WO2019019745A1 - 投保单自动分配的方法、装置、计算机设备和存储介质 - Google Patents

投保单自动分配的方法、装置、计算机设备和存储介质 Download PDF

Info

Publication number
WO2019019745A1
WO2019019745A1 PCT/CN2018/084977 CN2018084977W WO2019019745A1 WO 2019019745 A1 WO2019019745 A1 WO 2019019745A1 CN 2018084977 W CN2018084977 W CN 2018084977W WO 2019019745 A1 WO2019019745 A1 WO 2019019745A1
Authority
WO
WIPO (PCT)
Prior art keywords
policy
keyword
correlation value
processing
processing person
Prior art date
Application number
PCT/CN2018/084977
Other languages
English (en)
French (fr)
Inventor
张捷
高雪
李斌
陈杰
邵正铂
马向东
丁杰
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 WO2019019745A1 publication Critical patent/WO2019019745A1/zh

Links

Images

Classifications

    • 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 a method, apparatus, computer device and storage medium for automatic dispensing of insurance policies.
  • the insurance policy is generally assigned to the corresponding salesperson and other processing personnel, so that the corresponding underwriter can handle the insurance policy for the insurance policy, and whoever is the appropriate processor is currently allocated two ways.
  • One type is artificially selected by the ordering personnel according to the situation of each processing person who knows, and the other is automatically matched by the computer according to the complexity of the insurance policy and the level of each processing person.
  • the successful handler is the handler who handles the policy.
  • the inventor realizes that the first method described above needs to rely on the user to understand the processing capabilities of each processor, especially for newly recruited users; the second method only considers the rank of the handler, and does not consider The business capabilities and business direction of each processor cannot be reasonably allocated to resources such as insurance policies.
  • a method, apparatus, computer device, and storage medium for automatic dispensing of a policy is provided.
  • a method for automatically assigning a policy comprising:
  • the insurance policy is assigned to the processing person corresponding to the processing person identifier having the highest correlation value for processing.
  • a device for automatically dispensing an insurance policy comprising:
  • a keyword obtaining module configured to obtain a keyword indicating a policy classification in the policy to be assigned
  • a calculation module configured to calculate, according to a historical policy corresponding to the identifier of the processor, a correlation value between the handler identifier and the keyword;
  • an allocation module configured to allocate the insurance policy to a processing person corresponding to the processing person identifier with the highest correlation value for processing.
  • a computer device comprising a memory and one or more processors having stored therein computer readable instructions, the computer readable instructions being executable by the processor to cause the one or more processors to execute The steps of the method for automatically assigning a policy of insurance provided in any one of the embodiments of the present application.
  • One or more non-volatile storage media storing computer readable instructions that, when executed by one or more processors, cause one or more processors to perform the insured provided in any one embodiment of the present application The steps of a single automatic assignment method.
  • 1A is an application scenario diagram of a method for automatically assigning a policy in accordance with one or more embodiments
  • 1B is a flowchart of a method for automatic dispensing of a policy in accordance with one or more embodiments of the present application
  • FIG. 2 is a flow chart of a method for automatic dispensing of a policy in accordance with another embodiment of the present application
  • FIG. 3 is a flow chart of a method for automatic dispensing of a policy in accordance with yet another embodiment of the present application.
  • FIG. 4 is a block diagram of an apparatus for automatic dispensing of a policy in accordance with one or more embodiments of the present application
  • FIG. 5 is a block diagram of a computer device in accordance with one or more embodiments of the present application.
  • the method for automatically assigning a policy form provided by the present application can be applied to an application environment as shown in FIG. 1A.
  • the terminal 102 communicates with the server 104 over a network.
  • the server 104 calculates the keyword indicating the policy classification in the policy to be assigned, calculates the correlation value of the processor ID and the keyword according to the historical policy corresponding to the processor ID, and assigns the policy to the highest correlation value.
  • the person identifies the corresponding processing person, and the processing person can receive the assigned insurance policy through its corresponding terminal 102 and pass through the terminal 102 and perform related processing on the insurance policy.
  • the terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablets, and portable wearable devices, and the server 104 can be implemented with a stand-alone server or a server cluster composed of a plurality of servers.
  • FIG. 1B is a flowchart of a method for automatically assigning a policy in accordance with one embodiment of the present application.
  • a method for automatically assigning a policy according to one embodiment of the present application is described in detail below with reference to FIG. 1B, as shown in FIG. 1B.
  • the method for automatically assigning the policy includes the following steps S101, S102, and S103.
  • the insurance policy to be assigned may be an electronic policy entered by the record clerk according to the paper policy contract.
  • the keyword may identify the character phrase of the electronic policy according to the entered electronic policy, and then according to the key of the stored policy classification.
  • the font extracts the keywords contained in the policy in the recognized character phrase.
  • the policy to be assigned may also be a PDF file of the scanned paper policy contract, and the keyword may be obtained by identifying the character phrase in the file according to the scanned PDF file. Then, according to the stored keyword classification keyword library, the keywords included in the insurance policy are extracted in the recognized character phrase.
  • keywords of each taxonomy may be preset according to the following three classification criteria:
  • Keywords indicating the source of the policy of the policy including but not limited to “E”, “Online Insurance Confirmation”, “NBU”, etc.;
  • Keywords indicating the types of insurance including but not limited to “care for a lifetime”, “study of insurance”, “taxation”, “Shanghai account”, etc.;
  • Keywords that indicate the source of the insured business including but not limited to “Full Insurance”, “Package”, “Self-service Card”, “Long-term Insurance”, “Short Insurance”, etc.
  • the processing person identifier may be an employee's job number, or may be a processing person's ID number, or may be a processing person's name, and the processing person corresponding to the historical policy is pre-existing on the local computer.
  • the processing person may be one or more, and when the processing person has multiple, the step S102 further calculates a correlation value between the processing person identifier and the keyword according to the historical policy corresponding to the same processing person identifier. .
  • the correlation value is calculated by analyzing the historical policy corresponding to the same handler ID, and obtaining the correlation between the historical business direction of the processor and the policy to be assigned. When the correlation is high, it is determined that the processing has processing.
  • the experience of the policy category to be assigned, the policy to be assigned is assigned to the corresponding processor to make the assigned object more reasonable, and the method of the calculation will be mainly described in the following embodiments.
  • the processing person may directly send the electronic policy corresponding to the insurance policy to the processing person corresponding to the processing person identifier with the highest correlation value, or may also associate the policy identification of the insurance policy to be allocated on the display screen of the computer device.
  • the name or job number of the processor with the highest value corresponds to the display, indicating that the policy should be assigned to the processor for distribution by the policy assignor.
  • the method before the step of step S103, the method further includes: sorting the calculated correlation value; and assigning the policy to the processor corresponding to the processor with the highest correlation value according to the ranking result; Process it.
