WO2019071956A1 - 核保测试方法、应用服务器及计算机可读存储介质 - Google Patents

核保测试方法、应用服务器及计算机可读存储介质 Download PDF

Info

Publication number
WO2019071956A1
WO2019071956A1 PCT/CN2018/089349 CN2018089349W WO2019071956A1 WO 2019071956 A1 WO2019071956 A1 WO 2019071956A1 CN 2018089349 W CN2018089349 W CN 2018089349W WO 2019071956 A1 WO2019071956 A1 WO 2019071956A1
Authority
WO
WIPO (PCT)
Prior art keywords
underwriting
test
map
parameter
channel
Prior art date
Application number
PCT/CN2018/089349
Other languages
English (en)
French (fr)
Inventor
吴丽
姜堃
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2019071956A1 publication Critical patent/WO2019071956A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/22—Indexing; Data structures therefor; Storage structures
    • G06F16/2282—Tablespace storage structures; Management thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08—Insurance

Definitions

  • the present application relates to the field of communications technologies, and in particular, to a core insurance testing method, an application server, and a computer readable storage medium.
  • insurance bills generally include all aspects such as ordering, underwriting, and charging.
  • underwriting it refers to the insurer's review of the application for insurance, the decision whether to accept the risk of underwriting, and acceptance of underwriting.
  • risk the process of determining the insurance rate.
  • underwriting the underwriting personnel will give different rates according to different risk categories of the subject matter to ensure the quality of the business and ensure the stability of the insurance operation.
  • Underwriting is the core business in the underwriting business, and the underwriting part is the most critical step for insurance companies to control risks and improve the quality of insurance assets.
  • underwriting rules due to the large number of single channels, the underwriting rules are still complicated, and the test cycle of new products is short, resulting in low test efficiency. In this regard, testing may not be completed without increasing efficiency.
  • the present application proposes a nuclear insurance test method and an application server to improve the underwriting accuracy rate of the public liability insurance policy; and, in the premise of ensuring the accuracy rate, the nuclear insurance efficiency is greatly improved, in the face of a large number of public When the liability insurance policy is underwriting, it can also quickly complete the underwriting task and reduce the cost of underwriting.
  • the present application provides an application server, where the application server includes a memory, a processor, and a memory check test program executable on the processor, the underwriting test is stored on the memory.
  • the program implements the following steps when executed by the processor:
  • the present application further provides a core insurance test method, which is applied to an application server, and the method includes:
  • the present application further provides a computer readable storage medium storing a core test program, which can be executed by at least one processor, so that The at least one processor performs the steps of the underwriting test method as described above.
  • the application server, the underwriting test method, and the computer readable storage medium proposed by the present application first acquire a underwriting configuration file, and generate a channel mapping table channel map according to the underwriting configuration file; And inputting an entry parameter to the channel mapping table channel map; again, integrating the entry parameter in the channel mapping table channel map with a policy information table to obtain a parameter list in a Map form; and then acquiring an environment information class And inputting the parameter list and the environment information class to the pre-trained deep learning model; finally, obtaining the underwriting test result output by the deep learning model.
  • the underwriting result is affected by the professional level and experience of the underwriters.
  • 1 is a schematic diagram of an optional hardware architecture of an application server
  • Figure 2 is a block diagram showing the program of the first embodiment of the underwriting test procedure of the present application
  • Figure 3 is a block diagram showing the program of the second embodiment of the underwriting test procedure of the present application.
  • FIG. 4 is a flow chart of a first embodiment of a verification test method of the present application.
  • FIG. 6 is a flow chart of a third embodiment of the underwriting test method of the present application.
  • first, second and the like in the present application are for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. .
  • features defining “first” and “second” may include at least one of the features, either explicitly or implicitly.
  • the technical solutions between the various embodiments may be combined with each other, but must be based on the realization of those skilled in the art, and when the combination of the technical solutions is contradictory or impossible to implement, it should be considered that the combination of the technical solutions does not exist. Nor is it within the scope of protection required by this application.
  • FIG. 1 it is a schematic diagram of an optional hardware architecture of the application server 1.
  • the application server 1 may be a computing device such as a rack server, a blade server, a tower server, or a rack server.
  • the application server 1 may be a stand-alone server or a server cluster composed of multiple servers.
  • the application server 1 may include, but is not limited to, the memory 11, the processor 12, and the network interface 13 being communicably connected to each other through a system bus.
  • the application server 1 connects to the network through the network interface 13 to obtain information.
  • the network may be an intranet, an Internet, a Global System of Mobile communication (GSM), a Wideband Code Division Multiple Access (WCDMA), a 4G network, or a 5G network.
  • Wireless or wired networks such as networks, Bluetooth, Wi-Fi, and call networks.
  • Figure 1 only shows the application server 1 with components 11-13, but it should be understood that not all illustrated components may be implemented, and more or fewer components may be implemented instead.
  • the memory 11 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (eg, SD or DX memory, etc.), and a random access memory (RAM). , static random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disk, optical disk, and the like.
  • the memory 11 may be an internal storage unit of the application server 1, such as a hard disk or memory of the application server 1.
  • the memory 11 may also be an external storage device of the application server 1, such as a plug-in hard disk equipped with the application server 1, a smart memory card (SMC), and a secure digital ( Secure Digital, SD) cards, flash cards, etc.
  • the memory 11 can also include both the internal storage unit of the application server 1 and its external storage device.
  • the memory 11 is generally used to store an operating system installed in the application server 1 and various types of application software, such as program code of the underwriting test program 200. Further, the memory 11 can also be used to temporarily store various types of data that have been output or are to be output.
  • the processor 12 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments.
