WO2020140681A1

WO2020140681A1 - Numerical value calculation method and apparatus, computer device, and storage medium

Info

Publication number: WO2020140681A1
Application number: PCT/CN2019/123269
Authority: WO
Inventors: 宁培然
Original assignee: 深圳壹账通智能科技有限公司
Priority date: 2019-01-03
Filing date: 2019-12-05
Publication date: 2020-07-09
Also published as: CN109784706A

Abstract

The present application relates to a numerical value calculation method, comprising: receiving a numerical value calculation request, the numerical value calculation request carrying a data identifier; acquiring data to be processed, corresponding to the data identifier; acquiring an influencing factor node tree, the influencing factor node tree containing a plurality of influencing factor nodes; extracting, from said data, all target influencing data corresponding to influencing factor nodes; acquiring, on the basis of the influencing factor node tree, node weights corresponding to all the target influencing data; and obtaining, by calculation, a target numerical value according to the target influencing data and the corresponding node weights.

Description

数值计算方法、装置、计算机设备和存储介质Numerical calculation method, device, computer equipment and storage medium

本申请要求于2019年1月3日提交中国专利局，申请号为201910004212X，申请名称为“数值计算方法、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。This application requires priority to be submitted to the Chinese Patent Office on January 3, 2019, with the application number 201910004212X and the Chinese patent application titled "Numerical Calculation Methods, Devices, Computer Equipment, and Storage Media", the entire contents of which are incorporated by reference In this application.

技术领域Technical field

本申请涉及一种数值计算方法、装置、计算机设备和存储介质。The present application relates to a numerical calculation method, device, computer equipment and storage medium.

背景技术Background technique

随时市场的不断发展，对产品差异化、个性化的需求与日俱增。数值可以金融产品金额以及商场产品时价等，数值的确定往往受多重影响因素影响，比如金融产品金额可以是受投保实际情况影响的保险产品的保费，商场产品时价可以是受气候、供销量影响的菜品价格。传统方式中，通常需要基于大量影响因素对产品进行人工分析，最终得到所需的数值。然而人工分析方式主要基于个人经验，具有较强的主观性和不稳定性，导致难以准确、快速地确定数值。With the continuous development of the market at any time, the demand for product differentiation and individualization is increasing day by day. The value can be the amount of the financial product and the current price of the store product. The determination of the value is often affected by multiple influencing factors. For example, the amount of the financial product can be the premium of the insurance product affected by the actual situation of the insurance. The current price of the store product can be affected by the climate, supply and sales Affected dish prices. In the traditional way, it is usually necessary to manually analyze the product based on a large number of influencing factors to finally obtain the required value. However, the manual analysis method is mainly based on personal experience and has strong subjectivity and instability, which makes it difficult to determine the value accurately and quickly.

发明内容Summary of the invention

根据本申请公开的各种实施例，提供一种能够高效确定数值的数值计算方法、装置、计算机设备和存储介质。According to various embodiments disclosed in the present application, a numerical calculation method, apparatus, computer device, and storage medium capable of efficiently determining numerical values are provided.

一种数值计算方法，包括：接收数值计算请求；所述数值计算请求携带数据标识；获取与数据标识对应的待处理数据；获取影响因子节点树；所述影响因子节点树包含多个影响因子节点；提取所述待处理数据中每个与影响因子节点对应的目标影响数据；基于影响因子节点树获取与每个目标影响数据对应的节点权重；及根据所述目标影响数据和相应的节点权重计算得到目标数值。A numerical calculation method includes: receiving a numerical calculation request; the numerical calculation request carries a data identifier; acquiring data to be processed corresponding to the data identifier; acquiring an impact factor node tree; the impact factor node tree includes a plurality of impact factor nodes ; Extract the target impact data corresponding to each impact factor node in the data to be processed; obtain the node weights corresponding to each target impact data based on the impact factor node tree; and calculate according to the target impact data and the corresponding node weights Get the target value.

一种数值计算装置，所述装置包括：接收模块，用于接收数值计算请求；所述数值计算请求携带数据标识；获取模块，用于获取与数据标识对应的待处理数据；获取影响因子节点树；所述影响因子节点树由多个影响因子节点构成；提取模块，用于提取所述待处理数据中每个与影响因子节点对应的目标影响数据；计算模块，用于基于影响因子节点树获取与每个目标影响数据对应的节点权重；及根据所述目标影响数据和相应的节点权重计算得到目标数值。A numerical calculation device, the apparatus includes: a receiving module for receiving a numerical calculation request; the numerical calculation request carries a data identifier; an acquisition module for acquiring data to be processed corresponding to the data identifier; acquiring an impact factor node tree The impact factor node tree is composed of multiple impact factor nodes; an extraction module is used to extract target impact data corresponding to each impact factor node in the data to be processed; a calculation module is used to obtain based on the impact factor node tree The node weight corresponding to each target influence data; and calculating the target value according to the target influence data and the corresponding node weight.

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：接收数值计算请求；所述数值计算请求携带数据标识；获取与数据标识对应的待处理数据；获取影响因子节点树；所述影响因子节点树包含多个影响因子节点；提取所述待处理数据中每个与影响因子节点对应的目标影响数据；基于影响因子节点树获取与每项目标影响数据对应的节点权重；及根据所述目标影响数据和相应的节点权重计算得到目标数值。A computer device includes a memory and one or more processors. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the one or more processors, the one or more Each processor executes the following steps: receiving a numerical calculation request; the numerical calculation request carries a data identifier; acquiring data to be processed corresponding to the data identifier; acquiring an impact factor node tree; the impact factor node tree contains multiple impact factor nodes; Extract target impact data corresponding to each impact factor node in the data to be processed; obtain node weights corresponding to each target impact data based on the impact factor node tree; and calculate based on the target impact data and corresponding node weights The target value.

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：接收数值计算请求；所述数值计算请求携带数据标识；获取与数据标识对应的待处理数据；获取影响因子节点树；所述影响因子节点树包含多个影响因子节点；提取所述待处理数据中每个与影响因子节点对应的目标影响数据；基于影响因子节点树获取与每项目标影响数据对应的节点权重；及根据所述目标影响数据和相应的节点权重计算得到目标数值。One or more non-volatile computer-readable storage media storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to perform the following steps: Receive a numerical calculation request; the numerical calculation request carries a data identifier; obtain data to be processed corresponding to the data identifier; obtain an impact factor node tree; the impact factor node tree contains multiple impact factor nodes; extract the data to be processed Each target impact data corresponding to the impact factor node; obtaining the node weight corresponding to each target impact data based on the impact factor node tree; and calculating the target value based on the target impact data and the corresponding node weight.

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。The details of one or more embodiments of the application are set forth in the drawings and description below. Other features and advantages of this application will become apparent from the description, drawings, and claims.

附图说明BRIEF DESCRIPTION

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。In order to more clearly explain the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. Those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

图1为根据一个或多个实施例中数值计算方法的应用场景图。FIG. 1 is an application scenario diagram of a numerical calculation method according to one or more embodiments.

图2为根据一个或多个实施例中数值计算方法的流程示意图。FIG. 2 is a schematic flowchart of a numerical calculation method according to one or more embodiments.

图3为根据一个或多个实施例中影响因子节点树的示意图。FIG. 3 is a schematic diagram of an impact factor node tree according to one or more embodiments.

图4为另一个实施例中数值计算方法的流程示意图。4 is a schematic flowchart of a numerical calculation method in another embodiment.

图5为根据一个或多个实施例中数值计算装置的框图。5 is a block diagram of a numerical calculation device according to one or more embodiments.