  • the sorting may be sorting from low to high according to the correlation value, or sorting according to the correlation value from high to low.
  • the corresponding service capability level is pre-set for the processor ID
  • the method for automatically assigning the policy includes the following steps (1) to (4):
  • keywords indicating the complexity of the policy are: "complex”, “simple”, and the like.
  • the computer determines the complexity of the policy based on the complexity of the policy to be assigned entered by the user.
  • the complexity of the above simple component may be defined as 1, the complexity of the above complex component is defined as 2, and the first threshold value is, for example, 1, indicating that the complexity of the policy to be allocated is complicated.
  • the degree is 2 for a complex piece, it is necessary to consider the processing ability of the processing person.
  • keywords indicating the actual business capability of the salesperson “senior”, “advanced”, “general”, “entry”.
  • the above mapping relationship for example, the processing of the insured item of the complex piece needs to be processed by at least the processing person rated as “advanced”, indicating that the mapping relationship is "2 -> advanced or senior”, and needs to be rated as advanced or senior.
  • the corresponding processing person is selected according to the level of the relevant value, and is rated as senior or senior.
  • the processing person obtained in this step is the processing person who is rated as senior or senior in the above step (2).
  • the insurance policy is assigned to the processing person corresponding to the processor identifier with the largest correlation value.
  • the preset second threshold is, for example, 0.3, and setting a threshold of the relevant value to the processing person selected according to the complexity of the policy can avoid assigning the policy to the low correlation value. Dealing with people can improve the accuracy of policy distribution to a certain extent.
  • the correlation values indicating the remaining processors are all smaller than the preset second threshold, indicating that the senior and senior are The correlation between the selected processing person and the pending insurance policy is relatively low, indicating that the appropriate policyholder cannot be selected considering the complexity of the insurance policy.
  • the selection of the processing person is not considered by the factor of the complexity of the policy, and the specific steps include: When the largest correlation value among the calculated correlation values is less than the preset second threshold, the correlation value of each handler ID and the keyword is calculated according to the historical policy corresponding to all the processor identifiers; the insurance policy is assigned to the correlation value. The processing person corresponding to the highest handler ID is processed.
  • the insured order with higher complexity can be allocated to the experienced processing person for processing, and a related person is selected according to the complexity selection.
  • the threshold of degree is such that when the correlation between the processing person selected according to the complexity and the policy to be assigned is very low, the level of the correlation value is used as the selection criterion of the processing person, and the accuracy of the processing person selection is improved.
  • FIG. 2 is a flowchart of a method for automatically assigning a policy according to another embodiment of the present application. As shown in FIG. 2, when the number of the keywords is one, the policy is automatically allocated according to the embodiment.
  • the method includes the above steps S101 and S103, and the above step S102 specifically includes steps S201, S202 and S203.
  • the setting of the weight of the keyword may be manually set according to the input of the user, or may be automatically allocated by the system according to a preset standard.
  • the second method is used to automatically assign the weight.
  • the history policy corresponding to the processor identifier includes the key.
  • the number of policies for the word "self-service card” is 20% of the total number of policies in the history.
  • the product of the weight of the keyword and the percentage is used as a correlation value between the handler identifier and the keyword.
  • the weight stored in the keyword "self-service card" in the system is 0.8
  • the correlation value between the processor and the keyword in the policy to be assigned is 0.16.
  • the present embodiment provides a method for calculating a correlation value when the keyword acquired in the policy to be assigned is one.
  • FIG. 3 is a flowchart of a method for automatically assigning a policy according to another embodiment of the present application. As shown in FIG. 3, when the number of the keywords is two or more, the policy is automatically provided according to the embodiment.
  • the method of allocating includes the following steps S101 and S103, and the above step S102 specifically includes the following steps S301, S302, S303, and S304.
  • the weight of each keyword may be manually set by the user's input, or the system may automatically allocate according to a preset rule, but the weight of each keyword in the same policy is required to be guaranteed.
  • TF-IDF is a statistical method for evaluating a word for one of a file set or a corpus. The importance of the document. The importance of a word increases proportionally with the number of times it appears in the file, but it also decreases inversely with the frequency it appears in the corpus.
  • the importance of the underwriting process of the policy can be allocated according to the keyword, for example, due to the policy of the insurance policy.
  • the actual impact of the source on the actual policy content is not large.
  • the corresponding weight can be reduced to 0.1.
  • the correlation between the actual business capability of the salesperson and the policy processing efficiency is greater, and a higher weight can be assigned, for example, 0.5.
  • the remaining weights can be assigned empirically.
  • the formula for calculating the percentage is:
  • TF i,j represents the percentage result of the calculated keyword i involved in the processing person j
  • n i,j represents the number of policies of the processing person j including the keyword i
  • M j represents the processing person j The total number of historical policies processed.
  • the calculation formula of the correlation value is:
  • TF i,j is the percentage result of the keyword i involved in the processing person j calculated above
  • m represents the number of keywords acquired in the insurance to be allocated
  • w i is the weight of the keyword i
  • H represents The correlation value of the processing person j and the keyword i.
  • the present embodiment provides a method for calculating a correlation value when a keyword acquired in a policy to be assigned is a plurality (two or more).
  • FIGS. 1B-3 are sequentially displayed as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Except as explicitly stated herein, the execution of these steps is not strictly limited, and the steps may be performed in other orders. Moreover, at least some of the steps in FIGS. 1B-3 may include a plurality of sub-steps or stages, which are not necessarily performed at the same time, but may be performed at different times, or The order of execution of the stages is also not necessarily sequential, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
  • the device 10 for automatically assigning insurance policies includes:
  • the keyword obtaining module 11 is configured to obtain a keyword indicating a policy classification in the policy to be assigned.
  • the weight of the keyword can be set manually according to the user's input, or the system can automatically allocate according to the preset standard. When the second method is used to automatically assign the weight, you can refer to the existing TF.
  • IDF weighting technology when the weight of the keyword is manually preset by the user's input, the importance of the underwriting process of the policy can be assigned according to the keyword, for example, due to the source of the policy policy to the actual policy content The actual impact is not large. The corresponding weight can be reduced to 0.1. The correlation between the actual business capability of the salesperson and the processing efficiency of the policy is greatly affected. A higher weight can be assigned, for example, 0.5. The remaining weights can be based on experience. Make an assignment;
  • the calculating module 12 is configured to calculate, according to the historical policy corresponding to the processing person identifier, a correlation value between the processing person identifier and the keyword;