  • the processor 12 is typically used to control the overall operation of the application server 1, such as performing data interaction or communication related control and processing, and the like.
  • the processor 12 is configured to run program code or process data stored in the memory 11, such as running the underwriting test program 200 and the like.
  • the network interface 13 may comprise a wireless network interface or a wired network interface, which is typically used to establish a communication connection between the application server 1 and other electronic devices.
  • the application server 1 installs and runs a verification test program 200.
  • the application server 1 acquires a underwriting configuration file, and according to the underwriting configuration. a file generation channel mapping table channel map; writing an entry parameter to the channel mapping table channel map; integrating the entry parameter in the channel mapping table channel map with a policy information table to obtain a parameter list in a Map form; An environment information class, and inputting the parameter list and the environment information class to a pre-trained deep learning model; and obtaining a core test result output by the deep learning model.
  • the underwriting result is affected by the professional level and experience of the underwriters.
  • the present application proposes a underwriting test program 200.
  • FIG. 2 it is a program module diagram of the first embodiment of the underwriting test program 200 of the present application.
  • the underwriting test program 200 includes a series of computer program instructions stored in the memory 11, and when the computer program instructions are executed by the processor 12, the underwriting of the embodiments of the present application can be implemented. Test operation.
  • the underwriting test program 200 can be divided into one or more modules based on the particular operations implemented by the various portions of the computer program instructions. For example, in FIG. 2, the underwriting test program 200 can be divided into a first acquisition module 201, a generation module 202, an information integration module 203, a second acquisition module 204, an input module 205, and an output module 206. among them:
  • the first obtaining module 201 is configured to acquire a core protection configuration file.
  • the profile of the underwriting is obtained by the method of the Test Date Proc class build Field Code Name.
  • the configuration file of the underwriting includes a parameter setting rule in the channel map of the channel mapping table, and the channel mapping table can be automatically generated by using these parameter setting rules.
  • the underwriting configuration file further includes a connection attribute of the test environment.
  • the generating module 202 is configured to generate a channel mapping table channel map according to the underwriting configuration file.
  • the information integration module 203 writes an entry parameter to the channel map table, and integrates the entry parameter in the channel map table with the policy information table to obtain a parameter list in the form of a map.
  • the parameter list includes: a combination of one or more of a coverage, a security amount, a historical loss ratio, market environment information, and commercial competition information.
  • the information integration module 203 writes the entry parameter into the channel mapping table channel Map by using a first preset rule.
  • the information integration module 203 also converts the entry parameters into a Map form, for example, by converting the input parameters into a Map form by a Get Date Map() function.
  • the first preset rule is: writing the input parameter into the channel mapping table channel Map by using a Test Save Golden Collar Data For Undw method.
  • the second obtaining module 204 is configured to obtain an environment information class.
  • the second obtaining module 204 acquires the environment information class by using a second preset rule.
  • the second preset rule is: acquiring the environment information class by using EnvConvert().get UWS Context(region code).
  • the environmental information category includes a policy corresponding insurance category.
  • a policy corresponding insurance category For example, major illness insurance, child growth insurance, old-age insurance, etc.
  • the input module 205 inputs the parameter list and the environment information class to a pre-trained deep learning model.
  • the second obtaining module 204 may further return a corresponding UWS database name SID by using a GetDb Sid (region Code) function, and then use the deep learning model to perform data retrieval and deal with.
  • a GetDb Sid region Code
  • the output module 206 acquires the underwriting test result output by the deep learning model.
  • the underwriting test result output by the output module 206 can be displayed on the test client of the mobile terminal.
  • the mobile terminal may be a mobile phone, a smart phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a navigation device, and a car.
  • a mobile device such as a device, and a fixed terminal such as a digital TV, a desktop computer, a notebook, a server, and the like.
  • the first obtaining module 201 of the application server 2 is configured to acquire a core protection configuration file
  • the generating module 202 is configured to generate a channel mapping table channel map according to the underwriting configuration file.
  • the information integration module 203 writes an entry parameter to the channel map table Map, and integrates the entry parameter in the channel map table with the policy information table to obtain a parameter list in the form of a map;
  • a second obtaining module 204 configured to acquire an environment information class; the input module 205, input the parameter list and the environment information class into a pre-trained deep learning model; and the output module 206 acquires the depth Learn the results of the underwriting test output from the model.
  • the underwriting result is affected by the professional level and experience of the underwriters. It can also improve the accuracy of underwriting of public liability insurance policies; and, under the premise of ensuring accuracy, the efficiency of underwriting can be greatly improved, and in the face of a large number of public liability insurance policies, the underwriting can be completed quickly.
  • the task reduces the cost of underwriting, and also ensures that new products are delivered normally.
  • the underwriting test program 200 proposed by the present application first acquires a underwriting configuration file, and generates a channel mapping table channel map according to the underwriting configuration file; secondly, the channel mapping table is The channel map is written into the entry parameter; again, the entry parameter in the channel map table is integrated with the policy information table to obtain a parameter list in the form of a map; then, the environment information class is obtained, and the parameter list is obtained. And inputting the environmental information class to the pre-trained deep learning model; finally, obtaining the underwriting test result output by the deep learning model.
  • the underwriting result is affected by the professional level and experience of the underwriters.
  • the underwriting test program 200 further includes a calculation processing module 207, wherein:
  • the calculation processing module 207 is configured to:
