WO2020087981A1 - 风控审核模型生成方法、装置、设备及可读存储介质 - Google Patents

风控审核模型生成方法、装置、设备及可读存储介质 Download PDF

Info

Publication number
WO2020087981A1
WO2020087981A1 PCT/CN2019/095838 CN2019095838W WO2020087981A1 WO 2020087981 A1 WO2020087981 A1 WO 2020087981A1 CN 2019095838 W CN2019095838 W CN 2019095838W WO 2020087981 A1 WO2020087981 A1 WO 2020087981A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
audit
risk control
model
control audit
Prior art date
Application number
PCT/CN2019/095838
Other languages
English (en)
French (fr)
Inventor
罗成洋
Original Assignee
平安医疗健康管理股份有限公司
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 平安医疗健康管理股份有限公司 filed Critical 平安医疗健康管理股份有限公司
Publication of WO2020087981A1 publication Critical patent/WO2020087981A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q40/00Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08Insurance

Definitions

  • the present application relates to the field of data processing technology, and in particular, to a method, device, device, and readable storage medium for generating a risk control audit model.
  • the main purpose of the present application is to provide a method, device, equipment and readable storage medium for generating a risk control audit model, aiming to solve the technical problem of low efficiency of the risk control audit model corresponding to the existing risk control audit rules.
  • the present application provides a method for generating a risk control audit model.
  • the method for generating a risk control audit model includes the steps of:
  • the step of acquiring a preset risk control audit rule and configuring a data association model according to the risk control audit rule includes:
  • the step of determining the data type corresponding to the review details, and configuring the data association model according to the limiting conditions and logical relationships corresponding to the various data types includes:
  • the step of generating a data storage template in a preset format according to the data association model includes:
  • At least one link channel is set in the table to associate each table through the link channel to generate a data storage template in a preset format.
  • the step of acquiring the target data corresponding to the risk control review rule through the data storage template includes:
  • the corresponding data storage template is displayed according to the entry instruction for the entry personnel to enter the corresponding target data in the data storage template.
  • the step of generating a JSON file according to the target data and the corresponding data storage template, and importing the JSON file into a preset audit engine to generate a risk control audit model further includes:
  • the step of generating a JSON file according to the target data and the corresponding data storage template, and importing the JSON file into a preset audit engine to generate a risk control audit model further includes:
  • the data to be audited is compared with the target data corresponding to the JSON file in the auditing engine to audit the data to be audited.
  • the present application also provides a risk control audit model generation device, the risk control audit model generation device includes:
  • the acquisition module is used to obtain preset risk control audit rules
  • a configuration module configured to configure a data association model according to the risk control review rules
  • a generating module configured to generate a data storage template in a preset format according to the data association model
  • the obtaining module is further used to obtain the target data corresponding to the risk control audit rule through the data storage template;
  • the generating module is further configured to generate a JS object notation JSON file according to the target data and the corresponding data storage template;
  • the import module is used to import the JSON file into a preset audit engine to generate a risk control audit model.
  • the present application also provides a risk control audit model generation device, which includes a memory, a processor, and a A risk control audit model generation program that implements the steps of the risk control audit model generation method described above when executed by the processor.
  • the present application also provides a computer-readable storage medium on which a risk control audit model generation program is stored, which is implemented when the processor is executed by the processor The steps of the risk control audit model generation method as described above.
  • This application configures the data association model according to the acquired risk control audit rules, generates a data storage template corresponding to the data association model, and obtains the target data corresponding to the risk control audit rules through the data storage template, based on the target data and the corresponding data
  • the storage template generates a JSON file, and imports the JSON file into a preset audit engine to generate a risk control audit model, which realizes that in the process of generating specific content of the risk control audit rules, developers do not need to program according to the rule details provided by business personnel
  • the JSON file corresponding to the risk control audit rules can be directly generated according to the obtained target data, which improves the efficiency of generating the risk control audit model corresponding to the risk control audit rules.
  • FIG. 1 is a schematic flowchart of a first embodiment of a method for generating a risk control audit model of this application
  • FIG. 2 is a schematic flowchart of a second embodiment of a method for generating a risk control audit model of this application
  • FIG. 3 is a schematic flowchart of a third embodiment of a method for generating a risk control audit model of the present application
  • FIG. 4 is a functional schematic block diagram of a preferred embodiment of a risk control audit model generation device of this application.
  • FIG. 5 is a schematic structural diagram of a hardware operating environment involved in a solution of an embodiment of the present application.
  • FIG. 1 is a schematic flowchart of a first embodiment of a method for generating a risk control audit model in this application.
  • the embodiment of the present application provides an embodiment of a method for generating a risk control audit model. It should be noted that although the logic sequence is shown in the flowchart, in some cases, the sequence may be performed differently from the sequence shown here. Out or describe the steps.
  • the risk control audit model generation method is applied to a server or a terminal, and the terminal may include, for example, a mobile phone, a tablet computer, a notebook computer, a palmtop computer, and a personal digital assistant (Personal Digital Assistant, PDA) and other mobile terminals, and fixed terminals such as digital TV, desktop computers and so on.
  • the execution subject is omitted to explain each embodiment.
  • Risk control audit model generation methods include:
  • Step S10 Acquire preset risk control audit rules, and configure a data association model according to the risk control audit rules.
  • the preset risk control audit rules are obtained, and the data association model is configured according to the risk control audit rules.
  • the generation instruction can be triggered by the corresponding staff as needed, and the preset risk control audit rules are used to check whether various data meet the preset conditions.
  • the risk control review rules should include rules for reviewing the logical relationship and limiting conditions between various medical data.
  • the logical relationship specifically includes a positive correlation relationship, a negative correlation relationship, and a conditional relationship.
  • the positive correlation relationship is a relationship that must or can exist simultaneously between data
  • the negative correlation relationship is a relationship that cannot exist simultaneously between data.
  • a conditional relationship is a relationship between data when a piece of data satisfies a certain condition, there is corresponding another data, or there is no corresponding another data relationship.
  • the limiting condition may be the condition that the data to be audited needs to be satisfied, such as a numerical range, a preset type, etc.
  • step S10 includes:
  • Step a Acquire preset risk control audit rules and determine the audit type corresponding to the risk control audit rules.
  • Different audit types are set in the risk control audit rules, and the audit types corresponding to the risk control audit rules can be determined according to the audit requirements and audit content of the risk control audit rules. For example, when reviewing medical data, different risk control audit rules are set according to the different conditions of the disease, and the audit types corresponding to the risk control audit rules are divided according to the audit requirements and audit content in the risk control audit rules.
  • the audit types of risk control audit rules corresponding to medical data include but are not limited to medication audit types, inspection item audit types, and expense audit types.
  • the audit type corresponding to the risk control audit rules is determined according to the audit requirements and / or audit content corresponding to the risk control audit rules. If the audit content of the risk control audit rule is to check whether the cost of the drug used by the user is correct, then determine that the audit type corresponding to the risk control audit rule is the expense audit type; If the application medicine is correct, it is determined that the audit type corresponding to the risk control audit rule is the medicine audit type.