  • the distribution module 13 is configured to allocate the insurance policy to the processing person corresponding to the processing person identifier with the highest correlation value for processing.
  • the calculation module 12 specifically calculates the correlation value of the handler ID and the keyword by the following formula:
  • TF i,j is the percentage result of the keyword i involved in the processing person j calculated above
  • m represents the number of keywords acquired in the insurance to be allocated
  • w i is the weight of the keyword i
  • H represents The correlation value of the processing person j and the keyword i.
  • TF i,j represents the percentage result of the keyword i involved in the calculation of the processing person j
  • n i,j represents the number of policies including the keyword i in the history policy of the processing person j
  • M j indicates that the processing person j has processed The total number of historical policies.
  • the allocating module 13 further includes:
  • an allocating unit configured to allocate the insurance policy to the processing person corresponding to the processing person identifier with the highest correlation value according to the sorting result of the sorting unit.
  • the sorting unit may be sorted according to the size of the correlation value from low to high, or may be sorted according to the size of the correlation value from high to low.
  • the device ID is pre-configured with the corresponding service capability level
  • the device 10 for automatically assigning the policy includes:
  • the complexity acquisition module is configured to obtain the complexity of the input policy.
  • keywords indicating the complexity of the policy are: "complex”, “simple”, and the like.
  • the computer determines the complexity of the policy according to the complexity of the policy to be assigned input by the user;
  • the processing person obtaining module is configured to acquire a processing person having a corresponding service processing capability according to a mapping relationship between a preset complexity and a service capability level when the complexity exceeds a preset first threshold.
  • the complexity of the above simple component may be defined as 1
  • the complexity of the above complex component is defined as 2
  • the first threshold value is, for example, 1, indicating that the complexity of the policy to be allocated is complicated.
  • the degree is 2 for a complex piece, it is necessary to consider the processing ability of the processing person.
  • keywords indicating the actual business capability of the salesperson "senior", “advanced", "general”, "entry”.
  • mapping relationship for example, the processing of the insured item of the complex piece needs to be processed by at least the processing person rated as "advanced", indicating that the mapping relationship is "2 -> advanced or senior", and needs to be rated as advanced or senior.
  • the person selects the processing person corresponding to the corresponding processing person identifier according to the level of the correlation value, and the processing person is rated as senior or senior;
  • the calculation module 12 is further configured to calculate a correlation value between the obtained processing person identifier and the keyword according to the obtained historical policy corresponding to the processing person identifier, and the processing person obtained in the computing module is the evaluated by the processing person obtaining module. For advanced or experienced processors;
  • the foregoing allocation module 13 is further configured to allocate the insurance policy to the processing person with the largest correlation value when the largest correlation value among the calculated correlation values is not less than the preset second threshold.
  • the preset second threshold is, for example, 0.3, and setting a threshold of the relevant value to the processing person selected according to the complexity of the policy can avoid assigning the policy to the low correlation value. Dealing with people can improve the accuracy of policy distribution to a certain extent.
  • the correlation values indicating the remaining processors are all smaller than the preset second threshold, indicating that the senior and senior are The correlation between the selected processing person and the pending insurance policy is relatively low, indicating that the appropriate policyholder cannot be selected considering the complexity of the insurance policy.
  • the calculation module 12 when the maximum correlation value among the correlation values calculated by the calculation module 12 is less than the preset second threshold, the selection of the processing person is not considered according to the complexity of the policy, and the calculation module is further used for When the largest correlation value among the calculated correlation values is less than the preset second threshold, the correlation value of each handler ID and the keyword is calculated according to the history policy corresponding to all the handler IDs.
  • the distribution module 13 is further configured to allocate the insurance policy to a processing person corresponding to the processing person identifier with the highest correlation value for processing.
  • the calculating module 12 when the number of the keywords is one, the calculating module 12 further includes: a first weight obtaining unit, configured to acquire a weight of the keyword preset in the insurance policy; a first calculating unit, configured to calculate a percentage of the number of policies including the keyword in the historical policy corresponding to the same processor ID, and a second calculating unit, configured to use the weight of the keyword The product of the percentage is used as the correlation value of the handler ID and the keyword.
  • the calculating module 12 further includes: a second weight obtaining unit, configured to acquire each keyword preset in the insurance policy Weight, wherein the sum of the weights of all the keywords is 1; the third calculating unit is configured to calculate, for each of the keywords, the number of policies including the keyword in the historical policy corresponding to the same handler ID a percentage of the total number of historical policies corresponding to the same processor ID; a fourth calculating unit, configured to calculate a product of a weight of each keyword in the policy and a corresponding percentage of the keyword; and a fifth calculating unit, configured to: The sum of all products calculated is taken as the correlation value of the handler ID and the keyword.
  • FIG. 5 is a block diagram of a computer device according to one embodiment of the present application, such as the computer device shown in FIG. 5, including a processor connected through a system bus, a non-volatile storage medium, and an internal memory. , display and input device.
  • the non-volatile storage medium of the computer device can store an operating system and computer readable instructions, and when the computer readable instructions are executed, the processor can be caused to perform a method for automatically assigning a policy form according to various embodiments of the present application.
  • the specific implementation process of the method may refer to the specific content of each embodiment in FIG. 1B to FIG. 3, and details are not described herein again.
  • the processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device.
  • a display screen of the computer device is used for display, and an input device of the computer device is configured to receive a parameter such as a parameter value of a preset attribute associated with the insured person identifier input by the user.
  • a parameter such as a parameter value of a preset attribute associated with the insured person identifier input by the user.
  • a computer device comprising a memory and one or more processors having stored therein computer readable instructions that, when executed by a processor, implement a method of automatically assigning a policy form as provided in any one of the embodiments of the present application step.
  • One or more non-volatile storage media storing computer readable instructions, when executed by one or more processors, causing one or more processors to perform the insured provided in any one embodiment of the present application The steps of a single automatic assignment method.
  • Non-volatile memory can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
  • Volatile memory can include random access memory (RAM) or external cache memory.
  • RAM is available in a variety of formats, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronization chain.
  • SRAM static RAM
  • DRAM dynamic RAM
  • SDRAM synchronous DRAM
  • DDRSDRAM double data rate SDRAM
  • ESDRAM enhanced SDRAM
  • Synchlink DRAM SLDRAM
  • Memory Bus Radbus
  • RDRAM Direct RAM
  • DRAM Direct Memory Bus Dynamic RAM
  • RDRAM Memory Bus Dynamic RAM