图6为根据一个或多个实施例中计算机设备的框图。Figure 6 is a block diagram of a computer device in accordance with one or more embodiments.

具体实施方式detailed description

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。In order to make the purpose, technical solutions and advantages of the present application more clear, the following describes the present application in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

本申请提供的数值计算方法，可以应用于如图1所示的应用环境中。其中，终端102与服务器104通过网络进行通信。其中，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。服务器104接收终端102发送的携带数据标识的数值计算请求之后，可获取与数据标识对应的待处理数据，还可获取由多个影响因子节点构成的影响因子节点树，针对每个影响节点因子预设有对应的节点权重。服务器104可从待处理数据中提取每个与影响因子节点对应的目标影响数据，并获取与每个提取的目标影响数据对应的节点权重。服务器104还可以根据目标影响数据和相应的节点权重计算得到目标数值。The numerical calculation method provided by this application can be applied to the application environment shown in FIG. 1. Among them, the terminal 102 and the server 104 communicate via the network. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server 104 may be implemented by an independent server or a server cluster composed of multiple servers. After receiving the numerical calculation request carrying the data identifier sent by the terminal 102, the server 104 can obtain data to be processed corresponding to the data identifier, and can also obtain an impact factor node tree composed of multiple impact factor nodes. Set corresponding node weights. The server 104 may extract each target impact data corresponding to the impact factor node from the data to be processed, and obtain the node weight corresponding to each extracted target impact data. The server 104 can also calculate the target value according to the target influence data and the corresponding node weight.

在一个实施例中，如图2所示，提供了一种数值计算方法，以该方法应用于图1中的服务器104为例进行说明，包括以下步骤：In one embodiment, as shown in FIG. 2, a numerical calculation method is provided. Taking the method applied to the server 104 in FIG. 1 as an example for illustration, it includes the following steps:

步骤202，接收数值计算请求；数值计算请求携带数据标识。Step 202: Receive a numerical calculation request; the numerical calculation request carries a data identifier.

数值计算请求是指用于进行数值计算的请求。数值是指受所重影响因素影响取值的数值。数值可以金融产品金额，比如受投保实际情况影响的保险产品的保费，还可以是商场产品的时价，比如受气候、供销量等影响的菜品价格。数据标识是指用于获取待处理数据的标识。数据标识可以是由字母、数字、标点符号中至少一种构成的字符串。比如数据标识可以是待处理数据的URL(Uniform Resource Locator，统一资源定位符)。数据标识还可以为由字母、数字、标点符号中至少一种构成的字符串。比如数据标识可以是待处理数据的编号，服务器可通过待处理数据的编号去预设的数据库中获取相应的待处理数据。The numerical calculation request refers to a request for numerical calculation. The numerical value refers to the numerical value affected by the influence factors. The value can be the amount of the financial product, such as the premium of the insurance product affected by the actual situation of the insurance, or the current price of the product in the mall, such as the price of the dishes affected by the climate, supply and sales. Data identification refers to the identification used to obtain the data to be processed. The data identification may be a character string composed of at least one of letters, numbers, and punctuation marks. For example, the data identifier may be a URL (Uniform Resource Locator) of the data to be processed. The data identification may also be a character string composed of at least one of letters, numbers, and punctuation marks. For example, the data identifier may be the number of the data to be processed, and the server may obtain the corresponding data to be processed from the preset database through the number of the data to be processed.

在一个实施例中，数值可以是保险业务中的保费。举例来说，保证保险是指保险人承保因被保证人行为使被保险人受到经济损失时应负赔偿责任的保险形式。保证保险以信用风险作为保险标的，比如，当借款方向贷款方借贷资金时，借款方可作为被保证人向保险公司进行投保，请求保险人向贷款方担保借款方自己信用的保险。借款方缴纳保险费用之后，即借款方投保自己的信用风险之后，保险公司可承担保险责任。保证保险的保费往往受借款方、贷款方、借贷金额等多重因素影响。In one embodiment, the value may be the premium in the insurance business. For example, guaranteed insurance refers to the form of insurance in which the insurer insures the insured against financial losses due to the insured’s actions. Guarantee insurance uses credit risk as the insurance subject. For example, when the borrower borrows funds from the lender, the borrower can insure the insurance company as the insured and request the insurer to guarantee the lender's own credit insurance. After the borrower pays the insurance fee, that is, after the borrower insures his credit risk, the insurance company may bear the insurance liability. The premium of guaranteed insurance is often affected by multiple factors such as borrowers, lenders, and loan amount.

步骤204，获取与数据标识对应的待处理数据。Step 204: Obtain data to be processed corresponding to the data identifier.

待处理数据是指需要用于数值计算的数据。比如当需要确定保费时，待处理数据包括但不限于投保单数据、投保人信用数据、投保人账号数据等。待处理数据可以存储于预设的数据库中，可以是终端的数据库中，也可以是服务器的数据库中。Data to be processed refers to data that needs to be used for numerical calculation. For example, when the premium needs to be determined, the data to be processed includes but is not limited to policy data, policyholder credit data, and policyholder account data. The data to be processed may be stored in a preset database, it may be a database of a terminal, or a database of a server.

在一个实施例中，终端可提供数据上传界面，数据上传界面中可包含文本框、按钮、下拉框等输入控件，用户可通过输入控件输入待处理数据至终端。当终端检测到作用于确认控件的点击操作时，可将用户输入的待处理数据汇总打包，并将打包的待处理数据发送至服务器中。服务器还可通过网络爬虫在网络中采集所需的待处理数据，将待处理数据存储至预设的数据库中，以使服务器可从数据库中获取待处理数据进行业务处理。In one embodiment, the terminal may provide a data upload interface, and the data upload interface may include input controls such as text boxes, buttons, and drop-down boxes. The user may input data to be processed to the terminal through the input controls. When the terminal detects the click operation acting on the confirmation control, it can aggregate and package the data to be processed input by the user, and send the packaged data to be processed to the server. The server can also collect required data to be processed in the network through a web crawler, and store the data to be stored in a preset database, so that the server can obtain the data to be processed from the database for business processing.

步骤206，获取影响因子节点树；影响因子节点树包含多个影响因子节点。Step 206: Obtain an impact factor node tree; the impact factor node tree contains multiple impact factor nodes.

影响因子节点树是指包含多个影响因子节点的树形结构文件。影响因子节点是指对计算数值造成影响的影响因子所对应的节点。子节点对应的影响因子可为父节点对应的影响因子的细化因素。比如父节点对应的影响因子为信用等级时，子节点对应的影响因子可为交易信用等级、还款信用等级等。Impact factor node tree refers to a tree structure file containing multiple impact factor nodes. Impact factor node refers to the node corresponding to the impact factor that affects the calculated value. The influence factor corresponding to the child node may be a refinement factor of the influence factor corresponding to the parent node. For example, when the impact factor corresponding to the parent node is a credit rating, the impact factor corresponding to the child node may be a transaction credit rating, a repayment credit rating, and so on.

