Method and device for screening underwriting modes based on artificial intelligence

Abstract

The invention provides an artificial intelligence-based underwriting mode screening method and equipment. The method comprises the steps that multiple first underwriting modes are obtained, the multiple first underwriting modes have multiple types, the first underwriting mode in each type comprises an underwriting calculation mode, and for the underwriting calculation mode of each type, a first matching degree between the underwriting calculation mode and target data corresponding to the type is obtained, and screening the plurality of first underwriting modes based on the first matching degree to obtain a plurality of second underwriting modes, calculating the target data based on an underwriting calculation mode of the second underwriting modes to obtain an underwriting calculation result, and screening the second underwriting modes based on a preset target threshold and the underwriting calculation result to obtain a screening result. Through the method and the device, the efficiency and the accuracy of screening the underwriting modes can be improved, and the use requirements are met.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a screening method and device for underwriting methods based on artificial intelligence. Background Art

[0002] Underwriting is insurance underwriting, and underwriting is the insurer's choice of the insured, that is, the insurer's acceptance or rejection of the insured (also called the policyholder)'s insurance application. If the insurer accepts the insured's insurance application, it can assume the insurance liability specified in the insurance contract. In the related technology, multiple underwriting methods can be set, and the underwriting methods can be screened manually, but the efficiency of manual screening of underwriting methods is low, and the accuracy is poor, which cannot meet the use requirements. Summary of the invention

[0003] The embodiments of the present application provide a method and device for screening underwriting methods based on artificial intelligence, which can improve the efficiency and accuracy of screening underwriting methods and meet usage requirements.

[0004] The technical solution of the embodiment of the present application is implemented as follows:

[0005] The embodiment of the present application provides a method for screening underwriting methods based on artificial intelligence, the method comprising:

[0006] Acquire multiple first insurance methods, wherein the multiple first insurance methods have multiple types, and the first insurance method under each type includes an insurance calculation method;

[0007] For each of the types of insurance calculation methods, obtaining a first matching degree between the insurance calculation method and the target data corresponding to the type;

[0008] Screening the plurality of first insurance methods based on the first matching degree to obtain a plurality of second insurance methods;

[0009] The target data is calculated based on the underwriting calculation method of the second underwriting method to obtain an underwriting calculation result, and the second underwriting method is screened based on a preset target threshold and the underwriting calculation result to obtain a screening result.

[0010] The embodiment of the present application provides a screening device for insurance underwriting methods based on artificial intelligence, the device comprising:

[0011] An acquisition module, used for acquiring a plurality of first insurance methods, wherein the plurality of first insurance methods have a plurality of types, and the first insurance method under each type includes an insurance calculation method;

[0012] The acquisition module is further used to acquire, for each type of insurance calculation method, a first matching degree between the insurance calculation method and the target data corresponding to the type;

[0013] A screening module, configured to screen the plurality of first insurance methods based on the first matching degree to obtain a plurality of second insurance methods;

[0014] The screening module is also used to calculate the target data based on the underwriting calculation method of the second underwriting method to obtain an underwriting calculation result, and to screen the second underwriting method based on a pre-set target threshold and the underwriting calculation result to obtain a screening result.

[0015] In the above scheme, the insurance calculation method has a usage area; the acquisition module is also used to, for each type of insurance calculation method, if the usage area of ​​the insurance calculation method is larger than the target usage area, then according to the usage area, from the correspondence between the pre-set candidate usage areas and candidate data, determine multiple copies of data corresponding to the usage area, and determine the priority of the multiple copies of the data; use the data with the highest priority as the target data, and obtain the first degree of match between the insurance calculation method and the target data.

[0016] In the above scheme, the screening module is also used to input the second insurance method and the target data into a pre-trained insurance method screening model, and extract the characteristics of the second insurance method and the target data for each second insurance method through the insurance method screening model, determine the target data corresponding to the second insurance method based on the characteristics of the second insurance method and the characteristics of the target data, and calculate the target data corresponding to the second insurance method based on the insurance calculation method of the second insurance method to obtain the insurance calculation result; and screen the second insurance method based on the pre-set target threshold and the insurance calculation result through the insurance method screening model to obtain the screening result.

[0017] In the above scheme, the second underwriting method has a pre-set label, and the target data includes multiple target sub-data, each of which corresponds to a field; the screening module is also used to determine, for each of the second underwriting methods, the target field corresponding to the label of the second underwriting method from the correspondence between the pre-set candidate labels and candidate fields; and the target sub-data corresponding to the target field is calculated based on the underwriting calculation method of the second underwriting method to obtain the underwriting calculation result.

[0018] In the above scheme, the target threshold includes a first target threshold corresponding to the label of the second underwriting method, and a second target threshold corresponding to the type of the second underwriting method; the screening module is also used to, for each of the second underwriting methods, take the second underwriting method as the target underwriting method when the underwriting calculation result of the second underwriting method is greater than the first target threshold; divide the target underwriting method according to the type, each type includes multiple target underwriting methods, and for the multiple target underwriting methods under each type, obtain the average value of the underwriting calculation results of the multiple target underwriting methods, and when the average value is less than the second target threshold, mark the multiple target underwriting methods as available underwriting methods to obtain the screening result.

[0019] In the above scheme, the first underwriting method also includes an underwriting user screening method; the screening module is also used to screen the second underwriting method based on a preset target threshold and the underwriting calculation result, and before obtaining the screening result, for each of the underwriting user screening methods, obtain the user data in the target data, and screen the user data based on the underwriting user screening method to obtain the target user data; determine the target insurance corresponding to the target user data according to the correspondence between the pre-stored candidate user data and the candidate insurance; screen the second underwriting method based on the preset target threshold and the underwriting calculation result to obtain the first screening result; determine the similarity between the target insurance and the pre-set insurance, and screen the first underwriting method including the underwriting user screening method based on the similarity and the pre-set similarity threshold to obtain the second screening result; and merge the first screening result and the second screening result to obtain the screening result.

[0020] In the above scheme, the first underwriting method also includes an underwriting order setting method, and the underwriting order setting method is a method for setting a first arrangement order for multiple underwriting methods; the screening module is also used to screen the second underwriting method based on a preset target threshold and the underwriting calculation result to obtain a first screening result, and the first screening result includes multiple available underwriting methods; sort the multiple available underwriting methods according to a preset sorting method, calculate the sorted multiple available underwriting methods, and the underwriting order setting method includes the similarity between the multiple pre-set underwriting methods arranged in order, and adjust the first screening result based on the similarity to obtain a screening result.

[0021] An embodiment of the present application provides an electronic device, the electronic device comprising:

[0022] A memory for storing computer executable instructions or computer programs;

[0023] The processor is used to implement the artificial intelligence-based underwriting method screening method provided in the embodiment of the present application when executing the computer executable instructions or computer program stored in the memory.

[0024] An embodiment of the present application provides a computer-readable storage medium storing a computer program or computer-executable instructions for implementing the artificial intelligence-based underwriting screening method provided in the embodiment of the present application when executed by a processor.

[0025] An embodiment of the present application provides a computer program product, including a computer program or computer executable instructions. When the computer program or computer executable instructions are executed by a processor, the screening method of the underwriting method based on artificial intelligence provided in the embodiment of the present application is implemented.

[0026] The embodiments of the present application have the following beneficial effects:

[0027] The artificial intelligence-based underwriting method screening method provided in the embodiment of the present application can obtain multiple first underwriting methods, wherein the multiple first underwriting methods exist in multiple types, and the first underwriting method under each type includes an insurance calculation method. For each type of underwriting calculation method, a first matching degree between the underwriting calculation method and the target data corresponding to the type is obtained, and the multiple first underwriting methods are screened based on the first matching degree to obtain multiple second underwriting methods. The target data is calculated based on the underwriting calculation method of the second underwriting method to obtain the insurance calculation result, and the second underwriting method is screened based on the pre-set target threshold and the insurance calculation result to obtain the screening result.

