WO2020119299A1 - Procédé et dispositif de fusion de modèle - Google Patents

Procédé et dispositif de fusion de modèle Download PDF

Info

Publication number
WO2020119299A1
WO2020119299A1 PCT/CN2019/113993 CN2019113993W WO2020119299A1 WO 2020119299 A1 WO2020119299 A1 WO 2020119299A1 CN 2019113993 W CN2019113993 W CN 2019113993W WO 2020119299 A1 WO2020119299 A1 WO 2020119299A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
test sample
merging
prediction
prediction result
Prior art date
Application number
PCT/CN2019/113993
Other languages
English (en)
Chinese (zh)
Inventor
朱标
崔志伟
章鹏
陈诗奕
Original Assignee
阿里巴巴集团控股有限公司
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 阿里巴巴集团控股有限公司 filed Critical 阿里巴巴集团控股有限公司
Publication of WO2020119299A1 publication Critical patent/WO2020119299A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08—Insurance

Definitions

  • the invention relates to the field of computer technology, in particular to a method and device for merging models.
  • models are generally set at multiple stages of the business to identify whether there is risk at the corresponding stage.
  • the stages include: reporting, investigation and compensation.
  • Each stage corresponds to a model.
  • the reporting stage corresponds to the reporting model.
  • the reporting model is used to identify whether there is a risk in the reporting stage.
  • the embodiments of the present invention provide a method and a device for merging models, which can reduce the cost of risk identification.
  • an embodiment of the present invention provides a model merging method, including:
  • X i is used to characterize the set of variables included in the i-th model
  • X i+1 is used to characterize the set of variables included in the i+1-th model
  • i ⁇ j ⁇ n is the number of models
  • the merging the i-th model and the j-th model according to the first prediction result and the second prediction result includes:
  • the first prediction result includes: a risk score of a test sample of the i-th model by the i-th model;
  • the determining, according to the first prediction result, the prediction accuracy rate of the i-th model to the i-th model test sample includes:
  • the prediction accuracy rate of the i-th model to the test samples of the i-th model is determined.
  • merging the i-th model with the j-th model includes:
  • the merging the i-th model and the j-th model includes:
  • the jth model is a result of merging the ith model and the jth model.
  • an embodiment of the present invention provides a model merging device, including:
  • a first prediction unit used to predict the test sample of the i-th model according to the i-th model to obtain a first prediction result
  • a second prediction unit used to predict the test sample of the i-th model according to the j-th model to obtain a second prediction result; wherein, X i is used to characterize the set of variables included in the i-th model, X i+1 is used to characterize the set of variables included in the i+1-th model, i ⁇ j ⁇ n, and n is the number of models;
  • the merging unit is configured to merge the i-th model and the j-th model according to the first prediction result and the second prediction result.
  • the merging unit is used to determine the prediction accuracy rate of the i-th model to the i-th model test sample according to the first prediction result; according to the second prediction result, determine the j-th Prediction accuracy of the i model for the test samples of the i model; when the prediction accuracy of the i model for the test sample of the i model and the j model for the i When the prediction accuracy of the test samples of the three models meets the preset merging conditions, the i-th model and the j-th model are merged.
  • the first prediction result includes: a risk score of a test sample of the i-th model by the i-th model;
  • the merging unit is configured to determine whether the test sample of the i-th model is at risk according to the risk score of the i-th model for the test sample of the i-th model; according to the i Test samples of each model to determine the prediction accuracy rate of the i-th model for the i-th model test samples.
  • the merging unit is used when j takes different values, and the different values make the prediction accuracy of the i-th model to the i-th model test sample and the j-th model pair When the prediction accuracy of the test sample of the i-th model meets the merging condition, the i-th model and the a-th model are merged; wherein, a is used to characterize the maximum value among the different values.
  • the merging unit is configured to determine that the jth model is a result of merging the ith model and the jth model.
  • the at least one technical solution adopted in the embodiments of the present invention can achieve the following beneficial effects:
  • the method combines different models according to the prediction results of the models on the test samples, which can reduce the number of models and reduce the cost of risk identification.
  • this method can ensure the performance of the model at each stage and improve the accuracy of risk identification compared to directly reusing the model through missing value filling.
  • FIG. 1 is a flowchart of a model merging method provided by an embodiment of the present invention
  • FIG. 2 is a schematic diagram of a model variable relationship provided by an embodiment of the present invention.
  • FIG. 3 is a flowchart of a method for merging models provided by another embodiment of the present invention.
  • FIG. 4 is a schematic structural diagram of a model merging device provided by an embodiment of the present invention.
  • a model is generally set at each stage (risk point). Whether from a data perspective or a model perspective, this approach is simple and straightforward, with no need to focus on the business and data associations between different stages. However, as the number of models increases, the cost of R&D, deployment, and customer access increases rapidly.
  • an embodiment of the present invention provides a method for merging models. As shown in FIG. 1, the method may include the following steps:
  • Step 101 Predict the test sample of the i-th model according to the i-th model to obtain the first prediction result.
  • i is a variable, and its value range is (0, n), where n is the number of models, that is, the number of stages.
  • n is the number of models, that is, the number of stages.
  • the first model predicts the test samples of the first model
  • the second model predicts the test samples of the second model.
  • the model may be pre-set, or it may be obtained by training according to the training samples at the corresponding stage.
  • the i-th model is trained by its corresponding training sample.
  • Step 102 Predict the test sample of the i-th model according to the j-th model to obtain a second prediction result; wherein, X i is used to characterize the set of variables included in the i-th model, X i+1 is used to characterize the set of variables included in the i+1-th model, i ⁇ j ⁇ n, and n is the number of models.
  • each model corresponds to a corresponding business phase, and different business phases exist in chronological order.