在一个实施例中，如图3所示，为影响因子节点树的示意图。针对保证保险保费计算，影响因子节点可划分为三个层级，合作渠道、保险产品、产品要素。合作渠道是指销售保险产品的平台。产品要素包括资金方经营情况、借款方信用风险等级、贷款产品性质、借贷利率、贷款期限等。资金方经营情况，若资金方经营效益好则可适当降低保费。借款方信用风险等级是基于借款方的各项信用数据计算得到，借款方信用风险等级越高则需提高保费。贷款产品性质比如用于经营的贷款或用于消费的贷款，经营类型的风险高则可提高保费。借贷利率越高则需提高保费。针对不同合作渠道，相同合作渠道不同产品，相同产品不同产品要素的保费计算进行差异化配置，使得最终计算得到的保费更加符合实际情况，具有更高的准确性。In one embodiment, as shown in FIG. 3, it is a schematic diagram of an impact factor node tree. For the calculation of guaranteed insurance premiums, the impact factor node can be divided into three levels, cooperation channels, insurance products, and product elements. Cooperative channels refer to platforms that sell insurance products. The product elements include the operation of the funder, the credit risk level of the borrower, the nature of the loan product, the loan interest rate, and the loan term. The operating conditions of the capital side, if the capital side's operating efficiency is good, the premium can be appropriately reduced. The borrower's credit risk level is calculated based on the borrower's various credit data. The higher the borrower's credit risk level, the higher the premium. The nature of loan products, such as loans for business or loans for consumption, can increase the premium if the risk of the business type is high. The higher the lending rate, the higher the premium. For different cooperation channels, the same cooperation channel, different products, the same product and different product elements, the premium calculation is differentiated, so that the final calculated premium is more in line with the actual situation and has higher accuracy.

步骤208，提取待处理数据中每个与影响因子节点对应的目标影响数据。Step 208: Extract target impact data corresponding to each impact factor node in the data to be processed.

目标影响数据是指待处理数据经过与影响因子节点树进行匹配得到的数据。由于待处理数据中包含多种类型的信息，可通过影响节点因子对待处理数据中包含的信息进行筛选，得到计算目标数值所需的目标影响数据。通过对待处理数据进行筛选，避免对不必要的数据进行进一步地处理，从而减少数值计算的时间，提高数值计算的效率。Target impact data refers to the data obtained by matching the data to be processed with the impact factor node tree. Since the data to be processed contains multiple types of information, the information contained in the data to be processed can be filtered by the influence node factor to obtain the target influence data required to calculate the target value. By filtering the data to be processed, it is avoided to process further unnecessary data, thereby reducing the time of numerical calculation and improving the efficiency of numerical calculation.

步骤210，基于影响因子节点树获取与每个目标影响数据对应的节点权重。Step 210: Obtain the node weight corresponding to each target impact data based on the impact factor node tree.

可预先针对影响因子节点树中的每个影响因子节点预设相应的节点权重。通过预设的节点权重按照影响因子的影响程度调整目标数值的大小。比如，当资金方经营效益好则可适当降低保费时，则可针对效益更好的资金方经营，设置更低的节点权重；当借款方信用风险等级越高则需提高保费时，则可针对更高的借款方信用风险等级，设置更高的节点权重；当借贷利率越高则需提高保费时，则可针对更高的借贷利率，设置更高的节点权重。A corresponding node weight may be preset for each impact factor node in the impact factor node tree. The size of the target value is adjusted according to the influence degree of the influence factor through the preset node weight. For example, when the funder’s operating efficiency is good and the premium can be appropriately reduced, the lower cost of the node can be set for the funder’s better operating efficiency; when the borrower’s credit risk level needs to be increased, the premium can be targeted. The higher the credit risk level of the borrower, the higher the node weight; the higher the loan interest rate, the higher the premium, the higher the node interest rate, the higher the node weight.

举例来说，合作渠道包括合作渠道A和合作渠道B，通常针对不同的合作渠道没有差异化定价时，则可将合作渠道A和合作渠道B设置为相同的节点权值，比如1；当合作渠道A举办了促销活动，需要对产品进行折扣出售，则可将合作渠道A对应的节点权值降低为0.8。当检测到待处理数据中合作渠道节点对应的目标影响数据为合作渠道A时，则可计算出促销后价格更低的目标数值。For example, cooperation channels include cooperation channel A and cooperation channel B. Usually, when there is no differentiated pricing for different cooperation channels, you can set cooperation channel A and cooperation channel B to the same node weight, such as 1; when cooperation Channel A held a promotional event and needed to sell the product at a discount, then the node weight corresponding to channel A could be reduced to 0.8. When it is detected that the target impact data corresponding to the cooperation channel node in the data to be processed is the cooperation channel A, the target value of the lower price after the promotion can be calculated.

步骤212，根据目标影响数据和相应的节点权重计算得到目标数值。Step 212: Calculate the target value according to the target impact data and the corresponding node weight.

目标影响数据可为多项，通过每项目标影响数据与相应影响因子节点对应的节点权重，可计算得到考虑所有目标影响数据影响程度之后的目标数值。The target impact data can be multiple items. Through the weight of the node corresponding to each target impact data and the corresponding impact factor node, the target value after considering the impact of all target impact data can be calculated.

在一个实施例中，目标数值可为保费。可根据投保单数据中的实际数据对保费进行计算，比如可根据合作渠道、资金方、定位客群、贷款产品性质等对保费进行计算。根据预设的影响因子节点树，实现了根据不同入件渠道；相同入件渠道不同保险产品；相同保险产品不同产品要素的保费的差异化定价。确保保费定价的灵活性、差异性、合理性。在业务上，既满足了业务上对于保费灵活定价的需要，又满足了***设计上对于参数化配置的要求。In one embodiment, the target value may be the premium. The premium can be calculated based on the actual data in the insurance policy data. For example, the premium can be calculated based on the cooperation channel, the funder, the target customer group, and the nature of the loan product. According to the preset impact factor node tree, differentiated pricing based on different incoming channels; different insurance products in the same incoming channel; different insurance product elements of the same insurance product is realized. Ensure the flexibility, difference and rationality of premium pricing. In terms of business, it not only meets the business's need for flexible pricing of premiums, but also meets the requirements for parameterized configuration in system design.

在一个实施例中，根据目标影响数据和相应的节点权重计算得到目标数值，包括：将每个目标影响数据转换为相应的影响因子分值；根据多个影响因子分值和与每个影响因子分值相应的节点权重，计算得到比例系数；从待处理数据中提取得到基础数值；根据比例系数和基础数值计算得到目标数值。In one embodiment, the target value is calculated according to the target impact data and corresponding node weights, including: converting each target impact data into a corresponding impact factor score; according to multiple impact factor scores and each impact factor The node weight corresponding to the score is calculated to obtain the proportional coefficient; the basic value is extracted from the data to be processed; the target value is calculated according to the proportional coefficient and the basic value.

影响因子分值是指将目标影响数据转换为的具体分值，通过每个影响因子分值和相应的节点权重，可通过预设的公式计算得到比例系数。基础数值是指待处理数据中包含的用于作为计算目标数值的基数。举例来说，基础数值可以是保险金额，比例系数可以是保费系数，保费系数可通过每个影响因子分值和相应的节点权重进行加权求和得到，根据保险金额和保费系数可计算得到具体的保费数值。The impact factor score refers to the specific score into which the target impact data is converted. Through each impact factor score and the corresponding node weight, a proportional coefficient can be calculated by a preset formula. The basic value refers to the base used as the calculation target value contained in the data to be processed. For example, the basic value can be the insurance amount, and the proportional coefficient can be the premium coefficient. The premium coefficient can be obtained by weighted summation of each impact factor score and the corresponding node weight, and the specific value can be calculated according to the insurance amount and the premium coefficient. Premium value.