Abstract

一种投保单自动分配的方法，包括：获取待分配的投保单中表示保单分类的关键字；依据处理人标识对应的历史保单，计算该处理人标识与该关键字的相关值；将该投保单分配给相关值最高的处理人标识对应的处理人进行处理。

Description

投保单自动分配的方法、装置、计算机设备和存储介质
相关申请的交叉引用
本申请要求于2017年07月25日提交中国专利局，申请号为2017106144240，申请名称为“投保单自动分配的方法、装置、计算机设备和存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及投保单自动分配的方法、装置、计算机设备及存储介质。
背景技术
对于投保单的初处理一般是将投保单分配给对应的业务员等处理人，以便对应的核保人对该投保单进行核保工作的处理，选择谁作为合适的处理人目前分配方式有两种，一种是通过人为进行选择，由接单人员根据了解的各个处理人的情况进行人工分配，另一种是通过计算机依据投保单的复杂度以及各个处理人的等级进行自动匹配，将匹配成功的处理人作为处理该投保单的处理人。
然而，发明人意识到，上述第一种方式需要依赖用户了解各个处理人的业务处理能力，尤其是对于新入职的用户十分不便；上述第二种方式只考虑了处理人的等级，并不考虑各个处理人的业务能力和业务方向，无法对投保单这类的资源进行合理分配。
发明内容
根据本申请公开的各种实施例，提供一种投保单自动分配的方法、装置、计算机设备和存储介质。
一种投保单自动分配的方法，包括：
获取待分配的投保单中表示保单分类的关键字；
依据处理人标识对应的历史保单，计算该处理人标识与该关键字的相关值；
将该投保单分配给相关值最高的处理人标识对应的处理人进行处理。
一种投保单自动分配的装置，包括：
关键字获取模块，用于获取待分配的投保单中表示保单分类的关键字；
计算模块，用于依据处理人标识对应的历史保单，计算该处理人标识与该关键字的相关值；
分配模块，用于将该投保单分配给相关值最高的处理人标识对应的处理人进行处理。
一种计算机设备，包括存储器和一个或多个处理器，所述存储器中储存有计算机可读指令，所述计算机可读指令被所述处理器执行时，使得所述一个或多个处理器执行本申请任意一个实施例中提供的投保单自动分配的方法的步骤。
一个或多个存储有计算机可读指令的非易失性存储介质，计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器执行本申请任意一个实施例中提供的投保单自动分配的方法的步骤。
本申请的一个或多个实施例的细节在下面的附图和描述中提出。本申请的其它特征和优点将从说明书、附图以及权利要求书变得明显。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其它的附图。
图1A为根据一个或多个实施例中投保单自动分配的方法的应用场景图；
图1B为根据本申请的一个或多个实施例的投保单自动分配的方法的流程图；
图2为根据本申请的另一实施例的投保单自动分配的方法的流程图；
图3为根据本申请的又一实施例的投保单自动分配的方法的流程图；
图4为根据本申请的一个或多个其中一个实施例的投保单自动分配的装置的框图；
图5为根据本申请的一个或多个其中一个实施例的计算机设备的框图。
具体实施方式
为了使本申请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仅用以解释本申请，并不用于限定本申请。
本申请提供的投保单自动分配的方法，可以应用于如图1A所示的应用环境中。终端102与服务器104通过网络进行通信。服务器104通过获取待分配的投保单中表示保单分类的关键字，依据处理人标识对应的历史保单，计算该处理人标识与该关键字的相关值，将该投保单分配给相关值最高的处理人标识对应的处理人，该处理人可以通过其对应的终端102接收该分配的投保单并通过终端102并对该投保单进行相关的处理。终端102可以但不限于是各种个人计算机、笔记本电脑、智能手机、平板电脑和便携式可穿戴设备，服务器104可以用独立的服务器或者是多个服务器组成的服务器集群来实现。
图1B为根据本申请的其中一个实施例的投保单自动分配的方法的流程图，下面结合图1B来详细描述根据本申请的其中一个实施例的投保单自动分配的方法，如图1B所示，该投保单自动分配的方法包括以下步骤S101、S102和S103。
S101、获取待分配的投保单中表示保单分类的关键字。
该待分配的投保单可以为录单员根据纸质保单合同录入的电子保单，此 时，该关键字可以根据录入的电子保单，识别该电子保单的字符词组，再根据存储的保单分类的关键字库在识别的字符词组中提取出该投保单所包含的关键字。根据本实施例的另一示例，该待分配的保单也可以是扫描的纸质保单合同的PDF格式的文件，该关键字的获取方式可以是根据扫描的PDF文件识别该文件中的字符词组，再根据存储的保单分类的关键字库在识别的字符词组中提取出该投保单所包含的关键字。
根据本实施例的一些示例，可以依据以下三种分类标准预设每种分类标准的关键字：
表示投保单系统来源的关键字：包括但不限于“E化”、“网上投保确认”、“NBU”等；
表示投保险种类型的关键字：包括但不限于“关爱一生”、“学平险”、“税优”、“上海个账”等；
表示投保业务来源的关键字：包括但不限于“综福”、“套餐”、“自助卡”、“长险”、“短险”等。
S102、依据处理人标识对应的历史保单，计算该处理人标识与该关键字的相关值。
根据本实施例的一些示例，该处理人标识可以是员工的工号，也可以是处理人的身份证号码，还可以是处理人的姓名，该处理人标识对应的历史保单预存在本地计算机的存储器中，其中，处理人可以是一个也可以是多个，当处理人为多个时，该步骤S102进一步为依据同一处理人标识对应的历史保单，计算该处理人标识与该关键字的相关值。
该相关值的计算方式主要是通过分析同一处理人标识对应的历史保单，获取处理人的历史业务方向与该待分配的投保单的相关性，当相关性较高时，判断该处理有具有处理该待分配的保单类别的经验，将该待分配的保单分配给对应的处理人使得分配的对象更加合理，在下面的实施例中会着重描述该计算的方法。
S103、将该投保单分配给相关值最高的处理人标识对应的处理人进行处 理。
根据本实施例的一些示例，该分配的方式有两种，一种是提取预设的该投保单的保单标识，例如保单号，然后将该保单标识发送给相关值最高的处理人标识对应的处理人，还可以是直接将该投保单对应的电子保单发送给相关值最高的处理人标识对应的处理人，也可以在计算机设备的显示屏上将该待分配的投保单的保单标识与相关值最高的处理人的姓名或工号对应显示，表示应该将该投保单分配给该处理人，供保单分配人员进行分配。
根据本实施例的一些示例，在该步骤S103的步骤之前，还包括：对计算的该相关值进行排序；依据该排序结果，将该投保单分配给相关值最高的处理人标识对应的处理人进行处理。该排序可以是按照相关值从低到高进行排序，也可以是按照相关值从高到低的方式进行排序。
根据本实施例的另一示例，针对该处理人标识预设有对应的业务能力等级，该投保单自动分配的方法还包括以下步骤(1)～(4)：
(1)、获取输入的投保单的复杂度。
根据本实施例的一些示例，表示投保单复杂度的关键字：“复杂件”、“简单件”等。计算机根据用户输入的该待分配的投保单的复杂度确定该保单的复杂度。
