WO2019153489A1 - 一种反洗钱模型的运算方法、存储介质、终端设备及装置 - Google Patents

一种反洗钱模型的运算方法、存储介质、终端设备及装置 Download PDF

Info

Publication number
WO2019153489A1
WO2019153489A1 PCT/CN2018/082838 CN2018082838W WO2019153489A1 WO 2019153489 A1 WO2019153489 A1 WO 2019153489A1 CN 2018082838 W CN2018082838 W CN 2018082838W WO 2019153489 A1 WO2019153489 A1 WO 2019153489A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
intermediate result
money laundering
data processing
processing task
Prior art date
Application number
PCT/CN2018/082838
Other languages
English (en)
French (fr)
Inventor
刘晓兰
Original Assignee
平安科技(深圳)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技(深圳)有限公司 filed Critical 平安科技(深圳)有限公司
Publication of WO2019153489A1 publication Critical patent/WO2019153489A1/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
    • G06Q20/00Payment architectures, schemes or protocols
    • G06Q20/38Payment protocols; Details thereof
    • G06Q20/40Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/401Transaction verification
    • G06Q20/4016Transaction verification involving fraud or risk level assessment in transaction processing
    • 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
    • G06Q40/04Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
    • 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
    • G06Q40/02Banking, e.g. interest calculation or account maintenance