上述数值计算方法中，服务器接收携带数据标识的数值计算请求之后，可获取与数据标识对应的待处理数据，还可获取由多个影响因子节点构成的影响因子节点树，针对每个影响节点因子预设有对应的节点权重。服务器可从待处理数据中提取每个与影响因子节点对应的目标影响数据，并获取与每个提取的目标影响数据对应的节点权重。服务器还可以根据目标影响数据和相应的节点权重计算得到目标数值。通过预先配置的多种影响因子节点，使得服务器能够基于待处理数据自动化计算出相应的目标数值，由于在数据分析时考虑了多种影响因子，从而能够灵活、高效地计算得到准确的数值。In the above numerical calculation method, after receiving the numerical calculation request carrying the data identifier, the server can obtain the data to be processed corresponding to the data identifier, and can also obtain an impact factor node tree composed of multiple impact factor nodes, for each impact node factor The corresponding node weights are preset. The server may extract each target impact data corresponding to the impact factor node from the data to be processed, and obtain the node weight corresponding to each extracted target impact data. The server can also calculate the target value according to the target impact data and the corresponding node weight. Through pre-configured multiple impact factor nodes, the server can automatically calculate the corresponding target value based on the data to be processed. Since multiple impact factors are considered during data analysis, accurate values can be calculated flexibly and efficiently.

在一个实施例中，数值计算请求还携带计算时间，获取影响因子节点树，包括：查找多个版本的影响因子节点树；识别每个版本的影响因子节点树对应的生效时间；确定计算时间所处的生效时间区间，以及确定生效时间区间对应的上限生效时间；获取上限生效时间对应的影响因子节点树。In one embodiment, the numerical calculation request also carries the calculation time to obtain the impact factor node tree, including: finding multiple versions of the impact factor node tree; identifying the effective time corresponding to each version of the impact factor node tree; determining the calculation time The effective time interval at the location and the upper limit effective time corresponding to the determined effective time interval; obtain the influence factor node tree corresponding to the upper limit effective time.

由于影响因子节点树可根据实际需求不断进行调整更新，因此基于影响因子节点树对相同的待处理数据进行计算得到的目标数值可不相同。数值计算请求携带的计算时间是指所需计算目标数值的时间。比如说，计算时间可以是基于当前时间进行数值计算，也可以是基于过去的某个时间的实际情况进行数值计算。Since the impact factor node tree can be continuously adjusted and updated according to actual needs, the target value obtained by calculating the same to-be-processed data based on the impact factor node tree may be different. The calculation time carried in the numerical calculation request refers to the time required to calculate the target value. For example, the calculation time can be calculated based on the current time, or based on the actual situation at a certain time in the past.

每个版本的影响因子节点树对应有生效时间，且生效时长为该版本影响因子节点树的生效时间至该版本的下一版本影响因子节点树生效时间。通过确定计算时间所处的生效时间区间，可确定处所生效时间区间对应的上限生效时间。上限生效时间是指计算时间对应的所需获取的影响因子节点树的生效时间。因此可通过确定的上限生效时间获取相应的影响因子节点树。通过计算时间可查询到不同时期生效的影响因子节点树，能够基于相应版本的影响因子节点树准确计算出与计算时间对应的目标数值。通过生效时间对影响因子节点树进行版本管理，能够准确影响因子节点树的变更过程，从而准确查询出待处理数据的历史数值。Each version of the impact factor node tree corresponds to an effective time, and the effective duration is from the effective time of the version of the impact factor node tree to the next version of the impact factor node tree effective time. By determining the effective time interval in which the calculation time is located, the upper limit effective time corresponding to the effective time interval in the location can be determined. The upper limit effective time refers to the effective time of the impact factor node tree required to be obtained corresponding to the calculation time. Therefore, the corresponding impact factor node tree can be obtained through the determined upper limit effective time. Through the calculation time, the influencing factor node trees effective in different periods can be queried, and the target value corresponding to the calculating time can be accurately calculated based on the corresponding version of the influencing factor node tree. The version management of the influencing factor node tree through the effective time can accurately affect the changing process of the influencing factor node tree, so as to accurately query the historical value of the data to be processed.

在一个实施例中，影响因子节点包括第一层级节点，将每个目标影响数据转换为相应的影响因子分值，包括：提取对应于第一层级节点的目标影响数据；查找与第一层级节点对应的映射表；基于映射表将第一层级节点对应的目标影响数据转换为相应的第一影响因子分值。In one embodiment, the impact factor node includes a first-level node, and converting each target impact data into a corresponding impact factor score includes: extracting target impact data corresponding to the first-level node; searching for the first-level node Corresponding mapping table; based on the mapping table, the target impact data corresponding to the first-level nodes are converted into corresponding first impact factor scores.

在一个实施例中，影响因子节点包括多个第二层级节点，将每个目标影响数据转换为相应的影响因子分值，包括：提取对应于每个第二层级节点的目标影响数据；将对应于每个第二层级节点的目标影响数据转换为相应的特征值；根据多个特征值生成特征向量；根据特征向量计算与第二层级节点对应的第二影响因子分值。In one embodiment, the impact factor node includes a plurality of second-level nodes, and converting each target impact data into a corresponding impact factor score includes: extracting target impact data corresponding to each second-level node; The target impact data for each second level node is converted into corresponding feature values; a feature vector is generated based on multiple feature values; and a second impact factor score corresponding to the second level node is calculated according to the feature vector.

第一层级节点是指只能择一匹配的节点，第二层级节点是指能多节点匹配的层级中的节点。如图3举例来说，合作渠道和保险产品为第一层级节点，产品要素为第二层级节点。一项投保单数据中通常只包含一个合作渠道标识和一个保险产品标识。而可存在多个影响保费取值的产品要素。针对第一层级节点可直接预设映射表，通过映射表将目标影响数据转换为相应的第一影响因子分值。针对多个第二层级节点则可将多个第二层级节点对应的目标影响数据处理后汇总。The first level node refers to a node that can only select one match, and the second level node refers to a node in a level that can be matched by multiple nodes. For example, as shown in Figure 3, the cooperation channel and insurance products are the first level nodes, and the product elements are the second level nodes. An insurance policy data usually contains only a cooperation channel logo and an insurance product logo. There can be multiple product factors that affect the value of premiums. For the first-level nodes, a mapping table can be directly preset, and the target impact data can be converted into corresponding first impact factor scores through the mapping table. For multiple second-level nodes, the target impact data corresponding to the multiple second-level nodes can be processed and aggregated.

在一个实施例中，可以通过映射表将对应于每个第二层级节点的目标影响数据转换为相应的特征值。比如说，可将资金方经营情况、借款方信用风险等级、贷款产品性质、借贷利率等映射为特征值。举例来说信用风险可分为1-6个信用风险等级，由于借款方信用风险等级越高则需提高保费，若特征值以1为最大值，则可如下表1所示，将越高的信用风险等级映射为更高的特征值：In one embodiment, the target impact data corresponding to each second-level node may be converted into corresponding feature values through a mapping table. For example, the operating conditions of the funder, the credit risk level of the borrower, the nature of the loan product, and the loan interest rate can be mapped as characteristic values. For example, credit risk can be divided into 1-6 credit risk levels. Since the higher the credit risk level of the borrower, the higher the premium, if the characteristic value is 1 as the maximum value, it can be as shown in Table 1 below. The credit risk level is mapped to a higher eigenvalue:

表1Table 1

信用风险等级Credit risk rating	11	22	33	44	55	66
特征值Eigenvalues	1/61/6	1/31/3	1/21/2	2/32/3	5/65/6	11

在一个实施例中，Rx1至Rxn为各个第二层级节点的目标影响数据对应的特征值，特征向量可表示为Rx(Rx1，Rx2，Rx3……Rxn)，可根据公式：

将根据特征向量计算得到与第二层级节点对应的第二影响因子分值。 In one embodiment, Rx1 to Rxn are the eigenvalues corresponding to the target impact data of each second-level node, and the eigenvectors can be expressed as Rx(Rx1, Rx2, Rx3...Rxn), according to the formula:

The second impact factor score corresponding to the second-level node will be calculated according to the feature vector.