(2)、当该复杂度超过预设的第一阈值时，根据预设的复杂度与业务能力等级的映射关系获取具有对应业务处理能力的处理人。
根据本实施例的一些示例，可以将上述简单件的复杂度定义为1，将上述复杂件的复杂度定义为2，上述的第一阈值例如为1，表示当该待分配的投保单的复杂度为代表复杂件的2时，需要考虑处理人的业务处理能力。
根据本实施例的另一示例，表示业务员实际业务能力的关键字：“资深”、“高级”、“一般”、“入门”。上述映射关系例如处理复杂件的投保单需要至少被评为为“高级”的处理人进行处理，表示该映射关系为“2——>高级或资深”，需要在被评为高级或资深的处理人中根据相关值的高低选择对应的处理人，被评为高级或资深。
(3)、依据获取的处理人标识对应的历史保单，计算获取的处理人标识与该关键字的相关值。
根据本实施的一些示例，该步骤中获取的处理人为上述步骤(2)中获取的被评为高级或资深的处理人。
(4)、当计算的相关值中最大的相关值不小于预设的第二阈值时，将该投保单分配给相关值最大的处理人标识所对应的处理人。
根据本实施例的一些示例，该预设的第二阈值例如为0.3，对依据投保单的复杂度挑选出来的处理人设置一相关值的门槛，可以避免将投保单分配给相关值很低的处理人，在一定程度上可以提高保单分配的准确性。
根据本实施例的另一示例，当计算的相关值中的最大值都小于预设的第二阈值时，表示其余处理人的相关值均小于该预设的第二阈值，表示在高级和资深的处理人中选中的处理人与该待分配的投保单的相关性都比较低，表示考虑该投保单的复杂度无法选择合适的投保人。
根据本实施例的另一示例，当计算的相关值中最大的相关值小于预设的第二阈值时，不考虑投保单的复杂度这一因素对处理人的选择，具体的步骤包括：当计算的相关值中最大的相关值小于预设的第二阈值时，依据所有处理人标识对应的历史保单，计算每个处理人标识与该关键字的相关值；将该投保单分配给相关值最高的处理人标识对应的处理人进行处理。
本实施例通过将投保单的复杂度作为选择对应处理人的一个因素，使得复杂度较高的投保单可以分配给经验丰富的处理人进行处理，同时对依据复杂度选择的处理人设置一相关度的门槛，使得当依据复杂度选择的处理人与该待分配的投保单的相关性非常低时，还是以相关值的高低作为处理人的选择标准，提高处理人选择的准确性。
图2为根据本申请的另一实施例的投保单自动分配的方法的流程图，如图2所示，当该关键字的个数为一个时，根据本实施例提供的投保单自动分配的方法在包括上述步骤S101和S103的基础上，上述步骤S102具体包括步骤S201、S202和S203。
S201、获取该投保单中预设的该关键字的权值。
根据本实施例的一些示例，该关键字的权值的设定可以是依据用户的输入人工设定，也可以是系统依据预设的标准自动分配，当选用第二种方式自动分配权值时，可以参考目前已有的TF-IDF(term frequency–inverse document frequency)加权技术，TF-IDF是一种统计方法，用以评估一字词对于一个文件集或一个语料库中的其中一份文件的重要程度。字词的重要性随着它在文件中出现的次数成正比增加，但同时会随着它在语料库中出现的频率成反比下降。
S202、计算同一处理人标识对应的历史保单中包含有该关键字的保单数占该历史保单总数的百分比。
根据本实施例的一个使用场景例如，一个处理人一共处理过100份投保单，其中包括关键字“自助卡”的保单数有20个，则该处理人标识对应的历史保单中包含有该关键字“自助卡”的保单数占该历史保单总数的百分比为20％。
S203、将该关键字的权值与该百分比的乘积作为该处理人标识与该关键字的相关值。
根据本实施例的一个使用场景例如，系统中对“自助卡”这一关键字中存储的权值为0.8，则该处理人与该待分配的投保单中的关键字的相关值为0.16。
本实施例给出了一种当在待分配的投保单中获取的关键字为一个时的一种相关值的计算方法。
图3为根据本申请的又一实施例的投保单自动分配的方法的流程图，如图3所示，当该关键字的个数为两个以上时，根据本实施例提供的投保单自动分配的方法在包括上述步骤S101和S103的基础上，上述步骤S102具体包括以下步骤S301、S302、S303和S304。
S301、获取该投保单中预设的每个关键字的权值，其中，所有关键字的权值之和为1。
根据本实施例的一些示例，该每个关键字的权值可以通过用户的输入人工设置，也可以是系统依据预设的规则自动分配，但需要保证同一投保单中各个关键字的权值之和为1，当选用第二种方式自动分配权值时，可以参考TF-IDF加权技术，TF-IDF是一种统计方法，用以评估一字词对于一个文件集或一个语料库中的其中一份文件的重要程度。字词的重要性随着它在文件中出现的次数成正比增加，但同时会随着它在语料库中出现的频率成反比下降。
根据本实施例的其中一个使用场景，当通过用户的输入人工预设关键字的权值时，可以依据该关键字对该投保单的核保过程的重要性进行分配，例如，由于投保单系统来源对实际保单内容造成的实际影响并不大，在设定相应权值可以降低为0.1，业务员实际业务能力与保单处理效率相关性影响较大，可以分配较高权值，例如为0.5，其余权重可以按照经验进行分配。
S302、针对每个该关键字，计算同一处理人标识对应的历史保单中包含有该关键字的保单数占该同一处理人标识对应的历史保单总数的百分比。
根据本实施例的一些示例，该百分比的计算公式为：
Figure PCTCN2018084977-appb-000001
其中，TF i,j表示计算的处理人j涉及的关键字i的百分比结果，n i,j表示处理人j的历史保单中包含有该关键字i的保单数，M j表示该处理人j处理过的历史保单总数。
S303、计算该投保单中每个该关键字的权值与该关键字对应百分比的乘积。
S304、将计算的所有乘积之和作为该处理人标识与该关键字的相关值。
根据本实施例的一些示例，该相关值的计算公式为：
Figure PCTCN2018084977-appb-000002
TF i,j为上述计算的处理人j涉及的关键字i的百分比结果，m表示在该待分配的投保中获取的关键字的个数，w i为该关键字i的权值，H表示该处理 人j与该关键字i的相关值。
本实施例提供了一种当在待分配的投保单中获取的关键字为多个(两个或者两个以上)时的一种相关值的计算方法。
应该理解的是，虽然图1B-图3的流程图中的各个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。而且，图1B-图3中的至少一部分步骤可以包括多个子步骤或者多个阶段，这些子步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些子步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤的子步骤或者阶段的至少一部分轮流或者交替地执行。
图4为根据本申请的其中一个实施例的投保单自动分配的装置的框图，下面结合图4来具体描述根据本申请的其中一个实施例的投保单自动分配的装置，如图4所述的投保单自动分配的装置10，包括：
