CN113538154A - Risk object identification method and device, storage medium and electronic equipment - Google Patents
Risk object identification method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN113538154A CN113538154A CN202110839297.0A CN202110839297A CN113538154A CN 113538154 A CN113538154 A CN 113538154A CN 202110839297 A CN202110839297 A CN 202110839297A CN 113538154 A CN113538154 A CN 113538154A
- Authority
- CN
- China
- Prior art keywords
- index
- model
- risk
- evaluation
- target
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000003860 storage Methods 0.000 title claims abstract description 21
- 238000013210 evaluation model Methods 0.000 claims abstract description 153
- 238000012544 monitoring process Methods 0.000 claims abstract description 87
- 230000010354 integration Effects 0.000 claims abstract description 27
- 238000003066 decision tree Methods 0.000 claims description 68
- 238000012546 transfer Methods 0.000 claims description 40
- 238000011156 evaluation Methods 0.000 claims description 19
- 230000006399 behavior Effects 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 14
- 238000010276 construction Methods 0.000 claims description 8
- 238000009826 distribution Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 2
- 238000012502 risk assessment Methods 0.000 abstract 1
- 230000008569 process Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 9
- 230000008520 organization Effects 0.000 description 5
- 238000004140 cleaning Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013480 data collection Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012911 target assessment Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000002904 solvent Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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
- G06Q40/06—Asset management; Financial planning or analysis
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Accounting & Taxation (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure relates to the technical field of computers, and in particular relates to a risk object identification method and device, a storage medium and an electronic device. The method comprises the following steps: dividing the collected transaction data into a plurality of index dimensions, and setting monitoring indexes in the index dimensions; establishing a sub-evaluation model corresponding to each index dimension according to the monitoring index in each index dimension; integrating the obtained multiple sub-evaluation models according to a preset integration rule to obtain a target evaluation model; and identifying target risk objects from the risk objects to be evaluated based on the target evaluation model. The method takes transaction data as a data source, describes multi-dimensional monitoring indexes and corresponding risk assessment models, and has the characteristics of wide data source and high quality; the integrated model obtained by integrating the sub-evaluation models established based on the index dimensions is used for identifying the risk object, and has high identification accuracy and high reusability.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for identifying a risk object, a computer storage medium, and an electronic device.
Background
In many scenarios, the existence of the risk object has an influence on the production and life of people, for example, illegal funding behavior brings a great threat to the property safety of people. Therefore, it is an inelegant problem to be able to timely discriminate a risk target while preventing occurrence of a risk behavior.
In the related art, risk prediction is performed by a supervised machine learning model, and the method is characterized in that the method is a basic composition unit of the model, so that a large amount of label data is required to be possessed, namely, which accounts are known in advance as risk objects, and the risk behaviors of the risk objects can be acquired, while in an actual scene, a single organization is difficult to master a large amount of risk objects, even if a certain amount of risk objects are screened out in the system of the individual organization, the model constructed only aiming at a small amount of samples is difficult to popularize to other organizations, and the universality of the model is difficult to realize; in addition, the data disclosed through the network often has the problems of low accuracy, low timeliness, data clutter and the like, and the accuracy of recognition of the recognition model trained on the data is necessarily influenced.
It is to be noted that the information invented in the background section above is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
The purpose of the present disclosure is to provide a method and an apparatus for identifying a risk object, a computer storage medium, and an electronic device, so as to improve the identification accuracy and reusability of a risk object identification model at least to a certain extent.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.
According to an aspect of the present disclosure, there is provided a method for identifying a risk object, including: dividing the collected transaction data into a plurality of index dimensions, and setting monitoring indexes in the index dimensions; establishing a sub-evaluation model corresponding to each index dimension according to the monitoring index in each index dimension; integrating the obtained multiple sub-evaluation models according to a preset integration rule to obtain a target evaluation model; and identifying target risk objects from the risk objects to be identified based on the target evaluation model.
In an exemplary embodiment of the present disclosure, the establishing, according to a monitoring index in each index dimension, a sub-evaluation model corresponding to each index dimension includes:
according to a preset construction rule, constructing a structure of the sub-evaluation model corresponding to each index dimension;
and setting the parameter values of the corresponding sub-evaluation model structures according to the monitoring indexes in the index dimensions to obtain the sub-evaluation models corresponding to the index dimensions.
In an exemplary embodiment of the present disclosure, the sub-evaluation model is a decision tree model, and the establishing the sub-evaluation model corresponding to each index dimension according to the monitoring index in each index dimension includes: determining the depth, the node number and the node hierarchical relation of a corresponding decision tree model according to the attribute of each index dimension and the monitoring index number in each index dimension, wherein the monitoring index in each index dimension is used as a node of the corresponding decision tree model; setting node risk probability of each decision tree model; and determining a corresponding node threshold according to the quantile distribution of each monitoring index.
In an exemplary embodiment of the present disclosure, the number of the target evaluation models is plural;
the integrating the obtained multiple sub-evaluation models according to a preset integration rule to obtain a target evaluation model comprises the following steps: determining the number of the target evaluation models according to the attributes of the index dimensions, wherein the number of the target evaluation models is less than the number of the sub-evaluation models; and carrying out grouping integration processing on the sub-evaluation models to obtain the target evaluation models with the number.