  • Step b Configure audit rules corresponding to the risk control audit rules according to the audit type.
  • each audit type needs to be configured with corresponding audit rules, and the same audit type corresponds to multiple audit rules.
  • the audit rules can be set by the corresponding staff according to the specific situation, and the audit rules corresponding to different types of audits are different.
  • Step c Determine the data type corresponding to the audit details, and configure the data association model according to the limiting conditions and logical relationships corresponding to the various data types.
  • the data association model is preset to establish an association relationship between data types.
  • the duplicate drugs may be drugs with the same curative effect or drugs with mutually exclusive curative effects Wait.
  • the data types corresponding to the audit rules include but are not limited to the insured's condition, drugs with the same effect under the same condition, and drugs with mutually exclusive effects under the same condition.
  • the dosage of drugs can also be reviewed in the review rules corresponding to the drug review type. For example, the dosage of a certain drug should be within the preset range.
  • the data types corresponding to the review rules include but are not limited to the patient ’s condition, Drugs used in the same condition and the dosage range of the drugs used.
  • the drugs with the same curative effect in the same condition in the data type are related to the dosage range of the corresponding drugs.
  • the dosage range of drug A and the dosage range of drug B can be associated with drugs A and B of the same efficacy. If there are three possible dosage ranges of drug A, b, and c, when drug A is combined with drug B, drug A is in the dosage range of drug A, drug B should be in the dosage range of d, when drug A is in dosage b When within the range, drug B should be within the range of e dosage. (The dosage between different drugs will affect)
  • step c includes:
  • Step c1 Determine the data type corresponding to the audit details, and generate a tree-like data structure according to the qualification conditions and logical relationships corresponding to each data type in the audit details corresponding to the same audit type.
  • the audit type corresponding to each audit rule is determined, and the data type corresponding to the audit rules of the same audit type is obtained and recorded as the first data type. It can be understood that multiple data types are included in the first data type. After acquiring the first data type, the first data types are correlated according to the limiting conditions and logical relationships corresponding to the various first data types to generate a tree-like data structure.
  • Step c2 Correlate each data type in each of the tree-shaped data structures according to the logical relationship and limiting conditions of the corresponding data types of various audit types to generate a mesh data structure to obtain the data association model.
  • the tree data structure After generating the tree-like data structure, obtain the data type corresponding to each audit type and record it as the second data type, and then perform the various data types in each tree-like data structure according to the logical relationship and the limiting conditions corresponding to the second data type Correlation, generate a mesh data structure to get a data correlation model. It can be understood that the mesh data result is the resulting data association model.
  • the tree data structure is for the same audit type, which is to associate various data types in the same audit type; the mesh data structure is for different audit types, which are various data corresponding to different audit types Types are related.
  • the data association model is generated in an orderly manner, and the efficiency of generating the data association model is improved And the generated data association model includes the association relationship between all data types, ensuring the integrity of the generated data association model.
  • step S20 a data storage template in a preset format is generated according to the data association model, and target data corresponding to the risk control audit rule is obtained through the data storage template.
  • a data storage template in a preset format is generated according to the data association model, and the target data corresponding to the risk control audit rules is obtained through the data storage template.
  • the target data is the specific data in the audit rules corresponding to the risk control audit rules.
  • the preset formats include but are not limited to EXCEL format and TXT format.
  • the step of generating a data storage template in a preset format according to the data association model includes:
  • Step d Generate a characteristic field of the data storage template according to each data type in the data association model.
  • a feature field of a data storage template in a preset format is generated according to each data type in the data association model, and the data storage template displayed by the feature field is stored.
  • the data storage template may be an EXCEL table, and in other embodiments, the data storage template may be a TXT file or the like. If a certain data type is a drug with the same curative effect under the same condition, the corresponding characteristic field is a drug with the same curative effect.
  • Step e using the feature field as a table header of the table corresponding to the data association model.
  • the characteristic field After determining the characteristic field, use the characteristic field as the header of the table corresponding to the data association model. It can be understood that the characteristic fields corresponding to different data types can be respectively named as the corresponding EXCEL table, and the EXCEL table can be used to obtain the target data entered by the corresponding entry person. In the data association model, a data type can correspond to an EXCEL table.
  • Step f Set at least one link channel in the table to associate each table through the link channel to generate a data storage template in a preset format.
  • At least one link channel is set in each table to associate each table through the link channel to generate a data storage template in a preset format.
  • one or more link channels can be set for each item in the table.
  • the link channel can be determined according to the association relationship of the data types in the data association model. Specifically, when there is an association relationship between the two data types in the data association model, the link channel needs to be set in the table corresponding to the two data types . Different link channels are inserted into the EXCEL table with different icons, text, etc. as logos. Through the link channel, the person entering the target data can quickly find other forms associated with the type of data filled in and fill in the corresponding relevant data.
  • the step of obtaining the target data corresponding to the risk control audit rule through the data storage template includes:
  • step g when an entry instruction of target data is detected, the data storage template is displayed according to the entry instruction, so that an entry person can enter the corresponding target data in the data storage template.
  • the data storage template is displayed according to the entry instruction for the entry personnel to enter the corresponding target data in the data storage template.
  • the entry instruction is triggered by the entry personnel according to specific needs.
  • the corresponding target data can be automatically entered in the data storage template, specifically, the audit record corresponding to the audited data within a preset time period can be obtained, and the first data that has been audited by the risk control audit rules in the audited data, and Analyze the second data in the audited data that has not passed the audit of the risk control audit rules to extract the corresponding target data and fill it in the data storage template. If a certain two medicines pass the review of the risk control corresponding risk control review rules, the two medicines can be determined to be mutually exclusive, and the target data of the data storage template corresponding to the mutually exclusive medicine should be determined.
  • the preset duration can be set according to specific needs, and in this embodiment, there is no specific limit to the length of time corresponding to the preset duration.
  • Step S30 generating JS according to the target data and the corresponding data storage template Object notation JSON file, and import the JSON file into a preset audit engine to generate a risk control audit model.
  • the target data When the target data is obtained, fill the target data into the location corresponding to the data storage template, obtain the data storage template after filling the target data, and convert the data storage template after filling the target data into JSON (JavaScript Object Notation, JS Object notation) file, and import the JSON file into the preset audit engine to generate a risk control audit model.
  • the data storage template may be a data table including multiple EXCEL tables. Specifically, VBA (Visual Basic for Applications) or eclipse to convert the data storage template filled with the target data into a JSON file.