Definitions

  • the present application relates to the field of financial information processing technologies, and in particular, to an operation method of an anti-money laundering model, a computer readable storage medium, a terminal device and a device.
  • the embodiment of the present application provides an operation method of the anti-money laundering model, a computer readable storage medium, a terminal device and a device, which can effectively reduce the burden on the system operation anti-money laundering model and improve system performance.
  • a first aspect of the embodiments of the present application provides an operation method of an anti-money laundering model, including:
  • the financial monitoring system When the financial monitoring system operates the anti-money laundering model, it is determined whether the preset intermediate result data set contains the target intermediate result that the anti-money laundering model needs to use;
  • the target intermediate result is obtained from the intermediate result data set, and each intermediate result included in the intermediate result data set is generated by executing a preset data processing task,
  • the data processing task is set according to the computing requirements of each anti-money laundering model
  • a second aspect of the embodiments of the present application provides a computer readable storage medium storing computer readable instructions that are implemented by a processor to implement an embodiment of the present application.
  • the first aspect proposes the steps of the algorithm of the anti-money laundering model.
  • a third aspect of an embodiment of the present application provides a terminal device including a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, the processor executing the computer
  • the steps of the operation method of the anti-money laundering model proposed by the first aspect of the embodiment of the present application are implemented when the instruction is readable.
  • a fourth aspect of the embodiments of the present application provides an operation device for an anti-money laundering model, including:
  • a judging module configured to determine, when the financial monitoring system operates the anti-money laundering model, whether the preset intermediate result data set contains the target intermediate result that the anti-money laundering model needs to use;
  • An intermediate result obtaining module configured to: if the intermediate result data set includes the target intermediate result, obtain the target intermediate result from the intermediate result data set, where each intermediate result included in the intermediate result data set is executed The data processing task is generated, and the data processing task is set according to the computing requirements of each anti-money laundering model;
  • the anti-money laundering model computing module is configured to substitute the obtained intermediate result of the target into the anti-money laundering model, and calculate an output result of the anti-money laundering model.
  • the system executes The pre-set data processing task calculates the intermediate result of “the total transaction amount of the customer's last 30 days”, saves the intermediate result in the intermediate result data set, and then runs the anti-money laundering models A, B and C when the system runs, regardless of the day. How many times these models are run, the intermediate results can be directly obtained from the intermediate result data set without the need to calculate the intermediate result separately for each model. It can be seen that when the system needs to run a large number of anti-money laundering models, the method can effectively reduce the calculation amount, thereby reducing the burden on the system operation anti-money laundering model and improving the system performance.
  • FIG. 1 is a flowchart of a first embodiment of an operation method of an anti-money laundering model provided by an embodiment of the present application
  • FIG. 2 is a flowchart of a second embodiment of an operation method of an anti-money laundering model provided by an embodiment of the present application
  • FIG. 3 is a flowchart of a third embodiment of an operation method of an anti-money laundering model provided by an embodiment of the present application.
  • FIG. 4 is a structural diagram of an embodiment of an operation device of an anti-money laundering model according to an embodiment of the present application.
  • the embodiment of the present application provides an operation method of the anti-money laundering model, a computer readable storage medium, a terminal device and a device, which can effectively reduce the burden on the system operation anti-money laundering model and improve system performance.
  • a first embodiment of an operation method of an anti-money laundering model in the embodiment of the present application includes:
  • the anti-money laundering model here is a computing model pre-built by the system to identify whether the financial transaction data has a risk of money laundering. Through the acquisition and calculation of the transaction data, the result of whether there is risk is obtained.
  • the financial monitoring system calculates an anti-money laundering model, it is determined whether the preset intermediate result data set contains the target intermediate result that the anti-money laundering model needs to use.
  • the intermediate result data set collects intermediate results that may be used by each of the pre-calculated anti-money laundering models, such as “the total amount of the customer's last 30 days of transactions”, “the number of times the customer has transferred within one week”, and “the customer has a transfer within one month”. Intermediate results such as the number of days of behavior.
  • the respective intermediate results contained in the intermediate result data set are generated by executing a preset data processing task set according to the operational requirements of the respective anti-money laundering models. For example, if multiple anti-money laundering models need to use the intermediate result of “the total amount of the customer's last 30 days of transaction”, the system can establish a data processing task to calculate “the total amount of the customer's last 30 days of transactions” and save it. In the intermediate result data set. If the intermediate result data set contains the target intermediate result, steps 102 to 103 are performed, otherwise step 104 is performed.
  • the intermediate result data set contains the target intermediate result, so the target intermediate result can be obtained therefrom.
  • the target intermediate result For example, if the system runs the anti-money laundering model A and the intermediate results (ie, the target intermediate results) that the anti-money laundering model A needs to use are r, s, and t, then the intermediate results r, s, and t are found from the intermediate result data set. These intermediate results are extracted from these intermediate results in preparation for the next calculation.
  • the obtained intermediate result of the target is substituted into the anti-money laundering model, and the output result of the anti-money laundering model is calculated.
  • the output of the anti-money laundering model can be obtained by simple calculation based on the target intermediate result and part of the original transaction data.
  • the output result is generally “existing risk, early warning” or “risk free”. , no warning.”
  • the intermediate result data set does not include the target intermediate result, so the anti-money laundering model can only be directly calculated, and the target intermediate result is calculated when the anti-money laundering model is calculated, and then the target intermediate result and part of the original transaction data are calculated. Calculate the output of the anti-money laundering model.
  • the operation method of the anti-money laundering model proposed by the embodiment of the present application includes: when the financial monitoring system operates the anti-money laundering model, determining whether the preset intermediate result data set contains the target intermediate result that the anti-money laundering model needs to use;
  • the result data set includes the target intermediate result, the target intermediate result is obtained from the intermediate result data set, and the target intermediate result is substituted into the anti-money laundering model, and the output result of the anti-money laundering model is calculated;
  • Each intermediate result included in the intermediate result data set is generated by executing a preset data processing task, and the data processing task is set according to an operation requirement of each anti-money laundering model.
  • the system executes The pre-set data processing task calculates the intermediate result of “the total transaction amount of the customer's last 30 days”, saves the intermediate result in the intermediate result data set, and then runs the anti-money laundering models A, B and C when the system runs, regardless of the day. How many times these models are run, the intermediate results can be directly obtained from the intermediate result data set without the need to calculate the intermediate result separately for each model. It can be seen that when the system needs to run a large number of anti-money laundering models, the method can effectively reduce the calculation amount, thereby reducing the burden on the system operation anti-money laundering model and improving the system performance.
  • a second embodiment of an operation method of an anti-money laundering model in the embodiment of the present application includes:
  • the system first acquires original data, which is data generated during a financial transaction process, such as transaction time, transaction account, customer information, transaction amount, and transaction type.
  • each intermediate result is calculated according to the original data and the data processing task.
  • the data processing task can be regarded as the calculation or processing rule of the data. After the original data is obtained, the original data is calculated or processed according to the rule, and each intermediate result is obtained.