  • the preset value is set by the tester according to the required degree of test accuracy.
  • the underwriting test program 200 proposed by the present application can establish a pre-trained deep learning model, thereby avoiding the problem that the underwriting result is affected by the professional level and experience of the underwriters, and reducing the artificial input.
  • the error rate increases the accuracy of the underwriting of the public liability insurance policy; and, under the premise of ensuring the accuracy rate, the underwriting efficiency is greatly improved, and it can also be quickly faced in the face of a large number of public liability insurance policy underwriting tasks. Completing the underwriting task, reducing the cost of underwriting, and ensuring that new products are delivered normally.
  • the present application also proposes a nuclear insurance test method.
  • FIG. 4 it is a schematic diagram of an implementation process of the first embodiment of the underwriting test method of the present application.
  • the order of execution of the steps in the flowchart shown in FIG. 4 may be changed according to different requirements, and some steps may be omitted.
  • Step S401 obtaining a underwriting configuration file.
  • the profile of the underwriting is obtained by the method of the Test Date Proc class build Field Code Name.
  • the configuration file of the underwriting includes a parameter setting rule in the channel map of the channel mapping table, and the channel mapping table can be automatically generated by using these parameter setting rules.
  • the underwriting configuration file further includes a connection attribute of the test environment.
  • Step S402 generating a channel mapping table channel map according to the underwriting configuration file.
  • Step S403 writing an entry parameter to the channel mapping table channel Map.
  • Step S404 integrating the entry parameter in the channel map table and the policy information table to obtain a parameter list in the form of a map.
  • the parameter list includes: a combination of one or more of a coverage, a security amount, a historical loss ratio, market environment information, and commercial competition information.
  • Step S405 acquiring an environmental information class.
  • the application server 1 acquires the environment information class by using EnvConvert().get UWS Context(region code).
  • the environmental information category includes a policy corresponding insurance category.
  • a policy corresponding insurance category For example, major illness insurance, child growth insurance, old-age insurance, etc.
  • Step S406 inputting the parameter list and the environment information class into a pre-trained deep learning model.
  • the step of acquiring the deep learning model will be detailed in the second embodiment (FIG. 6) of the underwriting test method of the present application.
  • the application server 1 may further return the corresponding UWS database name SID through the GetDb Sid (region Code) function, and then perform data retrieval and processing by the deep learning model.
  • Step S407 acquiring a verification test result output by the deep learning model.
  • the output of the underwriting test result can be displayed on the test client of the mobile terminal.
  • the mobile terminal may be a mobile phone, a smart phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a navigation device, and a car.
  • a mobile device such as a device, and a fixed terminal such as a digital TV, a desktop computer, a notebook, a server, and the like.
  • the underwriting test method proposed by the present application firstly acquires a underwriting configuration file, and generates a channel mapping table channel map according to the underwriting configuration file; secondly, the channel mapping table channel Map Write the entry parameter; again, integrate the entry parameter in the channel map table with the policy information table to obtain a parameter list in the form of a map; then, obtain an environment information class, and list the parameter and the parameter The environmental information class is input to the pre-trained deep learning model; finally, the underwriting test result output by the deep learning model is obtained.
  • the underwriting result is affected by the professional level and experience of the underwriters.
  • the step of writing an entry parameter to the channel mapping table channel Map includes:
  • Step S501 the entry parameter is written into the channel mapping table channel Map by using a preset rule.
  • the preset rule is: writing the input parameter into the channel mapping table channel Map by using a Test Save Golden Collar Data For Undw method.
  • Step S502 converting the entry parameter into a Map form.
  • the input parameter is converted to a Map form by the Get Date Map() function.
  • the underwriting test method proposed by the present application can write the entry parameter to the channel map of the channel mapping table, thereby avoiding the problem that the underwriting result is affected by the professional level and experience of the underwriters. , reducing the error rate of human input, improving the accuracy of the underwriting of public liability insurance policies; and, under the premise of ensuring accuracy, greatly improving the efficiency of underwriting, in the face of a large number of public liability insurance policy underwriting tasks At the same time, the underwriting task can be completed quickly, the cost of underwriting is reduced, and the new product is guaranteed to be delivered normally.
  • FIG. 6 it is a schematic diagram of the implementation process of the second embodiment of the underwriting test method of the present application.
  • the order of execution of the steps in the flowchart shown in FIG. 6 may be changed according to different requirements, and some steps may be omitted.
  • the step of acquiring the deep learning model specifically includes:
  • Step S601 establishing a underwriting test algorithm based on the underwriting test step.
  • Step S602 selecting a plurality of accurately measured test sample data, and running the underwriting test algorithm.
  • Step S603 comparing the result calculated by the underwriting test algorithm with the sample result, and obtaining a relative error.
  • Step S604 adjusting the underwriting test algorithm parameters to minimize the relative error.
  • the underwriting test algorithm parameters are preset by the developer.
  • Step S605 when the relative error is less than a preset value, determining that the underwriting test algorithm is the deep learning model.
  • the preset value is set by the tester according to the required degree of test accuracy.
  • the underwriting test method proposed by the present application can establish a pre-trained deep learning model, which can improve the underwriting accuracy rate of the public liability insurance policy; and, under the premise of ensuring the accuracy rate, greatly improving The efficiency of underwriting has reduced the cost of underwriting.
  • the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases, the former is better.
  • Implementation Based on such understanding, the technical solution of the present application, which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk,
  • the optical disc includes a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • General Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Technology Law (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