[0028] In the present application, two screenings for underwriting methods can be achieved. The first screening is based on the match between the underwriting calculation method and the target data. The target data is used for subsequent calculations to obtain the underwriting calculation results. Through the first screening, an underwriting method that better matches the target data can be obtained, thereby improving the accuracy of the screened underwriting methods. The second screening is based on the underwriting calculation results and the target threshold, thereby further improving the accuracy of the screened underwriting methods. Compared with manual screening of underwriting methods, the efficiency and accuracy of screening underwriting methods can be improved, and usage requirements can be met. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a structural schematic diagram of an insurance screening system based on artificial intelligence provided in an embodiment of the present application;

[0030] Figure 2 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0031] Figure 3This is a flowchart of the screening method of the insurance method based on artificial intelligence provided in the embodiment of the present application. Figure 1 ;

[0032] Figure 4 This is a flowchart of the screening method of the insurance method based on artificial intelligence provided in the embodiment of the present application. Figure 2 ;

[0033] Figure 5 This is a flowchart of the screening method of the insurance method based on artificial intelligence provided in the embodiment of the present application. Figure 3 ;

[0034] Fig. 6A This is a flowchart of the screening method of the insurance method based on artificial intelligence provided in the embodiment of the present application. Figure 4 ;

[0035] Figure 6B It is a structural diagram of the insurance method screening model provided in the embodiment of the present application.

[0036] Figure 7 This is a flowchart of the screening method of the insurance method based on artificial intelligence provided in the embodiment of the present application. Figure 5 ;

[0037] Figure 8 This is a schematic diagram of the screening method of the underwriting method based on artificial intelligence provided in the embodiment of the present application. Figure 1 ;

[0038] Fig. 9 This is a schematic diagram of the screening method of the underwriting method based on artificial intelligence provided in the embodiment of the present application. Figure 2 ;

[0039] Fig.10 This is a schematic diagram of the screening method of the underwriting method based on artificial intelligence provided in the embodiment of the present application. Figure 3 ;

[0040] Fig.11 This is a schematic diagram of the screening method of the underwriting method based on artificial intelligence provided in the embodiment of the present application. Figure 4 . DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0042] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it can be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0043] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0044] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0045] Unless otherwise defined, all technical and scientific terms used in the embodiments of the present application have the same meanings as those commonly understood by those skilled in the art. The terms used in the embodiments of the present application are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0046] The relevant data collection and processing in the embodiments of this application should be strictly in accordance with the requirements of relevant laws and regulations when applied in examples, obtain the informed consent or separate consent of the personal information subject, and carry out subsequent data use and processing within the scope of authorization of laws and regulations and the personal information subject.

[0047] The embodiments of the present application provide a method, device, electronic device, computer-readable storage medium and computer program product for screening underwriting methods based on artificial intelligence, which can improve the efficiency and accuracy of screening underwriting methods and meet usage requirements.

[0048] See also Figure 1 , Figure 1 is a structural diagram of an insurance screening system based on artificial intelligence provided in an embodiment of the present application, Figure 1 The AI-based underwriting screening system 100 is shown to implement an AI-based underwriting screening application. The terminal 400-1 is connected to the server 200 via the network 300. The network 300 can be a wide area network or a local area network, or a combination of the two.

[0049] When the user needs to filter the insurance methods, in response to a filtering instruction triggered by the graphical interface 410 - 1 of the terminal 400 - 1 , the terminal 400 - 1 may generate a filtering request for the insurance methods and send the filtering request to the server 200 .

[0050] After receiving the screening request, the server 200 can obtain multiple first underwriting methods based on the screening request, wherein the multiple first underwriting methods exist in multiple types, and the first underwriting method under each type includes an insurance calculation method. For each type of insurance calculation method, a first matching degree between the insurance calculation method and the target data corresponding to the type is obtained, and the multiple first underwriting methods are screened based on the first matching degree to obtain multiple second underwriting methods. The target data is calculated based on the insurance calculation method of the second underwriting method to obtain the insurance calculation result, and the second underwriting method is screened based on the pre-set target threshold and the insurance calculation result to obtain the screening result.

[0051] After obtaining the screening results, the server 200 may send the screening results to the terminal 400 - 1 , and the terminal 400 - 1 may display the screening results after screening the underwriting methods on the graphical interface 410 - 1 , so that the user can know the screening results.

[0052] In the present application, two screenings for underwriting methods can be achieved. The first screening is based on the match between the underwriting calculation method and the target data. The target data is used for subsequent calculations to obtain the underwriting calculation results. Through the first screening, an underwriting method that better matches the target data can be obtained, thereby improving the accuracy of the screened underwriting methods. The second screening is based on the underwriting calculation results and the target threshold, thereby further improving the accuracy of the screened underwriting methods. Compared with manual screening of underwriting methods, the efficiency and accuracy of screening underwriting methods can be improved, and usage requirements can be met.

[0053] The electronic device provided in the embodiment of the present application is described below. The electronic device that implements the artificial intelligence-based underwriting screening method of the embodiment of the present application may be a terminal, a server, or a combination of the two.

[0054] The terminal can be a laptop, tablet computer, desktop computer, set-top box, smart phone, smart speaker, smart watch, smart TV, car terminal and other types of terminals. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms. The terminal and the server can be directly or indirectly connected by wired or wireless communication, which is not limited in the embodiments of the present application.

[0055] See also Figure 2 , Figure 2 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, Figure 2 The electronic device shown includes: at least one processor 410, a memory 450, at least one network interface 420 and a user interface 430. The various components in the electronic device are coupled together via a bus system 440. It is understood that the bus system 440 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 440 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 440 is not shown in FIG. Figure 2 Various buses are labeled as bus system 440 .

[0056] The processor 410 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0057] The user interface 430 includes one or more output devices 431 that enable presentation of media content, including one or more speakers and / or one or more visual display screens. The user interface 430 also includes one or more input devices 432, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

[0058] The memory 450 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard disk drives, optical disk drives, etc. The memory 450 may optionally include one or more storage devices that are physically remote from the processor 410.

[0059] The memory 450 includes a volatile memory or a non-volatile memory, and may also include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), and the volatile memory may be a random access memory (RAM). The memory 450 described in the embodiments of the present application is intended to include any suitable type of memory.

[0060] In some embodiments, memory 450 can store data to support various operations, examples of which include programs, modules, and data structures, or a subset or superset thereof, as exemplarily described below.

[0061] Operating system 451, including system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks;

[0062] A network communication module 452, used to reach other electronic devices via one or more (wired or wireless) network interfaces 420, exemplary network interfaces 420 include: Bluetooth, Wireless Compatibility Certification (WiFi), and Universal Serial Bus (USB), etc.;

[0063] a presentation module 453 for enabling presentation of information via one or more output devices 431 (e.g., display screen, speaker, etc.) associated with the user interface 430 (e.g., a user interface for operating peripherals and displaying content and information);

[0064] The input processing module 454 is used to detect one or more user inputs or interactions from one of the one or more input devices 432 and translate the detected inputs or interactions.

[0065] In some embodiments, the artificial intelligence-based insurance screening device provided in the embodiments of the present application can be implemented in a software manner. Figure 2 The screening device 455 based on artificial intelligence underwriting method stored in the memory 450 is shown, which can be software in the form of programs and plug-ins, etc., including the following software modules: an acquisition module 4551 and a screening module 4552. These modules are logical, so they can be arbitrarily combined or further split according to the functions implemented. The functions of each module will be explained below.

[0066] In other embodiments, the screening device for the artificial intelligence-based underwriting method provided in the embodiments of the present application can be implemented in hardware. As an example, the screening device for the artificial intelligence-based underwriting method provided in the embodiments of the present application can be a processor in the form of a hardware decoding processor, which is programmed to execute the screening method for the artificial intelligence-based underwriting method provided in the embodiments of the present application. For example, the processor in the form of a hardware decoding processor can adopt one or more application specific integrated circuits (Application Specific Integrated Circuit, ASIC), digital signal processors (Digital Signal Processor, DSP), programmable logic devices (Programmable Logic Device, PLD), complex programmable logic devices (Complex Programmable Logic Device, CPLD), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other electronic components.

[0067] The following is an introduction to the screening method of insurance underwriting methods based on artificial intelligence provided in the embodiment of the present application. As mentioned above, the electronic device that implements the screening method of insurance underwriting methods based on artificial intelligence in the embodiment of the present application can be a terminal, a server, or a combination of the two. Therefore, the execution subject of each step will not be repeatedly described below.

[0068] See also Figure 3 , Figure 3 This is a flowchart of the screening method of the insurance method based on artificial intelligence provided in the embodiment of the present application. Figure 1 , the following combination Figure 3 The steps shown, and taking the execution subject as a server as an example, the screening method of the underwriting method based on artificial intelligence provided in the embodiment of the present application is introduced.

[0069] In step 101, multiple first underwriting methods are obtained.

[0070] Among them, there are multiple types of multiple first underwriting methods, and the type is the insurance type. The insurance type may include the following types. The first type may be insurance set for the health of the insured, the second type may be insurance set for the life of the insured, the third type may be insurance set for the property of the insured, and the fourth type may be property set for special scenarios, for example, the scenarios may be travel scenarios, transportation scenarios, flight delay scenarios, etc. The fifth type may be insurance set for the insured's belongings, for example, insurance set for pets, insurance set for vehicles, etc. Of course, there may be other types, which will not be elaborated here.

