Underwriting method and device, computer equipment and storage medium

Abstract

The invention belongs to the field of artificial intelligence and financial science and technology, and relates to an underwriting method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining project demand data of an insured person; determining each underwriting link of the underwriting process according to the underwriting rule and the project demand data, and establishing a responsibility chain; determining the underwriting personnel corresponding to each underwriting link in the responsibility chain according to the historical underwriting records of the underwriting personnel; calculating a similarity value between the historical underwriting record of each underwriting person and the project demand data; screening a target underwriting person of each underwriting link based on the similarity value; and obtaining a risk assessment result obtained by performing risk assessment on the project demand data by the target underwriting personnel in each underwriting link. In addition, the invention also relates to a block chain technology, and data such as project demand data and historical underwriting records can be stored in a block chain. The method can be applied to underwriting scenes in the financial field, and personalized risk assessment can be carried out according to underwriting behaviors and project requirements.

Description

Technical Field

[0001] The present application relates to the fields of artificial intelligence and financial technology, and in particular to an underwriting method, apparatus, computer equipment and storage medium. Background Art

[0002] Risk control is an important and indispensable part of insurance companies. However, most traditional underwriting systems use fixed processes, lack flexibility, and cannot be adjusted in a timely manner according to specific circumstances. At the same time, traditional underwriting methods often face problems of inefficiency and unsatisfactory results. For example, although the current risk control strategy algorithm has made some attempts in multi-layer filtering and multiple recommendation rules, it still cannot accurately realize personalized risk assessment based on the behavior of underwriters and the needs of insurance projects, resulting in low satisfaction of policyholders. Summary of the invention

[0003] The purpose of the embodiments of the present application is to propose an underwriting method, apparatus, computer equipment and storage medium to achieve personalized risk assessment based on the behavior of underwriters and the requirements of insurance items.

[0004] In order to solve the above technical problems, the present application embodiment provides an underwriting method, which adopts the following technical solution:

[0005] Obtain project demand data of insured persons;

[0006] Obtaining preset underwriting rules, determining each underwriting link of the underwriting process according to the underwriting rules and the project demand data, and establishing a responsibility chain according to each underwriting link;

[0007] Obtaining historical underwriting records of underwriters, and determining the underwriters corresponding to each underwriting link in the chain of responsibility based on the historical underwriting records;

[0008] Calculate the similarity value between the historical underwriting records of the underwriting personnel corresponding to each underwriting link and the project demand data;

[0009] Target underwriters for each underwriting link are obtained by screening based on the similarity values;

[0010] Obtain the risk assessment results obtained by the target underwriter in performing risk assessment on the project demand data at each underwriting stage.

[0011] In order to solve the above technical problems, the embodiment of the present application further provides an underwriting device, which adopts the following technical solution:

[0012] Project acquisition module, used to obtain project demand data of insured persons;

[0013] A link determination module is used to obtain preset underwriting rules, determine each underwriting link of the underwriting process according to the underwriting rules and the project demand data, and establish a responsibility chain according to each underwriting link;

[0014] A personnel determination module is used to obtain the historical underwriting records of underwriters and determine the underwriters corresponding to each underwriting link in the responsibility chain according to the historical underwriting records;

[0015] A similarity calculation module, used to calculate the similarity value between the historical underwriting records of the underwriting personnel corresponding to each underwriting link and the project demand data;

[0016] A target screening module, used for screening and obtaining target underwriters for each underwriting link based on the similarity value;

[0017] The risk assessment module is used to obtain the risk assessment results obtained by the target underwriter in performing risk assessment on the project demand data in each underwriting link.

[0018] In order to solve the above technical problems, an embodiment of the present application also provides a computer device, which adopts the technical solution described below: the computer device includes a memory and a processor, the memory stores computer-readable instructions, and the processor implements the steps of the underwriting method described in any one of the above items when executing the computer-readable instructions.

[0019] In order to solve the above technical problems, an embodiment of the present application also provides a computer-readable storage medium, which adopts the following technical solution: the computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the underwriting method as described in any one of the above items are implemented.

[0020] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0021] The embodiment of the present application determines the underwriting process and its various underwriting links according to the project demand data and underwriting rules of the insured person, and can execute a personalized underwriting process for each insured project. In addition, by establishing a chain of responsibility model according to each underwriting link, the underwriting process is decomposed into multiple efficient and accurate underwriting links. By determining the underwriting personnel corresponding to each underwriting link in the chain of responsibility according to historical underwriting records, the historical underwriting records can be used to match appropriate underwriting personnel, which helps to improve the underwriting professionalism. By calculating the similarity value between the historical underwriting records of the underwriting personnel corresponding to each underwriting link and the project demand data, and screening the target underwriting personnel for each underwriting link based on the similarity value, the target underwriting personnel who are more matched with each underwriting link can be further screened, thereby improving the efficiency and underwriting quality of the entire underwriting process. By performing risk assessment on the project demand data according to each underwriting link in the chain of responsibility, the overall risk status of the insured project can be obtained more accurately and in detail. Based on this application plan, by fully considering the multi-dimensional characteristics of the insured items and the behavioral characteristics of the company's underwriters, personalized risk assessment is achieved based on the underwriter behavior and the needs of the insured items, which improves the matching degree and underwriting efficiency of the underwriters and improves the satisfaction of the insured. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0024] Figure 2 is a flowchart of an embodiment of an underwriting method according to the present application;

[0025] Figure 3 yes Figure 2 A flowchart of a specific implementation of step S202;

[0026] Figure 4 yes Figure 2 A flowchart of a specific implementation of step S203;

[0027] Figure 5 yes Figure 2 A flowchart of a specific implementation of step S204;

[0028] Figure 6is a schematic structural diagram of an embodiment of an underwriting device according to the present application;

[0029] Figure 7 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0030] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0031] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0032] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0033] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0034] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0035] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0036] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0037] It should be noted that the underwriting method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the underwriting device is generally set in the server / terminal device.

[0038] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0039] Continue to refer Figure 2 , shows a flow chart of an embodiment of the underwriting method according to the present application. The underwriting method comprises the following steps:

[0040] Step S201, obtaining the project demand data of the insured person;

[0041] In this embodiment, the electronic device on which the underwriting method is executed (eg Figure 1 The server / terminal device shown in the figure) can obtain the project demand data of the insured person through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 2G / 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other known or future developed wireless connection methods.