本申请公开了一种核保测试方法，所述方法包括：获取核保配置文件，并根据所述核保配置文件生成通道映射表channel Map；对所述通道映射表channel Map写入入口参数；将所述通道映射表channel Map中的所述入口参数与保单信息表格进行整合以得到Map形式的参数列表；获取环境信息类；将所述参数列表和所述环境信息类输入到预先训练好的深度学习模型；及获取所述深度学习模型输出的核保测试结果。本申请还提供一种应用服务器。本申请提供的应用服务器及核保测试方法提高了公众责任险保单的核保准确率；并且，在保证准确率的前提下大大提升了核保效率，在面对大量的公众责任险保单核保任务时，也能快速完成核保任务，降低了核保成本。

Description

核保测试方法、应用服务器及计算机可读存储介质
优先权申明
本申请要求于2017年10月12日提交中国专利局、申请号为201710948977.X，发明名称为“核保测试方法、应用服务器及计算机可读存储介质”的中国专利申请的优先权，其内容全部通过引用结合在本申请中。
技术领域
本申请涉及通信技术领域，尤其涉及一种核保测试方法、应用服务器及计算机可读存储介质。
背景技术
在金融保险领域，保险出单一般都包括录单、核保、收费等各个环节，针对保险核保，其是指保险人对投保申请进行审核，决定是否接受承保这一风险，并在接受承保风险的情况下，确定保险费率的过程。在核保过程中，核保人员会按标的物的不同风险类别给予不同的费率，保证业务质量，保证保险经营的稳定性。核保是承保业务中的核心业务，而承保部分又是保险公司控制风险、提高保险资产质量最为关键的一个步骤。另外在核保测试过程中，由于出单渠道多，核保规则多还复杂，且新产品测试周期短，导致测试效率低下。对此，若不提高效率则可能无法完成测试。
发明内容
有鉴于此，本申请提出一种核保测试方法及应用服务器，提高公众责任险保单的核保准确率；并且，在保证准确率的前提下大大提升了核保效率，在面对大量的公众责任险保单核保任务时，也能快速完成核保任务，降低了核保成本。
首先，为实现上述目的，本申请提出一种应用服务器，所述应用服务器包括存储器、处理器，所述存储器上存储有可在所述处理器上运行的核保测试程序，所述核保测试程序被所述处理器执行时实现如下步骤：
获取核保配置文件，并根据所述核保配置文件生成通道映射表channel Map；
对所述通道映射表channel Map写入入口参数；
将所述通道映射表channel Map中的所述入口参数与保单信息表格进行整合以得到Map形式的参数列表；
获取环境信息类；
将所述参数列表和所述环境信息类输入到预先训练好的深度学习模型；及
获取所述深度学习模型输出的核保测试结果。
此外，为实现上述目的，本申请还提供一种核保测试方法，该方法应用于应用服务器，所述方法包括：
获取核保配置文件，并根据所述核保配置文件生成通道映射表channel Map；
对所述通道映射表channel Map写入入口参数；
将所述通道映射表channel Map中的所述入口参数与保单信息表格进行整合以得到Map形式的参数列表；
获取环境信息类；
将所述参数列表和所述环境信息类输入到预先训练好的深度学习模型；及
获取所述深度学习模型输出的核保测试结果。
进一步地，为实现上述目的，本申请还提供一种计算机可读存储介质，所述计算机可读存储介质存储有核保测试程序，所述核保测试程序可被至少一个处理器执行，以使所述至少一个处理器执行如上述的核保测试方法的步 骤。
相较于现有技术，本申请所提出的应用服务器、核保测试方法及计算机可读存储介质，首先，获取核保配置文件，并根据所述核保配置文件生成通道映射表channel Map；其次，对所述通道映射表channel Map写入入口参数；再次，将所述通道映射表channel Map中的所述入口参数与保单信息表格进行整合以得到Map形式的参数列表；然后，获取环境信息类，并将所述参数列表和所述环境信息类输入到预先训练好的深度学习模型；最后，获取所述深度学习模型输出的核保测试结果。这样，既可以避免现有技术中在核保结果受核保人员的专业水平以及从业经验影响的弊端。又能够提高公众责任险保单的核保准确率；并且，在保证准确率的前提下大大提升了核保效率，在面对大量的公众责任险保单核保任务时，也能快速完成核保任务，降低了核保成本，同时也保证了新产品正常下发。
附图说明
图1是应用服务器一可选的硬件架构的示意图；
图2是本申请核保测试程序第一实施例的程序模块图；
图3是本申请核保测试程序第二实施例的程序模块图；
图4为本申请核保测试方法第一实施例的流程图；
图5为本申请核保测试方法第二实施例的流程图；
图6为本申请核保测试方法第三实施例的流程图。
附图标记：
应用服务器 1
存储器 11
处理器 12
网络接口 13
核保测试程序 200
第一获取模块 201
生成模块 202
信息整合模块 203
第二获取模块 204
输入模块 205
输出模块 206
计算处理模块 207
本申请目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本申请，并不用于限定本申请。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
需要说明的是，在本申请中涉及“第一”、“第二”等的描述仅用于描述目的，而不能理解为指示或暗示其相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。另外，各个实施例之间的技术方案可以相互结合，但是必须是以本领域普通技术人员能够实现为基础，当技术方案的结合出现相互矛盾或无法实现时应当认为这种技术方案的结合不存在，也不在本申请要求的保护范围之内。
参阅图1所示，是应用服务器1一可选的硬件架构的示意图。
所述应用服务器1可以是机架式服务器、刀片式服务器、塔式服务器或机柜式服务器等计算设备，该应用服务器1可以是独立的服务器，也可以是多个服务器所组成的服务器集群。
本实施例中，所述应用服务器1可包括，但不仅限于，可通过系统总线相互通信连接存储器11、处理器12、网络接口13。
所述应用服务器1通过网络接口13连接网络，获取资讯。所述网络可以是企业内部网(Intranet)、互联网(Internet)、全球移动通讯系统(Global System of Mobile communication，GSM)、宽带码分多址(Wideband Code Division Multiple Access，WCDMA)、4G网络、5G网络、蓝牙(Bluetooth)、Wi-Fi、通话网络等无线或有线网络。
需要指出的是，图1仅示出了具有组件11-13的应用服务器1，但是应理解的是，并不要求实施所有示出的组件，可以替代的实施更多或者更少的组件。