  • the data processing task may include multiple levels of data processing tasks, and the intermediate result may include intermediate results of multiple levels, and intermediate results of each level are sequentially generated according to the hierarchical number from small to large, and the specific steps are performed. for:
  • the intermediate result of the Nth level is calculated according to the intermediate result of the N-1th level and the data processing task of the Nth level, and N is an integer greater than or equal to 2.
  • the intermediate result of the first level is calculated according to the obtained original data and the data processing task of the first level; and then the intermediate result of the second level is calculated according to the intermediate result of the first level and the data processing task of the second level; Then, the intermediate result of the third level is calculated according to the intermediate result of the second level and the data processing task of the third level; and so on, the number of levels of the intermediate result that needs to be obtained is reasonably determined according to actual needs.
  • all the data results that have been generated can be utilized, for example, when calculating the intermediate result of the third level, based on the intermediate result of the second level, At the same time use the raw data and the intermediate results of the first level.
  • these intermediate results are stored in a preset intermediate result data set to facilitate the search and use of these intermediate results in the operation of the anti-money laundering model.
  • the financial monitoring system operates the anti-money laundering model, determining whether the intermediate result data set includes the target intermediate result that the anti-money laundering model needs to use;
  • step 207 is performed.
  • Steps 204 to 207 are the same as steps 101 to 104. For details, refer to the related description of steps 101 to 104.
  • the present embodiment defines the generation process of each intermediate result in the intermediate result data set.
  • these intermediate results can be directly obtained for subsequent operations in the anti-money laundering model operation.
  • this method can effectively reduce the amount of calculation, thereby reducing the burden on the system to operate the anti-money laundering model and improving system performance.
  • a third embodiment of an operation method of an anti-money laundering model in the embodiment of the present application includes:
  • Step 301 is the same as step 201.
  • Step 301 refers to the related description of step 201.
  • the original data is cleaned according to a preset data cleaning rule.
  • the system receives raw data such as transactions, customers, accounts, etc. from the bank ODS system every day, and runs data cleaning rules to clean and convert the data.
  • the institution to which the customer belongs is converted into a regulatory registration, the nationality field is cleaned to conform to the national and regional name codes of GB/T2659-2000 (cleaning "HK”, “Hong Kong”, “Hong Kong, China” to "HKG"),
  • the currency code is cleaned to meet the data of GB/T12406-1996, ISO-4217 ("RMB", “RMB” is washed as "CHY”) and so on.
  • the raw data after cleaning is processed by using a preset data processing template to obtain basic indicator data.
  • the system automatically loads the customer, account, and transaction basic indicator calculation template (for example, the number of times the customer transfers the local currency to a customer), and calculates the account basic indicator and the transaction basic indicator to form a basic indicator data pool.
  • each intermediate result is calculated according to the basic indicator data and the data processing task. For example, if the basic indicator data is “the number of times the customer transfers the local currency to a customer”, the basic indicator data and the preset data processing task can be used to calculate that “the customer has transferred the local currency to a customer within three days.
  • the first level of intermediate results such as the number of days out, the number of days in which a customer transfers a local currency within three business days of a customer, and the number of times a customer transfers a local currency to a customer in a short period of time.
  • the intermediate result of the second level may be further calculated according to the basic indicator data and the intermediate result of the first level, and so on, intermediate results of multiple levels may be obtained.
  • these intermediate results are stored in a preset intermediate result data set to facilitate the search and use of these intermediate results in the operation of the anti-money laundering model.
  • the original data, the respective intermediate results, and the data processing task whose time distance exceeds the first threshold from the current time are generated are transferred to a preset expired data table.
  • steps 306 to 307 the raw data, the respective intermediate results, and the data processing task whose time distance exceeds a first threshold (such as 3 months) are transferred to a preset expired data table, Thereby completing the archiving of expired data.
  • a first threshold such as 3 months
  • the financial monitoring system operates the anti-money laundering model, determining whether the intermediate result data set includes a target intermediate result that is needed to be used by the anti-money laundering model;
  • step 311 is performed.
  • Steps 308 to 311 are the same as steps 101 to 104. For details, refer to the related description of steps 101 to 104.
  • the embodiment performs pre-processing operations such as data cleaning and data processing on the original data, and can obtain basic indicator data that is more accurate and convenient to use, and then processes according to the basic indicator data and data.
  • the task calculates the intermediate results, and stores the intermediate results in the preset intermediate result data set.
  • these intermediate results can be directly obtained for calculation. It can be seen that when the system needs to run a large number of anti-money laundering models, the method can effectively reduce the calculation amount, thereby reducing the burden on the system operation anti-money laundering model and improving the system performance.
  • the embodiment also dumps the expired data in the system to the expired data table, and realizes the archiving of the expired data, which can maintain the data volume in the system data pool at a relatively stable level, thereby avoiding the continuous accumulation of data and causing anti-money laundering.
  • the burden of model calculations is exacerbated.
  • the above mainly describes an operation method of the anti-money laundering model, and an operation device of an anti-money laundering model will be described in detail below.
  • an embodiment of an operation device for an anti-money laundering model in the embodiment of the present application includes:
  • the determining module 401 is configured to: when the financial monitoring system operates the anti-money laundering model, determine whether the preset intermediate result data set includes the target intermediate result that is needed to be used by the anti-money laundering model;
  • the intermediate result obtaining module 402 is configured to: if the intermediate result data set includes the target intermediate result, obtain the target intermediate result from the intermediate result data set, and each intermediate result included in the intermediate result data set is executed Pre-set data processing tasks are generated, and the data processing tasks are set according to computing requirements of respective anti-money laundering models;
  • the anti-money laundering model operation module 403 is configured to substitute the obtained target intermediate result into the anti-money laundering model, and calculate an output result of the anti-money laundering model.
  • operation device of the anti-money laundering model may further include:
  • a raw data obtaining module configured to acquire raw data, where the raw data is data generated during a financial transaction process
  • the intermediate result calculation module is configured to calculate each intermediate result according to the original data and the data processing task, and store the obtained intermediate results into the intermediate result data set.
  • the intermediate result calculation module may include:
  • a first calculating unit configured to calculate an intermediate result of the first level according to the original data and the data processing task of the first level
  • a second calculating unit configured to calculate an intermediate result of the Nth level according to the intermediate result of the N-1th level and the data processing task of the Nth level, where N is an integer greater than or equal to 2.
  • operation device of the anti-money laundering model may further include:
  • a data cleaning module configured to clean the original data according to a preset data cleaning rule
  • a data processing module configured to process the cleaned original data by using a preset data processing template to obtain basic indicator data
  • the intermediate result calculation module is specifically configured to: calculate the intermediate result according to the basic indicator data and the data processing task.
  • operation device of the anti-money laundering model may further include:
  • a data generation time acquisition module configured to acquire the original data, the respective intermediate results, and a generation time of the data processing task
  • an expiration data dumping module configured to dump the original data, the respective intermediate results, and the data processing task, which generate a time distance from the current time, to a preset expired data table.
  • the embodiment of the present application further provides a computer readable storage medium storing computer readable instructions, and when the computer readable instructions are executed by a processor, implementing any one of the figures as shown in FIG. 1 to FIG. The steps of the algorithm of the anti-money laundering model.
  • the embodiment of the present application further provides a terminal device, including a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, when the processor executes the computer readable instruction.