[0071] The first underwriting method is different for different types. The underwriting method may include the method of determining the scope of insurance, the method of corresponding underwriting terms, the method of assessing underwriting risks, the method of corresponding underwriting review process, etc. The scope of insurance is based on the insured's information to determine the scope of insurance that the insured can purchase. For insurance, it is to determine the population to which the insurance is applicable.

[0072] The underwriting terms are the terms of insurance liability, exemptions, insurance amount, insurance period, etc. Each term can be used as an underwriting method. Assessing underwriting risk is to conduct risk assessment on the insured's information. Each method of assessing underwriting risk is an underwriting method. The underwriting review process is the process of reviewing the insured's insurance application during the underwriting process. One underwriting review process is an underwriting method.

[0073] The underwriting method can be set manually or obtained by adjusting the underwriting method already in use. The first underwriting method under each type can include an underwriting calculation method, which can be a method corresponding to the underwriting terms or a method for evaluating underwriting risks.

[0074] The first underwriting method may also include an underwriting user screening method, which corresponds to a method for determining the scope of underwriting. The first underwriting method may also include an underwriting order setting method, which may correspond to an underwriting review process, that is, the underwriting order setting method may be a setting method for the order of reviewing the insurance application provided by the insured during the underwriting process.

[0075] The underwriting order setting method can also be a setting method of the order between the methods corresponding to multiple underwriting clauses, and the underwriting order setting method can also be a setting method of the order between multiple methods of assessing underwriting risks. The specific setting can be combined with actual use needs, and will not be repeated here.

[0076] The underwriting calculation method may include data items to be filled in, weights of data items to be filled in, and calculation methods between data items to be filled in. The calculation methods between data items to be filled in may be addition, multiplication, exponentiation and other calculation methods, which may be specifically set according to actual usage requirements. The data items to be filled in may be filled in with the data of the target object, and the target object may be the insured, the insured's belongings, the insured's relatives, etc., which are all reasonable.

[0077] In step 102, for each type of underwriting calculation method, a first matching degree between the underwriting calculation method and the target data corresponding to the type is obtained.

[0078] The number of underwriting calculation methods under a type may be one or more, and for each underwriting calculation method under each type, a first matching degree between the underwriting calculation method and the target data corresponding to the type may be obtained.

[0079] The target data corresponds to the type. For the first type, the target data corresponding to the first type may include the age of the insured, data characterizing the physical condition of the insured, the region where the insured is located, the insurance density of the region where the insured is located, the insurance depth of the region where the insured is located, etc. Among them, the insurance density is used to characterize the degree of participation of users in the region where the insured is located, and the insurance depth is used to characterize the proportion of insurance in the income of users in the region where the insured is located.

[0080] For the second type, the target data corresponding to the second type may include the insurance amount, the age of the insured, data representing the physical condition of the insured, the insurance duration, the industry of the insured, etc. For the third type, the target data corresponding to the third type may include the insurance duration, risk assessment for the insured, the insurance amount, etc.

[0081] For the fourth type, the target data of the fourth type can be determined according to the scenario. For example, the target data of the travel scenario can be the age of the insured, data characterizing the physical condition of the insured, the location reached by the insured during the trip, the insurance duration, the insurance scope, etc.

[0082] For the fifth type, the target data of the fifth type can be determined according to the insured items. For example, for insurance set for pets, the target data can be the type of pet, the age of the pet, data representing the physical condition of the pet, the number of pets, etc. The specific data can be set according to actual usage requirements.

[0083] In some embodiments, for each type, there may be multiple subtypes of the type, and one subtype may correspond to a type of insurance. For example, for the fifth type, two fifth subtypes may be included, one fifth subtype is insurance set for pets, and the other fifth subtype is insurance set for vehicles.

[0084] In some embodiments, subtypes can be divided according to actual usage requirements, and one insurance can be used as a type. For example, for insurance set up for pets, insurance A can be used as a subtype, and insurance B can be used as another subtype, which is reasonable.

[0085] The first method of determining the degree of matching is introduced below. For the same type, different subtypes correspond to different storage areas. For each type of underwriting calculation method, the target subtype involved in the underwriting calculation method can be determined. The number of target subtypes can be one or more.

[0086] After determining the target subtype, target data corresponding to the target subtype can be obtained from the storage area corresponding to the target subtype, and then the first matching degree between the underwriting calculation method and the target data corresponding to the target subtype can be obtained.

[0087] The second method of determining the matching degree is introduced below. The number of underwriting calculation methods under a type can be one or more. An underwriting calculation method can correspond to one insurance or multiple insurances. An underwriting calculation method can also correspond to one clause in one insurance or multiple clauses in one insurance.

[0088] For an insurance calculation method, the subtype of the first insurance method to which the insurance calculation method belongs can be determined from the correspondence between pre-set candidate keywords and candidate subtypes based on the keywords in the first insurance method to which the insurance calculation method belongs, and the first matching degree between the insurance calculation method and the target data corresponding to the subtype can be obtained.

[0089] The third method for determining the matching degree is introduced below. Figure 4 , Figure 4 This is a flowchart of the screening method of the insurance method based on artificial intelligence provided in the embodiment of the present application. Figure 2 , the following combination Figure 4 The steps shown are Figure 3 Step 102 is shown for illustration, where a coverage calculation method exists using a region.

[0090] In step 1021, for each type of insurance calculation method, if the usage area of ​​the insurance calculation method exceeds the target usage area, multiple copies of data corresponding to the usage area are determined from the correspondence between the pre-set candidate usage areas and candidate data according to the usage area, and the priority of the multiple copies of data is determined.

[0091] In some embodiments, step 1021 is implemented in the following manner: for an insurance calculation method with a usage area, if the usage area of ​​the insurance calculation method exceeds the target usage area, multiple copies of data corresponding to the usage area can be determined based on the usage area using the correspondence between pre-set candidate usage areas and candidate data, and the priority of the multiple copies of data can be determined.

[0092] In some embodiments, the usage area of ​​the underwriting calculation method may be an area based on insurance that uses the underwriting calculation method. Accordingly, the target usage area may be an area based on insurance that has a usage frequency greater than a preset frequency threshold. The candidate data is the data corresponding to the insurance, and multiple copies of the data have different priorities. The description of the data may be equivalently replaced with the above-mentioned description of the target data, which will not be elaborated here.

[0093] For example, the usage area of ​​the underwriting calculation method is an area of ​​insurance 4-insurance 7 based on the use of the underwriting calculation method. Specifically, insurance 4-insurance 7 can be converted into a preset value, and insurance 4-insurance 7 corresponds to 4-7. The target usage area is an area of ​​insurance 4-insurance 6 where the usage frequency is greater than a preset frequency threshold. Accordingly, insurance 4-insurance 6 can be converted into a preset value, and insurance 4-insurance 6 corresponds to 4-6.

[0094] If the usage area of ​​the underwriting calculation method exceeds the target usage area, the data corresponding to the usage area of ​​the underwriting calculation method can be determined from the correspondence between the pre-set candidate usage areas and the candidate data, that is, the data corresponding to insurances 4 to 7 can be determined, and the multiple copies of data are the data corresponding to insurance 4 (one copy of data), the data corresponding to insurance 5 (one copy of data), the data corresponding to insurance 6 (one copy of data), and the data corresponding to insurance 7 (one copy of data).

[0095] In some embodiments, the usage area of ​​the underwriting calculation method can also be the area according to the company that uses the underwriting calculation method. Accordingly, the target usage area can be the area of ​​at least one company belonging to the same category. The candidate data is the data included in the company, and multiple copies of data have priorities.

[0096] For example, the usage area of ​​the underwriting calculation method is the area of ​​Company 1-Company 3 that uses the underwriting calculation method, where Formula 1 and Company 3 are both subsidiaries of Company 2, and the target usage area can be the area of ​​Company 1 and Company 3.

[0097] The use area of ​​the insurance calculation method is larger than the target use area. The data corresponding to the use area of ​​the insurance calculation method can be determined from the correspondence between the preset candidate use areas and the candidate data. That is, the data corresponding to Company 1-Company 3 can be determined. The multiple copies of data are the data corresponding to Company 1 (one copy of data), the data corresponding to Company 2 (one copy of data), and the data corresponding to Company 3 (one copy of data). Through step 1021, the data corresponding to the use area can be accurately determined.