其中，所述存储器11至少包括一种类型的可读存储介质，所述可读存储介质包括闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘等。在一些实施例中，所述存储器11可以是所述应用服务器1的内部存储单元，例如该应用服务器1的硬盘或内存。在另一些实施例中，所述存储器11也可以是所述应用服务器1的外部存储设备，例如该应用服务器1配备的插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)等。当然，所述存储器11还可以既包括所述应用服务器1的内部存储单元也包括其外部存储设备。本实施例中，所述存储器11通常用于存储安装于所述应用服务器1的操作系 统和各类应用软件，例如所述核保测试程序200的程序代码等。此外，所述存储器11还可以用于暂时地存储已经输出或者将要输出的各类数据。
所述处理器12在一些实施例中可以是中央处理器(Central Processing Unit，CPU)、控制器、微控制器、微处理器、或其他数据处理芯片。该处理器12通常用于控制所述应用服务器1的总体操作，例如执行数据交互或者通信相关的控制和处理等。本实施例中，所述处理器12用于运行所述存储器11中存储的程序代码或者处理数据，例如运行所述的核保测试程序200等。
所述网络接口13可包括无线网络接口或有线网络接口，该网络接口13通常用于在所述应用服务器1与其他电子设备之间建立通信连接。
本实施例中，所述应用服务器1内安装并运行有核保测试程序200，当所述核保测试程序200运行时，所述应用服务器1获取核保配置文件，并根据所述核保配置文件生成通道映射表channel Map；对所述通道映射表channel Map写入入口参数；将所述通道映射表channel Map中的所述入口参数与保单信息表格进行整合以得到Map形式的参数列表；获取环境信息类，并将所述参数列表和所述环境信息类输入到预先训练好的深度学习模型；获取所述深度学习模型输出的核保测试结果。这样，既可以避免现有技术中在核保结果受核保人员的专业水平以及从业经验影响的弊端。又能够提高公众责任险保单的核保准确率；并且，在保证准确率的前提下大大提升了核保效率，在面对大量的公众责任险保单核保任务时，也能快速完成核保任务，降低了核保成本，同时也保证了新产品正常下发。
至此，己经详细介绍了本申请各个实施例的应用环境和相关设备的硬件结构和功能。下面，将基于上述应用环境和相关设备，提出本申请的各个实施例。
首先，本申请提出一种核保测试程序200。
参阅图2所示，是本申请核保测试程序200第一实施例的程序模块图。
本实施例中，所述的核保测试程序200包括一系列的存储于存储器11上的计算机程序指令，当该计算机程序指令被处理器12执行时，可以实现本申请各实施例的核保的测试操作。在一些实施例中，基于该计算机程序指令各部分所实现的特定的操作，所述核保测试程序200可以被划分为一个或多个模块。例如，在图2中，所述的核保测试程序200可以被分割成第一获取模块201、生成模块202、信息整合模块203、第二获取模块204、输入模块205、及输出模块206。其中：
所述第一获取模块201，用于获取核保配置文件。
具体地，所述核保的配置文件通过Test Date Proc类build Field Code Name的方法获取。所述核保的配置文件包括所述通道映射表channel Map中参数设定规则，可以通过这些参数设定规则自动生成通道映射表。
进一步地，所述核保的配置文件还包括测试环境的连接属性。
所述生成模块202，用于根据所述核保配置文件生成通道映射表channel Map。
所述信息整合模块203，对所述通道映射表channel Map写入入口参数，并将所述通道映射表channel Map中的所述入口参数与保单信息表格进行整合以得到Map形式的参数列表。
本实施例中，所述参数列表包括：承保范围、保额、历史赔付率、市场环境信息和商业竞争信息中一种或多种的组合。
具体地，所述信息整合模块203通过第一预设规则把所述入口参数写入所述通道映射表channel Map中。所述信息整合模块203还将所述入口参数转变成Map形式，例如，通过Get Date Map()函数把所述入参转变成Map形式。
本实施例中，所述第一预设规则为：通过Test Save Golden Collar Data For Undw方法把所述入参写入所述通道映射表channel Map中。
所述第二获取模块204，用于获取环境信息类。
具体地，所述第二获取模块204通过第二预设规则获取所述环境信息类。
本实施例中，所述第二预设规则为：通过EnvConvert().get UWS Context(region code)获取所述环境信息类。
另外，所述环境信息类包括保单对应险种类别。例如，重大疾病险，儿童成长险，养老险等等。
所述输入模块205，将所述参数列表和所述环境信息类输入到预先训练好的深度学习模型。
在本实施方式中，获取环境信息类之后，所述第二获取模块204还可以通过GetDb Sid(region Code)函数返回对应的UWS数据库名称SID，进而供所述深度学习模型进行数据的调取和处理。
所述输出模块206，获取所述深度学习模型输出的核保测试结果。
具体地，所述输出模块206输出的核保测试结果可以在移动终端的测试客户端进行显示。本实施例中，所述移动终端可以是移动电话、智能电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、导航装置、车载装置等等的可移动设备，以及诸如数字TV、台式计算机、笔记本、服务器等等的固定终端。
从上文可知，所述应用服务器2的所述第一获取模块201，用于获取核保配置文件；所述生成模块202，用于根据所述核保配置文件生成通道映射表channel Map；所述信息整合模块203，对所述通道映射表channel Map写入入口参数；并将所述通道映射表channel Map中的所述入口参数与保单信息表格进行整合以得到Map形式的参数列表；所述第二获取模块204，用于获取环境信息类；所述输入模块205，将所述参数列表和所述环境信息类输入到预先训练好的深度学习模型；所述输出模块206，获取所述深度学习模型输出的核保测试结果。这样，既可以避免现有技术中在核保结果受核保人员的专业水平以及从业经验影响的弊端。又能够提高公众责任险保单的核保准确率；并且，在保证准确率的前提下大大提升了核保效率，在面对大量的公众责任险 保单核保任务时，也能快速完成核保任务，降低了核保成本，同时也保证了新产品正常下发。