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Engineering & Computer Science (AREA)
  • Finance (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Development Economics (AREA)
  • Technology Law (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Computer Security & Cryptography (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本申请提出一种反洗钱模型的运算方法、存储介质、终端设备及装置。所述方法包括:当金融监控系统运算反洗钱模型时,判断预设的中间结果数据集中是否包含所述反洗钱模型需要使用的目标中间结果;若所述中间结果数据集中包含所述目标中间结果,则从所述中间结果数据集中获取所述目标中间结果,并将所述目标中间结果代入所述反洗钱模型,计算得到所述反洗钱模型的输出结果;其中,所述中间结果数据集中包含的各个中间结果通过执行预设的数据处理任务产生,所述数据处理任务根据各个反洗钱模型的运算需求设置。当需要运行大量的反洗钱模型时,本方法能够有效减小计算量,从而减小系统运算反洗钱模型时的负担,提高系统性能。

Description

一种反洗钱模型的运算方法、存储介质、终端设备及装置
本申请要求于2018年2月7日提交中国专利局、申请号为201810121936.8、发明名称为“一种反洗钱模型的运算方法、存储介质和服务器”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及金融信息处理技术领域,尤其涉及一种反洗钱模型的运算方法、计算机可读存储介质、终端设备及装置。
背景技术
随着中国金融市场逐渐成熟,国家对反洗钱监管愈加重视,现有金融机构均建立反洗钱机制来识别金融交易过程中的反洗钱风险。目前采取的方式通常为:在金融监控系统上设置大量的反洗钱模型来识别每笔交易数据是否存在一定的洗钱风险,如果存在则将其标记出来。然而,由于金融交易的复杂性,导致往往需要大量的反洗钱模型才能从大量的交易数据中识别出各种各样的洗钱手段,从而导致系统上反洗钱模型的数量极多,系统在运算这些反洗钱模型时负担极大,容易拖垮系统的性能。
技术问题
本申请实施例提供了一种反洗钱模型的运算方法、计算机可读存储介质、终端设备及装置,能够有效减小系统运算反洗钱模型时的负担,提高系统性能。
技术解决方案
本申请实施例的第一方面,提供了一种反洗钱模型的运算方法,包括:
当金融监控系统运算反洗钱模型时,判断预设的中间结果数据集中是否包含所述反洗钱模型需要使用的目标中间结果;
若所述中间结果数据集中包含所述目标中间结果,则从所述中间结果数据集中获取所述目标中间结果,所述中间结果数据集中包含的各个中间结果通过执行预设的数据处理任务产生,所述数据处理任务根据各个反洗钱模型的运算需求设置;
将获取到的所述目标中间结果代入所述反洗钱模型,计算得到所述反洗钱模型的输出结果。
本申请实施例的第二方面,提供了一种计算机可读存储介质,所述计算机可读存储介质存储有计算机可读指令,所述计算机可读指令被处理器执行时实现如本申请实施例的第一方面提出的反洗钱模型的运算方法的步骤。
本申请实施例的第三方面提供了一种终端设备,包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机可读指令,所述处理器执行所述计算机可读指令时实现如本申请实施例的第一方面提出的反洗钱模型的运算方法的步骤。
本申请实施例的第四方面提供一种反洗钱模型的运算装置,包括:
判断模块,用于当金融监控系统运算反洗钱模型时,判断预设的中间结果数据集中是否包含所述反洗钱模型需要使用的目标中间结果;
中间结果获取模块,用于若所述中间结果数据集中包含所述目标中间结果,则从所述中间结果数据集中获取所述目标中间结果,所述中间结果数据集中包含的各个中间结果通过执行预设的数据处理任务产生,所述数据处理任务根据各个反洗钱模型的运算需求设置;
反洗钱模型运算模块,用于将获取到的所述目标中间结果代入所述反洗钱模型,计算得到所述反洗钱模型的输出结果。
有益效果
由于不同的反洗钱模型在运算时可能需要使用相同的中间结果,比如反洗钱模型A、B和C在运算时均需要使用“客户最近30天的交易总金额”这个中间结果,则系统通过执行预先设置的数据处理任务计算得到“客户最近30天的交易总金额”这个中间结果,将该中间结果保存在中间结果数据集中,然后当系统运行反洗钱模型A、B和C时,无论在一天内这几个模型运行多少次,都能从该中间结果数据集中直接获取到该中间结果,而无需每个模型单独计算一次该中间结果。可见,当系统需要运行大量的反洗钱模型时,采用本方法能够有效减小计算量,从而减小系统运算反洗钱模型时的负担,提高系统性能。
附图说明
图1是本申请实施例提供的一种反洗钱模型的运算方法的第一个实施例的流程图;
图2是本申请实施例提供的一种反洗钱模型的运算方法的第二个实施例的流程图;
图3是本申请实施例提供的一种反洗钱模型的运算方法的第三个实施例的流程图;
图4是本申请实施例提供的一种反洗钱模型的运算装置的一个实施例的结构图。
本发明的实施方式
本申请实施例提供了一种反洗钱模型的运算方法、计算机可读存储介质、终端设备及装置,能够有效减小系统运算反洗钱模型时的负担,提高系统性能。
请参阅图1,本申请实施例中一种反洗钱模型的运算方法的第一个实施例包括:
101、当金融监控系统运算反洗钱模型时,判断预设的中间结果数据集中是否包含所述反洗钱模型需要使用的目标中间结果;
