. In some embodiments, before sending the vehicle accident information to the medical management platform 230, the traffic management platform can process the vehicle accident information based on the security computing model to determine the vehicle accident characteristics. It can be understood that by encrypting the vehicle accident information through the security computing model, a vehicle accident feature vector (referred to as vehicle accident characteristics) that does not expose the privacy information of the object can be generated. For more information about the security computing model, please refer to Figure 7 and its related description.

[0150] Based on the vehicle management platform shown in some embodiments of this specification as a collaborative platform, and the vehicle accident characteristics as collaborative characteristics, the insurance and claims status of other types of insurance of the evaluation object can be further considered when determining the assessment value of the insured risk, thereby improving the accuracy of the assessment value of the insured risk.

[0151] Step 620, determining the assessment value of the insurance risk based on the target medical characteristics, target insurance characteristics and collaborative characteristics.

[0152] In some embodiments, the collaborative feature can be used as a determining factor in the assessment value of the insurance risk. For example, the insurance premium payment ability of the assessment object can be estimated based on the collaborative features such as financial features and social assistance features, and then the assessment value of the insurance risk can be adjusted. For another example, the claim probability of the assessment object after the accident can be estimated based on the vehicle accident, and then the assessment value of the insurance risk can be adjusted.

[0153] In some embodiments, the medical management platform 230 processes the target medical features, target insurance features, and collaborative features based on the risk assessment model to determine the assessment value of the insurance risk. For more information about the risk assessment model, please refer to Figure 7 and its related description.

[0154] Based on the collaborative features provided in the embodiments of this specification, relevant information of the evaluation object can be further reflected, thereby improving the accuracy of the evaluation value of the insurance risk.

[0155] Figure 7 It is an exemplary schematic diagram of determining the assessment value of insurance risk according to some embodiments of this specification.

[0156] In some embodiments, the medical management platform 230 may process the target medical feature 710-1 and the target insurance feature 710-2 through the secure computing model 720 to determine the target medical feature vector 730-1 and the target insurance feature vector 730-2. For more information about the target medical feature and the target insurance feature, see Figure 3-Figure 5 and its related description.

[0157] The security calculation model 720 can be used to extract the target medical feature vector 730-1 and the target bidding feature vector 730-2. In some embodiments, the security calculation model 720 can be a machine learning model. For example, a recurrent neural network (RNN). In some embodiments, the input of the security calculation model 720 can be the target medical feature 710-1 and the target insurance feature 710-2, and the output can be the target medical feature vector 730-1 and the target insurance feature vector 730-2.

[0158] It is worth noting that the target medical features 710-1 and the target insurance features 710-2 contain a large amount of privacy data of the evaluation object. Considering the data security issues of the medical information platform, after receiving the call request from the medical management platform, the medical information platform can perform multi-party secure computing processing on the target medical features 710-1 and the target insurance features 710-2 through the secure computing model 720. The processed target medical feature vector 730-1 and the target insurance feature vector 730-2 can reflect the target medical features of the evaluation object through encrypted data without involving the specific data of the evaluation object.

[0159] Multi-party secure computing can ensure that the information input by all parties involved in the calculation is not exposed without a trusted third party, and at the same time can obtain accurate calculation results. In some embodiments, the medical information platform, the collaborative platform, and the medical management platform can encrypt their respective data through multi-party secure computing. For example, the medical information platform can encrypt the target medical characteristics and target insurance characteristics through a secure computing model, and the collaborative platform can encrypt the financial collaborative information, social assistance collaborative information, and vehicle accident information through a secure computing model. Then, these encrypted data information are processed through a risk assessment model to calculate the assessment value of the insurance risk.

[0160] In some embodiments, the medical management platform 230 may process the target medical feature vector 730 - 1 and the target insurance feature vector 730 - 2 based on the risk assessment model 740 to determine an assessment value 750 of the insurance risk.