关键字获取模块11，用于获取待分配的投保单中表示保单分类的关键字。该关键字的权值的设定可以是依据用户的输入人工设定，也可以是系统依据预设的标准自动分配，当选用第二种方式自动分配权值时，可以参考目前已有的TF-IDF加权技术，当通过用户的输入人工预设关键字的权值时，可以依据该关键字对该投保单的核保过程的重要性进行分配，例如，由于投保单系统来源对实际保单内容造成的实际影响并不大，在设定相应权值可以降低为0.1，业务员实际业务能力与保单处理效率相关性影响较大，可以分配较高权值，例如为0.5，其余权重可以按照经验进行分配；
计算模块12，用于依据处理人标识对应的历史保单，计算该处理人标识与该关键字的相关值；及
分配模块13，用于将该投保单分配给相关值最高的处理人标识对应的处理人进行处理。
根据本实施例的一些示例，该计算模块12具体通过以下公式计算处理人 标识与该关键字的相关值：
Figure PCTCN2018084977-appb-000003
TF i,j为上述计算的处理人j涉及的关键字i的百分比结果，m表示在该待分配的投保中获取的关键字的个数，w i为该关键字i的权值，H表示该处理人j与该关键字i的相关值。
百分比TF i,j的计算公式为：
Figure PCTCN2018084977-appb-000004
TF i,j表示计算的处理人j涉及的关键字i的百分比结果，n i,j表示处理人j的历史保单中包含有该关键字i的保单数，M j表示该处理人j处理过的历史保单总数。
作为可选地，该分配模块13还包括：
排序单元，用于对计算的该相关值进行排序；
分配单元，用于根据上述排序单元的排序结果，将该投保单分配给相关值最高的处理人标识对应的处理人进行处理。
上述排序单元可以是按照相关值的大小从低到高进行排序，也可以是按照相关值的大小从高到低的方式进行排序。
作为可选地，针对该处理人标识预设有对应的业务能力等级，该投保单自动分配的装置10还包括：
复杂度获取模块，用于获取输入的该投保单的复杂度。根据本实施例的一些示例，表示投保单复杂度的关键字：“复杂件”、“简单件”等。计算机根据用户输入的该待分配的投保单的复杂度确定该保单的复杂度；
处理人获取模块，用于当该复杂度超过预设的第一阈值时，根据预设的复杂度与业务能力等级的映射关系获取具有对应业务处理能力的处理人。根据本实施例的一些示例，可以将上述简单件的复杂度定义为1，将上述复杂件的复杂度定义为2，上述的第一阈值例如为1，表示当该待分配的投保单的复杂度为代表复杂件的2时，需要考虑处理人的业务处理能力。根据本实施 例的另一示例，表示业务员实际业务能力的关键字：“资深”、“高级”、“一般”、“入门”。上述映射关系例如处理复杂件的投保单需要至少被评为为“高级”的处理人进行处理，表示该映射关系为“2——>高级或资深”，需要在被评为高级或资深的处理人中根据相关值的高低选择对应的处理人标识所对应的处理人，该处理人被评为高级或资深；
上述计算模块12还用于依据获取的处理人标识对应的历史保单，计算获取的处理人标识与该关键字的相关值，该计算模块中获取的处理人为通过上述处理人获取模块获取的被评为高级或资深的处理人；
上述分配模块13还用于当计算的相关值中最大的相关值不小于预设的第二阈值时，将该投保单分配给相关值最大的处理人。根据本实施例的一些示例，该预设的第二阈值例如为0.3，对依据投保单的复杂度挑选出来的处理人设置一相关值的门槛，可以避免将投保单分配给相关值很低的处理人，在一定程度上可以提高保单分配的准确性。根据本实施例的另一示例，当计算的相关值中的最大值都小于预设的第二阈值时，表示其余处理人的相关值均小于该预设的第二阈值，表示在高级和资深的处理人中选中的处理人与该待分配的投保单的相关性都比较低，表示考虑该投保单的复杂度无法选择合适的投保人。
作为可选地，当上述计算模块12计算的相关值中最大的相关值小于预设的第二阈值时，不考虑投保单的复杂度这一因素对处理人的选择，该计算模块还用于当计算的相关值中最大的相关值小于预设的第二阈值时，依据所有处理人标识对应的历史保单，计算每个处理人标识与该关键字的相关值。
上述分配模块13还用于将该投保单分配给相关值最高的处理人标识对应的处理人进行处理。
根据本实施例的一些示例，当该关键字的个数为一个时，该计算模块12还包括：第一权值获取单元，用于获取该投保单中预设的该关键字的权值；第一计算单元，用于计算同一处理人标识对应的历史保单中包含有该关键字的保单数占该历史保单总数的百分比；及第二计算单元，用于将该关键字的 权值与该百分比的乘积作为该处理人标识与该关键字的相关值。
根据本实施例的另一示例，当该关键字的个数为两个以上时，该计算模块12还包括：第二权值获取单元，用于获取该投保单中预设的每个关键字的权值，其中，所有关键字的权值之和为1；第三计算单元，用于针对每个该关键字，计算同一处理人标识对应的历史保单中包含有该关键字的保单数占该同一处理人标识对应的历史保单总数的百分比；第四计算单元，用于计算该投保单中每个该关键字的权值与该关键字对应百分比的乘积；及第五计算单元，用于将计算的所有乘积之和作为该处理人标识与该关键字的相关值。
进一步地，图5为根据本申请的其中一个实施例的计算机设备的框图，如图5所示的计算机设备，该计算机设备包括通过系统总线连接的处理器、非易失性存储介质、内存储器、显示屏和输入装置。其中，该计算机设备的非易失性存储介质可存储操作系统和计算机可读指令，该计算机可读指令被执行时，可使得处理器执行本申请各实施例的一种投保单自动分配的方法，该方法的具体实现过程可参考图1B至图3中各实施例的具体内容，在此不再赘述。该计算机设备的处理器用于提供计算和控制能力，支撑整个计算机设备的运行。计算机设备的显示屏用于进行显示，该计算机设备的输入装置用于接收用户输入的与被保人标识相关联的预设属性的参数值等参数。本领域技术人员可以理解，图5中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算机设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
一种计算机设备，包括存储器和一个或多个处理器，存储器中存储有计算机可读指令，计算机可读指令被处理器执行时实现本申请任意一个实施例中提供的投保单自动分配的方法的步骤。
一个或多个存储有计算机可读指令的非易失性存储介质，计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器实现本申请任意一个实施例中提供的投保单自动分配的方法的步骤。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机可读指令来指令相关的硬件来完成，所述的计算机可读指令可存储于一非易失性计算机可读取存储介质中，该计算机可读指令在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限，RAM以多种形式可得，诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据率SDRAM(DDRSDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。
以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本申请的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请专利的保护范围应以所附权利要求为准。