在一个实施例中，在获取与数据标识对应的待处理数据之后，还包括：对待处理数据进行分词，得到多个词序列；将每个词序列中包含的多个原始词语与标签词库中的关键词进行匹配，得到与每个词序列匹配的关键词；对每个词序列打上目标标签；目标标签与相应词序列匹配的关键词所属的标签词库相对应。In one embodiment, after obtaining the data to be processed corresponding to the data identifier, the method further includes: segmenting the data to be processed to obtain multiple word sequences; and combining multiple original words and tag thesaurus contained in each word sequence Match keywords to get keywords that match each word sequence; mark each word sequence with a target tag; the target tag corresponds to the tag lexicon to which the keyword matching the corresponding word sequence belongs.

在一个实施例中，在对每个词序列打上目标标签之后，还包括：查找与多个影响因子节点匹配的目标标签；提取待处理数据中每个与影响因子节点对应的目标影响数据，包括：提取每个匹配的目标标签对应的词序列。In one embodiment, after tagging each word sequence with target tags, the method further includes: finding target tags matching multiple impact factor nodes; extracting target impact data corresponding to the impact factor nodes in the data to be processed, including : Extract the word sequence corresponding to each matching target label.

当待处理数据为非结构化数据，比如文本文件或纸质文件扫描版时，可在服务器端基于字符串匹配的分词方法对待处理数据进行分词，得到词序列。词序列是指由多个原始词语按照原始顺序构成的序列。通过将原始词语与标签词库中的关键词进行匹配，可以确定每个词序列对应的标签词库，可通过确定的标签词库确定每个目标实际数据对应的目标标签。目标标签可与影响因子节点相对应，通过将目标标签与影响因子节点匹配，可从待处理数据中提取出多个所需用于计算数值的目标影响数据。When the data to be processed is unstructured data, such as a scanned version of a text file or a paper file, the data to be processed can be segmented on the server side based on the word segmentation method of string matching to obtain a word sequence. The word sequence refers to a sequence composed of multiple original words in the original order. By matching the original words with the keywords in the tag lexicon, the tag lexicon corresponding to each word sequence can be determined, and the target tag corresponding to each target actual data can be determined by the determined tag lexicon. The target label can correspond to the impact factor node. By matching the target label with the impact factor node, multiple target impact data needed to calculate the value can be extracted from the data to be processed.

在一个实施例中，还可在终端上传待处理数据时，便根据输入待处理数据的文本框对每个待处理数据进行标签标记。当投保单数据为JSON数据时，可为用户在前端填写form表单转换得到的JSON数据，则JSON数据中每一个键即可作为一个目标标签，键对应的值可即为待处理数据。In one embodiment, when the terminal uploads the data to be processed, each data to be processed is labeled according to the text box for inputting the data to be processed. When the insurance policy data is JSON data, the user can fill in the JSON data converted from the form in the front end, then each key in the JSON data can be used as a target label, and the value corresponding to the key can be the data to be processed.

在一个实施例中，如图4所示，提供了另一种数值计算方法，以该方法应用于图1中的服务器104为例进行说明，包括以下步骤：In one embodiment, as shown in FIG. 4, another numerical calculation method is provided. Taking the method applied to the server 104 in FIG. 1 as an example for illustration, it includes the following steps:

步骤402，接收数值计算请求；数值计算请求携带数据标识和计算时间。Step 402: Receive a numerical calculation request; the numerical calculation request carries the data identifier and the calculation time.

步骤404，获取与数据标识对应的待处理数据。Step 404: Obtain data to be processed corresponding to the data identifier.

步骤406，查找多个版本的影响因子节点树。Step 406: Find multiple versions of the impact factor node tree.

步骤408，识别每个版本的影响因子节点树对应的生效时间。Step 408: Identify the effective time corresponding to each version of the impact factor node tree.

步骤410，确定计算时间所处的生效时间区间，以及确定生效时间区间对应的上限生效时间。Step 410: Determine the effective time interval in which the calculation time is located, and determine the upper limit effective time corresponding to the effective time interval.

步骤412，获取上限生效时间对应的影响因子节点树；影响因子节点树包含多个影响因子节点。Step 412: Obtain an impact factor node tree corresponding to the upper limit effective time; the impact factor node tree includes multiple impact factor nodes.

步骤414，提取待处理数据中每个与影响因子节点对应的目标影响数据。Step 414: Extract target impact data corresponding to each impact factor node in the data to be processed.

步骤416，基于影响因子节点树获取与每个目标影响数据对应的节点权重。Step 416: Obtain the node weight corresponding to each target impact data based on the impact factor node tree.

步骤418，将每个目标影响数据转换为相应的影响因子分值。In step 418, each target impact data is converted into a corresponding impact factor score.

步骤420，根据多个影响因子分值和与每个影响因子分值相应的节点权重，计算得到比例系数。In step 420, a proportional coefficient is calculated according to multiple impact factor scores and node weights corresponding to each impact factor score.

步骤422，从待处理数据中提取得到基础数值。Step 422: Extract basic values from the data to be processed.

步骤424，根据比例系数和基础数值计算得到目标数值。Step 424: Calculate the target value according to the scale factor and the basic value.

上述数值计算方法中，服务器接收携带数据标识和计算时间的数值计算请求之后，可获取与数据标识对应的待处理数据，还可获取由多个影响因子节点构成的影响因子节点树，影响因子节点树为与计算时间对应的版本，针对每个影响节点因子预设有对应的节点权重。服务器可从待处理数据中提取每个与影响因子节点对应的目标影响数据，并获取与每个提取的目标影响数据对应的节点权重。将目标影响数据准还为影响因子分值之后，服务器还可以根据影响因子分值和相应的节点权重计算得到目标数值。通过预先配置的多种影响因子节点，使得服务器能够基于待处理数据自动化计算出相应的目标数值，由于在数据分析时考虑了多种影响因子，从而能够灵活、高效地计算得到准确的数值。In the above numerical calculation method, after receiving the numerical calculation request carrying the data identification and calculation time, the server can obtain the data to be processed corresponding to the data identification, and can also acquire an impact factor node tree composed of multiple impact factor nodes, and an impact factor node The tree is a version corresponding to the calculation time, and a corresponding node weight is preset for each influencing node factor. The server may extract each target impact data corresponding to the impact factor node from the data to be processed, and obtain the node weight corresponding to each extracted target impact data. After returning the target impact data to the impact factor score, the server can also calculate the target value according to the impact factor score and the corresponding node weight. Through pre-configured multiple impact factor nodes, the server can automatically calculate the corresponding target value based on the data to be processed. Since multiple impact factors are considered during data analysis, accurate values can be calculated flexibly and efficiently.

应该理解的是，虽然图2和4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2和4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。It should be understood that although the steps in the flowcharts of FIGS. 2 and 4 are displayed in order according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless clearly stated in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in FIGS. 2 and 4 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but may be executed at different times. These sub-steps or stages The execution order of is not necessarily sequential, but may be executed in turn or alternately with at least a part of other steps or sub-steps or stages of other steps.