  • the corresponding models are the first model, the second model, the third model... the nth model.
  • the model includes a report model, an investigation model and a compensation model, which are used to identify the risks that exist in the three stages of report, investigation and compensation.
  • the insured will report the incident after the accident (reporting stage).
  • the insurance company will send an investigator to investigate the accident site (inspection stage), and then after the investigation is completed
  • the insurance company will make compensation to the case (stage of compensation). Once the compensation is completed, the compensation will be sent to the insured's designated account.
  • Step 103 Combine the i-th model and the j-th model according to the first prediction result and the second prediction result.
  • the number of first prediction results and the number of second prediction results may be multiple, but the method of merging the models is consistent.
  • step 103 specifically includes:
  • A1 According to the first prediction result, determine the prediction accuracy rate of the i-th model to the i-th model test sample.
  • the first prediction result includes: the risk score of the i-th model on the test sample of the i-th model.
  • A1 specifically includes:
  • A11 According to the risk score of the i-th model on the test sample of the i-th model, determine whether the test sample of the i-th model is at risk.
  • the risk score of the i-th model's test sample of the i-th model can be matched with the preset risk range to determine whether the i-th model's test sample is at risk
  • A12 Determine the prediction accuracy of the i-th model to the i-th model test sample based on the test sample of the i-th model with risk.
  • the prediction accuracy rate of the i-th model to the i-th model test sample the number of i-th model test samples that are actually at risk among the i-th model test samples predicted to be at risk / Predict (determine) the number of test samples for the i-th model at risk.
  • the real risk refers to the confirmed risk, for example, the sample with the risk label is the sample with real risk.
  • A2 According to the second prediction result, determine the prediction accuracy of the jth model to the ith model test sample.
  • the second prediction result is similar to the first prediction result.
  • the second prediction result includes: the risk score of the j-th model on the i-th model test sample;
  • the method for determining the prediction accuracy rate of the test sample of the jth model to the ith model is similar to the process in the above A1, and will not be repeated here.
  • A3 When the prediction accuracy of the i-th model to the i-th model test sample and the j-th model to the i-th model's test sample meet the preset merge conditions, the i-th model and The jth model is merged.
  • the merging condition may be that the difference between the prediction accuracy of the i-th model to the i-th model test sample and the j-th model to the i-th model's test sample is less than the preset merge threshold. For example, when the merge threshold is 5%, that is, the difference between the two prediction accuracy rates is less than 5%, the i-th model and the j-th model can be merged.
  • A3 includes:
  • the preset merge threshold is 5%.
  • the difference between the prediction accuracy of the first model for the test sample of the first model and the prediction accuracy of the second model for the test sample of the first model is 2%, and at the same time, the first model for the first
  • the difference between the prediction accuracy of the test sample of the model and the prediction accuracy of the third model to the test sample of the first model is 3%, and then the first model is merged with the third model.
  • This method combines different models according to the prediction results of the model on the test sample, which can reduce the number of models and reduce the cost of risk identification. At the same time, this method can ensure the performance of the model at each stage and improve the accuracy of risk identification compared to directly reusing the model through missing value filling.
  • merging the i-th model and the j-th model includes: determining that the j-th model is the result of merging the i-th model and the j-th model.
  • merging the first model with the second model refers to keeping the second model. If there is a first model and a second model before the merge, only the second model exists after the merge, and only the second model is used. Model for risk identification.
  • step 102 may be performed for each value, or step 102 may be performed for only some of the values.
  • this method can determine the number of retained models according to the needs of the actual scene.
  • an embodiment of the present invention takes a vehicle insurance claim scenario as an example to describe in detail a method for merging models.
  • the method includes:
  • Step 301 Predict the test sample of the i-th model according to the i-th model to obtain a first prediction result; the first prediction result includes: a risk score of the i-th model for the test sample of the i-th model.
  • Step 302 Predict the test sample of the i-th model according to the j-th model to obtain a second prediction result; wherein, X i is used to characterize the set of variables included in the i-th model, X i+1 is used to characterize the set of variables included in the i+1-th model, i ⁇ j ⁇ n, and n is the number of models.
  • the second model is the investigation model
  • the third model is the compensation model.
  • Case 1 Determine whether it is possible to merge the investigation model and the compensation model.
  • the test sample of the investigation model is predicted according to the compensation model to obtain the second prediction result.
  • Case 2 Determine whether it is possible to combine the reporting model and the investigation model, or the reporting model and the compensation model.
  • the test sample of the report model is predicted according to the compensation model to obtain the second prediction result (corresponding to the compensation model).
  • the compensation model has the most complete variables, and the prediction performance is generally the best.
  • Step 303 Determine whether the i-th model test sample is at risk according to the i-th model's risk score for the i-th model test sample.
  • Step 304 Determine the prediction accuracy of the i-th model to the i-th model test sample based on the test sample of the i-th model with risk.
  • Step 305 According to the second prediction result, determine the prediction accuracy of the j-th model to the i-th model test sample.
  • Step 306 When the prediction accuracy of the i-th model to the i-th model test sample and the j-th model to the i-th model-test sample's prediction accuracy meet the preset merge conditions, determine the j-th model It is the result of merging the i-th model and the j-th model.
  • the model obtained by this method can be used to identify the risks existing in different stages of auto insurance claims settlement, detect fraud in time, and ensure the safety of funds.