Claims (20)

  1. 一种投保单自动分配的方法，包括：
    获取待分配的投保单中表示保单分类的关键字；
    依据处理人标识对应的历史保单，计算所述处理人标识与所述关键字的相关值；及
    将所述投保单分配给相关值最高的处理人标识对应的处理人进行处理。
  2. 根据权利要求1所述的方法，其特征在于，当所述关键字的个数为一个时，所述依据处理人标识对应的历史保单，计算所述处理人标识与所述关键字的相关值，包括：
    获取所述投保单中预设的所述关键字的权值；
    计算同一处理人标识对应的历史保单中包含有所述关键字的保单数占所述历史保单总数的百分比；及
    将所述关键字的权值与所述百分比的乘积作为所述处理人标识与所述关键字的相关值。
  3. 根据权利要求1所述的方法，其特征在于，当所述关键字的个数为两个以上时，所述依据处理人标识对应的历史保单，计算所述处理人标识与所述关键字的相关值，包括：
    获取所述投保单中预设的每个关键字的权值，其中，所有关键字的权值之和为1；
    针对每个所述关键字，计算同一处理人标识对应的历史保单中包含有所述关键字的保单数占所述同一处理人标识对应的历史保单总数的百分比；
    计算所述投保单中每个所述关键字的权值与所述关键字对应百分比的乘积；及
    将计算的所有乘积之和作为所述处理人标识与所述关键字的相关值。
  4. 根据权利要求1所述的方法，其特征在于，针对所述处理人标识预设有对应的业务能力等级，还包括：
    获取输入的所述投保单的复杂度；
    当所述复杂度超过预设的第一阈值时，根据预设的复杂度与业务能力等级的映射关系获取具有对应业务处理能力的处理人；
    依据获取的处理人标识对应的历史保单，计算获取的处理人标识与所述关键字的相关值；及
    当计算的相关值中最大的相关值不小于预设的第二阈值时，将所述投保单分配给相关值最大的处理人。
  5. 根据权利要求1至4任一项所述的方法，其特征在于，所述将所述投保单分配给相关值最高的处理人，还包括：
    对计算的所述相关值进行排序；及
    将所述投保单分配给相关值最高的处理人标识对应的处理人进行处理。
  6. 一种投保单自动分配的装置，包括：
    关键字获取模块，用于获取待分配的投保单中表示保单分类的关键字；
    计算模块，用于依据处理人标识对应的历史保单，计算所述处理人标识与所述关键字的相关值；及
    分配模块，用于将所述投保单分配给相关值最高的处理人标识对应的处理人进行处理。
  7. 根据权利要求6所述的装置，其特征在于，当所述关键字的个数为一个时，所述计算模块包括：
    第一权值获取单元，用于获取所述投保单中预设的所述关键字的权值；
    第一计算单元，用于计算同一处理人标识对应的历史保单中包含有所述关键字的保单数占所述历史保单总数的百分比；及
    第二计算单元，用于将所述关键字的权值与所述百分比的乘积作为所述处理人标识与所述关键字的相关值。
  8. 根据权利要求6所述的装置，其特征在于，当所述关键字的个数为两个以上时，所述计算模块包括：
    第二权值获取单元，用于获取所述投保单中预设的每个关键字的权值，其中，所有关键字的权值之和为1；
    第三计算单元，用于针对每个所述关键字，计算同一处理人标识对应的历史保单中包含有所述关键字的保单数占所述同一处理人标识对应的历史保单总数的百分比；
    第四计算单元，用于计算所述投保单中每个所述关键字的权值与所述关键字对应百分比的乘积；及
    第五计算单元，用于将计算的所有乘积之和作为所述处理人标识与所述关键字的相关值。
  9. 根据权利要求6所述的装置，其特征在于，针对所述处理人标识预设有对应的业务能力等级，还包括：
    复杂度获取模块，用于获取输入的所述投保单的复杂度；
    处理人获取模块，用于当所述复杂度超过预设的第一阈值时，根据预设的复杂度与业务能力等级的映射关系获取具有对应业务处理能力的处理人；
    所述计算模块还用于依据获取的处理人标识对应的历史保单，计算获取的处理人标识与所述关键字的相关值；及
    所述分配模块还用于当计算的相关值中最大的相关值不小于预设的第二阈值时，将所述投保单分配给相关值最大的处理人。
  10. 根据权利要求6至9中任意一项所述的装置，其特征在于，所述分配模块包括：
    排序单元，用于对计算的所述相关值进行排序；及
    分配单元，用于将所述投保单分配给相关值最高的处理人标识对应的处理人进行处理。
  11. 一种计算机设备，包括存储器及一个或多个处理器，所述存储器中储存有计算机可读指令，所述计算机可读指令被所述一个或多个处理器执行时，使得所述一个或多个处理器执行以下步骤：
    获取待分配的投保单中表示保单分类的关键字；
    依据处理人标识对应的历史保单，计算所述处理人标识与所述关键字的相关值；及
    将所述投保单分配给相关值最高的处理人标识对应的处理人进行处理。
  12. 根据权利要求11所述的计算机设备，其特征在于，当所述关键字的个数为一个时，所述依据处理人标识对应的历史保单，计算所述处理人标识与所述关键字的相关值，包括：
    获取所述投保单中预设的所述关键字的权值；
    计算同一处理人标识对应的历史保单中包含有所述关键字的保单数占所述历史保单总数的百分比；及
    将所述关键字的权值与所述百分比的乘积作为所述处理人标识与所述关键字的相关值。
  13. 根据权利要求11所述的计算机设备，其特征在于，当所述关键字的个数为两个以上时，所述依据处理人标识对应的历史保单，计算所述处理人标识与所述关键字的相关值，包括：
    获取所述投保单中预设的每个关键字的权值，其中，所有关键字的权值之和为1；
    针对每个所述关键字，计算同一处理人标识对应的历史保单中包含有所述关键字的保单数占所述同一处理人标识对应的历史保单总数的百分比；
    计算所述投保单中每个所述关键字的权值与所述关键字对应百分比的乘积；及
    将计算的所有乘积之和作为所述处理人标识与所述关键字的相关值。
  14. 根据权利要求11所述的计算机设备，其特征在于，针对所述处理人标识预设有对应的业务能力等级，所述处理器执行所述计算机可读指令时还执行以下步骤：
    获取输入的所述投保单的复杂度；
    当所述复杂度超过预设的第一阈值时，根据预设的复杂度与业务能力等级的映射关系获取具有对应业务处理能力的处理人；
    依据获取的处理人标识对应的历史保单，计算获取的处理人标识与所述关键字的相关值；及
    当计算的相关值中最大的相关值不小于预设的第二阈值时，将所述投保单分配给相关值最大的处理人。
  15. 根据权利要求11至14任意一项所述的计算机设备，其特征在于，所述将所述投保单分配给相关值最高的处理人，还包括：
    对计算的所述相关值进行排序；及
    将所述投保单分配给相关值最高的处理人标识对应的处理人进行处理。
  16. 一个或多个存储有计算机可读指令的非易失性计算机可读存储介质，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行以下步骤：
    获取待分配的投保单中表示保单分类的关键字；
    依据处理人标识对应的历史保单，计算所述处理人标识与所述关键字的相关值；及
    将所述投保单分配给相关值最高的处理人标识对应的处理人进行处理。
  17. 根据权利要求16所述的存储介质，其特征在于，当所述关键字的个数为一个时，所述依据处理人标识对应的历史保单，计算所述处理人标识与所述关键字的相关值，包括：
    获取所述投保单中预设的所述关键字的权值；
    计算同一处理人标识对应的历史保单中包含有所述关键字的保单数占所述历史保单总数的百分比；及
    将所述关键字的权值与所述百分比的乘积作为所述处理人标识与所述关键字的相关值。
  18. 根据权利要求16所述的存储介质，其特征在于，当所述关键字的个数为两个以上时，所述依据处理人标识对应的历史保单，计算所述处理人标识与所述关键字的相关值，包括：
    获取所述投保单中预设的每个关键字的权值，其中，所有关键字的权值之和为1；
    针对每个所述关键字，计算同一处理人标识对应的历史保单中包含有所 述关键字的保单数占所述同一处理人标识对应的历史保单总数的百分比；
    计算所述投保单中每个所述关键字的权值与所述关键字对应百分比的乘积；及
    将计算的所有乘积之和作为所述处理人标识与所述关键字的相关值。
  19. 根据权利要求16所述的存储介质，其特征在于，针对所述处理人标识预设有对应的业务能力等级，所述计算机可读指令被所述处理器执行时还执行以下步骤：
    获取输入的所述投保单的复杂度；
    当所述复杂度超过预设的第一阈值时，根据预设的复杂度与业务能力等级的映射关系获取具有对应业务处理能力的处理人；
    依据获取的处理人标识对应的历史保单，计算获取的处理人标识与所述关键字的相关值；及
    当计算的相关值中最大的相关值不小于预设的第二阈值时，将所述投保单分配给相关值最大的处理人。
  20. 根据权利要求16至19中任意一项所述的存储介质，其特征在于，
    所述将所述投保单分配给相关值最高的处理人，还包括：
    对计算的所述相关值进行排序；及
    将所述投保单分配给相关值最高的处理人标识对应的处理人进行处理。
PCT/CN2018/084977 2017-07-25 2018-04-28 投保单自动分配的方法、装置、计算机设备和存储介质 WO2019019745A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710614424.0A CN108510399B (zh) 2017-07-25 2017-07-25 投保单自动分配的方法、装置、计算机设备及存储介质
CN201710614424.0 2017-07-25