通过上述程序模块201-206，本申请所提出的核保测试程序200，首先，获取核保配置文件，并根据所述核保配置文件生成通道映射表channel Map；其次，对所述通道映射表channel Map写入入口参数；再次，将所述通道映射表channel Map中的所述入口参数与保单信息表格进行整合以得到Map形式的参数列表；然后，获取环境信息类，并将所述参数列表和所述环境信息类输入到预先训练好的深度学习模型；最后，获取所述深度学习模型输出的核保测试结果。这样，既可以避免现有技术中在核保结果受核保人员的专业水平以及从业经验影响的弊端。又能够提高公众责任险保单的核保准确率；并且，在保证准确率的前提下大大提升了核保效率，在面对大量的公众责任险保单核保任务时，也能快速完成核保任务，降低了核保成本，同时也保证了新产品正常下发。
进一步地，基于本申请核保测试程序200的上述第一实施例，提出本申请的第二实施例(如图3所示)。本实施例中，所述核保测试程序200还包括计算处理模块207，其中：
所述计算处理模块207用于：
基于核保测试步骤建立核保测试算法；挑选多个测算准确的测试样本数据，运行所述核保测试算法；根据所述核保测试算法计算的结果与样本结果进行比对，获取相对误差；调整所述核保测试算法参数以最小化所述相对误差；及当所述相对误差小于预设值时，确定所述核保测试算法为所述深度学习模型。
本实施例中，所述预设值由测试人员根据所需要的测试精确程度进行自行设定。
通过上述程序模块207，本申请所提出的核保测试程序200可以建立预先训练好的深度学习模型，这样避免了核保结果受核保人员的专业水平以及从业经验影响的问题，减少了人为输入的出错率，提高了公众责任险保单的核保准确率；并且，在保证准确率的前提下大大提升了核保效率，在面对大量的公众责任险保单核保任务时，也能快速完成核保任务，降低了核保成本，同时也保证了新产品正常下发。
此外，本申请还提出一种核保测试方法。
参阅图4所示，是本申请核保测试方法第一实施例的实施流程示意图。在本实施例中，根据不同的需求，图4所示的流程图中的步骤的执行顺序可以改变，某些步骤可以省略。
步骤S401，获取核保配置文件。
具体地，所述核保的配置文件通过Test Date Proc类build Field Code Name的方法获取。所述核保的配置文件包括所述通道映射表channel Map中参数设定规则，可以通过这些参数设定规则自动生成通道映射表。
进一步地，所述核保的配置文件还包括测试环境的连接属性。
步骤S402，根据所述核保配置文件生成通道映射表channel Map。
步骤S403，对所述通道映射表channel Map写入入口参数。
所述对所述通道映射表channel Map写入入口参数的步骤将在本申请核保测试方法第二实施例(图6)中详述。
步骤S404，将所述通道映射表channel Map中的所述入口参数与保单信息表格进行整合以得到Map形式的参数列表。
本实施例中，所述参数列表包括：承保范围、保额、历史赔付率、市场环境信息和商业竞争信息中一种或多种的组合。
步骤S405，获取环境信息类。具体地，所述应用服务器1通过EnvConvert().get UWS Context(region code)获取所述环境信息类。
另外，所述环境信息类包括保单对应险种类别。例如，重大疾病险，儿童成长险，养老险等等。
步骤S406，将所述参数列表和所述环境信息类输入到预先训练好的深度学习模型。
其中，获取所述深度学习模型的步骤将在本申请核保测试方法第二实施例(图6)中详述。
在本实施方式中，获取环境信息类之后，所述应用服务器1还可以通过GetDb Sid(region Code)函数返回对应的UWS数据库名称SID，进而供所述深度学习模型进行数据的调取和处理。
步骤S407，获取所述深度学习模型输出的核保测试结果。具体地，输出的核保测试结果可以在移动终端的测试客户端进行显示。本实施例中，所述移动终端可以是移动电话、智能电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、导航装置、车载装置等等的可移动设备，以及诸如数字TV、台式计算机、笔记本、服务器等等的固定终端。
通过上述步骤S401-407，本申请所提出的核保测试方法，首先，获取核保配置文件，并根据所述核保配置文件生成通道映射表channel Map；其次，对所述通道映射表channel Map写入入口参数；再次，将所述通道映射表channel Map中的所述入口参数与保单信息表格进行整合以得到Map形式的参数列表；然后，获取环境信息类，并将所述参数列表和所述环境信息类输入到预先训练好的深度学习模型；最后，获取所述深度学习模型输出的核保测试结果。这样，既可以避免现有技术中在核保结果受核保人员的专业水平以及从业经验影响的弊端。又能够提高公众责任险保单的核保准确率；并且，在保证准确率的前提下大大提升了核保效率，在面对大量的公众责任险保单核保任务时，也能快速完成核保任务，降低了核保成本，同时也保证了新产 品正常下发。
基于本申请核保测试方法第一实施例，提出本申请核保测试方法第二实施例。
参阅图5所示，是本申请基于核保测试方法第二实施例的实施流程示意图。在本实施例中，所述对所述通道映射表channel Map写入入口参数的步骤，包括：
步骤S501，通过预设规则把所述入口参数写入所述通道映射表channel Map中。本实施例中，所述预设规则为：通过Test Save Golden Collar Data For Undw方法把所述入参写入所述通道映射表channel Map中。
步骤S502，将所述入口参数转变成Map形式。例如，通过Get Date Map()函数把所述入参转变成Map形式。
通过上述步骤S501-502，本申请所提出的核保测试方法，可以对所述通道映射表channel Map写入入口参数，这样避免了核保结果受核保人员的专业水平以及从业经验影响的问题，减少了人为输入的出错率，提高了公众责任险保单的核保准确率；并且，在保证准确率的前提下大大提升了核保效率，在面对大量的公众责任险保单核保任务时，也能快速完成核保任务，降低了核保成本，同时也保证了新产品正常下发。
基于本申请核保测试方法第一及第二实施例，提出本申请核保测试方法第三实施例。
参阅图6所示，是本申请核保测试方法第二实施例的实施流程示意图。在本实施例中，根据不同的需求，图6所示的流程图中的步骤的执行顺序可以改变，某些步骤可以省略。在本实施例中，所述获取所述深度学习模型的步骤，具体包括：
步骤S601，基于核保测试步骤建立核保测试算法。
步骤S602，挑选多个测算准确的测试样本数据，运行所述核保测试算法。
步骤S603，根据所述核保测试算法计算的结果与样本结果进行比对，获取相对误差。
步骤S604，调整所述核保测试算法参数以最小化所述相对误差。所述核保测试算法参数由开发人员预先设置。
步骤S605，当所述相对误差小于预设值时，确定所述核保测试算法为所述深度学习模型。本实施例中，所述预设值由测试人员根据所需要的测试精确程度进行自行设定。