  • a data storage template corresponding to the data association model is generated, and the target data corresponding to the risk control audit rules are obtained through the data storage template.
  • the data storage template generates a JSON file, and imports the JSON file into a preset audit engine to generate a risk control audit model, which realizes that in the process of generating specific content of the risk control audit rules, developers do not need to proceed according to the rules details provided by business personnel
  • the program is input into the database, and the JSON file corresponding to the risk control audit rules can be generated directly according to the obtained target data, which improves the efficiency of generating the risk control audit rules corresponding to the risk control audit model.
  • the risk control audit model generation method further includes:
  • Step S40 when an update instruction to update the target data corresponding to the risk control review rule is detected, a JSON file corresponding to the risk control review rule is obtained.
  • the update instruction includes but is not limited to the delete instruction to delete the existing target data in the risk control audit model, the add instruction to add the target data in the risk control audit model, and the modify instruction to modify the target data in the risk control audit model.
  • the update instruction can be triggered by the user according to specific needs.
  • Step S50 Update the target data in the JSON file according to the update instruction.
  • the target data in the JSON file is updated according to the update instruction, that is, the target data in the JSON file is deleted, modified, or added according to the update instruction.
  • the target data in the JSON file can be directly modified to modify the data corresponding to the risk control review rules, thereby improving the efficiency of updating the risk control review rules.
  • the risk control audit model generation method further includes:
  • Step S60 when an audit request for auditing the data to be audited is detected, the data to be audited is compared with the target data corresponding to the JSON file in the audit engine to audit the data to be audited.
  • the process corresponding to the audit engine is called according to the audit request to run the risk control audit model in the audit engine, and the data to be audited corresponds to the risk control audit model in a JSON file To compare the target data to review the data to be reviewed.
  • the risk control review model is a medical risk control review model
  • the corresponding data to be reviewed is medical data
  • the risk control review model is a loan risk control review model
  • the corresponding data to be reviewed is loan data.
  • the generated JSON file is used to audit the data to be audited, which improves the security of the data to be audited.
  • the above-mentioned storage medium may be a non-volatile storage medium, such as a read-only memory, a magnetic disk, or an optical disk.
  • the present application also provides a risk control audit model generation device, which includes:
  • the obtaining module 10 is used to obtain preset risk control audit rules
  • a configuration module 20 configured to configure a data association model according to the risk control audit rules
  • the generating module 30 is configured to generate a data storage template in a preset format according to the data association model
  • the obtaining module 10 is further configured to obtain the target data corresponding to the risk control audit rule through the data storage template;
  • the generating module 30 is further configured to generate a JS object notation JSON file according to the target data and the corresponding data storage template;
  • the import module 40 is used to import the JSON file into a preset audit engine to generate a risk control audit model.
  • configuration module 20 includes:
  • a configuration unit configured to configure audit rules corresponding to the risk control audit rules according to the audit type
  • the determining unit is also used to determine the data type corresponding to the review details
  • the configuration unit is further configured to configure the data association model according to the limiting conditions and logical relationships corresponding to the various data types.
  • the configuration unit is also used to generate a tree-like data structure according to the qualification conditions and logical relationships corresponding to each data type in the audit details corresponding to the same audit type; according to the logical relationship of the data types corresponding to each audit type And limiting conditions, associate each data type in each of the tree-like data structures to generate a mesh data structure to obtain the data association model.
  • the generating module 30 is also used to:
  • a generating unit configured to generate a characteristic field of the data storage template according to each data type in the data association model
  • a definition unit configured to use the characteristic field as a header of a table corresponding to the data association model
  • the setting unit is configured to set at least one link channel in the table to associate each table through the link channel to generate a data storage template in a preset format.
  • the acquisition module 10 is also used to display the corresponding data storage template according to the input instruction when the input instruction of the target data is detected, for the entry personnel to enter the corresponding target data in the data storage template .
  • the obtaining module 10 is further configured to obtain a JSON file corresponding to the risk control review rule after detecting an update instruction to update the target data corresponding to the risk control review rule;
  • the risk control audit model generation device also includes:
  • the update module is used to update the target data in the JSON file according to the update instruction.
  • the risk control audit model generating device further includes:
  • the comparison module is used for comparing the data to be audited with the target data corresponding to the JSON file in the audit engine after detecting the audit request to audit the data to be audited, so as to audit the data to be audited.
  • the embodiments of the risk control audit model generation device are basically the same as the embodiments of the risk control audit model generation method described above, and details are not repeated here.
  • FIG. 5 is a schematic structural diagram of a hardware operating environment involved in a solution of an embodiment of the present application.
  • FIG. 5 is a schematic diagram of the hardware operating environment of the risk control audit model generation device.
  • the risk control audit model generation device in the embodiment of the present application may be a terminal device such as a PC or a portable computer.
  • the risk control audit model generation device may include: a processor 1001, such as a CPU, a memory 1005, a user interface 1003, a network interface 1004, and a communication bus 1002.
  • the communication bus 1002 is used to implement connection communication between these components.
  • the user interface 1003 may include a display (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
  • the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).
  • the memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as disk storage.
  • the memory 1005 may optionally be a storage device independent of the foregoing processor 1001.
  • the risk control audit model generation device may also include a camera, RF (Radio Frequency (radio frequency) circuits, sensors, audio circuits, WiFi modules, etc.
  • RF Radio Frequency
  • the structure of the risk control audit model generation device shown in FIG. 5 does not constitute a limitation on the risk control audit model generation device, and may include more or fewer components than shown, or a combination of certain Components, or different component arrangements.
  • the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a risk control audit model generation program.
  • the operating system is a program that manages and controls the hardware and software resources of the risk control audit model generation device, and supports the operation of the risk control audit model generation program and other software or programs.
  • the user interface 1003 can be used to receive the generation data risk control audit model generation instruction, and the target data entry instruction, etc .
  • the network interface 1004 is mainly used to connect the background server and the background server Perform data communication
  • the processor 1001 can be used to call the risk control audit model generation program stored in the memory 1005 and execute the steps of the risk control audit model generation method as described above.
  • the specific implementation manner of the risk control audit model generation device of the present application is basically the same as the above embodiments of the risk control audit model generation method, which will not be repeated here.
  • the embodiments of the present application also provide a computer-readable storage medium on which is stored a risk control audit model generation program, which is implemented as described above when executed by a processor Steps of the risk control audit model generation method.
  • the computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk,
  • the CD-ROM includes several instructions to enable a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to perform the methods described in the embodiments of the present application.