[0098] In step 1022, the data with the highest priority is used as the target data, and the first matching degree between the underwriting calculation method and the target data is obtained.

[0099] In some embodiments, step 1022 can be implemented in the following manner: after determining multiple copies of data corresponding to the usage area, since the multiple copies of data have priorities, the data with the highest priority can be used as the target data, and then the first matching degree between the underwriting calculation method and the target data can be obtained.

[0100] In the case where the area where the underwriting calculation method is used is the area of ​​insurance that uses the underwriting calculation method, the priority of the data is determined based on the frequency of use of the underwriting calculation method and the priority of the insurance. After determining the priority of the data, the data with the highest priority can be used as the target data, and then the first match between the underwriting calculation method and the target data can be obtained.

[0101] In some embodiments, for each piece of data, the frequency of use can be multiplied by the insurance priority to obtain the priority of the data. That is, for each piece of data, the product of the frequency of use using the underwriting calculation method and the insurance priority is determined as the priority of the data.

[0102] In some embodiments, for each piece of data, the frequency of use can be multiplied by the frequency of use weight to obtain a first product, the insurance priority can be multiplied by the priority weight to obtain a second product, and the sum of the first product and the second product is determined as the priority of the data.

[0103] In the case where the use area of ​​the underwriting calculation method is based on the area of ​​the company using the underwriting calculation method, the priority of the data can be determined according to the priority of the company where the data is located, and the priority of the company is preset. In some embodiments, the greater the priority of the formula, the greater the priority of the data. After determining the priority of the data, the data with the highest priority can be used as the target data, and then the first matching degree between the underwriting calculation method and the target data can be obtained. In this way, an accurate first matching degree can be obtained.

[0104] The fourth method of determining the degree of matching is introduced below. In response to a determination instruction including a time range triggered at the terminal, the time range of the data set by the user is obtained, or a pre-set time range is obtained. For each type of underwriting calculation method, a first degree of matching between the underwriting calculation method and the target data belonging to the time range corresponding to the type can be obtained.

[0105] The fifth method for determining the degree of matching is introduced below. The fifth method for determining the degree of matching is based on any one of the first method for determining the degree of matching to the fourth method for determining the degree of matching. After determining the underwriting calculation method and the target data, it can be determined whether the target data includes the data items to be filled in the underwriting calculation method, that is, the filling rate of the data items to be filled in the underwriting calculation method can be filled in by the target data, so that the first degree of matching between the underwriting calculation method and the target data can be obtained. In this way, an accurate first degree of matching can be obtained.

[0106] Step 102 can determine an accurate first matching degree through different methods, and the first matching degree is used for the first screening of the underwriting methods to facilitate improving the efficiency and accuracy of screening the underwriting methods and meet usage requirements.

[0107] Continue to see Figure 3 In step 103, multiple first insurance methods are screened based on the first matching degree to obtain multiple second insurance methods.

[0108] In some embodiments, step 103 can be implemented in the following manner: for each first insurance method, a first insurance method with a first matching degree greater than a preset matching degree threshold can be used as a second insurance method, thereby screening multiple first insurance methods to obtain multiple second insurance methods. For each first insurance method, a first insurance method with a first matching degree less than or equal to the preset matching degree threshold can be marked as an unavailable insurance method.

[0109] The second underwriting method is a first underwriting method for which the first matching degree is greater than a preset matching degree threshold, that is, the second underwriting method is a first underwriting method for which the underwriting calculation method has a first matching degree greater than a target number of the preset matching degree threshold. In this way, an accurate second underwriting method can be obtained.

[0110] In some embodiments, if there is no first underwriting method with a first matching degree greater than a preset matching degree threshold, or if the number of first underwriting methods with a first matching degree greater than the preset matching degree threshold is less than 2, in the case where the underwriting calculation method has a use area, new target data may be selected from multiple data based on priority to obtain a new first matching degree between the underwriting calculation method and the new target data. For example, the data with the second highest priority may be selected as the new target data.

[0111] Furthermore, for each first underwriting method, a first underwriting method with a new first matching degree greater than a preset matching degree threshold can be used as a new second underwriting method, thereby screening multiple first underwriting methods to obtain multiple second underwriting methods.

[0112] In the case where there is no usage area for the insurance calculation method, modification suggestions for the insurance calculation method and / or supplementary suggestions for the target data can be generated, and the modification suggestions and supplementary suggestions can be displayed, so that users can easily learn about the modification suggestions and supplementary suggestions.

[0113] In some embodiments, modification suggestions for the underwriting calculation method can be generated based on the data items to be filled in for which no target data exists, thereby making it convenient for users to adjust the data items to be filled in for which no target data exists.

[0114] In some embodiments, supplementary suggestions for underwriting calculation methods can be generated based on data items to be filled in where target data does not exist. The supplementary suggestions can be used to import replacement data, and the replacement data can be filled in the data items to be filled in. It can also be used for users to input replacement data, which is all reasonable.

[0115] Through step 103, an accurate second insurance method can be obtained, which is equivalent to completing the first screening of insurance methods, so as to improve the efficiency and accuracy of screening insurance methods and meet usage requirements.

[0116] In step 104, the target data is calculated based on the underwriting calculation method of the second underwriting method to obtain an underwriting calculation result, and the second underwriting method is screened based on a preset target threshold and the underwriting calculation result to obtain a screening result.

[0117] In some embodiments, step 104 can be implemented in the following manner: Figure 5 , Figure 5 This is a flowchart of the screening method of the insurance method based on artificial intelligence provided in the embodiment of the present application. Figure 3 , the following combination Figure 5 The steps shown are Figure 3 The step 104 shown is to explain "calculating the target data based on the insurance calculation method of the second insurance method to obtain the insurance calculation result".

[0118] In step 1041, for each second insurance method, a target field corresponding to the label of the second insurance method is determined from the pre-set correspondence between candidate labels and candidate fields.

[0119] The second insurance method has a pre-set label, which is a label that represents the data that needs to be filled in the data item to be filled in. For example, the label can be auto insurance, and the data that needs to be filled in the data item to be filled in is the data involved in the auto insurance scenario.

[0120] The target data includes multiple target sub-data, each of which corresponds to a field, that is, there is a corresponding relationship between the field and the target sub-data. The field is used to represent the meaning of the target sub-data. For example, the field can be age, and the target sub-data is 18. The field can represent the meaning of the target sub-data as age 18.

[0121] For each second insurance method, the target field corresponding to the label of the second insurance method can be determined according to the correspondence between the preset candidate labels and candidate fields, and the target field is used to represent the meaning of the data to be filled in the data item to be filled in. In this way, the target field corresponding to each second insurance method can be accurately determined.

[0122] In step 1042, the target sub-data corresponding to the target field is calculated based on the insurance calculation method of the second insurance method to obtain an insurance calculation result.

[0123] In some embodiments, the target sub-data corresponding to the target field can be determined based on the correspondence between the field and the target sub-data, and then the target sub-data corresponding to the target field can be calculated based on the underwriting calculation method of the second underwriting method to obtain the underwriting calculation result.

[0124] As mentioned above, the underwriting calculation method may include data items to be filled in, weights of the data items to be filled in, and calculation methods between the data items to be filled in. The calculation methods between the data items to be filled in may be addition, multiplication, exponentiation, and other calculation methods.

[0125] In some embodiments, based on the relationship between the target field and the insurance calculation method, the target sub-data corresponding to the target field can be brought into the insurance calculation method for calculation, so that the insurance calculation result can be obtained. In this way, accurate insurance calculation results can be obtained, and the insurance calculation results are used for a second screening of the insurance methods to facilitate improving the efficiency and accuracy of screening the insurance methods and meet usage requirements.

[0126] See also Fig. 6A , Fig. 6A This is a flowchart of the screening method of the insurance method based on artificial intelligence provided in the embodiment of the present application. Figure 4 , the following combination Fig. 6A The steps shown are Figure 3 The step 104 shown is to explain "screening the second underwriting method based on the preset target threshold and the underwriting calculation result to obtain the screening result".

[0127] In step 1403, for each second underwriting method, if the underwriting calculation result of the second underwriting method is greater than the first target threshold, the second underwriting method is used as the target underwriting method.

[0128] In some embodiments, step 1403 can be implemented in the following manner: in order to further improve the accuracy of screening underwriting methods, it can be determined for each second underwriting method whether the underwriting calculation result of the second underwriting method is greater than the first target threshold.

[0129] When the underwriting calculation result of the second underwriting method is less than or equal to the first target threshold, the second underwriting method can be marked as an unavailable underwriting method. When the underwriting calculation result of the second underwriting method is greater than the first target threshold, the second underwriting method is used as the target underwriting method.