这里的反洗钱模型是系统预先构建的用于识别金融交易数据是否存在洗钱风险的运算模型,通过交易数据的获取与计算,得到是否存在风险的结果。当金融监控系统运算某个反洗钱模型时,判断预设的中间结果数据集中是否包含所述反洗钱模型需要使用的目标中间结果。该中间结果数据集收集了预先计算得到的各个反洗钱模型可能需要使用的中间结果,比如“客户最近30天的交易总金额”、“一周内客户的转账次数”、“一月内客户存在转账行为的天数”等中间结果。该中间结果数据集中包含的各个中间结果通过执行预设的数据处理任务产生,所述数据处理任务根据各个反洗钱模型的运算需求设置。比如,多个反洗钱模型均需要使用“客户最近30天的交易总金额”这个中间结果,则系统可以建立某个数据处理任务计算得到“客户最近30天的交易总金额”,并将其保存在该中间结果数据集中。若所述中间结果数据集中包含所述目标中间结果,则执行步骤102至103,否则执行步骤104。
102、从所述中间结果数据集中获取所述目标中间结果;
该中间结果数据集中包含所述目标中间结果,因此可以从中获取所述目标中间结果。比如,系统运行反洗钱模型A,反洗钱模型A需要使用的中间结果(即目标中间结果)为r、s和t,则从该中间结果数据集中查找中间结果r、s和t,若能找到这些中间结果,则将这些中间结果提取出来,为下一步的计算作准备。
103、将获取到的所述目标中间结果代入所述反洗钱模型,计算得到所述反洗钱模型的输出结果;
在获取到目标中间结果后,将获取到的所述目标中间结果代入所述反洗钱模型,计算得到所述反洗钱模型的输出结果。将目标中间结果代入反洗钱模型后,根据目标中间结果和部分的原始交易数据,进行简单的计算即可得到反洗钱模型的输出结果,该输出结果一般为“存在风险,预警”或者“无风险,不预警”。
104、直接运算所述反洗钱模型,得到输出结果。
该中间结果数据集不包含所述目标中间结果,因此只能直接运算所述反洗钱模型,在运算该反洗钱模型时再计算得到该目标中间结果,然后根据目标中间结果和部分的原始交易数据计算得到反洗钱模型的输出结果。
本申请实施例提出的反洗钱模型的运算方法包括:当金融监控系统运算反洗钱模型时,判断预设的中间结果数据集中是否包含所述反洗钱模型需要使用的目标中间结果;若所述中间结果数据集中包含所述目标中间结果,则从所述中间结果数据集中获取所述目标中间结果,并将所述目标中间结果代入所述反洗钱模型,计算得到所述反洗钱模型的输出结果;其中,所述中间结果数据集中包含的各个中间结果通过执行预设的数据处理任务产生,所述数据处理任务根据各个反洗钱模型的运算需求设置。由于不同的反洗钱模型在运算时可能需要使用相同的中间结果,比如反洗钱模型A、B和C在运算时均需要使用“客户最近30天的交易总金额”这个中间结果,则系统通过执行预先设置的数据处理任务计算得到“客户最近30天的交易总金额”这个中间结果,将该中间结果保存在中间结果数据集中,然后当系统运行反洗钱模型A、B和C时,无论在一天内这几个模型运行多少次,都能从该中间结果数据集中直接获取到该中间结果,而无需每个模型单独计算一次该中间结果。可见,当系统需要运行大量的反洗钱模型时,采用本方法能够有效减小计算量,从而减小系统运算反洗钱模型时的负担,提高系统性能。
请参阅图2,本申请实施例中一种反洗钱模型的运算方法的第二个实施例包括:
201、获取原始数据;
在本申请实施例中,系统首先获取原始数据,所述原始数据为在金融交易过程中产生的数据,比如交易时间、交易账户、客户信息、交易金额和交易类型等数据。
202、根据所述原始数据和数据处理任务计算得到各个中间结果;
在获取所述原始数据后,根据所述原始数据和数据处理任务计算得到各个中间结果。数据处理任务可以视作数据的计算或加工规则,在获得原始数据后,对该原始数据按照该规则进行计算或加工,得到各个中间结果。
进一步的,所述数据处理任务可以包括多个层级的数据处理任务,所述中间结果可以包括多个层级的中间结果,各个层级的中间结果按照层级编号由小到大的顺序依次产生,具体步骤为:
(1)根据所述原始数据和第一层级的数据处理任务计算得到第一层级的中间结果;
(2)根据第N-1层级的中间结果和第N层级的数据处理任务计算得到第N层级的中间结果,N为大于或等于2的整数。
首先,根据获取到的原始数据和第一层级的数据处理任务计算得到第一层级的中间结果;然后根据第一层级的中间结果和第二层级的数据处理任务计算得到第二层级的中间结果;接着根据第二层级的中间结果和第三层级的数据处理任务计算得到第三层级的中间结果;以此类推,根据实际需求合理确定需要获得的中间结果的层级数。另外,需要说明的是,在计算某一层级的中间结果时,可以利用已经产生的所有数据结果,比如在计算第三层级的中间结果时,在利用第二层级的中间结果基础上,还可以同时利用原始数据和第一层级的中间结果。
203、将计算得到的各个中间结果存储到预设的中间结果数据集中;
在计算得到各个中间结果后,将这些中间结果存储到预设的中间结果数据集中,便于在运算反洗钱模型时查找并使用这些中间结果。
204、当金融监控系统运算反洗钱模型时,判断所述中间结果数据集中是否包含所述反洗钱模型需要使用的目标中间结果;
若所述中间结果数据集中包含所述目标中间结果,则执行步骤205至206,否则执行步骤207。
205、从所述中间结果数据集中获取所述目标中间结果;
206、将获取到的所述目标中间结果代入所述反洗钱模型,计算得到所述反洗钱模型的输出结果;
207、直接运算所述反洗钱模型,得到输出结果。
步骤204至207与步骤101至104相同,具体可参照步骤101至104的相关说明。
与本申请第一个实施例相比,本实施例对中间结果数据集中各个中间结果的产生过程进行了限定。通过将各个反洗钱模型需要使用的中间结果预先计算并保存在中间结果数据集中,后续进行反洗钱模型运算时可以直接获取这些中间结果进行运算。当系统需要运行大量的反洗钱模型时,采用这种方式能够有效减小计算量,从而减小系统运算反洗钱模型时的负担,提高系统性能。
请参阅图3,本申请实施例中一种反洗钱模型的运算方法的第三个实施例包括:
301、获取在金融交易过程中产生的原始数据;
步骤301与步骤201相同,具体可参照步骤201的相关说明。
302、根据预设的数据清洗规则对所述原始数据进行清洗;