通过上述步骤S601-605，本申请所提出的核保测试方法，可以建立预先训练好的深度学习模型，能够提高公众责任险保单的核保准确率；并且，在保证准确率的前提下大大提升了核保效率，降低了核保成本。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种核保测试方法，应用于应用服务器，其特征在于，所述方法包括：
    获取核保配置文件，并根据所述核保配置文件生成通道映射表channel Map；
    对所述通道映射表channel Map写入入口参数；
    将所述通道映射表channel Map中的所述入口参数与保单信息表格进行整合以得到Map形式的参数列表；
    获取环境信息类；
    将所述参数列表和所述环境信息类输入到预先训练好的深度学习模型；及
    获取所述深度学习模型输出的核保测试结果。
  2. 如权利要求1所述的核保测试方法，其特征在于，所述对所述通道映射表channel Map写入入口参数的步骤，包括：
    通过第一预设规则把所述入口参数写入所述通道映射表channel Map中。
  3. 如权利要求1所述的核保测试方法，其特征在于，所述对所述通道映射表channel Map写入入口参数的步骤，还包括：
    将所述入口参数转变成Map形式。
  4. 如权利要求1所述的核保测试方法，其特征在于，所述获取环境信息的步骤，包括：
    通过第二预设规则获取所述环境信息类，所述环境信息类包括保单对应险种类别。
  5. 如权利要求1所述的核保测试方法，其特征在于，获取所述深度学习模型的步骤，包括：
    基于核保测试步骤建立核保测试算法；
    挑选多个测算准确的测试样本数据，运行所述核保测试算法；
    根据所述核保测试算法计算的结果与样本结果进行比对，获取相对误差；
    调整所述核保测试算法参数以最小化所述相对误差；及
    当所述相对误差小于预设值时，确定所述核保测试算法为所述深度学习模型。
  6. 如权利要求1所述的核保测试方法，其特征在于，所述核保配置文件包括所述通道映射表的参数设定规则以及测试环境的连接属性。
  7. 如权利要求1所述的核保测试方法，其特征在于，所述参数列表包括承保范围、保额、历史赔付率、市场环境信息和商业竞争信息中一种或多种的组合。
  8. 一种应用服务器，其特征在于，所述应用服务器包括存储器、处理器，所述存储器上存储有可在所述处理器上运行的核保测试程序，所述核保测试程序被所述处理器执行时实现如下步骤：
    获取核保配置文件，并根据所述核保配置文件生成通道映射表channel Map；
    对所述通道映射表channel Map写入入口参数；
    将所述通道映射表channel Map中的所述入口参数与保单信息表格进行整合以得到Map形式的参数列表；
    获取环境信息类；
    将所述参数列表和所述环境信息类输入到预先训练好的深度学习模型；及
    获取所述深度学习模型输出的核保测试结果。
  9. 如权利要求8所述的应用服务器，其特征在于，所述对所述通道映射表channel Map写入入口参数的步骤，包括：
    通过第一预设规则把所述入口参数写入所述通道映射表channel Map中。
  10. 如权利要求8所述的应用服务器，其特征在于，所述对所述通道映射表channel Map写入入口参数的步骤，还包括：
    将所述入口参数转变成Map形式。
  11. 如权利要求8所述的应用服务器，其特征在于，所述获取环境信息的步骤，包括：
    通过第二预设规则获取所述环境信息类，所述环境信息类包括保单对应险种类别。
  12. 如权利要求8所述的应用服务器，其特征在于，获取所述深度学习模型的步骤，包括：
    基于核保测试步骤建立核保测试算法；
    挑选多个测算准确的测试样本数据，运行所述核保测试算法；
    根据所述核保测试算法计算的结果与样本结果进行比对，获取相对误差；
    调整所述核保测试算法参数以最小化所述相对误差；及
    当所述相对误差小于预设值时，确定所述核保测试算法为所述深度学习模型。
  13. 如权利要求8所述的应用服务器，其特征在于，所述核保配置文件包括所述通道映射表的参数设定规则以及测试环境的连接属性。
  14. 如权利要求8所述的应用服务器，其特征在于，所述参数列表包括承保范围、保额、历史赔付率、市场环境信息和商业竞争信息中一种或多种的组合。
  15. 一种计算机可读存储介质，所述计算机可读存储介质存储有核保测试程序，所述核保测试程序可被至少一个处理器执行，以使所述至少一个处理器执行如下步骤：
    获取核保配置文件，并根据所述核保配置文件生成通道映射表channel Map；
    对所述通道映射表channel Map写入入口参数；
    将所述通道映射表channel Map中的所述入口参数与保单信息表格进行整合以得到Map形式的参数列表；
    获取环境信息类；
    将所述参数列表和所述环境信息类输入到预先训练好的深度学习模型；及
    获取所述深度学习模型输出的核保测试结果。
  16. 如权利要求15所述的计算机可读存储介质，其特征在于，所述对所述通道映射表channel Map写入入口参数的步骤，包括：
    通过第一预设规则把所述入口参数写入所述通道映射表channel Map中；及
    将所述入口参数转变成Map形式。
  17. 如权利要求15所述的计算机可读存储介质，其特征在于，所述获取环境信息的步骤，包括：
    通过第二预设规则获取所述环境信息类，所述环境信息类包括保单对应险种类别。
  18. 如权利要求15所述的计算机可读存储介质，其特征在于，获取所述深度学习模型的步骤，包括：
    基于核保测试步骤建立核保测试算法；
    挑选多个测算准确的测试样本数据，运行所述核保测试算法；
    根据所述核保测试算法计算的结果与样本结果进行比对，获取相对误差；
    调整所述核保测试算法参数以最小化所述相对误差；及
    当所述相对误差小于预设值时，确定所述核保测试算法为所述深度学习模型。
  19. 如权利要求15所述的计算机可读存储介质，其特征在于，所述核保配置文件包括所述通道映射表的参数设定规则以及测试环境的连接属性。
  20. 如权利要求15所述的计算机可读存储介质，其特征在于，所述参数列表包括承保范围、保额、历史赔付率、市场环境信息和商业竞争信息中一种或多种的组合。
PCT/CN2018/089349 2017-10-12 2018-05-31 核保测试方法、应用服务器及计算机可读存储介质 WO2019071956A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710948977.XA CN108241730A (zh) 2017-10-12 2017-10-12 核保测试方法、应用服务器及计算机可读存储介质
CN201710948977.X 2017-10-12