[0042] In this embodiment, the project demand data refers to information collected to accurately understand the insurance needs of the insured, develop appropriate insurance plans, and assess potential risks. The project demand data may include but is not limited to the insured's basic information, health information, insurance needs and preferences, risk assessment related information, payment and financial information, etc. These data are the basis for insurance companies to conduct risk assessment, product design, premium pricing, and customer service when the insured needs to purchase relevant insurance.

[0043] Specifically, the project demand data of the insured person is obtained, wherein the project demand data can be obtained, for example, by obtaining the basic information of the insured person, such as name, age, gender, occupation, etc., from the human resources management system (HRMS); collecting the insured person's health questionnaire, physical examination report, medical record and other data from the underwriting website; collecting the insured person's interests, hobbies, lifestyle, social preferences and other data from social media through legal and compliant methods (such as user authorization, public data capture, etc.).

[0044] Optionally, after obtaining the project demand data of the insured person, the project demand data may be preprocessed, for example, data cleaning, data conversion and data standardization may be performed on the obtained project demand data to ensure data consistency and accuracy.

[0045] Step S202, obtaining preset underwriting rules, determining various underwriting links of the underwriting process according to the underwriting rules and the project demand data, and establishing a responsibility chain according to the various underwriting links;

[0046] In this embodiment, the underwriting rules are formulated according to business requirements and risk strategies to guide the decision-making of each link in the underwriting process. The preset underwriting rules can be pre-stored in the database or knowledge base in the form of structured data (such as tables, database records) or unstructured data (such as documents, files). After obtaining the project demand data of the insured person, the pre-stored underwriting rules are obtained from the database or knowledge base.

[0047] Specifically, the various underwriting links in the underwriting process are determined based on the acquired underwriting rules and project demand data. For example, the project demand data can be matched with multiple preset underwriting rules to obtain underwriting rules that match the project demand data. For example, if the project demand data is the age of the insured person, the age restriction conditions defined in the underwriting rules are obtained based on the age match; the various underwriting links in the underwriting process are determined based on the matched underwriting rules. For example, the underwriting links can include but are not limited to resume screening, background investigation, information entry, risk assessment, decision processing, etc. Among them, each underwriting link can contain specific filtering rules or restriction conditions.

[0048] Specifically, the responsibility chain refers to connecting the various underwriting links in the underwriting process in a sequential relationship to form an orderly process chain. According to the determined underwriting links, the underwriting links are sorted in the order of the underwriting process to form a responsibility chain. Among them, each underwriting link in the responsibility chain will be assigned one or more underwriters, who are used to perform underwriting processing on the project demand data and other data assigned to the relevant underwriting link.

[0049] In some optional implementations, reference Figure 3 The above-mentioned determination of each underwriting link of the underwriting process according to the underwriting rules and the project demand data may include the following steps:

[0050] Step S2021, obtaining attribute information of the project demand data;

[0051] In this embodiment, data analysis is performed on the acquired project demand data to extract attribute information of the project demand data, wherein the attribute information may include but is not limited to age attributes, gender attributes, health status attributes, financial level attributes, risk item attributes, etc.

[0052] Step S2022, matching the attribute information with the underwriting rule to obtain a target underwriting rule;

[0053] In this embodiment, the extracted attribute information is matched with a plurality of preset underwriting rules, specifically, the attribute information is compared with the conditions defined in the underwriting rule to determine whether the attribute information matches the conditions, and the underwriting rule corresponding to the conditions is determined as the target underwriting rule according to the matching result. For example, if the attribute information is an age attribute, and the condition defined by the randomly traversed underwriting rule is an age restriction condition, and it is determined that the obtained age attribute matches the age restriction condition, the underwriting rule corresponding to the age restriction condition is determined as the target underwriting rule.

[0054] Step S2023, determine the underwriting process for the project demand data, and decompose the underwriting process into various underwriting links according to the target underwriting rules.

[0055] In this embodiment, based on the acquired project demand data, the underwriting process of the project demand data is determined. For example, if the project demand data includes information such as the age, health status and financial status of the insured person, the corresponding underwriting process is determined according to different types of project demand data, such as the age review process, health status review process and financial status review process. According to the matched target underwriting rules, the underwriting process is decomposed into various underwriting links. For example, when the project demand data is the age of the insured person and the target underwriting rule is the underwriting rule corresponding to the age restriction condition, the age review process is decomposed into the age entry link, the age risk assessment link, the age restriction matching link, etc. according to the target underwriting rule.

[0056] The embodiment of the present application compares the attribute information of the project demand data with the preset underwriting rules to screen out the underwriting rules applicable to the current insured project, thereby ensuring the accuracy of the underwriting work. By determining the corresponding underwriting process for different types of project demand data, the pertinence of the underwriting work is ensured, and by decomposing the underwriting process into multiple specific underwriting links, the underwriting process is made clearer and more efficient.

[0057] Step S203, obtaining the historical underwriting records of the underwriters, and determining the underwriters corresponding to each underwriting link in the chain of responsibility according to the historical underwriting records;

[0058] In this embodiment, the historical underwriting record refers to the record generated after the insurance application of the insured person is reviewed during the historical underwriting process. The historical underwriting record may include but is not limited to the basic information of the underwriter, the type of underwriting item, the underwriting result, the processing time, feedback information, etc.

[0059] Specifically, the historical underwriting records of all underwriting personnel are extracted from a specific database, the behavioral characteristics of each underwriting personnel are analyzed based on the historical underwriting records, and the underwriting personnel corresponding to each underwriting link in the chain of responsibility are determined based on the behavioral characteristics.

[0060] Optionally, a method for determining the underwriting personnel corresponding to each underwriting link in the chain of responsibility based on historical underwriting records may be, for example, to use a machine learning algorithm to perform behavioral characteristic analysis on historical underwriting records to obtain the behavioral characteristics of each underwriting personnel; based on the correlation between the behavioral characteristics and the underwriting links, determine the underwriting personnel corresponding to each underwriting link in the chain of responsibility.

[0061] In some optional implementations, reference Figure 4 The above-mentioned determination of the underwriting personnel corresponding to each underwriting link in the chain of responsibility according to the historical underwriting records may include the following steps:

[0062] Step S2031, obtaining the underwriting requirements of each underwriting link in the responsibility chain;

[0063] In this embodiment, for each underwriting link in the chain of responsibility, the underwriting requirements pre-defined for each underwriting link are obtained. The underwriting requirements may include but are not limited to professional knowledge requirements, experience level requirements, approval authority requirements, pass probability requirements, etc. of the underwriting personnel.