在获取到原始数据后,根据预设的数据清洗规则对这些原始数据进行清洗。比如:系统每天从银行ODS系统接收交易、客户、账户等原始数据,并运行数据清洗规则对这些数据进行清洗、转换。如将客户所属机构转换为监管登记的机构,将国籍字段清洗为符合GB/T2659-2000世界各国和地区名称代码(将“HK”、“香港”、“中国香港”清洗为“HKG”),将货币代码清洗为符合GB/T12406-1996,ISO-4217的数据(将“RMB”、“人民币”清洗为“CHY”)等等。
303、采用预设的数据加工模板对清洗后的所述原始数据进行加工,得到基础指标数据;
在数据清洗完成后,采用预设的数据加工模板对清洗后的所述原始数据进行加工,得到基础指标数据。系统自动加载客户、账户、交易基础指标计算模板(如:客户对某一客户的本币转账转出次数),计算得到账户基础指标、交易基础指标,从而形成基础指标数据池。
304、根据所述基础指标数据和数据处理任务计算得到各个中间结果;
在得到各个基础指标数据后,根据所述基础指标数据和数据处理任务计算得到各个中间结果。比如,某个基础指标数据为“客户对某一客户的本币转账转出次数”,则可通过该基础指标数据和预设的数据处理任务计算得到“客户对某一客户三天内发生本币转账转出天数”、“客户对某一客户三个工作日内发生本币转账转出天数”以及“短期内客户对某一客户的本币转账转出次数”等第一层级的中间结果。进一步的,在获得第一层级的中间结果后,可以根据所述基础指标数据和第一层级的中间结果进一步计算得到第二层级的中间结果,以此类推可以得到多个层级的中间结果。
305、将计算得到的各个中间结果存储到预设的中间结果数据集中;
在计算得到各个中间结果后,将这些中间结果存储到预设的中间结果数据集中,便于在运算反洗钱模型时查找并使用这些中间结果。
306、获取所述原始数据,所述各个中间结果和所述数据处理任务的产生时间;
307、将产生时间距离当前时间超过第一阈值的所述原始数据、所述各个中间结果和所述数据处理任务转存至预设的过期数据表;
在步骤306至307中,将产生时间距离当前时间超过第一阈值(比如3个月)的所述原始数据、所述各个中间结果和所述数据处理任务转存至预设的过期数据表,从而完成过期数据的归档。通过这样设置,一方面实现了过期数据的备查,另一方面使得系统数据池中的数据量维持在一个相对稳定的水平,避免数据持续累积而导致反洗钱模型计算的负担加重。
308、当金融监控系统运算反洗钱模型时,判断所述中间结果数据集中是否包含所述反洗钱模型需要使用的目标中间结果;
若所述中间结果数据集中包含所述目标中间结果,则执行步骤309至310,否则执行步骤311。
309、从所述中间结果数据集中获取所述目标中间结果;
310、将获取到的所述目标中间结果代入所述反洗钱模型,计算得到所述反洗钱模型的输出结果;
311、直接运算所述反洗钱模型,得到输出结果。
步骤308至311与步骤101至104相同,具体可参照步骤101至104的相关说明。
与本申请的第二个实施例相比,本实施例对原始数据进行了数据清洗、数据加工等预处理操作,能够获得更准确且便于使用的基础指标数据,然后根据基础指标数据和数据处理任务计算得到各个中间结果,将这些中间结果存储在预设的中间结果数据集中,后续进行反洗钱模型运算时可以直接获取这些中间结果进行运算。可见,当系统需要运行大量的反洗钱模型时,采用本方法能够有效减小计算量,从而减小系统运算反洗钱模型时的负担,提高系统性能。另外,本实施例还将系统中过期的数据转存至过期数据表,实现过期数据的归档,能够使得系统数据池中的数据量维持在一个相对稳定的水平,避免数据持续累积而导致反洗钱模型计算的负担加重。
应理解,上述实施例中各步骤的序号的大小并不意味着执行顺序的先后,各过程的执行顺序应以其功能和内在逻辑确定,而不应对本申请实施例的实施过程构成任何限定。
上面主要描述了一种反洗钱模型的运算方法,下面将对一种反洗钱模型的运算装置进行详细描述。
请参阅图4,本申请实施例中一种反洗钱模型的运算装置的一个实施例包括:
判断模块401,用于当金融监控系统运算反洗钱模型时,判断预设的中间结果数据集中是否包含所述反洗钱模型需要使用的目标中间结果;
中间结果获取模块402,用于若所述中间结果数据集中包含所述目标中间结果,则从所述中间结果数据集中获取所述目标中间结果,所述中间结果数据集中包含的各个中间结果通过执行预设的数据处理任务产生,所述数据处理任务根据各个反洗钱模型的运算需求设置;
反洗钱模型运算模块403,用于将获取到的所述目标中间结果代入所述反洗钱模型,计算得到所述反洗钱模型的输出结果。
进一步的,所述反洗钱模型的运算装置还可以包括:
原始数据获取模块,用于获取原始数据,所述原始数据为在金融交易过程中产生的数据;
中间结果计算模块,用于根据所述原始数据和所述数据处理任务计算得到各个中间结果,并将得到的各个中间结果存储到所述中间结果数据集中。
更进一步的,所述中间结果计算模块可以包括:
第一计算单元,用于根据所述原始数据和第一层级的数据处理任务计算得到第一层级的中间结果;
第二计算单元,用于根据第N-1层级的中间结果和第N层级的数据处理任务计算得到第N层级的中间结果,N为大于或等于2的整数。
进一步的,所述反洗钱模型的运算装置还可以包括:
数据清洗模块,用于根据预设的数据清洗规则对所述原始数据进行清洗;
数据加工模块,用于采用预设的数据加工模板对清洗后的所述原始数据进行加工,得到基础指标数据;
所述中间结果计算模块具体用于:根据所述基础指标数据和所述数据处理任务计算得到所述中间结果。
进一步的,所述反洗钱模型的运算装置还可以包括:
数据产生时间获取模块,用于获取所述原始数据,所述各个中间结果和所述数据处理任务的产生时间;
过期数据转存模块,用于将产生时间距离当前时间超过第一阈值的所述原始数据、所述各个中间结果和所述数据处理任务转存至预设的过期数据表。
本申请实施例还提供一种计算机可读存储介质,所述计算机可读存储介质存储有计算机可读指令,所述计算机可读指令被处理器执行时实现如图1至图3表示的任意一种反洗钱模型的运算方法的步骤。
本申请实施例还提供一种终端设备,包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机可读指令,所述处理器执行所述计算机可读指令时实现如图1至图3表示的任意一种反洗钱模型的运算方法的步骤。