在一个实施例中，如图5所示，提供了一种数值计算装置500，包括：接收模块502，用于接收数值计算请求；数值计算请求携带数据标识；获取模块504，用于获取与数据标识对应的待处理数据；获取影响因子节点树；影响因子节点树由多个影响因子节点构成；提取模块506，用于提取待处理数据中每个与影响因子节点对应的目标影响数据；计算模块508，用于基于影响因子节点树获取与每个目标影响数据对应的节点权重；根据目标影响数据和相应的节点权重计算得到目标数值。In one embodiment, as shown in FIG. 5, a numerical calculation device 500 is provided, including: a receiving module 502 for receiving a numerical calculation request; a numerical calculation request carrying a data identifier; an acquisition module 504 for acquiring and data Identify the corresponding data to be processed; obtain the impact factor node tree; the impact factor node tree is composed of multiple impact factor nodes; the extraction module 506 is used to extract the target impact data corresponding to the impact factor node in the data to be processed; the calculation module 508, used to obtain the node weight corresponding to each target influence data based on the influence factor node tree; calculate the target value according to the target influence data and the corresponding node weight.

在一个实施例中，数值计算请求还携带计算时间，获取模块504还用于查找多个版本的影响因子节点树；识别每个版本的影响因子节点树对应的生效时间；确定计算时间所处的生效时间区间，以及确定生效时间区间对应的上限生效时间；获取上限生效时间对应的影响因子节点树。In one embodiment, the numerical calculation request also carries the calculation time, and the acquisition module 504 is also used to find multiple versions of the impact factor node tree; identify the effective time corresponding to each version of the impact factor node tree; determine the calculation time Effective time interval, and determine the upper limit effective time corresponding to the effective time interval; obtain the influence factor node tree corresponding to the upper limit effective time.

在一个实施例中，计算模块508还用于将每个目标影响数据转换为相应的影响因子分值；根据多个影响因子分值和与每个影响因子分值相应的节点权重，计算得到比例系数；从待处理数据中提取得到基础数值；根据比例系数和基础数值计算得到目标数值。In one embodiment, the calculation module 508 is also used to convert each target impact data into corresponding impact factor scores; based on multiple impact factor scores and node weights corresponding to each impact factor score, the ratio is calculated Coefficient; extract the basic value from the data to be processed; calculate the target value according to the proportional coefficient and the basic value.

在一个实施例中，影响因子节点包括第一层级节点，计算模块508还用于提取对应于第一层级节点的目标影响数据；查找与第一层级节点对应的映射表；基于映射表将第一层级节点对应的目标影响数据转换为相应的第一影响因子分值。In one embodiment, the influence factor node includes a first-level node, and the calculation module 508 is further used to extract target impact data corresponding to the first-level node; look up a mapping table corresponding to the first-level node; The target impact data corresponding to the level nodes are converted into corresponding first impact factor scores.

在一个实施例中，影响因子节点包括多个第二层级节点，计算模块508还用于提取对应于每个第二层级节点的目标影响数据；将对应于每个第二层级节点的目标影响数据转换为相应的特征值；根据多个特征值生成特征向量；根据特征向量计算与第二层级节点对应的第二影响因子分值。In one embodiment, the impact factor node includes a plurality of second-level nodes, and the calculation module 508 is further used to extract target impact data corresponding to each second-level node; the target impact data corresponding to each second-level node Convert to corresponding eigenvalues; generate eigenvectors based on multiple eigenvalues; calculate the second impact factor score corresponding to the second level node according to the eigenvectors.

在一个实施例中，该装置还包括标签模块，用于对待处理数据进行分词，得到多个词序列；将每个词序列中包含的多个原始词语与标签词库中的关键词进行匹配，得到与每个词序列匹配的关键词；对每个词序列打上目标标签；目标标签与相应词序列匹配的关键词所属的标签词库相对应。In one embodiment, the device further includes a tag module for segmenting the data to be processed to obtain multiple word sequences; matching multiple original words contained in each word sequence with keywords in the tag lexicon, Get keywords that match each word sequence; mark each word sequence with a target tag; the target tag corresponds to the tag lexicon to which the keyword matching the corresponding word sequence belongs.

在一个实施例中，标签模块还用于查找与多个影响因子节点匹配的目标标签；提取待处理数据中每个与影响因子节点对应的目标影响数据，包括：提取每个匹配的目标标签对应的词序列。In one embodiment, the tag module is also used to find target tags matching multiple impact factor nodes; extracting target impact data corresponding to the impact factor nodes in the data to be processed includes: extracting the corresponding target tag Word sequence.

关于数值计算装置的具体限定可以参见上文中对于数值计算方法的限定，在此不再赘述。上述数值计算装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。For the specific limitation of the numerical calculation device, reference may be made to the limitation on the numerical calculation method in the foregoing, which will not be repeated here. Each module in the above numerical calculation device may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in the hardware form or independent of the processor in the computer device, or may be stored in the memory in the computer device in the form of software so that the processor can call and execute the operations corresponding to the above modules.

在一个实施例中，提供了一种计算机设备，该计算机设备可以是服务器，其内部结构图可以如图6所示。该计算机设备包括通过***总线连接的处理器、存储器、网络接口和数据库。其中，该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性存储介质、内存储器。该非易失性存储介质存储有操作***、计算机可读指令和数据库。该内存储器为非易失性存储介质中的操作***和计算机可读指令的运行提供环境。该计算机设备的数据库用于存储影响因子节点树等数据。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机可读指令被处理器执行时以实现一种数值计算方法。In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure may be as shown in FIG. 6. The computer device includes a processor, memory, network interface, and database connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer-readable instructions, and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the non-volatile storage medium. The database of the computer device is used to store data such as impact factor node trees. The network interface of the computer device is used to communicate with external terminals through a network connection. The computer readable instructions are executed by the processor to implement a numerical calculation method.

本领域技术人员可以理解，图6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。Those skilled in the art can understand that the structure shown in FIG. 6 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. The specific computer equipment may Include more or less components than shown in the figure, or combine certain components, or have a different arrangement of components.

在一个实施例中，提供了一种计算机设备，包括存储器及一个或多个处理器，存储器中储存有计算机可读指令，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上述各个实施例中提供的步骤。In one embodiment, a computer device is provided, which includes a memory and one or more processors. The memory stores computer-readable instructions. When the computer-readable instructions are executed by one or more processors, one or more Each processor executes the steps provided in the above embodiments.

在一个实施例中，提供了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，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上述各个实施例中提供的步骤。In one embodiment, one or more non-volatile computer-readable storage media storing computer-readable instructions are provided. When the computer-readable instructions are executed by one or more processors, the one or more processors Perform the steps provided in the various embodiments described above.

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。A person of ordinary skill in the art may understand that all or part of the process in the method of the foregoing embodiments may be completed by instructing relevant hardware through computer-readable instructions, and the computer-readable instructions may be stored in a non-volatile computer In a readable storage medium, when the computer-readable instructions are executed, they may include the processes of the foregoing method embodiments. Wherein, any reference to the memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and/or volatile memory. Non-volatile memory may 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. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

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。The technical features of the above embodiments can be arbitrarily combined. In order to simplify the description, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered as the scope described in this specification.

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。The above-mentioned embodiments only express several implementations of the present application, and their descriptions are more specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that, for those of ordinary skill in the art, without departing from the concept of the present application, a number of modifications and improvements can also be made, which all fall within the protection scope of the present application. Therefore, the protection scope of the patent of this application shall be subject to the appended claims.