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Technology Law (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种风控审核模型生成方法、装置、设备及可读存储介质,该方法包括步骤:获取预设的风控审核规则,根据风控审核规则配置数据关联模型(S10);根据数据关联模型生成预设格式的数据存储模板,并通过数据存储模板获取风控审核规则对应的目标数据(S20);根据目标数据和对应的数据存储模板生成JS对象简谱JSON文件,并将JSON文件导入预设的审核引擎中,以生成风控审核模型(S30)。上述方法通过大数据分析生成风控审核模型,实现了在生成风控审核规则具体内容过程中,不需要开发人员根据业务人员提供的规则明细进行编程录入至数据库,可直接根据所获取的目标数据生成风控审核规则对应的JSON文件,提高了生成风控审核规则对应风控审核模型的效率。

Description

风控审核模型生成方法、装置、设备及可读存储介质
本申请要求于2018年10月29日提交中国专利局、申请号为201811272598.4、发明名称为“风控审核模型生成方法、装置、设备及可读存储介质”的中国专利申请的优先权,其全部内容通过引用结合在申请中。
技术领域
本申请涉及数据处理技术领域,尤其涉及一种风控审核模型生成方法、装置、设备及可读存储介质。
背景技术
在医疗费用急剧上升今天,医疗保险基金收入小于支出的情况时有发生。对医疗保险进行风险控制就显的异常重要与迫切,通过信息技术手段,对医疗保险理赔的相关医疗数据进行风险监控与分析,从而有效避免由于欺诈、滥用等行为导致保险基金的损失,以达到保护医疗保险基金的目的。为了有效避免医疗保险被滥用的风险,需要风控审核规则对医疗数据进行监控审核。目前,风控审核规则的具体内容需由开发人员根据业务人员提供的规则明细进行编程录入至数据库,然而此种方式导致生成风控审核规则对应风控审核模型的效率低下。
发明内容
本申请的主要目的在于提供一种风控审核模型生成方法、装置、设备及可读存储介质,旨在解决现有的生成风控审核规则对应的风控审核模型效率低下的技术问题。
为实现上述目的,本申请提供一种风控审核模型生成方法,所述风控审核模型生成方法包括步骤:
获取预设的风控审核规则,根据所述风控审核规则配置数据关联模型;
根据所述数据关联模型生成预设格式的数据存储模板,并通过所述数据存储模板获取所述风控审核规则对应的目标数据;
根据所述目标数据和对应的所述数据存储模板生成JS 对象简谱JSON文件,并将所述JSON文件导入预设的审核引擎中,以生成风控审核模型。
优选地,所述获取预设的风控审核规则,根据所述风控审核规则配置数据关联模型的步骤包括:
获取预设的风控审核规则,确定所述风控审核规则对应的审核类型;
根据所述审核类型配置所述风控审核规则对应的审核细则;
确定所述审核细则对应的数据类型,根据各种所述数据类型对应的限定条件和逻辑关系配置数据关联模型。
优选地,所述确定所述审核细则对应的数据类型,根据各种所述数据类型对应的限定条件和逻辑关系配置数据关联模型的步骤包括:
确定所述审核细则对应的数据类型,根据同种审核类型对应的所述审核细则中,各数据类型对应的限定条件和逻辑关系生成树状数据结构;
根据各种审核类型对应数据类型的逻辑关系和限定条件,将各个所述树状数据结构中的各数据类型进行关联,生成网状数据结构,以得到所述数据关联模型。
优选地,所述根据所述数据关联模型生成预设格式的数据存储模板的步骤包括:
根据所述数据关联模型中各数据类型生成所述数据存储模板的特征字段;
将所述特征字段作为所述数据关联模型对应表格的表头;
在所述表格中设置至少一个链接通道,以通过所述链接通道将各个表格关联起来,生成预设格式的数据存储模板。
优选地,所述通过所述数据存储模板获取所述风控审核规则对应的目标数据的步骤包括:
当侦测到目标数据的录入指令时,根据所述录入指令显示对应的数据存储模板,以供录入人员在所述数据存储模板中录入对应的目标数据。
优选地,所述根据所述目标数据和对应的所述数据存储模板生成JSON文件,并将所述JSON文件导入预设的审核引擎中,以生成风控审核模型的步骤之后,还包括:
当侦测到更新所述风控审核规则对应目标数据的更新指令后,获取与所述风控审核规则对应的JSON文件;
根据所述更新指令更新所述JSON文件中的目标数据。
优选地,所述根据所述目标数据和对应的所述数据存储模板生成JSON文件,并将所述JSON文件导入预设的审核引擎中,以生成风控审核模型的步骤之后,还包括:
当侦测到审核待审核数据的审核请求后,将所述待审核数据与所述审核引擎中JSON文件对应的目标数据进行对比,以对所述待审核数据进行审核。
此外,为实现上述目的,本申请还提供一种风控审核模型生成装置,所述风控审核模型生成装置包括:
获取模块,用于获取预设的风控审核规则;
配置模块,用于根据所述风控审核规则配置数据关联模型;
生成模块,用于根据所述数据关联模型生成预设格式的数据存储模板;
所述获取模块还用于通过所述数据存储模板获取所述风控审核规则对应的目标数据;
所述生成模块还用于根据所述目标数据和对应的所述数据存储模板生成JS 对象简谱JSON文件;
导入模块,用于将所述JSON文件导入预设的审核引擎中,以生成风控审核模型。
此外,为实现上述目的,本申请还提供一种风控审核模型生成设备,所述风控审核模型生成设备包括存储器、处理器和存储在所述存储器上并可在所述处理器上运行的风控审核模型生成程序,所述风控审核模型生成程序被所述处理器执行时实现如上所述的风控审核模型生成方法的步骤。
此外,为实现上述目的,本申请还提供一种计算机可读存储介质,所述计算机可读存储介质上存储有风控审核模型生成程序,所述风控审核模型生成程序被处理器执行时实现如上所述的风控审核模型生成方法的步骤。
本申请通过根据所获取的风控审核规则配置数据关联模型,生成与该数据关联模型对应的数据存储模板,并通过数据存储模板获取风控审核规则对应的目标数据,根据目标数据和对应的数据存储模板生成JSON文件,将JSON文件导入预设的审核引擎中,以生成风控审核模型,实现了在生成风控审核规则具体内容过程中,不需要开发人员根据业务人员提供的规则明细进行编程录入至数据库,可直接根据所获取的目标数据生成风控审核规则对应的JSON文件,提高了生成风控审核规则对应风控审核模型的效率。
附图说明
图1是本申请风控审核模型生成方法第一实施例的流程示意图;
图2是本申请风控审核模型生成方法第二实施例的流程示意图;
图3是本申请风控审核模型生成方法第三实施例的流程示意图;
图4为本申请风控审核模型生成装置较佳实施例的功能示意图模块图;
图5是本申请实施例方案涉及的硬件运行环境的结构示意图。
本申请目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
具体实施方式
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。
本申请提供一种风控审核模型生成方法,参照图1,图1为本申请风控审核模型生成方法第一实施例的流程示意图。
本申请实施例提供了风控审核模型生成方法的实施例,需要说明的是,虽然在流程图中示出了逻辑顺序,但是在某些情况下,可以以不同于此处的顺序执行所示出或描述的步骤。
风控审核模型生成方法应用于服务器或者终端中,终端可以包括诸如手机、平板电脑、笔记本电脑、掌上电脑、个人数字助理(Personal Digital Assistant,PDA)等移动终端,以及诸如数字TV、台式计算机等固定终端。在风控审核模型生成方法的各个实施例中,为了便于描述,省略执行主体进行阐述各个实施例。风控审核模型生成方法包括:
步骤S10,获取预设的风控审核规则,根据所述风控审核规则配置数据关联模型。
当侦测到生成数据风控审核模型生成指令后,获取预设的风控审核规则,并根据该风控审核规则配置数据关联模型。其中,生成指令可由对应的工作人员根据需要而触发,预设的风控审核规则用于审核各种数据是否符合预设条件。如当该风控审核规则用于审核医疗保险理赔相关的数据时,该风控审核规则中应包括审核各个医疗数据之间的逻辑关系、限定条件等的规则。在本实施例中,逻辑关系具体包括正相关关系、负相关关系和条件关系等,正相关关系为数据之间必须或可以同时存在的关系,负相关关系为数据之间不能同时存在的关系,条件关系为数据之间当一数据满足一定条件时,存在对应的另一数据,或不存在对应的另一数据的关系。限定条件可为被审核的数据所需满足的条件,如数值范围、预设类型等。
进一步地,为了提高所配置的数据关联模型的准确率,步骤S10包括:
步骤a,获取预设的风控审核规则,确定所述风控审核规则对应的审核类型。
在风控审核规则中,设置有不同的审核类型,风控审核规则对应的审核类型可根据风控审核规则的审核需求和审核内容确定。如在审核医疗数据时,根据病情的不同对应设置有不同的风控审核规则,根据风控审核规则中审核需求和审核内容等划分风控审核规则对应的审核类型。如医疗数据对应的风控审核规则的审核类型包括但不限于用药审核类型、检验项目审核类型和费用审核类型等。
当获取到预设的风控审核规则后,根据风控审核规则对应的审核需求和/或审核内容确定风控审核规则对应的审核类型。如当风控审核规则的审核内容为检测用户所使用药物的费用是否正确,则确定风控审核规则对应的审核类型为费用审核类型;如当风控审核规则的审核内容为审核用户所患疾病对应用药是否正确,则确定该风控审核规则对应的审核类型为用药审核类型。
步骤b,根据所述审核类型配置所述风控审核规则对应的审核细则。
当确定风控审核规则对应的审核类型后,根据审核类型配置对应风控审核规则对应的审核细则。需要说明的是,每种审核类型都需配置对应的审核细则,同一审核类型对应着多种审核细则。具体地,该审核细则可由对应的工作人员根据具体情况而设置,不同审核类型对应的审核细则不一样。
步骤c,确定所述审核细则对应的数据类型,根据各种所述数据类型对应的限定条件和逻辑关系配置数据关联模型。
当确定审核细则后,确定审核细则对应的数据类型,并确定各种数据类型对应限定条件和逻辑条件,根据各种数据类型对应的限定条件和逻辑关系将各种数据类型进行关联,以配置出数据关联模型。需要说明的是,数据关联模型是预先设置的用于建立数据类型间的关联关系,在数据关联模型中,各种数据类型之间是存在不同的关联关系的。如在用药审核类型对应的审核细则中,需确定被保险人的用药中是否包含了重复药物,即不可能同时出现的药物,重复药物可能为疗效一致的药物,也可能是疗效相斥的药物等。由于不同的病情所使用的药物会有差异,因而审核细则对应的数据类型包括但不限于被保险人的病情、同一病情下具有相同疗效的药物和同一病情下疗效相斥的药物。进一步的,用药审核类型对应的审核细则中还可对药物的用量进行审核,如某种药物的用量应处于预设范围内,此时,审核细则对应的数据类型包括但不限于患者的病情、同一病情下使用的药物和所使用药物的用量范围。如将数据类型中同一病情下相同疗效的药物,与对应所使用药物的用量范围进行关联。如A药物与B药物为相同疗效的药物,则在配置数据关联模型时,可将A药物的用量范围,以及B药物的用量范围与相同疗效的药物A药物与B药物对应关联。如A药物存在a、b、c三种可能的用量范围时,当A药物与B药物结合使用时,A药物在a用量范围内,B药物应在d用量范围内,当A药物在b用量范围内时,B药物应在e用量范围内。(不同药物之间的用量会有影响)
进一步地,为了提高生成数据关联模型的效率,以及保证所生成数据关联模型的完整度,步骤c包括:
步骤c1,确定所述审核细则对应的数据类型,根据同种审核类型对应的所述审核细则中,各数据类型对应的限定条件和逻辑关系生成树状数据结构。
当确定审核细则后,确定各个审核细则对应的审核类型,获取同一审核类型对应审核细则的数据类型,记为第一数据类型。可以理解的是,第一数据类型中包括了多种数据类型。当获取到第一数据类型后,根据各种第一数据类型对应的限定条件和逻辑关系将各种第一数据类型进行关联,生成树状数据结构。
步骤c2,根据各种审核类型对应数据类型的逻辑关系和限定条件,将各个所述树状数据结构中的各数据类型进行关联,生成网状数据结构,以得到所述数据关联模型。
当生成树状数据结构后,获取各个审核类型对应的数据类型,记为第二数据类型,然后根据第二数据类型对应的逻辑关系和限定条件将各个树状数据结构中的各种数据类型进行关联,生成网状数据结构,以得到数据关联模型。可以理解的是,网状数据结果即为所得的数据关联模型。树状数据结构是针对同一审核类型而言的,是将同一审核类型中的各种数据类型关联起来;网状数据结构是针对不同审核类型而言的,是将不同审核类型对应的各种数据类型关联起来。本实施例先通过在同一审核类型中构建树状数据结构,然后在不同审核类型中,根据树状数据结构构建网状数据结构,有序的生成数据关联模型,提高了生成数据关联模型的效率,且使所生成的数据关联模型囊括了所有数据类型之间的关联关系,保证了所生成数据关联模型的完整度。
步骤S20,根据所述数据关联模型生成预设格式的数据存储模板,并通过所述数据存储模板获取所述风控审核规则对应的目标数据。
当得到数据关联模型后,根据该数据关联模型生成预设格式的数据存储模板,并通过数据存储模板获取风控审核规则对应的目标数据。需要说明的是,目标数据为风控审核规则对应审核细则中具体的数据。如审核细则中重复药物的药物名称,某种药物用量对应范围的上限值和下限值等。预设格式包括但不限于EXCEL格式和TXT格式。
进一步地,根据所述数据关联模型生成预设格式的数据存储模板的步骤包括:
步骤d,根据所述数据关联模型中各数据类型生成所述数据存储模板的特征字段。
当得到数据关联模型后,根据数据关联模型中各数据类型生成预设格式的数据存储模板的特征字段,并将该特征字段显示的数据存储模板中。在本实施例中,数据存储模板可为EXCEL表格,在其它实施例中,数据存储模板可为TXT文档等。如某种数据类型为同一病情下相同疗效的药物,则对应的特征字段为相同疗效的药物。
步骤e,将所述特征字段作为所述数据关联模型对应表格的表头。
当确定特征字段后,将该特征字段作为数据关联模型对应表格的表头。可以理解的是,不同的数据类型所对应的特征字段可分别作为对应EXCEL表格的命名,EXCEL表格可用于获取对应录入人员录入的目标数据。在数据关联模型中,一种数据类型可对应一个EXCEL表格。
步骤f,在所述表格中设置至少一个链接通道,以通过所述链接通道将各个表格关联起来,生成预设格式的数据存储模板。
在各个表格中设置至少一个链接通道,以通过该链接通道将各个表格关联起来,生成预设格式的数据存储模板。具体地,可为表格内每一项内容设置一个或者多个链接通道。该链接通道可根据数据关联模型中数据类型的关联关系来确定,具体地,当在数据关联模型中,两种数据类型存在关联关系时,需要在这两种数据类型对应的表格中设置链接通道。不同的链接通道以不同图标、文字等作为标识***至EXCEL表格内。通过链接通道,录入目标数据的录入人员可快速查找到与所填写的数据类型相关联的其它表格中填写对应相关的数据。
进一步地,通过所述数据存储模板获取所述风控审核规则对应的目标数据的步骤包括:
步骤g,当侦测到目标数据的录入指令时,根据所述录入指令显示所述数据存储模板,以供录入人员在所述数据存储模板中录入对应的目标数据。
当侦测到目标数据的录入指令时,根据该录入指令显示该数据存储模板,以供录入人员在数据存储模板中录入对应的目标数据。其中,该录入指令由录入人员根据具体需要而触发。
进一步地,可自动在数据存储模板中录入对应的目标数据,具体地,获取预设时长内已审核数据对应的审核记录,分别对已审核数据中通过风控审核规则审核的第一数据,以及对已审核数据中未通过风控审核规则审核的第二数据进行分析,以提取到相应的目标数据填写至数据存储模板中。如某两个药物通过疗效相斥对应风控审核规则的审核,即可确定这两个药物的疗效相斥,为疗效相斥药物对应数据存储模板的目标数据。其中,预设时长可根据具体需要而设置,在本实施例中对预设时长对应的时间长短不做具体限制。
步骤S30,根据所述目标数据和对应的所述数据存储模板生成JS 对象简谱JSON文件,并将所述JSON文件导入预设的审核引擎中,以生成风控审核模型。
当得到目标数据后,将目标数据填入数据存储模板对应的位置中,得到填充目标数据后的数据存储模板,并将填充目标数据后的数据存储模板转换成JSON(JavaScript Object Notation,JS 对象简谱)文件,并将JSON文件导入预设的审核引擎中,以生成风控审核模型。可以理解的是,数据存储模板可为一个包括多个EXCEL表格的数据表,具体地,可用VBA(Visual Basic for Applications)或者eclipse等将填充目标数据后的数据存储模板转换成JSON文件。
本实施例通过根据所获取的风控审核规则配置数据关联模型,生成与该数据关联模型对应的数据存储模板,并通过数据存储模板获取风控审核规则对应的目标数据,根据目标数据和对应的数据存储模板生成JSON文件,将JSON文件导入预设的审核引擎中,以生成风控审核模型,实现了在生成风控审核规则具体内容过程中,不需要开发人员根据业务人员提供的规则明细进行编程录入至数据库,可直接根据所获取的目标数据生成风控审核规则对应的JSON文件,提高了生成风控审核规则对应风控审核模型的效率。