[0064] Step S2032, screening the historical underwriting records of each underwriting personnel according to the underwriting requirements of each underwriting link, and obtaining the target underwriting records corresponding to each underwriting link;

[0065] In this embodiment, according to the underwriting requirements of each underwriting link, the historical underwriting records of each underwriting personnel are screened to obtain the target underwriting records corresponding to each underwriting link. More specifically, the behavioral characteristics of each underwriting personnel, such as years of work experience, approval authority, underwriting link and pass probability, are extracted from the historical underwriting records of each underwriting personnel, and the extracted behavioral characteristics are matched with the underwriting requirements of each underwriting link, and the underwriting records corresponding to the matching behavioral characteristics are determined as the target underwriting records corresponding to the underwriting link. For example, for the preliminary review link, the underwriting records of underwriters who have preliminary review authority and a high preliminary review pass rate in the historical underwriting records are screened according to the underwriting requirements of the preliminary review link to serve as the target underwriting records corresponding to the preliminary review link.

[0066] Step S2033, determining the underwriting personnel corresponding to each underwriting link according to the target underwriting record.

[0067] In this embodiment, after selecting the corresponding target underwriting records for each underwriting link in the responsibility chain, the underwriting personnel corresponding to each target underwriting record are determined. The underwriting personnel are the executors responsible for the underwriting work of the corresponding underwriting link.

[0068] It should be noted that the number of underwriting personnel corresponding to each underwriting link can be one or more.

[0069] The embodiment of the present application compares the underwriting requirements of the underwriting link with the historical underwriting records of the underwriters, and selects the records that best match the current underwriting link requirements, ensuring that each underwriting link can be performed by underwriters with corresponding skills and experience. After selecting the target underwriting records, the underwriters who are most suitable for the current underwriting link are determined based on the performance and effects of these records, achieving accurate matching of underwriters and underwriting links. By accurately matching underwriting links and underwriters, the problem of inefficiency caused by mismatched personnel is avoided.

[0070] Step S204, calculating the similarity value between the historical underwriting records of the underwriting personnel corresponding to each underwriting link and the project demand data;

[0071] In this embodiment, for one or more underwriting personnel corresponding to each underwriting stage, a similarity value between the historical underwriting record of each underwriting personnel corresponding to the underwriting stage and the project demand data is calculated.

[0072] Specifically, one of the underwriting links in the responsibility chain is selected, one or more underwriting personnel corresponding to the underwriting link is determined, and the historical underwriting records of each underwriting personnel are obtained. Based on the collaborative filtering algorithm, feature vectors are extracted according to the historical underwriting records of each underwriting personnel and a feature vector matrix is ​​established. A specific similarity measurement method is selected to calculate the similarity value between the feature vector matrix and the project demand data, that is, the similarity value between the historical underwriting records of each underwriting personnel and the project demand data. Afterwards, other underwriting links in the responsibility chain are continued to be selected according to the above method, and the similarity values ​​between the historical underwriting records of the underwriting personnel corresponding to other underwriting links and the project demand data are calculated.

[0073] In some optional implementations, reference Figure 5 , the above-mentioned calculation of the similarity value between the historical underwriting records of the underwriting personnel corresponding to each underwriting link and the project demand data may include the following steps:

[0074] Step S2041, determining the historical underwriting records of one or more underwriting personnel corresponding to each underwriting step;

[0075] Step S2042, acquiring attribute information of the project demand data, and extracting feature vectors from historical underwriting records of the one or more underwriters according to the attribute information;

[0076] Step S2043: Calculate similarity between the feature vectors and the project demand data respectively to obtain similarity values ​​between each feature vector and the project demand data.

[0077] In this embodiment, one or more underwriters corresponding to each underwriting link in the responsibility chain are determined, and the historical underwriting records of each underwriter are obtained. The attribute information of the project demand data is obtained, and the attribute information may include but is not limited to basic information attributes, health status attributes, project type attributes, financial information attributes, etc. Based on the attribute information, feature vectors are extracted from the historical underwriting records of each underwriter, and a feature vector matrix is ​​established based on the extracted feature vectors. A specific similarity measurement method is selected to calculate the similarity value between the feature vector matrix and the project demand data, and the similarity value between each feature vector and the project demand data is obtained, which is the similarity value between the historical underwriting records of each underwriter in the responsibility chain and the project demand data.

[0078] By acquiring the attribute information of the project demand data, the embodiment of the present application can extract the feature vectors related to the project demand from the historical underwriting records in a targeted manner. By calculating the similarity between the feature vectors and the project demand data respectively, the similarity values ​​between each feature vector and the project demand data are obtained, and the matching degree between the historical records of each underwriter and the current project demand can be quantitatively evaluated.

[0079] Step S205, screening and obtaining target underwriters for each underwriting stage based on the similarity value;

[0080] In this embodiment, the target underwriters corresponding to each underwriting link in the responsibility chain are screened according to the calculated similarity values. For example, for each underwriting link, the underwriter with the highest similarity value is selected as the target underwriter for the underwriting link.

[0081] In some optional implementations, the above-mentioned screening based on the similarity value to obtain the target underwriters for each underwriting link may include the following steps:

[0082] Sorting the underwriters of each underwriting stage according to the similarity value to obtain a sequence list of underwriting personnel of each underwriting stage;

[0083] Obtain a preset ranking quota, and determine the target underwriting personnel for each underwriting link from the underwriting personnel sequence list according to the ranking quota.

[0084] In this embodiment, the underwriters of each underwriting link are sorted according to the calculated similarity values, wherein the sorting principle may be that the higher the similarity value, the higher the position of the corresponding underwriter in the sequence list. After the sorting is completed, the underwriters of each underwriting link are organized into an underwriter sequence list according to the sorting results. A preset sorting quota is obtained, and the sorting quota is used to specify the number of target underwriters required for each underwriting link. According to the preset sorting quota, the top-ranked underwriters are selected from the underwriter sequence list of each underwriting link. The selected underwriter becomes the target underwriter of the underwriting link.

[0085] The embodiment of the present application selects a certain number of target underwriting personnel from the sorted underwriting personnel sequence list according to preset sorting quotas, and these personnel have the highest degree of match with specific underwriting links, thereby achieving accurate matching.

[0086] Step S206, obtaining the risk assessment results obtained by the target underwriter performing risk assessment on the project demand data in each underwriting link.

[0087] In this embodiment, after determining the target underwriters of each underwriting link in the responsibility chain, the project demand data is recommended to the target underwriters corresponding to each underwriting link of the responsibility chain in sequence according to the order of the responsibility chain. After receiving the recommended project demand data, each target underwriter performs risk assessment on it and obtains a risk assessment result. The risk assessment result obtained by each target underwriter after performing risk assessment on the project demand data in each underwriting link is obtained.