[0161] The risk assessment model 740 can be used to determine the assessment value of the insurance risk of the assessment object. In some embodiments, the risk assessment model 740 can be a machine learning model. For example, a deep neural network (DNN). In some embodiments, the input of the risk assessment model 740 can include a target medical feature vector 730-1 and a target insurance feature vector 730-2, and the output can be an assessment value 750 of the insurance risk.

[0162] In some embodiments, the input of the risk assessment model 740 may also include collaborative features, such as financial collaborative features, social assistance collaborative features, vehicle accident features, etc. For more information about collaborative features, see Figure 5 and its related description.

[0163] In some embodiments, the input of the risk assessment model 740 may be the output of the security calculation model 720, namely the target medical feature vector 730-1, the target bidding feature vector 730-2 and the collaborative feature, and the output may be the assessment value 750 of the insurance risk.

[0164] In some embodiments, the security computing model 720 can be jointly trained with the risk assessment model 740. For example, the training sample can be input into the security computing model, the output of the security computing model can be used as the input of the risk assessment model, and a loss function can be constructed based on the output of the risk assessment model, and the parameters of the security computing model and the risk assessment model can be iteratively updated based on the loss function at the same time until the preset conditions are met and the training is completed.

[0165] In some embodiments, the training sample may include the sample target medical features, sample target insurance features and sample collaborative features of the sample evaluation object. The training sample may be obtained based on historical evaluation data. The historical evaluation data may be historical data for evaluating the insurance risk of the sample evaluation object, and the label is the evaluation value of the insurance risk of the sample evaluation object. For example, user A before February 2, 2020 may be selected as the sample evaluation object, and the off-line cloud platform may obtain the historical target medical features, historical target insurance features and historical collaborative features of the user and its associated persons before February 2, 2020 and use them as training samples for the security calculation model, and determine the historical evaluation value of the user's insurance risk according to the user's claims settlement (such as the total claim amount, the number of claims, etc.) after February 2, 2020 (such as the higher the total claim amount, the higher the evaluation value), and use the historical evaluation value as the label corresponding to the training sample for model training. For another example, the historical evaluation value of user A may also be manually evaluated by the staff of the insurance institution based on factors such as user A's occupation and family income. For example, for ordinary employees of a company, their actual evaluation value may be a normal value (e.g., an evaluation value between 40-60 points is a normal value); for people with higher positions and living in more affluent areas (who are generally in better health), their actual evaluation value may be lower (e.g., an evaluation value between 0-40 points is lower); for people who clearly suffer from more serious illnesses or are engaged in special types of work (such as miners, who may be at risk of occupational diseases), their actual evaluation value may be higher (e.g., an evaluation value between 60-100 points is higher).

[0166] In some embodiments, when the security computing model 720 can be jointly trained with the risk assessment model 740, it can be carried out in a multi-platform collaborative training manner, that is, at least one platform in the network cloud platform 150 can be trained in collaboration with the medical management platform 230. For example, the medical information platform and the financial platform, as one of the multiple parties, can jointly train the security computing model 720 with the risk assessment model 740. When training, the medical information platform can first determine the sample evaluation object and the corresponding sample associated person, send the information of the sample evaluation object and the sample associated person to multiple platforms in the network cloud platform 150, so as to obtain the relevant sample feature data of the sample evaluation object and the sample associated person (for example, sample financial features, sample social assistance features, sample vehicle accident features, etc.), and input the relevant sample feature data into the security computing model 720, use the output of the security computing model 720 as the input of the risk assessment model 740, and construct a loss function based on the output of the risk assessment model 740, and iteratively update the parameters of the security computing model 720 and the risk assessment model 740 based on the loss function, until the preset conditions are met and the training is completed. After the training is completed, one or more platforms in the network cloud platform can obtain the corresponding security computing model 720, and the medical information platform can obtain the corresponding risk assessment model 740.