[0130] In step 1404, the target underwriting methods are divided into types, each type includes multiple target underwriting methods, and for the multiple target underwriting methods under each type, the average value of the underwriting calculation results of the multiple target underwriting methods is obtained. When the average value is less than the second target threshold, the multiple target underwriting methods are marked as available underwriting methods to obtain the screening results.

[0131] In some embodiments, step 1404 can be implemented in the following manner: after obtaining the target underwriting method, the target underwriting method can be divided according to type, that is, for multiple target underwriting methods, the multiple target underwriting methods can be divided into a first type, a second type, a third type, a fourth type and a fifth type to obtain multiple target underwriting methods of different types.

[0132] In some embodiments, only multiple target underwriting methods of one type may be included. For such a situation, the average value of the underwriting calculation results of the multiple target underwriting methods may be obtained. After obtaining the average value, it may be determined whether the average value is less than a second target threshold value. If the average value is less than the second target threshold value, the multiple target underwriting methods of this type may be marked as available underwriting methods to obtain a screening result.

[0133] If the average value is greater than the second target threshold, then for each target underwriting method, it can be compared whether the underwriting calculation result of the target underwriting method is less than the average value; if the underwriting calculation result of the target underwriting method is less than the average value, then the target underwriting method with an underwriting calculation result less than the average value can be marked as an available underwriting method.

[0134] If the underwriting calculation result of the target underwriting method is greater than or equal to the average value, the target underwriting method with an underwriting calculation result less than the average value can be marked as an unavailable underwriting method. If the underwriting calculation result of the target underwriting method is greater than or equal to the average value, all target underwriting methods of this type can be marked as unavailable underwriting methods.

[0135] That is, the screening result is used to indicate whether the insurance method is available, and the screening result may include available insurance methods and unavailable insurance methods. In this way, accurate screening results can be obtained, which can improve the efficiency and accuracy of screening insurance methods and meet usage requirements.

[0136] In some embodiments, step 104 can also be implemented in the following manner: the underwriting calculation result includes conversion parameters of insurance using the underwriting calculation method, wherein the conversion parameters can be obtained by converting multiple sub-results included in the underwriting calculation result. In some embodiments, the conversion method can be to adjust the sub-results and then use the conversion calculation formula to calculate the conversion parameters.

[0137] After obtaining the underwriting calculation results of the second underwriting method, the second underwriting method can be screened based on the conversion parameter and the pre-set target conversion threshold to obtain the screening result. When the conversion parameter is greater than or equal to the pre-set target conversion threshold, the second underwriting method can be marked as an unavailable underwriting method. When the conversion parameter is less than the pre-set target conversion threshold, the second underwriting method can be marked as an available underwriting method.

[0138] In some embodiments, step 104 can also be implemented by a pre-trained underwriting method screening model. The pre-trained underwriting method screening model may include an input layer, a matching layer, a calculation layer, and a screening layer, wherein the input layer is used to extract the characteristics of each second underwriting method and extract the characteristics of the target data, and the matching layer is used to match the second underwriting method and the target data, thereby determining the target data corresponding to the second underwriting method.

[0139] The calculation layer is used to determine the insurance calculation method of the second insurance method, calculate the target data corresponding to the second insurance method, and obtain the insurance calculation result. The screening layer is used to screen multiple second insurance methods to obtain the screening result.

[0140] In some embodiments, the second insurance method and the target data are input into a pre-trained insurance method screening model, and the insurance method screening model extracts the characteristics of the second insurance method and the characteristics of the target data for each second insurance method, determines the target data corresponding to the second insurance method based on the characteristics of the second insurance method and the characteristics of the target data, and calculates the target data corresponding to the second insurance method based on the insurance calculation method of the second insurance method to obtain an insurance calculation result. The insurance method screening model screens the second insurance method based on the pre-set target threshold and the insurance calculation result to obtain a screening result.

[0141] Combine the following Figure 6B For specific instructions, Figure 6B It is a schematic diagram of the structure of the insurance method screening model provided in the embodiment of the present application. Figure 6B , the second insurance method is input into the pre-trained insurance method screening model 601.

[0142] The characteristics of each second underwriting method are extracted through the input layer 602 in the underwriting method screening model 601, and the characteristics of the target data are extracted. That is, the characteristics of the second underwriting method are extracted for each second underwriting method through the input layer 602 in the underwriting method screening model 601, and the characteristics of the target data are extracted.

[0143] After the characteristics of the second insurance method and the characteristics of the target data are acquired, the target data corresponding to the second insurance method may be determined based on the characteristics of the second insurance method and the characteristics of the target data through the matching layer 603 .

[0144] In some embodiments, the matching layer 603 may be a hidden layer, through which the relationship between the first feature and the second insurance method, the relationship between the second feature and the target data, and the relationship between the first feature and the second feature may be learned. The first feature is the feature of the second insurance method, and the second feature is the feature of the target data.

[0145] The matching layer can output the corresponding relationship between the second underwriting calculation method and the target data corresponding to the second underwriting method, and then for each corresponding relationship, a calculation layer can be used to calculate the underwriting calculation result. The number of calculation layers can be multiple, which can be set according to actual usage requirements. Figure 6B Only computing layer 604, computing layer 605, and computing layer 606 are shown.

[0146] The underwriting calculation results of different second underwriting calculation methods can be obtained through calculation layer 604 , calculation layer 605 and calculation layer 606 , respectively. The underwriting calculation results and multiple second underwriting methods can be input into screening layer 607 .

[0147] The screening layer 607 can screen the second underwriting method based on the preset target threshold and the underwriting calculation result to obtain the screening result. The process of the screening layer 607 obtaining the screening result can refer to the above description of obtaining the screening result, which will not be repeated here. In this way, accurate screening results can be obtained.

[0148] The following describes the training method of the underwriting method screening model. The sample underwriting method and sample data can be input into the underwriting method screening model to be trained, and then the characteristics of the sample underwriting method and the characteristics of the sample data are extracted through the input layer. The matching layer determines the target data corresponding to the sample underwriting method based on the characteristics of the sample underwriting method and the characteristics of the sample data.

[0149] The matching layer may be a hidden layer, through which the relationship between the first sample feature and the sample underwriting method, the relationship between the second sample feature and the sample data, and the relationship between the first sample feature and the second sample feature may be learned. The first sample feature is the feature of the sample underwriting method, and the second sample feature is the feature of the sample data.

[0150] The matching layer can output the corresponding relationship between the second underwriting calculation method and the target data corresponding to the second underwriting method, and then for each corresponding relationship, a calculation layer can be used to calculate the underwriting calculation result. The number of calculation layers can be multiple, which can be set according to actual usage requirements. The underwriting calculation results of different sample underwriting calculation methods can be obtained through the calculation layer, the calculation layer, and the calculation layer, respectively, and the underwriting calculation results and multiple sample underwriting methods can be input into the screening layer.

[0151] The screening layer can screen the sample underwriting methods based on the pre-set target threshold and underwriting calculation results to obtain the predicted screening results, and then update the model parameters of the underwriting method screening model according to the difference between the predicted screening results and the pre-set available underwriting methods.

[0152] In the present application, two screenings for underwriting methods can be achieved. The first screening is based on the match between the underwriting calculation method and the target data. The target data is used for subsequent calculations to obtain the underwriting calculation results. Through the first screening, an underwriting method that better matches the target data can be obtained, thereby improving the accuracy of the screened underwriting methods. The second screening is based on the underwriting calculation results and the target threshold, thereby further improving the accuracy of the screened underwriting methods. Compared with manual screening of underwriting methods, the efficiency and accuracy of screening underwriting methods can be improved, and usage requirements can be met.

[0153] In some embodiments, the first underwriting method also includes an underwriting user screening method, see Figure 7 , Figure 7 This is a flowchart of the screening method of the insurance method based on artificial intelligence provided in the embodiment of the present application. Figure 5 , the following combination Figure 7 The steps shown illustrate the method for screening underwriting users and the method for screening underwriting methods.

[0154] in, Figure 7 The steps shown in Figure 3 Before the step 104 of "screening the second underwriting method based on the preset target threshold and the underwriting calculation result to obtain the screening result", a detailed description is given below.

[0155] In step 105, for each insured user screening method, the user data in the target data is obtained, and the user data is screened based on the insured user screening method to obtain the target user data.

[0156] In some embodiments, step 105 may be implemented in the following manner: in order to determine whether the insured user screening method is available, user data may be obtained for each insured user screening method. In some embodiments, user data under a type may be obtained based on the type corresponding to the insured user screening method. The user data may include the age of the insured, data characterizing the physical condition of the insured, the region where the insured is located, the industry where the insured is located, etc.