[0088] In some optional implementations, the step of obtaining the risk assessment results obtained by the target underwriter performing risk assessment on the project demand data at each underwriting stage may include the following steps:

[0089] Inputting the project demand data into the initial underwriting link of the responsibility chain to obtain an initial risk assessment result obtained by a target underwriting personnel corresponding to the initial underwriting link performing a risk assessment on the project demand data;

[0090] In this embodiment, the project demand data is input into the initial underwriting link of the responsibility chain. After receiving the project demand data, the target underwriter corresponding to the initial underwriting link performs risk assessment, and after completing the risk assessment, generates an initial risk assessment result. The initial risk assessment result obtained by the target underwriter corresponding to the initial underwriting link performing risk assessment on the project demand data is obtained.

[0091] Input the initial risk assessment result and the project demand data into the next underwriting link of the initial underwriting link in the order of the responsibility chain, so as to obtain the risk assessment result obtained by the target underwriter corresponding to the next underwriting link performing risk assessment on the project demand data;

[0092] In this embodiment, the initial risk assessment result and the project demand data are input into the next underwriting link of the initial underwriting link in the order of the responsibility chain. After receiving the data, the target underwriter corresponding to the next underwriting link performs further risk assessment based on the existing risk assessment results and project demand data. After completing the risk assessment, the risk assessment result of this link is generated. The risk assessment result obtained by the target underwriter corresponding to the next underwriting link performing risk assessment on the project demand data and the initial risk assessment result is obtained.

[0093] A traversal method is adopted to input the risk assessment results obtained from the previous underwriting link and the project demand data into the current underwriting link in sequence according to the order of the responsibility chain for risk assessment until the end underwriting link of the responsibility chain is reached, thereby obtaining the risk assessment results corresponding to each underwriting link in the responsibility chain.

[0094] In this embodiment, the above-mentioned input and risk assessment process is repeated for each subsequent underwriting link in the responsibility chain. That is, the risk assessment results and project demand data of the previous underwriting link are input into the current underwriting link in turn in a traversal manner. The target underwriter of the current underwriting link performs risk assessment based on the input data and generates a new risk assessment result. The above steps are repeated until the terminal underwriting link of the responsibility chain. At the terminal underwriting link, after completing the final risk assessment, the risk assessment results corresponding to each underwriting link in the responsibility chain are obtained.

[0095] The embodiment of the present application can ensure a comprehensive analysis of project demand data through risk assessment of each link in the chain of responsibility. Each underwriting link is further evaluated based on the results of the previous link. Through the evaluation of multiple links, they can verify and supplement each other to improve the accuracy of risk assessment. Through the transmission mechanism of the chain of responsibility, risk assessment results and project demand data can be shared between various underwriting links, which helps to promote collaborative work between different underwriting links and improve the efficiency and quality of overall risk management.

[0096] In some optional implementations, after obtaining the risk assessment results obtained by the target underwriter performing risk assessment on the project demand data in each underwriting link, the following steps may also be included:

[0097] The risk assessment results are sorted according to preset sorting rules to obtain a risk sorting list.

[0098] In this embodiment, a pre-set sorting rule is determined, and the risk assessment results corresponding to each underwriting link obtained are sorted according to the sorting rule to obtain a risk sorting list.

[0099] More specifically, the above-mentioned sorting of the risk assessment results according to the preset sorting rules to obtain the risk sorting list may include the following steps:

[0100] Obtaining weight values ​​corresponding to each underwriting link;

[0101] Calculate the risk assessment value corresponding to the insured person at each underwriting stage according to the weight value and the risk assessment result;

[0102] The risk assessment results corresponding to the various underwriting stages are sorted according to the risk assessment values ​​to obtain a risk ranking list corresponding to the insured person in each underwriting stage.

[0103] In this embodiment, the preset weight values ​​corresponding to each underwriting link are obtained, and the weight values ​​are set based on the risk level of each underwriting link. According to the weight values ​​of each underwriting link and the risk assessment results corresponding to each underwriting link, the risk assessment values ​​corresponding to the insured person in each underwriting link are calculated. For example, the risk assessment results of each underwriting link are multiplied by the corresponding weight values ​​to obtain the weighted risk assessment values. According to the numerical values, the risk assessment results corresponding to each underwriting link are sorted based on the calculated risk assessment values ​​to obtain a risk ranking list corresponding to each underwriting link of the insured person. The risk ranking list clearly shows in which underwriting link the insured person has the highest risk level.

[0104] By introducing weight values, the embodiment of the present application can comprehensively consider the importance of different underwriting links in the overall risk assessment, making the risk assessment results more comprehensive and accurate. The risk ranking list provides a clear risk level or risk size ranking for the insured and underwriters, which helps underwriters quickly identify high-risk links and take corresponding risk control measures.

[0105] The embodiment of the present application adopts the above-mentioned scheme, specifically by determining the underwriting process and its various underwriting links according to the project demand data and underwriting rules of the insured, it is possible to execute a personalized underwriting process for each insured project, and by establishing a responsibility chain model according to each underwriting link, the underwriting process is decomposed into multiple efficient and accurate underwriting links; by determining the underwriting personnel corresponding to each underwriting link in the responsibility chain according to historical underwriting records, it is possible to use historical underwriting records to match appropriate underwriting personnel, which helps to improve the underwriting professionalism; by calculating the similarity value between the historical underwriting records of the underwriting personnel corresponding to each underwriting link and the project demand data, and screening the target underwriting personnel for each underwriting link based on the similarity value, it is possible to further screen out target underwriting personnel that are more matched with each underwriting link, thereby improving the efficiency and underwriting quality of the entire underwriting process; by performing risk assessment on the project demand data according to each underwriting link in the responsibility chain, it is possible to obtain the overall risk status of the insured project in a more accurate and detailed manner. Based on this application plan, by fully considering the multi-dimensional characteristics of the insured items and the behavioral characteristics of the company's underwriters, personalized risk assessment is achieved based on the underwriter behavior and the needs of the insured items, which improves the matching degree and underwriting efficiency of the underwriters and improves the satisfaction of the insured.

[0106] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned project demand data, historical underwriting records, risk assessment results and other data, the above-mentioned project demand data, historical underwriting records, risk assessment results and other data can also be stored in a blockchain node.