进一步地,提出本申请风控审核模型生成方法第二实施例。
所述风控审核模型生成方法第二实施例与所述风控审核模型生成方法第一实施例的区别在于,参照图2,风控审核模型生成方法还包括:
步骤S40,当侦测到更新所述风控审核规则对应目标数据的更新指令后,获取与所述风控审核规则对应的JSON文件。
当侦测到更新风控审核规则对应目标数据的更新指令后,获取与该风控审核规则对应的JSON文件。其中,更新指令包括但不限于删除风控审核模型中已有目标数据的删除指令、增加风控审核模型中目标数据的增加指令和修改风控审核模型中目标数据的修改指令。更新指令可由用户根据具体需要而触发。
步骤S50,根据所述更新指令更新所述JSON文件中的目标数据。
当获取到JSON文件时,根据更新指令更新JSON文件中的目标数据,即根据更新指令删除、修改或者增加JSON文件中的目标数据。
本实施例通过当需要修改风控审核规则对应的数据时,直接修改JSON文件中的目标数据即可实现对风控审核规则对应数据的修改,提高了风控审核规则更新的效率。
进一步地,提出本申请风控审核模型生成方法第三实施例。
所述风控审核模型生成方法第三实施例与所述风控审核模型生成方法第一或第二实施例的区别在于,参照图3,风控审核模型生成方法还包括:
步骤S60,当侦测到审核待审核数据的审核请求后,将所述待审核数据与所述审核引擎中JSON文件对应的目标数据进行对比,以对所述待审核数据进行审核。
当侦测到审核待审核数据的审核请求后,根据该审核请求调用审核引擎对应的进程,以运行该审核引擎中的风控审核模型,将待审核数据与该风控审核模型对应JSON文件中的目标数据进行对比,以对待审核数据进行审核。其中,当风控审核模型为医疗风控审核模型时,对应的待审核数据为医疗数据;当风控审核模型为贷款风控审核模型时,对应的待审核数据为贷款数据。
本实施例通过所生成的JSON文件对待审核数据进行审核,提高了待审核数据运用的安全性。
需要说明的是,本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过硬件来完成,也可以通过程序来指令相关的硬件完成,所述的程序可以存储于一种计算机可读存储介质中,上述提到的存储介质可以是非易失性存储介质,如只读存储器,磁盘或光盘等。
此外,参照图4,本申请还提供一种风控审核模型生成装置,所述风控审核模型生成装置包括:
获取模块10,用于获取预设的风控审核规则;
配置模块20,用于根据所述风控审核规则配置数据关联模型;
生成模块30,用于根据所述数据关联模型生成预设格式的数据存储模板;
所述获取模块10还用于通过所述数据存储模板获取所述风控审核规则对应的目标数据;
所述生成模块30还用于根据所述目标数据和对应的所述数据存储模板生成JS 对象简谱JSON文件;
导入模块40,用于将所述JSON文件导入预设的审核引擎中,以生成风控审核模型。
进一步地,所述配置模块20包括:
确定单元,用于确定所述风控审核规则对应的审核类型;
配置单元,用于根据所述审核类型配置所述风控审核规则对应的审核细则;
所述确定单元还用于确定所述审核细则对应的数据类型;
所述配置单元还用于根据各种所述数据类型对应的限定条件和逻辑关系配置数据关联模型。
进一步地,所述配置单元还用于根据同种审核类型对应的所述审核细则中,各数据类型对应的限定条件和逻辑关系生成树状数据结构;根据各种审核类型对应数据类型的逻辑关系和限定条件,将各个所述树状数据结构中的各数据类型进行关联,生成网状数据结构,以得到所述数据关联模型。
进一步地,所述生成模块30还用于:
生成单元,用于根据所述数据关联模型中各数据类型生成所述数据存储模板的特征字段;
定义单元,用于将所述特征字段作为所述数据关联模型对应表格的表头;
设置单元,用于在所述表格中设置至少一个链接通道,以通过所述链接通道将各个表格关联起来,生成预设格式的数据存储模板。
进一步地,所述获取模块10还用于当侦测到目标数据的录入指令时,根据所述录入指令显示对应的数据存储模板,以供录入人员在所述数据存储模板中录入对应的目标数据。
进一步地,所述获取模块10还用于当侦测到更新所述风控审核规则对应目标数据的更新指令后,获取与所述风控审核规则对应的JSON文件;
所述风控审核模型生成装置还包括:
更新模块,用于根据所述更新指令更新所述JSON文件中的目标数据。
进一步地,所述风控审核模型生成装置还包括:
对比模块,用于当侦测到审核待审核数据的审核请求后,将所述待审核数据与所述审核引擎中JSON文件对应的目标数据进行对比,以对所述待审核数据进行审核。
需要说明的是,风控审核模型生成装置的各个实施例与上述风控审核模型生成方法的各实施例基本相同,在此不再详细赘述。
此外,本申请还提供一种风控审核模型生成设备。如图5所示,图5是本申请实施例方案涉及的硬件运行环境的结构示意图。
需要说明的是,图5即可为风控审核模型生成设备的硬件运行环境的结构示意图。本申请实施例风控审核模型生成设备可以是PC,便携计算机等终端设备。
如图5所示,该风控审核模型生成设备可以包括:处理器1001,例如CPU,存储器1005,用户接口1003,网络接口1004,通信总线1002。其中,通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏(Display)、输入单元比如键盘(Keyboard),可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口(如WI-FI接口)。存储器1005可以是高速RAM存储器,也可以是稳定的存储器(non-volatile memory),例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
可选地,风控审核模型生成设备还可以包括摄像头、RF(Radio Frequency,射频)电路,传感器、音频电路、WiFi模块等等。
本领域技术人员可以理解,图5中示出的风控审核模型生成设备结构并不构成对风控审核模型生成设备的限定,可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置。
如图5所示,作为一种计算机存储介质的存储器1005中可以包括操作***、网络通信模块、用户接口模块以及风控审核模型生成程序。其中,操作***是管理和控制风控审核模型生成设备硬件和软件资源的程序,支持风控审核模型生成程序以及其它软件或程序的运行。
在图5所示的风控审核模型生成设备中,用户接口1003可用于接收生成数据风控审核模型生成指令,以及目标数据的录入指令等;网络接口1004主要用于连接后台服务器,与后台服务器进行数据通信;处理器1001可以用于调用存储器1005中存储的风控审核模型生成程序,并执行如上所述的风控审核模型生成方法的步骤。
本申请风控审核模型生成设备具体实施方式与上述风控审核模型生成方法各实施例基本相同,在此不再赘述。
此外,本申请实施例还提出一种计算机可读存储介质,所述计算机可读存储介质上存储有风控审核模型生成程序,所述风控审核模型生成程序被处理器执行时实现如上所述的风控审核模型生成方法的步骤。
本申请计算机可读存储介质具体实施方式与上述风控审核模型生成方法各实施例基本相同,在此不再赘述。
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。
上述本申请实施例序号仅仅为了描述,不代表实施例的优劣。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端设备(可以是手机,计算机,服务器,空调器,或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例,并非因此限制本申请的专利范围,凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种风控审核模型生成方法,其特征在于,所述风控审核模型生成方法包括以下步骤:
    获取预设的风控审核规则,根据所述风控审核规则配置数据关联模型;
    根据所述数据关联模型生成预设格式的数据存储模板,并通过所述数据存储模板获取所述风控审核规则对应的目标数据;
    根据所述目标数据和对应的所述数据存储模板生成JS 对象简谱JSON文件,并将所述JSON文件导入预设的审核引擎中,以生成风控审核模型。
  2. 如权利要求1所述的风控审核模型生成方法,其特征在于,所述获取预设的风控审核规则,根据所述风控审核规则配置数据关联模型的步骤包括:
    获取预设的风控审核规则,确定所述风控审核规则对应的审核类型;
    根据所述审核类型配置所述风控审核规则对应的审核细则;
    确定所述审核细则对应的数据类型,根据各种所述数据类型对应的限定条件和逻辑关系配置数据关联模型。
  3. 如权利要求2所述的风控审核模型生成方法,其特征在于,所述确定所述审核细则对应的数据类型,根据各种所述数据类型对应的限定条件和逻辑关系配置数据关联模型的步骤包括:
    确定所述审核细则对应的数据类型,根据同种审核类型对应的所述审核细则中,各数据类型对应的限定条件和逻辑关系生成树状数据结构;
    根据各种审核类型对应数据类型的逻辑关系和限定条件,将各个所述树状数据结构中的各数据类型进行关联,生成网状数据结构,以得到所述数据关联模型。
  4. 如权利要求1所述的风控审核模型生成方法,其特征在于,所述根据所述数据关联模型生成预设格式的数据存储模板的步骤包括:
    根据所述数据关联模型中各数据类型生成所述数据存储模板的特征字段;
    将所述特征字段作为所述数据关联模型对应表格的表头;
    在所述表格中设置至少一个链接通道,以通过所述链接通道将各个表格关联起来,生成预设格式的数据存储模板。
  5. 如权利要求1所述的风控审核模型生成方法,其特征在于,所述通过所述数据存储模板获取所述风控审核规则对应的目标数据的步骤包括:
    当侦测到目标数据的录入指令时,根据所述录入指令显示对应的数据存储模板,以供录入人员在所述数据存储模板中录入对应的目标数据。
  6. 如权利要求1所述的风控审核模型生成方法,其特征在于,所述根据所述目标数据和对应的所述数据存储模板生成JSON文件,并将所述JSON文件导入预设的审核引擎中,以生成风控审核模型的步骤之后,还包括:
    当侦测到更新所述风控审核规则对应目标数据的更新指令后,获取与所述风控审核规则对应的JSON文件;
    根据所述更新指令更新所述JSON文件中的目标数据。
  7. 如权利要求1所述的风控审核模型生成方法,其特征在于,所述根据所述目标数据和对应的所述数据存储模板生成JSON文件,并将所述JSON文件导入预设的审核引擎中,以生成风控审核模型的步骤之后,还包括:
    当侦测到审核待审核数据的审核请求后,将所述待审核数据与所述审核引擎中JSON文件对应的目标数据进行对比,以对所述待审核数据进行审核。
  8. 如权利要求2所述的风控审核模型生成方法,其特征在于,所述根据所述目标数据和对应的所述数据存储模板生成JSON文件,并将所述JSON文件导入预设的审核引擎中,以生成风控审核模型的步骤之后,还包括:
    当侦测到审核待审核数据的审核请求后,将所述待审核数据与所述审核引擎中JSON文件对应的目标数据进行对比,以对所述待审核数据进行审核。
  9. 如权利要求3所述的风控审核模型生成方法,其特征在于,所述根据所述目标数据和对应的所述数据存储模板生成JSON文件,并将所述JSON文件导入预设的审核引擎中,以生成风控审核模型的步骤之后,还包括:
    当侦测到审核待审核数据的审核请求后,将所述待审核数据与所述审核引擎中JSON文件对应的目标数据进行对比,以对所述待审核数据进行审核。
  10. 如权利要求4所述的风控审核模型生成方法,其特征在于,所述根据所述目标数据和对应的所述数据存储模板生成JSON文件,并将所述JSON文件导入预设的审核引擎中,以生成风控审核模型的步骤之后,还包括:
    当侦测到审核待审核数据的审核请求后,将所述待审核数据与所述审核引擎中JSON文件对应的目标数据进行对比,以对所述待审核数据进行审核。
  11. 如权利要求5所述的风控审核模型生成方法,其特征在于,所述根据所述目标数据和对应的所述数据存储模板生成JSON文件,并将所述JSON文件导入预设的审核引擎中,以生成风控审核模型的步骤之后,还包括:
    当侦测到审核待审核数据的审核请求后,将所述待审核数据与所述审核引擎中JSON文件对应的目标数据进行对比,以对所述待审核数据进行审核。
  12. 一种风控审核模型生成装置,其特征在于,所述风控审核模型生成装置包括:
    获取模块,用于获取预设的风控审核规则;
    配置模块,用于根据所述风控审核规则配置数据关联模型;
    生成模块,用于根据所述数据关联模型生成预设格式的数据存储模板;
    所述获取模块还用于通过所述数据存储模板获取所述风控审核规则对应的目标数据;
    所述生成模块还用于根据所述目标数据和对应的所述数据存储模板生成JS 对象简谱JSON文件;
    导入模块,用于将所述JSON文件导入预设的审核引擎中,以生成风控审核模型。
  13. 如权利要求12所述的风控审核模型生成装置,其特征在于,所述配置模块包括:
    确定单元,用于确定所述风控审核规则对应的审核类型;
    配置单元,用于根据所述审核类型配置所述风控审核规则对应的审核细则;
    所述确定单元还用于确定所述审核细则对应的数据类型;
    所述配置单元还用于根据各种所述数据类型对应的限定条件和逻辑关系配置数据关联模型。
  14. 如权利要求13所述的风控审核模型生成装置,其特征在于,所述配置单元还用于根据同种审核类型对应的所述审核细则中,各数据类型对应的限定条件和逻辑关系生成树状数据结构;根据各种审核类型对应数据类型的逻辑关系和限定条件,将各个所述树状数据结构中的各数据类型进行关联,生成网状数据结构,以得到所述数据关联模型。
  15. 如权利要求12所述的风控审核模型生成装置,其特征在于,所述生成模块还用于:
    生成单元,用于根据所述数据关联模型中各数据类型生成所述数据存储模板的特征字段;
    定义单元,用于将所述特征字段作为所述数据关联模型对应表格的表头;
    设置单元,用于在所述表格中设置至少一个链接通道,以通过所述链接通道将各个表格关联起来,生成预设格式的数据存储模板。
  16. 如权利要求12所述的风控审核模型生成装置,其特征在于,所述获取模块还用于当侦测到目标数据的录入指令时,根据所述录入指令显示对应的数据存储模板,以供录入人员在所述数据存储模板中录入对应的目标数据。
  17. 如权利要求12所述的风控审核模型生成装置,其特征在于,所述获取模块还用于当侦测到更新所述风控审核规则对应目标数据的更新指令后,获取与所述风控审核规则对应的JSON文件;
    所述风控审核模型生成装置还包括:
    更新模块,用于根据所述更新指令更新所述JSON文件中的目标数据。
  18. 如权利要求12所述的风控审核模型生成装置,其特征在于,所述风控审核模型生成装置还包括:
    对比模块,用于当侦测到审核待审核数据的审核请求后,将所述待审核数据与所述审核引擎中JSON文件对应的目标数据进行对比,以对所述待审核数据进行审核。
  19. 一种风控审核模型生成设备,其特征在于,所述风控审核模型生成设备包括存储器、处理器和存储在所述存储器上并可在所述处理器上运行的风控审核模型生成程序,所述风控审核模型生成程序被所述处理器执行时实现如下步骤:
    获取预设的风控审核规则,根据所述风控审核规则配置数据关联模型;
    根据所述数据关联模型生成预设格式的数据存储模板,并通过所述数据存储模板获取所述风控审核规则对应的目标数据;
    根据所述目标数据和对应的所述数据存储模板生成JS 对象简谱JSON文件,并将所述JSON文件导入预设的审核引擎中,以生成风控审核模型。
  20. 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质上存储有风控审核模型生成程序,所述风控审核模型生成程序被处理器执行时实现如下步骤:
    获取预设的风控审核规则,根据所述风控审核规则配置数据关联模型;
    根据所述数据关联模型生成预设格式的数据存储模板,并通过所述数据存储模板获取所述风控审核规则对应的目标数据;
    根据所述目标数据和对应的所述数据存储模板生成JS 对象简谱JSON文件,并将所述JSON文件导入预设的审核引擎中,以生成风控审核模型。
PCT/CN2019/095838 2018-10-29 2019-07-12 风控审核模型生成方法、装置、设备及可读存储介质 WO2020087981A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811272598.4 2018-10-29
CN201811272598.4A CN109615534A (zh) 2018-10-29 2018-10-29 风控审核模型生成方法、装置、设备及可读存储介质