  • an embodiment of the present invention provides a model merging device, including:
  • the first prediction unit 401 is used to predict the test sample of the i-th model according to the i-th model to obtain a first prediction result;
  • the second prediction unit 402 is used to predict the test sample of the i-th model according to the j-th model to obtain a second prediction result; wherein, X i is used to characterize the set of variables included in the i-th model, X i+1 is used to characterize the set of variables included in the i+1-th model, i ⁇ j ⁇ n, n is the number of models;
  • the merging unit 403 is configured to merge the i-th model and the j-th model according to the first prediction result and the second prediction result.
  • the merging unit 403 is used to determine the prediction accuracy of the i-th model to the i-th model test sample based on the first prediction result; according to the second prediction result, determine the j-th model The prediction accuracy of the i-th model's test sample; when the i-th model's prediction accuracy of the i-th model's test sample and the j-th model's prediction accuracy of the i-th model's test sample meet the preset When merging conditions, merge the i-th model with the j-th model.
  • the first prediction result includes: the risk score of the i-th model on the test sample of the i-th model;
  • the merging unit 403 is used to determine whether the test sample of the i-th model is at risk according to the risk score of the i-th model on the test sample of the i-th model; according to the test sample of the i-th model with risk, determine the i-th The prediction accuracy of the test samples of the i model to the i model.
  • the merging unit 403 is used when j takes different values, and the different values make the prediction accuracy of the i-th model to the i-th model test sample and the j-th model pair When the prediction accuracy of the test sample of the i-th model meets the merging conditions, the i-th model and the a-th model are merged; where a is used to characterize the maximum value among different values.
  • the merging unit 403 is used to determine that the jth model is the result of merging the ith model and the jth model.
  • the improvement of a technology can be clearly distinguished from the improvement in hardware (for example, the improvement of circuit structures such as diodes, transistors, and switches) or the improvement in software (the improvement of the process flow).
  • the improvement of many methods and processes can be regarded as a direct improvement of the hardware circuit structure.
  • Designers almost get the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be realized by hardware physical modules.
  • a programmable logic device Programmable Logic Device, PLD
  • PLD Programmable Logic Device
  • FPGA Field Programmable Gate Array
  • HDL Hardware Description Language
  • ABEL Advanced Boolean Expression
  • AHDL AlteraHardwareDescriptionLanguage
  • Confluence a specific programming language
  • CUPL CornellUniversityProgrammingLanguage
  • HDCal JHDL (JavaHardwareDescriptionLanguage)
  • Lava Lola
  • MyHDL PALASM
  • RHDL RubyHardwareDescription
  • the controller may be implemented in any suitable manner, for example, the controller may take a microprocessor or processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor , Logic gates, switches, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable logic controllers and embedded microcontrollers.
  • Examples of controllers include but are not limited to the following microcontrollers: ARC625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicon Labs C8051F320, the memory controller can also be implemented as part of the control logic of the memory.
  • controller in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to logically program method steps to make the controller use logic gates, switches, application specific integrated circuits, programmable logic controllers and embedded The same function is realized in the form of a microcontroller or the like. Therefore, such a controller can be regarded as a hardware component, and the device for implementing various functions included therein can also be regarded as a structure within the hardware component. Or even, the means for realizing various functions can be regarded as both a software module of an implementation method and a structure within a hardware component.
  • the system, device, module or unit explained in the above embodiments may be specifically implemented by a computer chip or entity, or implemented by a product with a certain function.
  • a typical implementation device is a computer.
  • the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or A combination of any of these devices.
  • the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.
  • computer usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • each flow and/or block in the flowchart and/or block diagram and a combination of the flow and/or block in the flowchart and/or block diagram may be implemented by computer program instructions.
  • These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processing machine, or other programmable data processing device to produce a machine that enables the generation of instructions executed by the processor of the computer or other programmable data processing device
  • These computer program instructions may also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, the instructions
  • the device implements the functions specified in one block or multiple blocks of the flowchart one flow or multiple flows and/or block diagrams.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operating steps are performed on the computer or other programmable device to produce computer-implemented processing, which is executed on the computer or other programmable device
  • the instructions provide steps for implementing the functions specified in one block or multiple blocks of the flowchart one flow or multiple flows and/or block diagrams.
  • the computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-permanent memory, random access memory (RAM) and/or non-volatile memory in computer-readable media, such as read only memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
  • RAM random access memory
  • ROM read only memory
  • flash RAM flash random access memory
  • Computer-readable media including permanent and non-permanent, removable and non-removable media, can store information by any method or technology.
  • the information may be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, read-only compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, Magnetic tape cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices.
  • computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.
  • the present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules.
  • program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types.
  • the present application may also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected through a communication network.
  • program modules may be located in local and remote computer storage media including storage devices.