[0107] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0108] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0109] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0110] Further references Figure 6 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a security device, and the device embodiment is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0111] like Figure 6 As shown, the underwriting device 400 described in this embodiment includes: a project acquisition module 401, a link determination module 402, a personnel determination module 403, a similarity calculation module 404, a target screening module 405 and a risk assessment module 406. Among them:

[0112] Project acquisition module 401, used to acquire project demand data of the insured person;

[0113] The link determination module 402 is used to obtain preset underwriting rules, determine various underwriting links of the underwriting process according to the underwriting rules and the project demand data, and establish a responsibility chain according to the various underwriting links;

[0114] The personnel determination module 403 is used to obtain the historical underwriting records of the underwriting personnel, and determine the underwriting personnel corresponding to each underwriting link in the responsibility chain according to the historical underwriting records;

[0115] A similarity calculation module 404 is used to calculate the similarity value between the historical underwriting records of the underwriting personnel corresponding to each underwriting link and the project demand data;

[0116] A target screening module 405, for screening target underwriters for each underwriting stage based on the similarity value;

[0117] The risk assessment module 406 is used to obtain the risk assessment results obtained by the target underwriter performing risk assessment on the project demand data in each underwriting link.

[0118] In this embodiment, the project demand data refers to information collected to accurately understand the insurance needs of the insured, develop appropriate insurance plans, and assess potential risks. The project demand data may include but is not limited to the insured's basic information, health information, insurance needs and preferences, risk assessment related information, payment and financial information, etc. These data are the basis for insurance companies to conduct risk assessment, product design, premium pricing, and customer service when the insured needs to purchase relevant insurance.

[0119] Specifically, the project acquisition module 401 is used to obtain the project demand data of the insured person, wherein the project demand data can be obtained by, for example, obtaining the basic information of the insured person, such as name, age, gender, occupation, etc., from the human resources management system (HRMS); collecting the insured person's health questionnaire, physical examination report, medical record and other data from the underwriting website; collecting the insured person's interests, hobbies, lifestyle, social preferences and other data from social media through legal and compliant methods (such as user authorization, public data capture, etc.).

[0120] Optionally, after obtaining the project demand data of the insured person, the project demand data may be preprocessed, for example, data cleaning, data conversion and data standardization may be performed on the obtained project demand data to ensure data consistency and accuracy.

[0121] Specifically, underwriting rules are formulated based on business needs and risk strategies to guide decision-making at each stage of the underwriting process. Pre-set underwriting rules can be pre-stored in a database or knowledge base in the form of structured data (such as tables, database records) or unstructured data (such as documents, files).

[0122] Specifically, the link determination module 402 is used to obtain the pre-stored underwriting rules from the database or knowledge base after obtaining the project demand data of the insured person. According to the obtained underwriting rules and project demand data, the various underwriting links in the underwriting process are determined. For example, the project demand data can be matched with multiple preset underwriting rules to obtain underwriting rules that match the project demand data. For example, if the project demand data is the age of the insured person, the age restriction conditions defined in the underwriting rules are obtained according to the age matching; according to the matched underwriting rules, the various underwriting links in the underwriting process are determined. For example, the underwriting links can include but are not limited to resume screening, background investigation, information entry, risk assessment, decision processing, etc. Among them, each underwriting link can contain specific filtering rules or restriction conditions. The responsibility chain refers to connecting the various underwriting links in the underwriting process in a sequential relationship to form an orderly process chain. According to the determined underwriting links, the various underwriting links are sorted according to the order of the underwriting process to form a responsibility chain. Among them, each underwriting link in the responsibility chain will be assigned one or more underwriting personnel, who will be used to underwrite the project demand data and other data assigned to the relevant underwriting link.

[0123] Specifically, the historical underwriting record refers to the record generated after the insurance application of the insured person is reviewed during the historical underwriting process. The historical underwriting record may include but is not limited to the basic information of the underwriter, the type of underwriting item, the underwriting result, the processing time, feedback information, etc.

[0124] Specifically, the personnel determination module 403 is used to extract the historical underwriting records of all underwriting personnel from a specific database, analyze the behavioral characteristics of each underwriting personnel according to the historical underwriting records, and determine the underwriting personnel corresponding to each underwriting link in the responsibility chain based on the behavioral characteristics.

[0125] Optionally, a method for determining the underwriting personnel corresponding to each underwriting link in the chain of responsibility based on historical underwriting records may be, for example, to use a machine learning algorithm to perform behavioral characteristic analysis on historical underwriting records to obtain the behavioral characteristics of each underwriting personnel; based on the correlation between the behavioral characteristics and the underwriting links, determine the underwriting personnel corresponding to each underwriting link in the chain of responsibility.

[0126] Specifically, the similarity calculation module 404 is used to calculate the similarity value between the historical underwriting records of each underwriting personnel corresponding to each underwriting link and the project demand data for one or more underwriting personnel corresponding to the underwriting link. More specifically, one of the underwriting links in the responsibility chain is selected, one or more underwriting personnel corresponding to the underwriting link is determined, and the historical underwriting records of each underwriting personnel are obtained. Based on the collaborative filtering algorithm, feature vectors are extracted according to the historical underwriting records of each underwriting personnel and a feature vector matrix is ​​established. A specific similarity measurement method is selected to calculate the similarity value between the feature vector matrix and the project demand data, that is, the similarity value between the historical underwriting records of each underwriting personnel and the project demand data. Afterwards, other underwriting links in the responsibility chain are continued to be selected according to the above method, and the similarity values ​​between the historical underwriting records of the underwriting personnel corresponding to other underwriting links and the project demand data are calculated.

[0127] Specifically, the target screening module 405 is used to screen the target underwriters corresponding to each underwriting link in the responsibility chain according to the calculated similarity value. For example, for each underwriting link, the underwriter with the highest similarity value is selected as the target underwriter of the underwriting link.

[0128] Specifically, the risk assessment module 406 is used to recommend the project demand data to the target underwriters corresponding to each underwriting link in the responsibility chain in sequence according to the order of the responsibility chain after determining the target underwriters of each underwriting link in the responsibility chain. After receiving the recommended project demand data, each target underwriter performs risk assessment on it and obtains a risk assessment result. The risk assessment result obtained by each target underwriter after performing risk assessment on the project demand data in each underwriting link is obtained.

[0129] The underwriting device of the embodiment of the present application, by fully considering the multi-dimensional characteristics of the insured items and the behavioral characteristics of the enterprise's underwriters, realizes personalized risk assessment based on the underwriters' behaviors and the insured items' needs, thereby improving the matching degree and underwriting efficiency of the underwriters and enhancing the satisfaction of the insured persons.

[0130] In some optional implementations of this embodiment, the link determination module 402 may include an attribute acquisition submodule, a rule matching submodule, and a process decomposition submodule.