In an exemplary embodiment of the present disclosure, the identifying a target risk object from risk objects to be identified based on the target evaluation model includes:
respectively inputting monitoring indexes corresponding to any risk object to be identified into each target evaluation model, and outputting a plurality of evaluation scores; obtaining a highest evaluation score of the plurality of evaluation scores as a risk score; and comparing the risk score with a risk threshold, and determining the risk object to be identified corresponding to the risk score larger than the risk threshold as the target risk object.
In an exemplary embodiment of the present disclosure, the inputting the monitoring index corresponding to any risk object to be identified into each target evaluation model, and outputting a plurality of evaluation scores includes: and the evaluation score output by any target evaluation model is the average value of the output scores of the sub-evaluation models corresponding to any target evaluation model.
In an exemplary embodiment of the present disclosure, the index dimension includes a transfer duty ratio of a private account to a transaction, a return of a preset dedicated resource, a distributed transfer to a centralized transfer out resource, a centralized transfer to a distributed transfer out resource, and corresponds to the first decision tree model, the second decision tree model, the third decision tree model, the fourth decision tree model, and the fifth decision tree model, respectively; the enterprise account corresponding to the first target evaluation model in the target evaluation models serves as a risk behavior collection account, the enterprise account corresponding to the second target evaluation model serves as a risk behavior refund account, and the enterprise account corresponding to the third target evaluation model serves as a risk behavior collection and refund account.
In an exemplary embodiment of the present disclosure, the integrating, according to a preset integration rule, the obtained multiple sub-evaluation models to obtain a target evaluation model includes: combining the first decision tree model and a fourth decision tree model to obtain the first target evaluation model; combining the second decision tree model with a fifth decision tree model to obtain the second target evaluation model; taking the third decision tree model as the third target evaluation model.
In an exemplary embodiment of the disclosure, before dividing the collected transaction data into a plurality of index dimensions and setting a monitoring index in the plurality of index dimensions, the method further comprises: transaction data is collected from a transaction institution and is cleaned.
According to an aspect of the present disclosure, there is provided a system for identifying a risk object, the system comprising: the index setting module is used for dividing the collected transaction data into a plurality of index dimensions and setting monitoring indexes in the index dimensions; the model establishing module is used for establishing a sub-evaluation model corresponding to each index dimension according to the monitoring index in each index dimension; the model integration module is used for integrating the obtained multiple sub-evaluation models according to a preset integration rule to obtain a target evaluation model; and the object identification module is used for identifying the target risk object from the risk objects to be identified based on the target evaluation model.
According to an aspect of the present disclosure, there is provided a computer storage medium having stored thereon a computer program which, when executed by a processor, implements a method of identifying a risk object as in any of the above.
According to an aspect of the present disclosure, there is provided an electronic device including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the method of risk object identification of any of the above via execution of the executable instructions.
In the identification method of the risk object in the exemplary embodiment of the disclosure, monitoring indexes of multiple dimensions are set based on transaction data, and sub-evaluation models corresponding to the dimensions of the indexes are established, so that the multiple sub-evaluation models are integrated and processed into a target evaluation model, and the target evaluation model is utilized to identify the risk object. On one hand, the collected transaction data is used as a data source to depict multi-dimensional monitoring indexes, and the transaction data can be directly obtained from related transaction institutions and has the characteristics of wide source, timeliness and high quality; meanwhile, the collected transaction data is used as sample data for constructing the model, and known risk objects are not used as the sample data, so that the objects do not need to be known as risk objects, and modeling can be realized under the condition that enough risk objects are not used as samples; on the other hand, sub-evaluation models corresponding to different index dimensions are integrated into a target evaluation model, so that the accuracy of risk object identification is high; on the other hand, the division of the index dimension, the determination of the monitoring index under the index dimension and the setting of the model parameters in the process of constructing the model can be combined with the manual actual business experience to adjust the corresponding parameters, so that the constructed model has more business interpretability.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present disclosure will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the present disclosure are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
FIG. 1 shows a flow chart of a method of risk object identification according to an exemplary embodiment of the present disclosure;
FIG. 2 illustrates a sub-assessment model building flow diagram according to an exemplary embodiment of the present disclosure;
FIG. 3 shows a sub-assessment model (decision tree model) modeling diagram according to an example embodiment of the present disclosure;
FIG. 4 illustrates a model integration flow diagram in accordance with an exemplary embodiment of the present disclosure;
FIG. 5 illustrates a flow diagram for identifying a target risk object based on a target assessment model according to an exemplary embodiment of the present disclosure;
FIG. 6 shows a schematic structural diagram of a risk object identification system according to an exemplary embodiment of the present disclosure;
FIG. 7 shows a schematic diagram of a storage medium according to an exemplary embodiment of the present disclosure; and
fig. 8 shows a block diagram of an electronic device according to an exemplary embodiment of the present disclosure.