Claims (20)

  1. 一种反洗钱模型的运算方法,其特征在于,包括:
    当金融监控系统运算反洗钱模型时,判断预设的中间结果数据集中是否包含所述反洗钱模型需要使用的目标中间结果;
    若所述中间结果数据集中包含所述目标中间结果,则从所述中间结果数据集中获取所述目标中间结果,所述中间结果数据集中包含的各个中间结果通过执行预设的数据处理任务产生,所述数据处理任务根据各个反洗钱模型的运算需求设置;
    将获取到的所述目标中间结果代入所述反洗钱模型,计算得到所述反洗钱模型的输出结果。
  2. 根据权利要求1所述的反洗钱模型的运算方法,其特征在于,所述中间结果数据集中包含的各个中间结果通过以下步骤产生:
    获取原始数据,所述原始数据为在金融交易过程中产生的数据;
    根据所述原始数据和所述数据处理任务计算得到所述各个中间结果。
  3. 根据权利要求2所述的反洗钱模型的运算方法,其特征在于,所述数据处理任务包括多个层级的数据处理任务,所述中间结果包括多个层级的中间结果,各个层级的中间结果按照层级编号由小到大的顺序依次产生,具体步骤为:
    根据所述原始数据和第一层级的数据处理任务计算得到第一层级的中间结果;
    根据第N-1层级的中间结果和第N层级的数据处理任务计算得到第N层级的中间结果,N为大于或等于2的整数。
  4. 根据权利要求2所述的反洗钱模型的运算方法,其特征在于,在根据所述原始数据和所述数据处理任务计算得到所述各个中间结果之前,还包括:
    根据预设的数据清洗规则对所述原始数据进行清洗;
    采用预设的数据加工模板对清洗后的所述原始数据进行加工,得到基础指标数据;
    所述根据所述原始数据和所述数据处理任务计算得到所述各个中间结果具体为:
    根据所述基础指标数据和所述数据处理任务计算得到所述各个中间结果。
  5. 根据权利要求2至4中任一项所述的反洗钱模型的运算方法,其特征在于,还包括:
    获取所述原始数据,所述各个中间结果和所述数据处理任务的产生时间;
    将产生时间距离当前时间超过第一阈值的所述原始数据、所述各个中间结果和所述数据处理任务转存至预设的过期数据表。
  6. 一种计算机可读存储介质,所述计算机可读存储介质存储有计算机可读指令,其特征在于,所述计算机可读指令被处理器执行时实现如下步骤:
    当金融监控系统运算反洗钱模型时,判断预设的中间结果数据集中是否包含所述反洗钱模型需要使用的目标中间结果;
    若所述中间结果数据集中包含所述目标中间结果,则从所述中间结果数据集中获取所述目标中间结果,所述中间结果数据集中包含的各个中间结果通过执行预设的数据处理任务产生,所述数据处理任务根据各个反洗钱模型的运算需求设置;
    将获取到的所述目标中间结果代入所述反洗钱模型,计算得到所述反洗钱模型的输出结果。
  7. 根据权利要求6所述的计算机可读存储介质,其特征在于,所述中间结果数据集中包含的各个中间结果通过以下步骤产生:
    获取原始数据,所述原始数据为在金融交易过程中产生的数据;
    根据所述原始数据和所述数据处理任务计算得到所述各个中间结果。
  8. 根据权利要求7所述的计算机可读存储介质,其特征在于,所述数据处理任务包括多个层级的数据处理任务,所述中间结果包括多个层级的中间结果,各个层级的中间结果按照层级编号由小到大的顺序依次产生,具体步骤为:
    根据所述原始数据和第一层级的数据处理任务计算得到第一层级的中间结果;
    根据第N-1层级的中间结果和第N层级的数据处理任务计算得到第N层级的中间结果,N为大于或等于2的整数。
  9. 根据权利要求7所述的计算机可读存储介质,其特征在于,在根据所述原始数据和所述数据处理任务计算得到所述各个中间结果之前,还包括:
    根据预设的数据清洗规则对所述原始数据进行清洗;
    采用预设的数据加工模板对清洗后的所述原始数据进行加工,得到基础指标数据;
    所述根据所述原始数据和所述数据处理任务计算得到所述各个中间结果具体为:
    根据所述基础指标数据和所述数据处理任务计算得到所述各个中间结果。
  10. 根据权利要求7至9中任一项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处理器执行时还实现以下步骤:
    获取所述原始数据,所述各个中间结果和所述数据处理任务的产生时间;
    将产生时间距离当前时间超过第一阈值的所述原始数据、所述各个中间结果和所述数据处理任务转存至预设的过期数据表。
  11. 一种终端设备,包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机可读指令,其特征在于,所述处理器执行所述计算机可读指令时实现如下步骤:
    当金融监控系统运算反洗钱模型时,判断预设的中间结果数据集中是否包含所述反洗钱模型需要使用的目标中间结果;
    若所述中间结果数据集中包含所述目标中间结果,则从所述中间结果数据集中获取所述目标中间结果,所述中间结果数据集中包含的各个中间结果通过执行预设的数据处理任务产生,所述数据处理任务根据各个反洗钱模型的运算需求设置;
    将获取到的所述目标中间结果代入所述反洗钱模型,计算得到所述反洗钱模型的输出结果。
  12. 根据权利要求11所述的终端设备,其特征在于,所述中间结果数据集中包含的各个中间结果通过以下步骤产生:
    获取原始数据,所述原始数据为在金融交易过程中产生的数据;
    根据所述原始数据和所述数据处理任务计算得到所述各个中间结果。
  13. 根据权利要求12所述的终端设备,其特征在于,所述数据处理任务包括多个层级的数据处理任务,所述中间结果包括多个层级的中间结果,各个层级的中间结果按照层级编号由小到大的顺序依次产生,具体步骤为:
    根据所述原始数据和第一层级的数据处理任务计算得到第一层级的中间结果;
    根据第N-1层级的中间结果和第N层级的数据处理任务计算得到第N层级的中间结果,N为大于或等于2的整数。
  14. 根据权利要求12所述的终端设备,其特征在于,在根据所述原始数据和所述数据处理任务计算得到所述各个中间结果之前,还包括:
    根据预设的数据清洗规则对所述原始数据进行清洗;
    采用预设的数据加工模板对清洗后的所述原始数据进行加工,得到基础指标数据;
    所述根据所述原始数据和所述数据处理任务计算得到所述各个中间结果具体为:
    根据所述基础指标数据和所述数据处理任务计算得到所述各个中间结果。
  15. 根据权利要求12至14中任一项所述的终端设备,其特征在于,所述处理器执行所述计算机可读指令时还实现以下步骤:
    获取所述原始数据,所述各个中间结果和所述数据处理任务的产生时间;
    将产生时间距离当前时间超过第一阈值的所述原始数据、所述各个中间结果和所述数据处理任务转存至预设的过期数据表。
  16. 一种反洗钱模型的运算装置,其特征在于,包括:
    判断模块,用于当金融监控系统运算反洗钱模型时,判断预设的中间结果数据集中是否包含所述反洗钱模型需要使用的目标中间结果;
    中间结果获取模块,用于若所述中间结果数据集中包含所述目标中间结果,则从所述中间结果数据集中获取所述目标中间结果,所述中间结果数据集中包含的各个中间结果通过执行预设的数据处理任务产生,所述数据处理任务根据各个反洗钱模型的运算需求设置;
    反洗钱模型运算模块,用于将获取到的所述目标中间结果代入所述反洗钱模型,计算得到所述反洗钱模型的输出结果。
  17. 根据权利要求16所述的反洗钱模型的运算装置,其特征在于,还包括:
    原始数据获取模块,用于获取原始数据,所述原始数据为在金融交易过程中产生的数据;
    中间结果计算模块,用于根据所述原始数据和所述数据处理任务计算得到所述各个中间结果。
  18. 根据权利要求17所述的反洗钱模型的运算装置,其特征在于,所述中间结果计算模块包括:
    第一计算单元,用于根据所述原始数据和第一层级的数据处理任务计算得到第一层级的中间结果;
    第二计算单元,用于根据第N-1层级的中间结果和第N层级的数据处理任务计算得到第N层级的中间结果,N为大于或等于2的整数。
  19. 根据权利要求17所述的反洗钱模型的运算装置,其特征在于,还包括:
    数据清洗模块,用于根据预设的数据清洗规则对所述原始数据进行清洗;
    数据加工模块,用于采用预设的数据加工模板对清洗后的所述原始数据进行加工,得到基础指标数据;
    所述中间结果计算模块具体用于:根据所述基础指标数据和所述数据处理任务计算得到所述中间结果。
  20. 根据权利要求17至19中任一项所述的反洗钱模型的运算装置,其特征在于,还包括:
    数据产生时间获取模块,用于获取所述原始数据,所述各个中间结果和所述数据处理任务的产生时间;
    过期数据转存模块,用于将产生时间距离当前时间超过第一阈值的所述原始数据、所述各个中间结果和所述数据处理任务转存至预设的过期数据表。
PCT/CN2018/082838 2018-02-07 2018-04-12 一种反洗钱模型的运算方法、存储介质、终端设备及装置 WO2019153489A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810121936.8 2018-02-07
CN201810121936.8A CN108376366A (zh) 2018-02-07 2018-02-07 一种反洗钱模型的运算方法、存储介质和服务器