Publications (1)

Publication Number Publication Date
WO2019071956A1 true WO2019071956A1 (zh) 2019-04-18

Family

ID=62700309

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/089349 WO2019071956A1 (zh) 2017-10-12 2018-05-31 核保测试方法、应用服务器及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN108241730A (zh)
WO (1) WO2019071956A1 (zh)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020087364A1 (en) * 2000-11-07 2002-07-04 Lerner Andrew S. System and method for enabling real time underwriting of insurance policies
CN102436629A (zh) * 2011-05-18 2012-05-02 深圳市航天星网通讯有限公司 基于obd技术为汽车提供车险核保方法
CN106651588A (zh) * 2016-11-09 2017-05-10 前海企保科技（深圳）有限公司 一种物流保险保单的核保方法和装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106600417A (zh) * 2016-11-09 2017-04-26 前海企保科技（深圳）有限公司 一种财产保险保单的核保方法和装置
CN106600419A (zh) * 2016-11-09 2017-04-26 前海企保科技（深圳）有限公司 一种公众责任险保单的核保方法和装置

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020087364A1 (en) * 2000-11-07 2002-07-04 Lerner Andrew S. System and method for enabling real time underwriting of insurance policies
CN102436629A (zh) * 2011-05-18 2012-05-02 深圳市航天星网通讯有限公司 基于obd技术为汽车提供车险核保方法
CN106651588A (zh) * 2016-11-09 2017-05-10 前海企保科技（深圳）有限公司 一种物流保险保单的核保方法和装置

Also Published As

Publication number Publication date
CN108241730A (zh) 2018-07-03

Similar Documents

Publication Publication Date Title
WO2020211491A1 (zh) 基于区块链的项目审核系统、方法、计算设备及存储介质
US20180373890A1 (en) Data processing systems for identity validation of data subject access requests and related methods
WO2020057016A1 (zh) 基于区块链的保险理赔方法、电子装置及存储介质
US10963830B2 (en) Systems and methods for determining an optimal strategy
WO2019001278A1 (zh) 医疗保险基金精算预测方法、装置以及计算机设备
WO2019041518A1 (zh) 电子装置、保险案件理赔审核方法、系统及计算机可读存储介质
US20120116984A1 (en) Automated evaluation of compliance data from heterogeneous it systems
WO2019085463A1 (zh) 部门需求的推荐方法、应用服务器及计算机可读存储介质
US10691640B1 (en) Storing an asset update record
US8290969B2 (en) Systems and methods for validating interpolation results using monte carlo simulations on interpolated data inputs
WO2020119097A1 (zh) 一种数据标准化处理方法、装置及存储介质
WO2019062190A1 (zh) 电子装置、账单数据处理方法及计算机存储介质
CN111340584A (zh) 一种资金方的确定方法、装置、设备及存储介质
CN111815457A (zh) 目标对象的评估方法以及装置
CN108038667B (zh) 保单生成方法、装置及设备
CN110362630A (zh) 数据管理方法、装置、设备与计算机可读存储介质
US20140180949A1 (en) System and method for automated coding and testing of benefits
CN114219596A (zh) 一种基于决策树模型的数据处理方法及相关设备
WO2024045725A1 (zh) 用于目标保单的处理方法、电子设备和可读存储介质
CN116702726A (zh) 薪税管理系统、方法、电子设备及存储介质
WO2019071956A1 (zh) 核保测试方法、应用服务器及计算机可读存储介质
CN109636625A (zh) 保险电子合同的处理方法及装置、存储介质、计算机设备
CN112905635A (zh) 一种业务的处理方法、装置、设备及存储介质
CN106570576A (zh) 数据预测方法及预测装置
WO2019080503A1 (zh) 薪资中间指标的计算方法、应用服务器及计算机可存储介质

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205N DATED 24/06/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18865780

Country of ref document: EP

Kind code of ref document: A1