[0157] In some embodiments, the underwriting user screening method has a usage area. If the usage area of ​​the user screening method is larger than the target usage area, then according to the usage area of ​​the user screening method, multiple user data corresponding to the usage area of ​​the user screening method are determined from the correspondence between the preset candidate usage areas and the candidate user data, and the priority of the multiple user data is determined. Figure 4 1021 in the description and Figure 4 The description of step 1021 in is equivalently replaced and will not be repeated here.

[0158] After acquiring the user data, the user data may be screened based on the insured user screening method to obtain the target user data. In some embodiments, after determining the priority of the data of multiple users, the user data with a priority greater than a priority threshold may be screened based on the insured user screening method to obtain the target user data.

[0159] In order to facilitate understanding of the insured user screening method provided in the embodiment of the present application, the insured user screening method is illustrated below. For example, the insured user screening method can be implemented by setting the age range of the insured users to screen the users. The insured user screening method can also be implemented by setting the area where the insured users are located to screen the users. The specific settings can be made according to the actual usage.

[0160] In step 106, the target insurance corresponding to the target user data is determined according to the pre-stored correspondence between the candidate user data and the candidate insurance.

[0161] After obtaining the target user data, that is, after obtaining the user data that meets the conditions of the underwriting user screening method, the target insurance corresponding to the target user data can be determined based on the correspondence between the pre-stored candidate user data and the candidate insurance. In this way, the target insurance corresponding to the user who meets the conditions of the underwriting user screening method can be determined.

[0162] Figure 3 In step 104 shown, "based on the preset target threshold and the underwriting calculation result, the second underwriting method is screened to obtain a screening result" can also be achieved in the following manner, which is described in detail below.

[0163] In some embodiments, the second underwriting method can be screened based on a preset target threshold and underwriting calculation results to obtain a first screening result. For details, see Figure 3 The description of step 104 is not repeated here.

[0164] In some embodiments, the similarity between the target insurance and the pre-set insurance is determined, and based on the similarity and the pre-set similarity threshold, the first underwriting method including the underwriting user screening method is screened to obtain a second screening result.

[0165] After the target insurance is determined, the similarity between the target insurance and the pre-set insurance can be determined, wherein for one target insurance, insurance of the same type as the target insurance can be determined from the pre-set insurances, and if there is no insurance of the same type as the target insurance, the type similarity between the target insurance and the pre-set insurance can be calculated. The pre-set insurance is the insurance targeted by the insurance user screening method.

[0166] If there are insurances of the same type as the target insurance, the content similarity between the target insurance and the pre-set insurance can be calculated, that is, for one target insurance, the similarity between the target insurance and the pre-set insurance may include type similarity or content similarity. For multiple target insurances, the similarity between the target insurance and the pre-set insurance may include type similarity and / or content similarity.

[0167] After determining the similarity between the target insurance and the pre-set insurance, the first underwriting method including the underwriting user screening method may be screened based on the similarity and the pre-set similarity threshold to obtain a second screening result.

[0168] In some embodiments, for each target insurance, if the type similarity is greater than the type similarity threshold, the first underwriting method corresponding to the target insurance including the underwriting user screening method may be marked as an available underwriting method. If the type similarity is less than or equal to the type similarity threshold, the first underwriting method corresponding to the target insurance including the underwriting user screening method may be marked as an unavailable underwriting method.

[0169] For each target insurance, if the content similarity is greater than the content similarity threshold, the first underwriting method corresponding to the target insurance including the underwriting user screening method may be marked as an available underwriting method. If the content similarity is less than or equal to the content similarity threshold, the first underwriting method corresponding to the target insurance including the underwriting user screening method may be marked as an unavailable underwriting method. The type similarity threshold is greater than the content similarity threshold.

[0170] That is, the second screening result is used to indicate whether the insurance method is available, and the screening result may include available insurance methods and unavailable insurance methods. In this way, accurate second screening results can be obtained, which can improve the efficiency and accuracy of screening insurance methods and meet usage requirements.

[0171] After obtaining the first screening result and the second screening result, the first screening result and the second screening result can be fused to obtain the screening result. In some embodiments, for each first insurance method, if the first screening result and the second screening result both mark the first insurance method as an available insurance method, then the first insurance method in the screening result is an available insurance method.

[0172] If the first screening result marks the first insurance method as an available insurance method, and the second insurance method determines that the first insurance method is an unavailable insurance method through type similarity, then the first insurance method is an unavailable insurance method in the screening result.

[0173] If the first screening result marks the first insurance method as an available insurance method, and the second insurance method is determined by content similarity that the first insurance method is an unavailable insurance method, then the first insurance method is an available insurance method in the screening result.

[0174] If the first screening result marks the first insurance method as an unavailable insurance method, and the second insurance method is to determine that the first insurance method is an available insurance method through type similarity, then the first insurance method in the screening result is an unavailable insurance method.

[0175] If the first screening result marks the first insurance method as an unavailable insurance method, and the second insurance method is determined by content similarity to be an available insurance method, then the first insurance method is an available insurance method in the screening result. In this way, more accurate screening results can be obtained, that is, the efficiency and accuracy of screening insurance methods can be improved, and usage requirements can be met.

[0176] In some embodiments, the first underwriting method may further include an underwriting order setting method, which is a method for setting a first arrangement order for a plurality of underwriting methods. Figure 3 In step 104 shown, "based on the preset target threshold and the underwriting calculation result, the second underwriting method is screened to obtain a screening result" can also be achieved in the following manner, which is described in detail below.

[0177] Based on the preset target threshold and the underwriting calculation result, the second underwriting method is screened to obtain the first screening result, which includes multiple available underwriting methods. For details, please refer to Figure 3The description of step 104 is not repeated here.

[0178] After obtaining the first screening result, multiple available insurance methods can be sorted according to a preset sorting method to obtain a second arrangement order. In some embodiments, the insurance calculation results can be arranged in descending order to obtain multiple sorted available insurance methods, that is, to obtain the second arrangement order.

[0179] In some embodiments, the available insurance methods may be arranged in descending order according to the frequency of use of the insurance using the available insurance methods, to obtain a plurality of sorted available insurance methods, that is, to obtain a second sorting order. In some embodiments, the available insurance methods may be arranged in descending order according to the priority of the company to which the available insurance methods belong, to obtain a plurality of sorted available insurance methods, that is, to obtain a second sorting order.

[0180] The underwriting order setting method is a method for setting a first arrangement order for multiple underwriting methods, and the first arrangement order may be an order preset by a user. After obtaining the second arrangement order, the similarity between the first arrangement order and the second arrangement order may be calculated.

[0181] In some embodiments, for the first arrangement order and the second arrangement order, the insurance method similarity between the insurance method in the first arrangement order and the insurance method in the second arrangement order can be calculated first. If the insurance method similarity is less than the insurance method similarity threshold, the available insurance method in the second arrangement order that does not belong to the first arrangement order can be adjusted to an unavailable insurance method to obtain a screening result. That is to say, in the screening result, the insurance method included in the insurance order setting method is an available insurance method.

[0182] In some embodiments, if the underwriting method similarity is greater than or equal to the underwriting method similarity threshold, the sequence similarity between the first arrangement order and the second arrangement order can be further calculated. If the sequence similarity is greater than the similarity threshold, the first screening result may not be adjusted, and the first screening result is the screening result.

[0183] If the order similarity is less than or equal to the similarity threshold, the available underwriting methods in the second arrangement order that are different from the first arrangement order can be adjusted to unavailable underwriting methods to obtain the screening results. In other words, in the screening results, the underwriting methods whose order is consistent with the first arrangement order of the underwriting methods in the underwriting order setting method are available underwriting methods.

[0184] In the case where the first underwriting method also includes an underwriting sequence setting method, if the number of available underwriting methods in the screening results is less than the preset number threshold, it means that the first underwriting method corresponding to the underwriting sequence setting method is not available; if the number of available underwriting methods in the screening results is greater than or equal to the preset number threshold, it means that the first underwriting method corresponding to the underwriting sequence setting method is available, and the screening results are updated to obtain updated screening results.

[0185] After obtaining the screening results, in order to further improve the efficiency and accuracy of screening underwriting methods, the available underwriting methods in the screening results can be further screened through manual review, and adjustments can be made based on the unavailable underwriting methods in the screening results, thereby realizing manual screening of underwriting methods.