[0167] In some embodiments, the risk assessment model may not be jointly trained with the security computing model. For example, the risk assessment model may be trained based on the sample target medical feature vector and the sample target insurance feature vector acquired in advance. For another example, the risk assessment model may be trained based on a trained security computing model.

[0168] The method for determining the assessment value of insurance risk provided in the embodiments of this specification can accurately and quickly determine the assessment value of insurance risk by processing the target medical characteristics and target insurance characteristics through the risk assessment model. In some embodiments, the privacy of the assessment object can be well protected by adding a security calculation model and a risk assessment model to jointly determine the assessment value of insurance risk.

[0169] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0170] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0171] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0172] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0173] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0174] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0175] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A smart city medical insurance data evaluation method based on the Internet of Things, executed by a medical management platform, It is characterized in that The method comprises: Obtaining a risk query request from a user through a user platform based on the service platform, wherein the risk query request is used to conduct a risk assessment on the insurance risk of the assessment object; Obtaining the associated persons of the assessment object based on the population information platform; A medical knowledge graph is obtained based on a medical information platform. The medical knowledge graph is a semantic network constructed based on the medical data and insurance data of residents. The medical knowledge graph includes node data and edge data. The node data includes resident nodes and institution nodes. The resident node corresponds to one resident, and the node attributes corresponding to the resident node include the age information and address information of the resident. The institution node corresponds to an institution. The institution node includes a medical institution node and an insurance institution node. The node attributes corresponding to the institution node include the name and address information of the institution. The edge data includes the type of edge and the attribute of the edge. The type of the edge between the resident nodes includes an edge indicating the existence of a first-generation direct relative relationship and an edge indicating the same address. The type of the edge between the resident node and the institution node includes an edge indicating the existence of an insurance relationship with the corresponding insurance institution and an edge indicating the existence of a treatment relationship with the corresponding medical institution. Acquire the medical characteristics and insurance characteristics of the evaluation object and the associated person based on the medical knowledge graph; Determine target medical characteristics and target insurance characteristics based on the medical characteristics and insurance characteristics of the assessment subject and the associated person; Based on the secure computing model, multi-party secure computing is performed on the target medical feature and the target insurance feature to determine a target medical feature vector and a target insurance feature vector, wherein the multi-party secure computing is a computing that ensures that information input by all parties involved in the computing is not exposed without a trusted third party; Acquire collaborative features of the assessment object based on a collaborative platform, wherein the collaborative features refer to other feature data that can be used to determine the assessment value of the insurance risk of the assessment object, wherein the collaborative platform at least includes a financial platform, a social assistance platform and a traffic management platform, and the collaborative features at least include financial collaborative features, social assistance collaborative features and vehicle accident collaborative features; the financial collaborative features are obtained by processing financial collaborative information based on the security calculation model, and the financial collaborative information is obtained based on a financial knowledge graph, and the financial knowledge graph is constructed based on the financial information of the residents, and the node data of the financial knowledge graph includes the resident nodes and financial institution nodes, wherein the financial institution nodes correspond to a financial institution, and the node attributes corresponding to the financial institution nodes include the address information of the financial institution, and the edge data of the financial knowledge graph includes the type of edge and the attributes of the edge, wherein the type of edge between the resident nodes includes an edge indicating that the residents have the same address. , the type of edge between the resident node and the financial institution node includes an edge with a financial business corresponding to the financial institution; the social assistance collaboration feature is obtained by processing the social assistance collaboration information based on the security computing model, and the social assistance collaboration information is obtained based on the social assistance knowledge graph; the social assistance knowledge graph is constructed based on the social assistance information of the residents, and the node data of the social assistance knowledge graph includes the resident node and the assistance agency node, the assistance agency node corresponds to a assistance agency, and the node attributes corresponding to the assistance agency node include the address information of the assistance agency, and the edge data of the social assistance knowledge graph includes the type of edge and the attribute of the edge, wherein the type of edge between the resident nodes includes an edge indicating that the residents have the same address, and the type of edge between the resident node and the assistance agency node includes an edge indicating that free food has been received at the assistance agency and an edge indicating that an application for assistance has been submitted at the assistance agency; Processing the target medical feature vector, the target insurance feature vector, and the collaborative feature based on a risk assessment model to determine an assessment value of the insurance risk; and The evaluation value is fed back to the user through the user platform based on the service platform.