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)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

La présente invention concerne un procédé et un dispositif de fusion de modèle. Le procédé comprend les étapes consistant à : prédire des échantillons de test d'un i-ième modèle en fonction du i-ième modèle de façon à obtenir un premier résultat de prédiction (101); prédire des échantillons de test du i-ième modèle en fonction d'un j-ième modèle de façon à obtenir un second résultat de prédiction; Xi ⊆ Xi+1, Xi étant utilisée pour représenter un ensemble de variables intégrées au i-ième modèle, Xi+1 étant utilisée pour représenter un ensemble de variables intégrées à un (i+1)-ième modèle, i＜j≤n, n étant le nombre de modèles (102); et fusionner le i-ième modèle et le j-ième modèle en fonction du premier résultat de prédiction et du second résultat de prédiction (103).
PCT/CN2019/113993 2018-12-14 2019-10-29 Procédé et dispositif de fusion de modèle WO2020119299A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811538668.6 2018-12-14
CN201811538668.6A CN109903165B (zh) 2018-12-14 2018-12-14 一种模型合并方法和装置

Publications (1)

Publication Number Publication Date
WO2020119299A1 true WO2020119299A1 (fr) 2020-06-18

Family

ID=66943426

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/113993 WO2020119299A1 (fr) 2018-12-14 2019-10-29 Procédé et dispositif de fusion de modèle

Country Status (3)

Country Link
CN (1) CN109903165B (fr)
TW (1) TWI718690B (fr)
WO (1) WO2020119299A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109903165B (zh) * 2018-12-14 2020-10-16 阿里巴巴集团控股有限公司 一种模型合并方法和装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140025354A1 (en) * 2012-07-20 2014-01-23 Tata Consultancy Services Limited Method and system for adaptive forecast of wind resources
CN105809264A (zh) * 2014-12-29 2016-07-27 西门子公司 电力负载预测方法和装置
CN106845638A (zh) * 2016-12-26 2017-06-13 大唐软件技术股份有限公司 一种数据预测方法及装置
CN107590569A (zh) * 2017-09-25 2018-01-16 山东浪潮云服务信息科技有限公司 一种数据预测方法及装置
CN108596415A (zh) * 2017-12-15 2018-09-28 阿里巴巴集团控股有限公司 一种模型整合方法及装置
CN109903165A (zh) * 2018-12-14 2019-06-18 阿里巴巴集团控股有限公司 一种模型合并方法和装置