[0186] In some embodiments, for the case where the underwriting method also includes an underwriting user screening method, if the underwriting user screening method is available, the underwriting user screening method can allow the user to screen the underwriting users, and can also be used to determine the match between the user and the insurance the user intends to purchase, and can also be used to combine user information to determine the insurance that matches the user, thereby realizing insurance recommendations for the user. The specific settings can be made in combination with the actual usage scenario.

[0187] In order to facilitate understanding of the screening method of insurance underwriting methods based on artificial intelligence provided in the embodiment of the present application, the following is combined with Figure 8-11 The figure illustrates an example of the artificial intelligence-based underwriting screening method provided in an embodiment of the present application.

[0188] See also Figure 8 , Figure 8 This is a schematic diagram of the screening method of the underwriting method based on artificial intelligence provided in the embodiment of the present application. Figure 1 ,exist Figure 8 In the example, multiple controls may be displayed, including a filter setting control 801, an underwriting method setting control 802, an underwriting method verification control 803, and an underwriting method filter control 804.

[0189] In response to the setting operation for the filter setting control 801, the target threshold, user authority and time range can be set, wherein the target threshold can include any one or more thresholds involved in the target use area, preset matching threshold, first target threshold, second target threshold, target conversion threshold, etc. For example, the target threshold can be a cost rate.

[0190] User permissions are used to set whether users can create insurance methods, view insurance methods, filter insurance methods, etc. The time range corresponds to the time range of the data set by the user. It can be set according to actual usage needs and is not specifically limited here.

[0191] In response to the setting operation for the underwriting method setting control 802, the underwriting method can be set, which can be specifically used to set the underwriting calculation method, the underwriting user screening method, the underwriting order setting method, etc., among which the underwriting order setting method can be represented in the form of a flowchart.

[0192] In response to the triggering operation of the underwriting mode verification control 803, the following operations may be performed: Figure 3 Steps 101 to 104 are shown, so that the screening results can be displayed. For details, please refer to Figure 3 The description of steps 101 to 104 is not repeated here.

[0193] In response to the trigger operation of the underwriting method verification control 803, the target data can also be imported to facilitate the execution Figure 3 Steps 101 to 104 are shown, so that the screening results can be displayed. For details, please refer to Figure 3 The description of steps 101 to 104 is not repeated here. For example, the underwriting calculation result may include a new cost rate. In response to the triggering operation of the underwriting method screening control 804, the underwriting methods may be screened manually or by the underwriting method screening model.

[0194] In some embodiments, in response to Figure 8 The triggering operation of the underwriting mode verification control 803 shown can display Fig. 9 , see Fig. 9 , Fig. 9 This is a schematic diagram of the screening method of the underwriting method based on artificial intelligence provided in the embodiment of the present application. Figure 2 .

[0195] For example, in Fig. 9 , an underwriting method selection control 901, a priority setting control 902, and a time range selection control 903 are shown. In response to a selection operation on the underwriting method selection control 901, multiple first underwriting methods can be acquired. In response to a setting operation on the priority setting control 902, the priority of the company using the underwriting calculation method in the first underwriting method can be set. In response to a time range selection control 903, the time range corresponding to the target data can be set.

[0196] After setting the priority and / or time frame, you can execute Figure 3 Steps 102 to 104 are shown, so that the screening results can be displayed. For details, please refer to Figure 3 The description of steps 102 to 104 is not repeated here.

[0197] In some embodiments, in order to facilitate the user to obtain the information involved in the screening process, the Fig.10 , see Fig.10 , Fig.10 This is a schematic diagram of the screening method of the underwriting method based on artificial intelligence provided in the embodiment of the present application. Figure 3 .

[0198] exist Fig.10 In the Fig. 9 The time range selection control 903 shown sets the time range 1001, the first underwriting method 1002, the first matching degree 1003 between the underwriting calculation method and the target data corresponding to the type, etc.

[0199] In some embodiments, in response to Fig.10 On the displayed page, users can view the target data corresponding to each first underwriting method according to actual usage needs, and can also view the remaining margin corresponding to the first underwriting method.

[0200] In some embodiments, multiple first underwriting methods can constitute one insurance, or one first underwriting method can correspond to one insurance. The target data and remaining margin corresponding to the insurance can be displayed in the display interface according to the insurance, and the user can view the first underwriting method corresponding to the insurance according to actual usage needs.

[0201] In some embodiments, the insurance calculation results can also be displayed, so that the user can easily know the insurance calculation results. In some embodiments, in response to the triggering operation of the insurance method screening control 804, the available insurance methods in the screening results can be sent to the screening personnel, wherein the screening personnel is based on Figure 8 The filter settings control 801 shown is set.

[0202] See also Fig.11 , Fig.11 This is a schematic diagram of the screening method of the underwriting method based on artificial intelligence provided in the embodiment of the present application. Figure 4 ,exist Fig.11 In the figure, a first insurance method 1101, a type 1102 of the first insurance method 1101, and a screening state 1103 for the first insurance method 1101 are shown. The screening state 1103 may be screening, screening completed, screening result, etc., and may be specifically set according to actual use requirements.

[0203] The following is a description of an exemplary structure of the artificial intelligence-based underwriting screening device 455 provided in the present application as a software module. In some embodiments, Figure 2 As shown, the software modules stored in the screening device 455 of the artificial intelligence-based underwriting method in the memory 450 may include:

[0204] An acquisition module 4551 is used to acquire a plurality of first insurance methods, wherein the plurality of first insurance methods have a plurality of types, and the first insurance method under each type includes an insurance calculation method;

[0205] The acquisition module 4551 is further used to acquire, for each type of insurance calculation method, a first matching degree between the insurance calculation method and the target data corresponding to the type;

[0206] A screening module 4552, configured to screen the plurality of first insurance methods based on the first matching degree to obtain a plurality of second insurance methods;

[0207] The screening module 4552 is also used to calculate the target data based on the underwriting calculation method of the second underwriting method to obtain an underwriting calculation result, and to screen the second underwriting method based on a pre-set target threshold and the underwriting calculation result to obtain a screening result.

[0208] In some embodiments, the insurance calculation method has a usage area; the acquisition module 4551 is also used to, for each type of insurance calculation method, if the usage area of ​​the insurance calculation method is larger than the target usage area, then according to the usage area, from the correspondence between the pre-set candidate usage areas and candidate data, determine multiple copies of data corresponding to the usage area, and determine the priority of the multiple copies of the data; use the data with the highest priority as the target data, and obtain the first degree of match between the insurance calculation method and the target data.

[0209] In some embodiments, the screening module 4552 is also used to input the second insurance method and the target data into a pre-trained insurance method screening model, and extract the characteristics of the second insurance method and the target data for each second insurance method through the insurance method screening model, determine the target data corresponding to the second insurance method based on the characteristics of the second insurance method and the characteristics of the target data, and calculate the target data corresponding to the second insurance method based on the insurance calculation method of the second insurance method to obtain an insurance calculation result; and screen the second insurance method based on a pre-set target threshold and the insurance calculation result through the insurance method screening model to obtain a screening result.

[0210] In some embodiments, there is a pre-set label for the second underwriting method, and the target data includes multiple target sub-data, each of which corresponds to a field; the screening module 4552 is also used to determine, for each of the second underwriting methods, the target field corresponding to the label of the second underwriting method from the correspondence between the pre-set candidate labels and candidate fields; and calculate the target sub-data corresponding to the target field based on the underwriting calculation method of the second underwriting method to obtain an underwriting calculation result.

[0211] In some embodiments, the target threshold includes a first target threshold corresponding to the label of the second underwriting method, and a second target threshold corresponding to the type of the second underwriting method; the screening module 4552 is also used to, for each of the second underwriting methods, use the second underwriting method as the target underwriting method when the underwriting calculation result of the second underwriting method is greater than the first target threshold; divide the target underwriting method according to the type, each type includes multiple target underwriting methods, and for each of the multiple target underwriting methods under the type, obtain the average value of the underwriting calculation results of the multiple target underwriting methods, and when the average value is less than the second target threshold, mark the multiple target underwriting methods as available underwriting methods to obtain a screening result.

[0212] In some embodiments, the first underwriting method also includes an underwriting user screening method; the screening module 4552 is also used to screen the second underwriting method based on a preset target threshold and the underwriting calculation result, and before obtaining the screening result, for each of the underwriting user screening methods, obtain the user data in the target data, and screen the user data based on the underwriting user screening method to obtain the target user data; determine the target insurance corresponding to the target user data according to the correspondence between the pre-stored candidate user data and the candidate insurance; screen the second underwriting method based on the preset target threshold and the underwriting calculation result to obtain a first screening result; determine the similarity between the target insurance and the pre-set insurance, and screen the first underwriting method including the underwriting user screening method based on the similarity and the pre-set similarity threshold to obtain a second screening result; and merge the first screening result and the second screening result to obtain a screening result.