[0131] The attribute acquisition submodule is used to acquire the attribute information of the project demand data;

[0132] A rule matching submodule, used to match the attribute information with the underwriting rule to obtain a target underwriting rule;

[0133] The process decomposition submodule is used to determine the underwriting process for the project demand data and decompose the underwriting process into various underwriting links according to the target underwriting rules.

[0134] Specifically, the attribute acquisition submodule is used to perform data analysis on the acquired project demand data to extract attribute information of the project demand data, wherein the attribute information may include but is not limited to age attributes, gender attributes, health status attributes, financial level attributes, risk item attributes, etc.

[0135] Specifically, the rule matching submodule is used to match the extracted attribute information with multiple preset underwriting rules, specifically to compare the attribute information with the conditions defined by the underwriting rule, determine whether the attribute information matches the conditions, and determine the underwriting rule corresponding to the conditions as the target underwriting rule according to the matching result. For example, if the attribute information is an age attribute, and the condition defined by the randomly traversed underwriting rule is an age restriction condition, it is determined that the age attribute matches the age restriction condition, and the underwriting rule corresponding to the age restriction condition is determined as the target underwriting rule.

[0136] Specifically, the process decomposition submodule is used to determine the underwriting process of the project demand data based on the acquired project demand data. For example, if the project demand data includes information such as the age, health status and financial status of the insured person, the corresponding underwriting process is determined according to different types of project demand data, such as the age review process, health status review process and financial status review process. According to the matched target underwriting rules, the underwriting process is decomposed into various underwriting links. For example, when the project demand data is the age of the insured person and the target underwriting rule is the underwriting rule corresponding to the age restriction condition, the age review process is decomposed into the age entry link, the age risk assessment link, the age restriction matching link, etc. according to the target underwriting rule.

[0137] The link determination module 402 of the embodiment of the present application screens out the underwriting rules applicable to the current insured project by comparing the attribute information of the project demand data with the preset underwriting rules, thereby ensuring the accuracy of the underwriting work. By determining the corresponding underwriting process for different types of project demand data, the pertinence of the underwriting work is ensured, and by decomposing the underwriting process into multiple specific underwriting links, the underwriting process is made clearer and more efficient.

[0138] In some optional implementations of this embodiment, the personnel determination module 403 may include a requirement acquisition submodule, a record screening submodule, and a personnel determination submodule.

[0139] A requirement acquisition submodule, used to acquire the underwriting requirements of each underwriting link in the responsibility chain;

[0140] A record screening submodule, for screening the historical underwriting records of each underwriting personnel according to the underwriting requirements of each underwriting link, and obtaining the target underwriting records corresponding to each underwriting link;

[0141] The personnel determination submodule is used to determine the underwriting personnel corresponding to each underwriting link according to the target underwriting record.

[0142] Specifically, the requirement acquisition submodule is used to obtain the underwriting requirements pre-defined for each underwriting link in the chain of responsibility. The underwriting requirements may include but are not limited to the professional knowledge requirements, experience level requirements, approval authority requirements, and pass probability requirements of the underwriters.

[0143] Specifically, the record screening submodule is used to screen the historical underwriting records of each underwriter according to the underwriting requirements of each underwriting link, and obtain the target underwriting records corresponding to each underwriting link. More specifically, the behavioral characteristics of each underwriter are extracted from the historical underwriting records of each underwriter, such as years of work experience, approval authority, underwriting link and pass probability, etc., and the extracted behavioral characteristics are matched with the underwriting requirements of each underwriting link, and the underwriting records corresponding to the matching behavioral characteristics are determined as the target underwriting records corresponding to the underwriting link. For example, for the preliminary review link, the underwriting records of underwriters who have preliminary review authority and a high preliminary review pass rate in the historical underwriting records are screened according to the underwriting requirements of the preliminary review link to serve as the target underwriting records corresponding to the preliminary review link.

[0144] Specifically, the personnel determination submodule is used to screen out the corresponding target underwriting records for each underwriting link in the responsibility chain, and then determine the underwriting personnel corresponding to each target underwriting record. The underwriting personnel is the executor of the underwriting work in the corresponding underwriting link.

[0145] It should be noted that the number of underwriting personnel corresponding to each underwriting link can be one or more.

[0146] The personnel determination module 403 of the embodiment of the present application compares the underwriting requirements of the underwriting link and the historical underwriting records of the underwriters to select the records that best match the requirements of the current underwriting link, thereby ensuring that each underwriting link can be performed by an underwriter with corresponding skills and experience. After selecting the target underwriting records, the underwriter that best suits the current underwriting link is determined based on the performance and effect of these records, thereby achieving accurate matching of the underwriter and the underwriting link. By accurately matching the underwriting links and underwriters, the inefficiency caused by mismatched personnel is avoided.

[0147] In some optional implementations of this embodiment, the similarity calculation module 404 may include a record determination submodule, a feature extraction submodule, and a numerical calculation submodule.

[0148] A record determination submodule, used to determine the historical underwriting records of one or more underwriting personnel corresponding to each underwriting link;

[0149] A feature extraction submodule, configured to obtain attribute information of the project demand data, and extract feature vectors from historical underwriting records of the one or more underwriters according to the attribute information;

[0150] The numerical calculation submodule is used to perform similarity calculation on the feature vectors and the project demand data respectively, so as to obtain the similarity value between each feature vector and the project demand data.

[0151] In this embodiment, the record determination submodule is used to determine one or more underwriting personnel corresponding to each underwriting link in the responsibility chain, and obtain the historical underwriting record of each underwriting personnel. The feature extraction submodule is used to obtain the attribute information of the project demand data, and the attribute information may include but is not limited to basic information attributes, health status attributes, project type attributes, financial information attributes, etc. Based on the attribute information, feature vectors are extracted from the historical underwriting records of each underwriting personnel, and a feature vector matrix is ​​established based on the extracted feature vectors. The numerical calculation submodule is used to select a specific similarity measurement method, calculate the similarity value between the feature vector matrix and the project demand data, and obtain the similarity value between each feature vector and the project demand data, that is, the similarity value between the historical underwriting records of each underwriting personnel in the responsibility chain and the project demand data.

[0152] The similarity calculation module 404 of the embodiment of the present application can extract feature vectors related to project requirements from historical underwriting records in a targeted manner by acquiring attribute information of project requirement data. By performing similarity calculations on the feature vectors and the project requirement data respectively, the similarity values ​​between each feature vector and the project requirement data are obtained, and the degree of match between the historical records of each underwriter and the current project requirements can be quantitatively evaluated.