Publications (1)

Publication Number Publication Date
WO2020087981A1 true WO2020087981A1 (zh) 2020-05-07

Family

ID=66002677

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/095838 WO2020087981A1 (zh) 2018-10-29 2019-07-12 风控审核模型生成方法、装置、设备及可读存储介质

Country Status (2)

Country Link
CN (1) CN109615534A (zh)
WO (1) WO2020087981A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114462373A (zh) * 2022-02-09 2022-05-10 星环信息科技(上海)股份有限公司 审计规则确定方法、装置、电子设备及存储介质

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109615534A (zh) * 2018-10-29 2019-04-12 平安医疗健康管理股份有限公司 风控审核模型生成方法、装置、设备及可读存储介质
CN110334536A (zh) * 2019-05-30 2019-10-15 深圳壹账通智能科技有限公司 基于区块链的数据保存方法、装置和计算机设备
CN110348711A (zh) * 2019-06-27 2019-10-18 上海淇馥信息技术有限公司 一种基于差错预判的案件质检方法、装置和电子设备
CN111414585B (zh) * 2020-03-26 2023-05-05 深圳前海微众银行股份有限公司 变量管理方法、装置、设备及计算机可读存储介质
CN111813399B (zh) * 2020-07-23 2022-05-31 平安医疗健康管理股份有限公司 基于机器学习的审核规则处理方法、装置及计算机设备
CN112131184B (zh) * 2020-09-18 2022-11-11 四创科技有限公司 一种实现模型及其接口标准化输入输出的方法
CN112308466A (zh) * 2020-11-26 2021-02-02 东莞市盟大塑化科技有限公司 企业资质审核方法、装置、计算机设备和存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020107764A1 (en) * 2000-12-07 2002-08-08 Mccoy Mary Kay Method and product for calculating a net operating income audit and for enabling substantially identical audit practices among a plurality of audit firms
CN107845033A (zh) * 2017-11-08 2018-03-27 上海壹账通金融科技有限公司 风控报告生成方法、装置、设备及计算机可读存储介质
CN108052310A (zh) * 2017-11-22 2018-05-18 链家网(北京)科技有限公司 一种基于业务模型描述信息的数据处理方法及服务器
CN108171600A (zh) * 2018-01-19 2018-06-15 深圳前海大数金融服务有限公司 征信报告解析方法、服务器及存储介质
CN109615534A (zh) * 2018-10-29 2019-04-12 平安医疗健康管理股份有限公司 风控审核模型生成方法、装置、设备及可读存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104809355A (zh) * 2015-05-14 2015-07-29 天津智康医疗科技有限公司 一种基于任务调度的医疗处方规则审核引擎设计方法
CN108257024B (zh) * 2017-04-14 2020-04-24 平安科技(深圳)有限公司 一种理赔案件处理方法和装置
CN108257029A (zh) * 2017-09-13 2018-07-06 平安科技(深圳)有限公司 保险数据审核方法、装置、计算机设备及可读存储介质
CN108334452B (zh) * 2018-02-08 2021-02-05 深圳壹账通智能科技有限公司 规则数据移交测试方法、装置、计算机设备和存储介质
CN108536846A (zh) * 2018-04-13 2018-09-14 深圳壹账通智能科技有限公司 风控引擎变量库规则适配方法、装置、设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020107764A1 (en) * 2000-12-07 2002-08-08 Mccoy Mary Kay Method and product for calculating a net operating income audit and for enabling substantially identical audit practices among a plurality of audit firms
CN107845033A (zh) * 2017-11-08 2018-03-27 上海壹账通金融科技有限公司 风控报告生成方法、装置、设备及计算机可读存储介质
CN108052310A (zh) * 2017-11-22 2018-05-18 链家网(北京)科技有限公司 一种基于业务模型描述信息的数据处理方法及服务器
CN108171600A (zh) * 2018-01-19 2018-06-15 深圳前海大数金融服务有限公司 征信报告解析方法、服务器及存储介质
CN109615534A (zh) * 2018-10-29 2019-04-12 平安医疗健康管理股份有限公司 风控审核模型生成方法、装置、设备及可读存储介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114462373A (zh) * 2022-02-09 2022-05-10 星环信息科技(上海)股份有限公司 审计规则确定方法、装置、电子设备及存储介质
CN114462373B (zh) * 2022-02-09 2022-11-15 星环信息科技(上海)股份有限公司 审计规则确定方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN109615534A (zh) 2019-04-12

Similar Documents

Publication Publication Date Title
WO2020087981A1 (zh) 风控审核模型生成方法、装置、设备及可读存储介质
WO2020015067A1 (zh) 数据采集方法、装置、设备及存储介质
WO2020087978A1 (zh) 风控审核模型的生成方法、装置、设备及存储介质
WO2020233077A1 (zh) ***服务的监控方法、装置、设备及存储介质
WO2020147385A1 (zh) 数据录入方法、装置、终端及计算机可读存储介质
WO2020119115A1 (zh) 数据审核方法、装置、设备及存储介质
WO2020119116A1 (zh) 基于数据分析的医保审核方法、装置、设备和存储介质
WO2020119384A1 (zh) 基于大数据分析的医保异常检测方法、装置、设备和介质
WO2020078058A1 (zh) 医疗数据异常识别方法、装置、终端及存储介质
WO2020107591A1 (zh) 重复投保限制方法、装置、设备及可读存储介质
WO2020224250A1 (zh) 智能合约的触发方法、装置、设备及存储介质
WO2020119176A1 (zh) 报销数据的排查方法、识别服务端及存储介质
WO2018205373A1 (zh) 人伤理赔定损费用测算方法、装置、服务器和介质
WO2020233090A1 (zh) 基于h5页面的应用配置方法、装置、设备及存储介质
WO2020253112A1 (zh) 测试策略的获取方法、装置、终端及可读存储介质
WO2020062658A1 (zh) 合同生成方法、装置、设备及存储介质
WO2020000632A1 (zh) ***开具方法、装置、设备及计算机可读存储介质
WO2019024485A1 (zh) 数据共享方法、装置及计算机可读存储介质
WO2021003956A1 (zh) 产品信息的管理方法、装置、设备及存储介质
WO2020042464A1 (zh) 数据交互方法、装置、设备及可读存储介质
WO2020119369A1 (zh) 智能it运维故障定位方法、装置、设备及可读存储介质
WO2020253135A1 (zh) 自动化分析方法、用户设备、存储介质及装置
WO2020108111A1 (zh) 医保欺诈行为的识别方法、装置、设备及可读存储介质
WO2020062661A1 (zh) 合同数据一致性的核实方法、装置、设备及存储介质
WO2020119402A1 (zh) 无关用药的识别方法、装置、终端及计算机可读存储介质

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: 19879491

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

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

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 22/06/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19879491

Country of ref document: EP

Kind code of ref document: A1