Claims

一种数值计算方法，包括：A numerical calculation method, including:

接收数值计算请求；所述数值计算请求携带数据标识；Receiving a numerical calculation request; the numerical calculation request carries a data identifier;

获取与数据标识对应的待处理数据；Obtain the data to be processed corresponding to the data identifier;

获取影响因子节点树；所述影响因子节点树包含多个影响因子节点；Obtain an impact factor node tree; the impact factor node tree contains multiple impact factor nodes;

提取所述待处理数据中每个与影响因子节点对应的目标影响数据；Extract target impact data corresponding to each impact factor node in the data to be processed;

基于影响因子节点树获取与每个目标影响数据对应的节点权重；及Obtain the node weight corresponding to each target impact data based on the impact factor node tree; and

根据所述目标影响数据和相应的节点权重计算得到目标数值。The target value is calculated according to the target influence data and the corresponding node weight.
根据权利要求1所述的方法，其特征在于，所述数值计算请求还携带计算时间，所述获取影响因子节点树包括：The method according to claim 1, wherein the numerical calculation request further carries a calculation time, and the obtaining an impact factor node tree includes:

查找多个版本的影响因子节点树；Find multiple versions of the impact factor node tree;

识别每个版本的影响因子节点树对应的生效时间；Identify the effective time corresponding to each version of the impact factor node tree;

确定所述计算时间所处的生效时间区间，以及确定所述生效时间区间对应的上限生效时间；及Determine the effective time interval in which the calculation time is located, and determine the upper limit effective time corresponding to the effective time interval; and

获取所述上限生效时间对应的影响因子节点树。Obtain an impact factor node tree corresponding to the upper limit effective time.
根据权利要求1所述的方法，其特征在于，所述提取所述待处理数据中每个与影响因子节点对应的目标影响数据包括：The method according to claim 1, wherein the extracting each target impact data corresponding to an impact factor node in the data to be processed comprises:

通过所述影响因子对所述待处理数据中包含的多种类型的信息进行筛选，得到计算所述目标数值所需的目标影响数据。Filtering various types of information contained in the data to be processed by the impact factor to obtain target impact data required for calculating the target value.
根据权利要求1所述的方法，其特征在于，所述根据所述目标影响数据和相应的节点权重计算得到目标数值包括：The method according to claim 1, wherein the calculation of the target value based on the target impact data and corresponding node weights includes:

将每个所述目标影响数据转换为相应的影响因子分值；Convert each of the target impact data into corresponding impact factor scores;

获取所述影响因子节点树中的每个影响因子节点预设的节点权重；Acquiring the preset node weight of each impact factor node in the impact factor node tree;

根据每个影响因子分值与相对应的节点权重，通过预设的公式计算得到比例系数；According to the score of each impact factor and the corresponding node weight, the proportional coefficient is calculated by a preset formula;

从所述待处理数据中提取得到基础数值；及Extract basic values from the data to be processed; and

根据所述比例系数和所述基础数值计算得到目标数值。The target value is calculated according to the scale factor and the basic value.
根据权利要求4所述的方法，其特征在于，所述影响因子节点包括第一层级节点，所述将每个所述目标影响数据转换为相应的影响因子分值，包括：The method according to claim 4, wherein the impact factor node includes a first-level node, and the converting each of the target impact data into a corresponding impact factor score includes:

提取对应于所述第一层级节点的目标影响数据；Extract target impact data corresponding to the first-level node;

查找与所述第一层级节点对应的映射表；及Look up a mapping table corresponding to the first level node; and

基于所述映射表将所述第一层级节点对应的目标影响数据转换为相应的第一影响因子分值。Based on the mapping table, the target impact data corresponding to the first level node is converted into a corresponding first impact factor score.
根据权利要求4所述的方法，其特征在于，所述影响因子节点包括多个第二层级节点，所述将每个所述目标影响数据转换为相应的影响因子分值，包括：The method according to claim 4, wherein the impact factor node includes a plurality of second-level nodes, and the converting each of the target impact data into a corresponding impact factor score includes:

提取对应于每个所述第二层级节点的目标影响数据；Extract target impact data corresponding to each of the second-level nodes;

通过所述映射表将对应于每个所述第二层级节点的目标影响数据转换为相应的特征值；Converting the target impact data corresponding to each of the second-level nodes into corresponding feature values through the mapping table;

根据多个所述特征值生成特征向量；及Generating a feature vector based on a plurality of the feature values; and

根据所述特征向量计算与第二层级节点对应的第二影响因子分值。The second impact factor score corresponding to the second level node is calculated according to the feature vector.
根据权利要求1所述的方法，其特征在于，在所述获取与数据标识对应的待处理数据之后，还包括：The method according to claim 1, wherein after the acquiring the data to be processed corresponding to the data identifier, the method further comprises:

当所述待处理数据为非结构化数据时，对所述待处理数据进行分词，得到多个词序列；When the data to be processed is unstructured data, segment the data to be processed to obtain multiple word sequences;

将每个所述词序列中包含的多个原始词语与标签词库中的关键词进行匹配，得到与每个所述词序列匹配的关键词以及确定每个词序列对应的标签词库；及Matching a plurality of original words contained in each of the word sequences with keywords in a tag lexicon to obtain keywords matching each of the word sequences and determining a tag lexicon corresponding to each word sequence; and

通过确定的标签词库对每个所述词序列打上目标标签；所述目标标签与相应词序列匹配的关键词所属的标签词库相对应。Each of the word sequences is marked with a target tag by the determined tag lexicon; the target tag corresponds to the tag lexicon to which the keywords matching the corresponding word sequence belong.
根据权利要求7所述的方法，其特征在于，在对每个所述词序列打上目标标签之后，还包括：The method according to claim 7, wherein after the target tag is added to each of the word sequences, the method further comprises:

查找与所述多个影响因子节点匹配的目标标签；及Find target tags matching the multiple impact factor nodes; and

所述提取所述待处理数据中每个与影响因子节点对应的目标影响数据，包括：提取每个匹配的目标标签对应的词序列。The extracting each target impact data corresponding to an impact factor node in the data to be processed includes extracting a word sequence corresponding to each matching target tag.
一种数值计算装置，包括：A numerical calculation device, including:

接收模块，用于接收数值计算请求；所述数值计算请求携带数据标识；A receiving module, for receiving a numerical calculation request; the numerical calculation request carries a data identifier;

获取模块，用于获取与数据标识对应的待处理数据；获取影响因子节点树；所述影响因子节点树由多个影响因子节点构成；An acquisition module, for acquiring data to be processed corresponding to the data identifier; acquiring an impact factor node tree; the impact factor node tree is composed of multiple impact factor nodes;

提取模块，用于提取所述待处理数据中每个与影响因子节点对应的目标影响数据；及An extraction module for extracting target impact data corresponding to each impact factor node in the data to be processed; and

计算模块，用于基于影响因子节点树获取与每个目标影响数据对应的节点权重；根据所述目标影响数据和相应的节点权重计算得到目标数值。The calculation module is used to obtain the node weight corresponding to each target impact data based on the impact factor node tree; calculate the target value according to the target impact data and the corresponding node weight.
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：A computer device includes a memory and one or more processors. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the one or more processors, the one or more Each processor performs the following steps:

接收数值计算请求；所述数值计算请求携带数据标识；Receiving a numerical calculation request; the numerical calculation request carries a data identifier;

获取与数据标识对应的待处理数据；Obtain the data to be processed corresponding to the data identifier;

获取影响因子节点树；所述影响因子节点树包含多个影响因子节点；Obtain an impact factor node tree; the impact factor node tree contains multiple impact factor nodes;

提取所述待处理数据中每个与影响因子节点对应的目标影响数据；Extract target impact data corresponding to each impact factor node in the data to be processed;

基于影响因子节点树获取与每项目标影响数据对应的节点权重；及Obtain the node weight corresponding to the impact data of each target based on the impact factor node tree; and

根据所述目标影响数据和相应的节点权重计算得到目标数值。The target value is calculated according to the target influence data and the corresponding node weight.
根据权利要求10所述的计算机设备，其特征在于，所述数值计算请求还携带计算时间，所述计算机可读指令被所述一个或多个处理器执行时，还执行以下步骤：The computer device according to claim 10, wherein the numerical calculation request further carries a calculation time, and when the computer-readable instructions are executed by the one or more processors, the following steps are also performed:

查找多个版本的影响因子节点树；Find multiple versions of the impact factor node tree;

识别每个版本的影响因子节点树对应的生效时间；Identify the effective time corresponding to each version of the impact factor node tree;

确定所述计算时间所处的生效时间区间，以及确定所述生效时间区间对应的上限生效时间；及Determine the effective time interval in which the calculation time is located, and determine the upper limit effective time corresponding to the effective time interval; and

获取所述上限生效时间对应的影响因子节点树。Obtain an impact factor node tree corresponding to the upper limit effective time.
根据权利要求10所述计算机设备，其特征在于，所述计算机可读指令被所述一个或多个处理器执行时，还执行以下步骤：The computer device according to claim 10, wherein when the computer-readable instructions are executed by the one or more processors, the following steps are further performed:

通过所述影响因子对所述待处理数据中包含的多种类型的信息进行筛选，得到计算所述目标数值所需的目标影响数据。Filtering various types of information contained in the data to be processed by the impact factor to obtain target impact data required for calculating the target value.
根据权利要求10所述计算机设备，其特征在于，所述计算机可读指令被所述一个或多个处理器执行时，还执行以下步骤：The computer device according to claim 10, wherein when the computer-readable instructions are executed by the one or more processors, the following steps are further performed:

将每个所述目标影响数据转换为相应的影响因子分值；Convert each of the target impact data into corresponding impact factor scores;

获取所述影响因子节点树中的每个影响因子节点预设的节点权重；Acquiring the preset node weight of each impact factor node in the impact factor node tree;

根据每个影响因子分值与相对应的节点权重，通过预设的公式计算得到比例系数；According to the score of each impact factor and the corresponding node weight, the proportional coefficient is calculated by a preset formula;

从所述待处理数据中提取得到基础数值；及Extract basic values from the data to be processed; and

根据所述比例系数和所述基础数值计算得到目标数值。The target value is calculated according to the scale factor and the basic value.
根据权利要求13所述计算机设备，其特征在于，所述影响因子节点包括第一层级节点，所述计算机可读指令被所述一个或多个处理器执行时，还执行以下步骤：The computer device according to claim 13, wherein the impact factor node includes a first-level node, and when the computer-readable instructions are executed by the one or more processors, the following steps are further performed:

提取对应于所述第一层级节点的目标影响数据；Extract target impact data corresponding to the first-level node;

查找与所述第一层级节点对应的映射表；及Look up a mapping table corresponding to the first level node; and

基于所述映射表将所述第一层级节点对应的目标影响数据转换为相应的第一影响因子分值。Based on the mapping table, the target impact data corresponding to the first level node is converted into a corresponding first impact factor score.
根据权利要求13所述计算机设备，其特征在于，所述影响因子节点包括多个第二层级节点，所述计算机可读指令被所述一个或多个处理器执行时，还执行以下步骤：The computer device according to claim 13, wherein the impact factor node includes a plurality of second-level nodes, and when the computer-readable instructions are executed by the one or more processors, the following steps are further performed:

提取对应于每个所述第二层级节点的目标影响数据；Extract target impact data corresponding to each of the second-level nodes;

通过所述映射表将对应于每个所述第二层级节点的目标影响数据转换为相应的特征值；Converting the target impact data corresponding to each of the second-level nodes into corresponding feature values through the mapping table;

根据多个所述特征值生成特征向量；及Generating a feature vector based on a plurality of the feature values; and

根据所述特征向量计算与第二层级节点对应的第二影响因子分值。The second impact factor score corresponding to the second level node is calculated according to the feature vector.
根据权利要求10所述计算机设备，其特征在于，所述计算机可读指令被所述一个或多个处理器执行时，还执行以下步骤：The computer device according to claim 10, wherein when the computer-readable instructions are executed by the one or more processors, the following steps are further performed:

当所述待处理数据为非结构化数据时，对所述待处理数据进行分词，得到多个词序列；When the data to be processed is unstructured data, segment the data to be processed to obtain multiple word sequences;

将每个所述词序列中包含的多个原始词语与标签词库中的关键词进行匹配，得到与每个所述词序列匹配的关键词以及确定每个词序列对应的标签词库；及Matching a plurality of original words contained in each of the word sequences with keywords in a tag lexicon to obtain keywords matching each of the word sequences and determining a tag lexicon corresponding to each word sequence; and

通过确定的标签词库对每个所述词序列打上目标标签；所述目标标签与相应词序列匹配的关键词所属的标签词库相对应。Each of the word sequences is marked with a target tag by the determined tag lexicon; the target tag corresponds to the tag lexicon to which the keywords matching the corresponding word sequence belong.
根据权利要求16所述计算机设备，其特征在于，所述计算机可读指令被所述一个或多个处理器执行时，还执行以下步骤：The computer device of claim 16, wherein when the computer-readable instructions are executed by the one or more processors, the following steps are further performed:

查找与所述多个影响因子节点匹配的目标标签；及Find target tags matching the multiple impact factor nodes; and

所述提取所述待处理数据中每个与影响因子节点对应的目标影响数据，包括：提取每个匹配的目标标签对应的词序列。The extracting each target impact data corresponding to an impact factor node in the data to be processed includes extracting a word sequence corresponding to each matching target tag.
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：One or more non-volatile computer-readable storage media storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to perform the following steps:

接收数值计算请求；所述数值计算请求携带数据标识；Receiving a numerical calculation request; the numerical calculation request carries a data identifier;

获取与数据标识对应的待处理数据；Obtain the data to be processed corresponding to the data identifier;

获取影响因子节点树；所述影响因子节点树包含多个影响因子节点；Obtain an impact factor node tree; the impact factor node tree contains multiple impact factor nodes;

提取所述待处理数据中每个与影响因子节点对应的目标影响数据；Extract target impact data corresponding to each impact factor node in the data to be processed;

基于影响因子节点树获取与每项目标影响数据对应的节点权重；及Obtain the node weight corresponding to the impact data of each target based on the impact factor node tree; and

根据所述目标影响数据和相应的节点权重计算得到目标数值。The target value is calculated according to the target influence data and the corresponding node weight.
根据权利要求18所述的计算机可读存储介质，其特征在于，所述计算机可读指令被一个或多个处理器执行时，还执行以下步骤：The computer-readable storage medium of claim 18, wherein when the computer-readable instructions are executed by one or more processors, the following steps are further performed:

通过所述影响因子对所述待处理数据中包含的多种类型的信息进行筛选，得到计算所述目标数值所需的目标影响数据。Filtering various types of information contained in the data to be processed by the impact factor to obtain target impact data required for calculating the target value.
根据权利要求18所述的计算机可读存储介质，其特征在于，所述计算机可读指令被一个或多个处理器执行时，还执行以下步骤：The computer-readable storage medium of claim 18, wherein when the computer-readable instructions are executed by one or more processors, the following steps are further performed:

将每个所述目标影响数据转换为相应的影响因子分值；Convert each of the target impact data into corresponding impact factor scores;

获取所述影响因子节点树中的每个影响因子节点预设的节点权重；Acquiring the preset node weight of each impact factor node in the impact factor node tree;

根据每个影响因子分值与相对应的节点权重，通过预设的公式计算得到比例系数；According to the score of each impact factor and the corresponding node weight, the proportional coefficient is calculated by a preset formula;

从所述待处理数据中提取得到基础数值；及Extract basic values from the data to be processed; and

根据所述比例系数和所述基础数值计算得到目标数值。The target value is calculated according to the scale factor and the basic value.