[0213] In some embodiments, the first underwriting method also includes an underwriting order setting method, and the underwriting order setting method is a method for setting a first arrangement order for multiple underwriting methods; the screening module 4552 is also used to screen the second underwriting method based on a preset target threshold and the underwriting calculation result to obtain a first screening result, and the first screening result includes multiple available underwriting methods; sort the multiple available underwriting methods according to a preset sorting method, calculate the sorted multiple available underwriting methods, and the underwriting order setting method includes the similarity between the multiple pre-set underwriting methods arranged in order, and adjust the first screening result based on the similarity to obtain a screening result.

[0214] The embodiment of the present application provides a computer program product, which includes a computer program or a computer executable instruction, and the computer program or the computer executable instruction is stored in a computer-readable storage medium. The processor of the electronic device reads the computer program or the computer executable instruction from the computer-readable storage medium, and the processor executes the computer program or the computer executable instruction, so that the electronic device executes the above-mentioned artificial intelligence-based underwriting method screening method of the embodiment of the present application.

[0215] The present application embodiment provides a computer-readable storage medium, in which computer executable instructions or computer programs are stored. When the computer executable instructions or computer programs are executed by a processor, the processor will be caused to execute the screening method of the underwriting method based on artificial intelligence provided by the present application embodiment, for example, Figure 3 The screening method for artificial intelligence-based underwriting approach is shown.

[0216] In some embodiments, the computer-readable storage medium may be a memory such as RAM, ROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories.

[0217] In some embodiments, computer executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0218] As an example, computer-executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0219] As an example, computer executable instructions or computer programs may be deployed to be executed on one electronic device, or on multiple electronic devices located at one site, or on multiple electronic devices distributed at multiple sites and interconnected by a communication network.

[0220] In the present application, two screenings for underwriting methods can be achieved. The first screening is based on the match between the underwriting calculation method and the target data. The target data is used for subsequent calculations to obtain the underwriting calculation results. Through the first screening, an underwriting method that better matches the target data can be obtained, thereby improving the accuracy of the screened underwriting methods. The second screening is based on the underwriting calculation results and the target threshold, thereby further improving the accuracy of the screened underwriting methods. Compared with manual screening of underwriting methods, the efficiency and accuracy of screening underwriting methods can be improved, and usage requirements can be met.

[0221] The above is only an embodiment of the present application and is not intended to limit the protection scope of the present application. Any modifications, equivalent substitutions and improvements made within the spirit and scope of the present application are included in the protection scope of the present application.

Claims

1. A screening method for underwriting methods based on artificial intelligence, characterized in that: The method comprises: Acquire multiple first insurance methods, wherein the multiple first insurance methods have multiple types, and the first insurance method under each type includes an insurance calculation method; For each of the types of insurance calculation methods, obtaining a first matching degree between the insurance calculation method and the target data corresponding to the type; Screening the plurality of first insurance methods based on the first matching degree to obtain a plurality of second insurance methods; The target data is calculated based on the underwriting calculation method of the second underwriting method to obtain an underwriting calculation result, and the second underwriting method is screened based on a preset target threshold and the underwriting calculation result to obtain a screening result.

2. The method according to claim 1, characterized in that The coverage calculation method described above has a usage area; The obtaining, for each type of insurance calculation method, a first matching degree between the insurance calculation method and target data corresponding to the type includes: For each type of insurance calculation method, if the usage area of ​​the insurance calculation method exceeds the target usage area, then according to the usage area, from the correspondence between the preset candidate usage areas and candidate data, multiple copies of data corresponding to the usage area are determined, and the priorities of the multiple copies of the data are determined; The data with the highest priority is used as the target data, and a first matching degree between the insurance calculation method and the target data is obtained.

3. The method according to claim 1, characterized in that The insurance calculation method based on the second insurance method calculates the target data to obtain an insurance calculation result, and the second insurance method is screened based on a preset target threshold and the insurance calculation result to obtain a screening result, including: Inputting the second insurance method and the target data into a pre-trained insurance method screening model, extracting the characteristics of the second insurance method and the characteristics of the target data for each second insurance method through the insurance method screening model, determining the target data corresponding to the second insurance method based on the characteristics of the second insurance method and the characteristics of the target data, and calculating the target data corresponding to the second insurance method based on the insurance calculation method of the second insurance method to obtain an insurance calculation result; The second underwriting method is screened by the underwriting method screening model based on a preset target threshold and the underwriting calculation result to obtain a screening result.

4. The method according to claim 1, characterized in that: The second underwriting method has a preset label, the target data includes a plurality of target sub-data, and each of the target sub-data corresponds to a field; The insurance calculation method based on the second insurance method calculates the target data to obtain an insurance calculation result, including: For each of the second insurance method, determine the target field corresponding to the label of the second insurance method from the preset correspondence between the candidate labels and the candidate fields; The target sub-data corresponding to the target field is calculated based on the insurance calculation method of the second insurance method to obtain an insurance calculation result.

5. The method according to claim 4, characterized in that The target threshold comprises a first target threshold corresponding to the label of the second underwriting method, and a second target threshold corresponding to the type of the second underwriting method; The second underwriting method is screened based on the preset target threshold and the underwriting calculation result to obtain a screening result, including: For each of the second insurance methods, when the insurance calculation result of the second insurance method is greater than the first target threshold, the second insurance method is used as the target insurance method; The target underwriting method is divided into the types, each type includes multiple target underwriting methods, and for the multiple target underwriting methods under each type, the average value of the underwriting calculation results of the multiple target underwriting methods is obtained. When the average value is less than the second target threshold, the multiple target underwriting methods are marked as available underwriting methods to obtain a screening result.

6. The method according to claim 1, characterized in that The first underwriting method also includes an underwriting user screening method; The second underwriting method is screened based on the preset target threshold and the underwriting calculation result, and before obtaining the screening result, the method further includes: For each of the insured user screening methods, obtaining user data in the target data, and screening the user data based on the insured user screening method to obtain target user data; Determine the target insurance corresponding to the target user data according to the pre-stored correspondence between the candidate user data and the candidate insurance; The second underwriting method is screened based on the preset target threshold and the underwriting calculation result to obtain a screening result, including: Based on the preset target threshold and the underwriting calculation result, the second underwriting method is screened to obtain a first screening result; Determine the similarity between the target insurance and the pre-set insurance, and based on the similarity and the pre-set similarity threshold, screen the first underwriting method including the underwriting user screening method to obtain a second screening result; The first screening result and the second screening result are integrated to obtain a screening result.

7. The method according to claim 1, characterized in that The first underwriting method further includes an underwriting sequence setting method, wherein the underwriting sequence setting method is a method for setting a first arrangement sequence of multiple underwriting methods; The second underwriting method is screened based on the preset target threshold and the underwriting calculation result to obtain a screening result, including: Based on a preset target threshold and the underwriting calculation result, the second underwriting method is screened to obtain a first screening result, wherein the first screening result includes a plurality of available underwriting methods; The plurality of available underwriting methods are sorted according to a preset sorting method to obtain a second sorting order, the similarity between the first sorting order and the second sorting order is calculated, and the first screening result is adjusted based on the similarity to obtain a screening result.

8. An insurance screening device based on artificial intelligence, characterized in that: The device comprises: An acquisition module, used for acquiring a plurality of first insurance methods, wherein the plurality of first insurance methods have a plurality of types, and the first insurance method under each type includes an insurance calculation method; The acquisition module is further used to acquire, for each type of insurance calculation method, a first matching degree between the insurance calculation method and the target data corresponding to the type; A screening module, configured to screen the plurality of first insurance methods based on the first matching degree to obtain a plurality of second insurance methods; The screening module is also used to calculate the target data based on the underwriting calculation method of the second underwriting method to obtain an underwriting calculation result, and to screen the second underwriting method based on a pre-set target threshold and the underwriting calculation result to obtain a screening result.

9. An electronic device, characterized in that: The electronic device comprises: A memory for storing computer executable instructions or computer programs; A processor is used to implement the artificial intelligence-based underwriting method screening method as described in any one of claims 1 to 7 when executing the computer executable instructions or computer programs stored in the memory.

10. A computer-readable storage medium storing computer-executable instructions or a computer program, characterized in that: When the computer executable instructions or computer program are executed by a processor, the screening method for underwriting methods based on artificial intelligence as described in any one of claims 1 to 7 is implemented.

Images