2. The method according to claim 1, It is characterized in that The determining of target medical characteristics and target insurance characteristics based on the medical characteristics and insurance characteristics of the assessment object and the associated person includes: performing weighted processing on the medical features of the evaluation object and the medical features of the associated person, assigning different weights to the medical features of the evaluation object and the medical features of the associated person, and determining the target medical features, wherein the weight is related to the neighbor degree between the resident node corresponding to the associated person and the resident node corresponding to the evaluation object, and the neighbor degree is related to the number of edges involved in the shortest path between two nodes; and The insurance characteristics of the assessment object and the insurance characteristics of the associated person are weighted to determine the target insurance characteristics.

3. The method according to claim 2, It is characterized in that The medical characteristics include at least a first medical characteristic and a second medical characteristic, The step of weighting the medical features of the evaluation object and the medical features of the associated person to determine the target medical features includes: Determine a first associated person and a second associated person based on the medical knowledge graph, and determine the first medical feature of the first associated person and the second medical feature of the second associated person; weighting the first medical feature of the first associated person and the first medical feature of the evaluation object to obtain a weighted first medical feature; weighting the second medical characteristic of the second associated person and the second medical characteristic of the evaluation object to obtain a weighted second medical characteristic; The target medical feature is determined based on the weighted first medical feature and the weighted second medical feature.

4. The method according to claim 3, It is characterized in that The step of weighting the insurance characteristics of the assessment object and the insurance characteristics of the associated person to determine the target insurance characteristics includes: Determine the insurance characteristics of the first associated person and the insurance characteristics of the second associated person based on the medical knowledge graph; The insurance characteristics of the first associated person, the insurance characteristics of the second associated person, and the insurance characteristics of the evaluation object are weighted to determine the target insurance characteristics.

5. The method according to claim 1, It is characterized in that The security calculation model and the risk assessment model are obtained through joint training.