Publications (1)

Publication Number Publication Date
WO2019019745A1 true WO2019019745A1 (zh) 2019-01-31

Family

ID=63373458

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/084977 WO2019019745A1 (zh) 2017-07-25 2018-04-28 投保单自动分配的方法、装置、计算机设备和存储介质

Country Status (2)

Country Link
CN (1) CN108510399B (zh)
WO (1) WO2019019745A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109461088A (zh) * 2018-11-13 2019-03-12 泰康保险集团股份有限公司 一种保全工单的分单方法、装置、介质和电子设备
CN110728429B (zh) * 2019-09-18 2024-04-05 平安科技（深圳）有限公司 案件分配方法、装置、介质和计算机设备
CN111160637B (zh) * 2019-12-18 2024-04-05 中国平安财产保险股份有限公司 智能化人力分配方法、装置及计算机可读存储介质
CN114281489A (zh) * 2020-09-17 2022-04-05 华为终端有限公司 一种多服务的执行方法及电子设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070226340A1 (en) * 2006-03-22 2007-09-27 Cellco Partnership (D/B/A Verizon Wireless) Electronic communication work flow manager system, method and computer program product
CN104580284A (zh) * 2013-10-14 2015-04-29 方正宽带网络服务股份有限公司 业务分配装置和业务分配方法
CN105046443A (zh) * 2015-08-07 2015-11-11 北京思特奇信息技术股份有限公司 一种业务工单分配方法及系统
CN105809323A (zh) * 2016-02-23 2016-07-27 平安科技（深圳）有限公司 任务分配方法和系统

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090006230A1 (en) * 2007-06-27 2009-01-01 Checkfree Corporation Identity Risk Scoring
CN104182856A (zh) * 2014-07-24 2014-12-03 余少勇 一种国际货代空运平台系统
CN106296318A (zh) * 2015-04-26 2017-01-04 上海墨盾电脑科技有限公司 一种电子商务场景处理方法及系统
CN106527381B (zh) * 2016-12-14 2019-05-17 北京化工大学 一种面向并行批处理机动态调度的快速评估方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070226340A1 (en) * 2006-03-22 2007-09-27 Cellco Partnership (D/B/A Verizon Wireless) Electronic communication work flow manager system, method and computer program product
CN104580284A (zh) * 2013-10-14 2015-04-29 方正宽带网络服务股份有限公司 业务分配装置和业务分配方法
CN105046443A (zh) * 2015-08-07 2015-11-11 北京思特奇信息技术股份有限公司 一种业务工单分配方法及系统
CN105809323A (zh) * 2016-02-23 2016-07-27 平安科技（深圳）有限公司 任务分配方法和系统

Also Published As

Publication number Publication date
CN108510399A (zh) 2018-09-07
CN108510399B (zh) 2020-11-24

Similar Documents

Publication Publication Date Title
WO2019019745A1 (zh) 投保单自动分配的方法、装置、计算机设备和存储介质
WO2019019752A1 (zh) 审批人的辅助选择方法、装置、计算机设备和存储介质
US20210337069A1 (en) Exclusive Agent Pool Allocation Method, Electronic Device, And Computer Readable Storage Medium
WO2019041912A1 (zh) 理赔案件分配方法、装置、计算机设备和存储介质
US20140310691A1 (en) Method and device for testing multiple versions
WO2013128555A1 (ja) タスク管理方法及びタスク管理装置
JP2017515184A (ja) 一時的な取引制限の決定
US10963888B2 (en) Payment complaint method, device, server and readable storage medium
CN109245996B (zh) 邮件推送方法、装置、计算机设备和存储介质
CN112529702B (zh) 用户授信策略分配方法、装置及电子设备
CN109710402A (zh) 处理资源获取请求的方法、装置、计算机设备和存储介质
US9298780B1 (en) Method and system for managing user contributed data extraction templates using weighted ranking score analysis
US20140164416A1 (en) Aggregating content related to a notable individual
US20170070557A1 (en) Analytic data export tool
CN111598360A (zh) 服务策略确定方法、装置及电子设备
CN111062572B (zh) 任务分配的方法和装置
WO2019019753A1 (zh) 提供健康报告的判断方法、装置、计算机设备和存储介质
CN111626898B (zh) 用于实现事件归因的方法、装置、介质和电子设备
US8918406B2 (en) Intelligent analysis queue construction
WO2021000406A1 (zh) 请求处理方法、装置、计算机设备和存储介质
US20150242952A1 (en) Methods And Systems For Constructing Risk Parity Portfolios
CN115729687A (zh) 任务调度方法、装置、计算机设备、存储介质
WO2019019751A1 (zh) 撤回任务的方法、装置、计算机设备和存储介质
CN107408127B (zh) 用于索引队列的动态阈值门
CN113989058A (zh) 一种服务生成方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18837196

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18837196

Country of ref document: EP

Kind code of ref document: A1

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 1205A DATED 04.08.2020.

122 Ep: pct application non-entry in european phase

Ref document number: 18837196

Country of ref document: EP

Kind code of ref document: A1