[0153] In some optional implementations of this embodiment, the target screening module 405 may include a numerical ranking submodule and a quota determination submodule.

[0154] A numerical sorting submodule, used to sort the underwriters of each underwriting link according to the similarity value to obtain a sequence list of underwriters of each underwriting link;

[0155] The quota determination submodule is used to obtain a preset ranking quota, and determine the target underwriting personnel for each underwriting link from the underwriting personnel sequence list according to the ranking quota.

[0156] Specifically, the numerical sorting submodule is used to sort the underwriters of each underwriting link according to the calculated similarity values, wherein the sorting principle may be that the higher the similarity value, the higher the position of the corresponding underwriter in the sequence list. After the sorting is completed, the underwriters of each underwriting link are organized into an underwriting personnel sequence list according to the sorting results. The quota determination submodule is used to obtain a pre-set sorting quota, which is used to specify the number of target underwriters required for each underwriting link. According to the preset sorting quota, the top-ranked underwriters are selected from the underwriting personnel sequence list of each underwriting link. The selected underwriter becomes the target underwriter of that underwriting link.

[0157] The target screening module 405 of the embodiment of the present application selects a certain number of target underwriting personnel from the sorted underwriting personnel sequence list according to a preset sorting quota. These personnel have the highest degree of matching with specific underwriting links, thereby achieving accurate matching.

[0158] In some optional implementations of this embodiment, the risk assessment module 406 may also be used to: input the project demand data into the initial underwriting link of the responsibility chain to obtain an initial risk assessment result obtained by the target underwriting personnel corresponding to the initial underwriting link performing risk assessment on the project demand data;

[0159] Input the initial risk assessment result and the project demand data into the next underwriting link of the initial underwriting link in the order of the responsibility chain, so as to obtain the risk assessment result obtained by the target underwriter corresponding to the next underwriting link performing risk assessment on the project demand data;

[0160] A traversal method is adopted to input the risk assessment results obtained from the previous underwriting link and the project demand data into the current underwriting link in sequence according to the order of the responsibility chain for risk assessment until the end underwriting link of the responsibility chain is reached, thereby obtaining the risk assessment results corresponding to each underwriting link in the responsibility chain.

[0161] Specifically, the risk assessment module 406 is used to input the project demand data into the initial underwriting link of the responsibility chain. After receiving the project demand data, the target underwriter corresponding to the initial underwriting link performs a risk assessment, and after completing the risk assessment, generates an initial risk assessment result. The initial risk assessment result obtained by the target underwriter corresponding to the initial underwriting link performing a risk assessment on the project demand data is obtained. The initial risk assessment result and the project demand data are input into the next underwriting link of the initial underwriting link in the order of the responsibility chain. After receiving the data, the target underwriter corresponding to the next underwriting link performs a further risk assessment based on the existing risk assessment results and project demand data. After completing the risk assessment, the risk assessment result of this link is generated. The risk assessment result obtained by the target underwriter corresponding to the next underwriting link performing a risk assessment on the project demand data and the initial risk assessment result is obtained. A traversal method is adopted to input the risk assessment results obtained from the previous underwriting link and the project demand data into the current underwriting link in sequence according to the order of the responsibility chain for risk assessment until the end underwriting link of the responsibility chain is reached, thereby obtaining the risk assessment results corresponding to each underwriting link in the responsibility chain.

[0162] The risk assessment module 406 of the embodiment of the present application can ensure a comprehensive analysis of the project demand data through the risk assessment of each link of the responsibility chain. Each underwriting link is further evaluated based on the results of the previous link. Through the evaluation of multiple links, they can verify and supplement each other to improve the accuracy of risk assessment. Through the transmission mechanism of the responsibility chain, the risk assessment results and project demand data can be shared between the various underwriting links, which helps to promote the collaborative work between different underwriting links and improve the efficiency and quality of overall risk management.

[0163] In some optional implementations of this embodiment, the underwriting device 400 may further include a risk sorting module, which is used to sort the risk assessment results according to preset sorting rules to obtain a risk sorting list.

[0164] Specifically, the risk sorting module is used to determine a pre-set sorting rule, and sort the risk assessment results corresponding to each underwriting link obtained according to the sorting rule to obtain a risk sorting list.

[0165] In some optional implementations of this embodiment, the risk ranking module may also be used to: obtain weight values ​​corresponding to the various underwriting links;

[0166] Calculate the risk assessment value corresponding to the insured person at each underwriting stage according to the weight value and the risk assessment result;

[0167] The risk assessment results corresponding to the various underwriting stages are sorted according to the risk assessment values ​​to obtain a risk ranking list corresponding to the insured person in each underwriting stage.

[0168] Specifically, the risk ranking module can also be used to obtain the predefined weight values ​​corresponding to each underwriting link, and the weight values ​​can be set based on the risk level of each underwriting link. According to the weight values ​​of each underwriting link and the risk assessment results corresponding to each underwriting link, the risk assessment values ​​corresponding to the insured person in each underwriting link are calculated. For example, the risk assessment results of each underwriting link are multiplied by the corresponding weight values ​​to obtain the weighted risk assessment values. According to the numerical size, the risk assessment results corresponding to each underwriting link are sorted based on the calculated risk assessment values ​​to obtain a risk ranking list corresponding to each underwriting link of the insured person. The risk ranking list clearly shows in which underwriting link the insured person has the highest risk level.

[0169] The risk ranking module of the embodiment of the present application can comprehensively consider the importance of different underwriting links in the overall risk assessment by introducing weight values, making the risk assessment results more comprehensive and accurate. The risk ranking list provides a clear risk level or risk size ranking for the insured and underwriters, which helps underwriters quickly identify high-risk links and take corresponding risk control measures.

[0170] To solve the above technical problems, the present application also provides a computer device. Figure 7 , Figure 7 This is a basic structural block diagram of the computer device in this embodiment.

[0171] The computer device 6 includes a memory 61, a processor 62, and a network interface 63 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 6 with a memory 61, a processor 62, and a network interface 63, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0172] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0173] The memory 61 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 61 can be an internal storage unit of the computer device 6, such as a hard disk or memory of the computer device 6. In other embodiments, the memory 61 can also be an external storage device of the computer device 6, such as a plug-in hard disk equipped on the computer device 6, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 61 can also include both the internal storage unit of the computer device 6 and its external storage device. In this embodiment, the memory 61 is generally used to store the operating system and various application software installed on the computer device 6, such as computer-readable instructions of the underwriting method, etc. In addition, the memory 61 can also be used to temporarily store various types of data that have been output or are to be output.