6. A smart city medical insurance data evaluation system based on the Internet of Things, comprising a user platform, a service platform and a medical management platform, wherein the medical management platform is configured to perform the following operations: Obtaining a risk query request from a user based on a user platform through the service platform, wherein the risk query request is used to conduct a risk assessment on the insurance risk of the assessment object; Obtaining the associated persons of the assessment object based on the population information platform; Obtain a medical knowledge graph, wherein the medical knowledge graph is a semantic network constructed based on the medical data and insurance data of residents, and the medical knowledge graph includes node data and edge data, wherein the node data includes resident nodes and institution nodes, wherein the resident node corresponds to one of the residents, and the node attributes corresponding to the resident node include the age information and address information of the corresponding resident; the institution node corresponds to an institution, and the institution node includes a medical institution node and an insurance institution node, and the node attributes corresponding to the institution node include the name and address information of the corresponding institution; the edge data includes the type of edge and the attribute of the edge, wherein the type of the edge between the resident nodes includes an edge indicating the existence of a first-degree direct relative relationship and an edge indicating the same address, and the type of the edge between the resident node and the institution node includes an edge indicating the existence of an insurance relationship with the corresponding insurance institution and an edge indicating the existence of a treatment relationship with the corresponding medical institution; Based on the medical knowledge graph, the medical characteristics and insurance characteristics of the evaluation object and the associated person are obtained through the medical information platform; Determine target medical characteristics and target insurance characteristics based on the medical characteristics and insurance characteristics of the assessment subject and the associated person; Based on the secure computing model, multi-party secure computing is performed on the target medical feature and the target insurance feature to determine a target medical feature vector and a target insurance feature vector, wherein the multi-party secure computing is a computing that ensures that information input by all parties involved in the computing is not exposed without a trusted third party; Acquire collaborative features of the assessment object based on a collaborative platform, wherein the collaborative features refer to other feature data that can be used to determine the assessment value of the insurance risk of the assessment object, wherein the collaborative platform at least includes a financial platform, a social assistance platform and a traffic management platform, and the collaborative features at least include financial collaborative features, social assistance collaborative features and vehicle accident collaborative features; the financial collaborative features are obtained by processing financial collaborative information based on the security calculation model, and the financial collaborative information is obtained based on a financial knowledge graph, and the financial knowledge graph is constructed based on the financial information of the residents, and the node data of the financial knowledge graph includes the resident nodes and financial institution nodes, wherein the financial institution nodes correspond to a financial institution, and the node attributes corresponding to the financial institution nodes include the address information of the financial institution, and the edge data of the financial knowledge graph includes the type of edge and the attributes of the edge, wherein the type of edge between the resident nodes includes an edge indicating that the residents have the same address. , the type of edge between the resident node and the financial institution node includes an edge with a financial business corresponding to the financial institution; the social assistance collaboration feature is obtained by processing the social assistance collaboration information based on the security computing model, and the social assistance collaboration information is obtained based on the social assistance knowledge graph; the social assistance knowledge graph is constructed based on the social assistance information of the residents, and the node data of the social assistance knowledge graph includes the resident node and the assistance agency node, the assistance agency node corresponds to a assistance agency, and the node attributes corresponding to the assistance agency node include the address information of the assistance agency, and the edge data of the social assistance knowledge graph includes the type of edge and the attribute of the edge, wherein the type of edge between the resident nodes includes an edge indicating that the residents have the same address, and the type of edge between the resident node and the assistance agency node includes an edge indicating that free food has been received at the assistance agency and an edge indicating that an application for assistance has been submitted at the assistance agency; Processing the target medical feature vector, the target insurance feature vector, and the collaborative feature based on a risk assessment model to determine an assessment value of the insurance risk; and The evaluation value is fed back to the user through the service platform based on the user platform.

7. The system according to claim 6, It is characterized in that The medical management platform is configured to further perform the following operations: Performing weighted processing on the medical characteristics of the evaluation object and the medical characteristics of the associated person, assigning different weights to the medical characteristics of the evaluation object and the medical characteristics of the associated person, and determining the target medical characteristics, wherein the weight is related to the neighbor degree between the resident node corresponding to the associated person and the resident node corresponding to the evaluation object, and the neighbor degree is related to the number of edges involved in the shortest path between two nodes; as well as The insurance characteristics of the assessment object and the insurance characteristics of the associated person are weighted to determine the target insurance characteristics.

8. The system according to claim 7, It is characterized in that The medical characteristics include at least a first medical characteristic and a second medical characteristic, The medical management platform is configured to further perform the following operations: Determine a first associated person and a second associated person based on the medical knowledge graph, and determine the first medical feature of the first associated person and the second medical feature of the second associated person; weighting the first medical feature of the first associated person and the first medical feature of the evaluation object to obtain a weighted first medical feature; weighting the second medical characteristic of the second associated person and the second medical characteristic of the evaluation object to obtain a weighted second medical characteristic; The target medical feature is determined based on the weighted first medical feature and the weighted second medical feature.

9. The system according to claim 8, It is characterized in that The medical management platform is configured to further perform the following operations: Determine the insurance characteristics of the first associated person and the insurance characteristics of the second associated person based on the medical knowledge graph; The insurance characteristics of the first associated person, the insurance characteristics of the second associated person, and the insurance characteristics of the evaluation object are weighted to determine the target insurance characteristics.

10. The system according to claim 6, It is characterized in that The security calculation model and the risk assessment model are obtained through joint training.

11. A computer-readable storage medium, It is characterized in that The storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images