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106779271A (zh) * 2015-11-23 2017-05-31 阿里巴巴集团控股有限公司 确定风险特征的方法及装置和账户风险评分方法及装置
CN108428188A (zh) * 2018-01-24 2018-08-21 顺丰科技有限公司 理赔风险预测方法、系统、设备及存储介质
CN108364106A (zh) * 2018-02-27 2018-08-03 平安科技（深圳）有限公司 一种报销单风险预测方法、装置、终端设备及存储介质
CN108960561A (zh) * 2018-05-04 2018-12-07 阿里巴巴集团控股有限公司 一种基于不平衡数据的风控模型处理方法、装置及设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140025354A1 (en) * 2012-07-20 2014-01-23 Tata Consultancy Services Limited Method and system for adaptive forecast of wind resources
CN105809264A (zh) * 2014-12-29 2016-07-27 西门子公司 电力负载预测方法和装置
CN106845638A (zh) * 2016-12-26 2017-06-13 大唐软件技术股份有限公司 一种数据预测方法及装置
CN107590569A (zh) * 2017-09-25 2018-01-16 山东浪潮云服务信息科技有限公司 一种数据预测方法及装置
CN108596415A (zh) * 2017-12-15 2018-09-28 阿里巴巴集团控股有限公司 一种模型整合方法及装置
CN109903165A (zh) * 2018-12-14 2019-06-18 阿里巴巴集团控股有限公司 一种模型合并方法和装置

Also Published As

Publication number Publication date
TWI718690B (zh) 2021-02-11
CN109903165A (zh) 2019-06-18
CN109903165B (zh) 2020-10-16
TW202032484A (zh) 2020-09-01

Similar Documents

Publication Publication Date Title
TWI679592B (zh) 風控規則生成方法和裝置
TWI709931B (zh) 一種指標異常檢測方法、裝置以及電子設備
TW201928841A (zh) 訓練風控模型和風控的方法、裝置及設備
TWI712913B (zh) 模型安全檢測方法、裝置以及電子設備
JP7048738B2 (ja) 仮想カード開設方法およびシステム、決済システム、ならびにカード発行システム
CN110245047B (zh) 时间序列异常检测方法、装置及设备
TW201935387A (zh) 反洗錢方法、裝置及設備
CN110119860B (zh) 一种垃圾账号检测方法、装置以及设备
WO2021120845A1 (fr) Procédé, appareil et dispositif de génération d'ensemble de caractéristiques d'unité de risque homogène, et support
TW201833851A (zh) 風控事件自動處理方法及裝置
TWI718379B (zh) 針對使用共享物品的使用者評估方法、裝置及設備
WO2020019892A1 (fr) Procédé et dispositif de tenue de comptes et système intégré de transaction et financier
CN109345221A (zh) 资源流转的核对方法及装置
WO2020155831A1 (fr) Procédé et appareil de génération d'étiquette de données, procédé et appareil d'entraînement de modèle, et procédé et appareil d'identification d'événement
WO2020155788A1 (fr) Procédé de détermination de données, appareil et dispositif, et support
WO2020119299A1 (fr) Procédé et dispositif de fusion de modèle
TWI705394B (zh) 針對風控指令的處理方法、裝置及設備
CN109145821B (zh) 一种对人眼图像中瞳孔图像进行定位的方法及装置
CN116861976A (zh) 一种异常检测模型的训练方法、装置、设备及存储介质
CN116151466A (zh) 一种企业风险预警模型的训练方法、装置、介质及设备
CN110263816A (zh) 一种企业的分类方法以及装置
TW201942835A (zh) 評價商戶的經營狀況的方法、裝置及設備
CN109598511B (zh) 一种账户风险识别方法、装置及设备
CN116204838A (zh) 一种异常业务识别的方法、装置、存储介质及电子设备
CN110458393B (zh) 一种风险识别方案的确定方法、装置及电子设备

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: 19894687

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19894687

Country of ref document: EP

Kind code of ref document: A1