[0174] The processor 62 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 62 is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is used to run computer-readable instructions stored in the memory 61 or process data, such as computer-readable instructions for running the underwriting method.

[0175] The network interface 63 may include a wireless network interface or a wired network interface. The network interface 63 is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0176] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the underwriting method as described above.

[0177] The computer device, computer-readable storage medium and computer-readable instructions provided in the embodiments of the present application can determine the underwriting process and its various underwriting links according to the project demand data and underwriting rules of the insured person through the processor, and can execute a personalized underwriting process for each insured project, and by establishing a responsibility chain model according to each underwriting link, the underwriting process is decomposed into multiple efficient and accurate underwriting links; by determining the underwriting personnel corresponding to each underwriting link in the responsibility chain according to historical underwriting records, it is possible to use historical underwriting records to match appropriate underwriting personnel, which helps to improve underwriting professionalism; by calculating the similarity value between the historical underwriting records of the underwriting personnel corresponding to each underwriting link and the project demand data, and screening the target underwriting personnel for each underwriting link based on the similarity value, it is possible to further screen out target underwriting personnel that are more matched with each underwriting link, thereby improving the efficiency and underwriting quality of the entire underwriting process; by performing risk assessment on the project demand data according to each underwriting link in the responsibility chain, the overall risk status of the insured project can be obtained more accurately and in detail. Based on this application plan, by fully considering the multi-dimensional characteristics of the insured items and the behavioral characteristics of the company's underwriters, personalized risk assessment is achieved based on the underwriter behavior and the needs of the insured items, which improves the matching degree and underwriting efficiency of the underwriters and improves the satisfaction of the insured.

[0178] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0179] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to replace some of the technical features therein with equivalents. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

[0180] The non-Company software tools or components appearing in the embodiments of this application are merely examples and do not represent actual use.

Claims

1. An underwriting method, characterized in that: The steps include: Obtain project demand data of insured persons; Obtaining preset underwriting rules, determining each underwriting link of the underwriting process according to the underwriting rules and the project demand data, and establishing a responsibility chain according to each underwriting link; Obtaining historical underwriting records of underwriters, and determining the underwriters corresponding to each underwriting link in the chain of responsibility based on the historical underwriting records; Calculate the similarity value between the historical underwriting records of the underwriting personnel corresponding to each underwriting link and the project demand data; Target underwriters for each underwriting link are obtained by screening based on the similarity values; Obtain the risk assessment results obtained by the target underwriter in performing risk assessment on the project demand data at each underwriting stage.

2. The underwriting method according to claim 1, characterized in that: The step of determining each underwriting link of the underwriting process according to the underwriting rules and the project demand data includes: Acquiring attribute information of the project demand data; Matching the attribute information with the underwriting rule to obtain a target underwriting rule; Determine the underwriting process for the project demand data, and decompose the underwriting process into various underwriting links according to the target underwriting rules.

3. The underwriting method according to claim 1, characterized in that: The step of determining the underwriting personnel corresponding to each underwriting link in the chain of responsibility according to the historical underwriting records includes: Obtain the underwriting requirements of each underwriting link in the responsibility chain; According to the underwriting requirements of each underwriting link, the historical underwriting records of each underwriting personnel are screened to obtain the target underwriting records corresponding to each underwriting link; The underwriting personnel corresponding to each underwriting link are determined according to the target underwriting record.

4. The underwriting method according to claim 1, characterized in that: The step of calculating the similarity value between the historical underwriting records of the underwriting personnel corresponding to each underwriting link and the project demand data includes: Determine the historical underwriting records of one or more underwriting personnel corresponding to each underwriting link; Acquire attribute information of the project demand data, and extract feature vectors from historical underwriting records of the one or more underwriters according to the attribute information; The similarity between the feature vectors and the project demand data is calculated respectively to obtain a similarity value between each feature vector and the project demand data.

5. The underwriting method according to claim 1, characterized in that: The step of obtaining the target underwriters for each underwriting link by screening based on the similarity value includes: Sorting the underwriters of each underwriting stage according to the similarity value to obtain a sequence list of underwriting personnel of each underwriting stage; Obtain a preset ranking quota, and determine the target underwriting personnel for each underwriting link from the underwriting personnel sequence list according to the ranking quota.

6. The underwriting method according to claim 1, characterized in that: The step of obtaining the risk assessment results obtained by performing risk assessment on the project demand data in each underwriting link includes: Inputting the project demand data into the initial underwriting link of the responsibility chain to obtain an initial risk assessment result obtained by a target underwriting personnel corresponding to the initial underwriting link performing a risk assessment on the project demand data; Input the initial risk assessment result and the project demand data into the next underwriting link of the initial underwriting link in the order of the responsibility chain, so as to obtain the risk assessment result obtained by the target underwriter corresponding to the next underwriting link performing risk assessment on the project demand data; A traversal method is adopted to input the risk assessment results obtained from the previous underwriting link and the project demand data into the current underwriting link in sequence according to the order of the responsibility chain for risk assessment until the end underwriting link of the responsibility chain is reached, thereby obtaining the risk assessment results corresponding to each underwriting link in the responsibility chain.

7. The underwriting method according to claim 1, characterized in that: After the step of obtaining the risk assessment results obtained by the target underwriter performing risk assessment on the project demand data in each underwriting link, the method further includes: Obtaining weight values ​​corresponding to each underwriting link; Calculate the risk assessment value corresponding to the insured person at each underwriting stage according to the weight value and the risk assessment result; The risk assessment results corresponding to the various underwriting stages are sorted according to the risk assessment values ​​to obtain a risk ranking list corresponding to the insured person in each underwriting stage.

8. A nuclear security device, characterized in that: The device comprises: Project acquisition module, used to obtain project demand data of insured persons; A link determination module is used to obtain preset underwriting rules, determine each underwriting link of the underwriting process according to the underwriting rules and the project demand data, and establish a responsibility chain according to each underwriting link; A personnel determination module is used to obtain the historical underwriting records of underwriters and determine the underwriters corresponding to each underwriting link in the responsibility chain according to the historical underwriting records; A similarity calculation module, used to calculate the similarity value between the historical underwriting records of the underwriting personnel corresponding to each underwriting link and the project demand data; A target screening module, used for screening target underwriters for each underwriting link based on the similarity value; The risk assessment module is used to obtain the risk assessment results obtained by the target underwriter in performing risk assessment on the project demand data in each underwriting link.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the underwriting method as claimed in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the underwriting method according to any one of claims 1 to 7 are implemented.

Images