Publications (1)

Publication Number Publication Date
WO2019153489A1 true WO2019153489A1 (zh) 2019-08-15

Family

ID=63017522

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/082838 WO2019153489A1 (zh) 2018-02-07 2018-04-12 一种反洗钱模型的运算方法、存储介质、终端设备及装置

Country Status (2)

Country Link
CN (1) CN108376366A (zh)
WO (1) WO2019153489A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116402512B (zh) * 2023-05-31 2023-08-22 无锡锡商银行股份有限公司 一种基于人工智能的账户安全排查管理方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105719033A (zh) * 2014-12-02 2016-06-29 阿里巴巴集团控股有限公司 用于识别客体风险的方法及装置
WO2016138183A1 (en) * 2015-02-24 2016-09-01 Pneuron Corp. Distributed money laundering detection system
CN106484780A (zh) * 2016-09-06 2017-03-08 努比亚技术有限公司 数据统计方法及装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106547838B (zh) * 2016-10-14 2019-06-18 北京银丰新融科技开发有限公司 基于资金网络监测可疑资金交易的方法
CN106651463A (zh) * 2016-12-30 2017-05-10 上海富聪金融信息服务有限公司 金融机构服务接入系统及其接入方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105719033A (zh) * 2014-12-02 2016-06-29 阿里巴巴集团控股有限公司 用于识别客体风险的方法及装置
WO2016138183A1 (en) * 2015-02-24 2016-09-01 Pneuron Corp. Distributed money laundering detection system
CN106484780A (zh) * 2016-09-06 2017-03-08 努比亚技术有限公司 数据统计方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ZHONG, CHONGMIN ET AL.: "Analysis on the Application of Big Data in the Performance of the Central Bank", FINANCIAL TECHNOLOGY TIME, 30 November 2016 (2016-11-30) *

Also Published As

Publication number Publication date
CN108376366A (zh) 2018-08-07

Similar Documents

Publication Publication Date Title
US20200218737A1 (en) Method, system and program product for matching of transaction records
WO2022267735A1 (zh) 业务数据处理方法、装置、计算机设备和存储介质
US8229835B2 (en) Determination of implied orders in a trade matching system
WO2019154108A1 (zh) 处理交易数据的方法及装置
CN107025236B (zh) 清算系统间的数据处理方法及数据清算系统
EP2983117A1 (en) Event processing method in stream processing system and stream processing system
WO2020258994A1 (zh) 一种节点数据预测方法及装置
JP2019519017A (ja) 精算処理方法、精算処理装置、端末機器及び記憶媒体
WO2016084642A1 (ja) 与信審査用サーバと与信審査用システム及び与信審査用プログラム
TW202008231A (zh) 外匯交易量預測方法和裝置
WO2018184550A1 (zh) 理赔金的计算方法、装置、终端设备及介质
CN107403382B (zh) 资产匹配系统
WO2019153489A1 (zh) 一种反洗钱模型的运算方法、存储介质、终端设备及装置
CN112035681A (zh) 基于知识图谱的信用卡费率信息确定方法及装置
Novignon et al. Fiscal space for health in sub-Saharan African countries: an efficiency approach
US20220318903A1 (en) Machine learning based prediction for multiple currency goals
US9483332B2 (en) Event processing method in stream processing system and stream processing system
CN114997576A (zh) 一种达标提示对象的确定方法、装置、设备、介质及产品
JP7151870B2 (ja) スコア分布変換装置、スコア分布変換方法およびスコア分布変換プログラム
WO2020034752A1 (zh) 浮动收益计算方法、装置、设备及计算机可读存储介质
CN114138743A (zh) 基于机器学习的etl任务自动配置方法及装置
US11521274B2 (en) Cost allocation estimation using direct cost vectors and machine learning
JP5650290B1 (ja) オペレーショナルリスクの計量方法及び装置
TWI665634B (zh) 外匯交易管理系統及其管理方法
JP2016031571A (ja) 情報処理方法、情報処理装置、及び、プログラム

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: 18904933

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 1205A DATED 03.11.2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18904933

Country of ref document: EP

Kind code of ref document: A1