In the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
Detailed Description
Exemplary embodiments will now be described more fully with reference to the accompanying drawings. The exemplary embodiments, however, may be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and thus their detailed description will be omitted.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known structures, methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the disclosure.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in the form of software, or in one or more software-hardened modules, or in different networks and/or processor devices and/or microcontroller devices.
In the related technology in the field, risk objects are predicted and identified through a supervised machine learning model, and the characteristics are basic constituent units of the model, so that a large amount of label data is needed, namely, which accounts are known to be risk objects, and meanwhile, recent transaction flow of the accounts is obtained, so that model training can be performed in a targeted manner based on the fact, and the risk objects are identified. In a related technology, a multi-dimensional portrait of a risk object is depicted based on data disclosed by a network, the similarity between the risk object to be identified and the depicted multi-dimensional portrait is calculated, and a target risk object is identified according to the similarity.
Accordingly, the identification method of the risk object in the related art has the following defects: on one hand, in an actual scene, a single organization (such as a bank) is difficult to master a large number of risk objects (such as illegal funding enterprise accounts), even if a certain amount of risk objects are screened by a certain organization in the system of the individual organization, a model constructed only aiming at a small amount of samples is difficult to popularize to other organizations, and the universality of the model is difficult to realize; on the other hand, the network public data has low accuracy, low timeliness and disordered data, and the accuracy and timeliness of the obtained multi-dimensional image are difficult to ensure by processing the data based on the data to depict the risk object, so that the identification rate of the risk object is low.
As one example of identifying risk objects, preventing illegal funding behavior requires many organizations (such as banks, securities companies, insurance companies, trust companies, fund management companies, etc.) to accurately identify illegal funding enterprises in time so as to prevent property security of the people from being threatened.
Based on this, in the exemplary embodiment of the present disclosure, a method for identifying a risk object is first provided. Referring to fig. 1, the method for identifying a risk object includes the following steps:
step S110: dividing the collected transaction data into a plurality of index dimensions, and setting monitoring indexes in the index dimensions;
step S120: establishing a sub-evaluation model corresponding to each index dimension according to the monitoring index in each index dimension;
step S130: integrating the obtained multiple sub-evaluation models according to a preset integration rule to obtain a target evaluation model;
step S140: and identifying target risk objects from the identification objects to be evaluated based on the target evaluation model.
According to the identification method of the risk object in the embodiment, on one hand, collected transaction data are used as a data source to depict multi-dimensional monitoring indexes, the transaction data can be directly obtained from related transaction institutions, and the identification method has the characteristics of wide source, timeliness and high quality; meanwhile, the collected transaction data is used as sample data for constructing the model, and known risk objects are not used as the sample data, so that the objects do not need to be known as risk objects, and modeling can be realized under the condition that enough risk objects are not used as samples; on the other hand, sub-evaluation models corresponding to different index dimensions are integrated into a target evaluation model, so that the accuracy of risk object identification can be improved; on the other hand, the division of the index dimension, the determination of the monitoring index under the index dimension and the parameter setting of the model in the process of constructing the model can be combined with the manual actual business experience to adjust the corresponding parameters, so that the constructed model has more business interpretability.
The method for identifying a risk object in the exemplary embodiment of the present disclosure is described below with reference to fig. 1.
In step S110, the collected transaction data is divided into a plurality of index dimensions, and a monitoring index in the plurality of index dimensions is set.
In an exemplary embodiment of the disclosure, the index dimension is obtained by dividing transaction data, is determined according to the attribute of an enterprise account, and is used for characterizing the dimension of the account, taking the identification of an illegal funding account as an example, the index dimension includes five dimensions of transfer-in transaction duty ratio of a private account, transfer-out transaction duty ratio of the private account, reproduction of preset exclusive resources, decentralized transfer-in centralized transfer-out resources, and centralized transfer-in decentralized transfer-out resources; the monitoring indexes refer to index objects used for describing the transaction data of each dimension, the number of the monitoring indexes can be determined according to the actual condition of risk objects to be identified, for example, the number of the monitoring indexes can be 5, 8, 10, 15, and the like, and the number of the monitoring indexes in each dimension is not particularly limited in the disclosure. For example, eight monitoring indexes can be set under the index dimension "private account transfer transaction ratio", which is the ratio of the past X time of the account to the number of the private transfer accounts, the past X time of the account to the amount of the private transfer accounts, the past X time of the enterprise to the amount of the private transfer accounts per transaction, the past X time of the enterprise to the amount of the private transfer pens per transaction, the past X time of the account to the number of the private transfer accounts, the past X time of the account to the amount of the private transfer accounts per transaction, and the past X time of the account to the amount of the private transfer accounts per transaction.
It should be noted that the number of monitoring indexes included in each index dimension may be the same or different, and may be adjusted according to actual needs, which is not limited in this disclosure.
In exemplary embodiments of the present disclosure, transaction data may also be collected from a transaction facility, for example, collecting transaction flows (including account posting transactions and account posting transactions) for an enterprise account from a bank, before dividing the collected transaction data into a plurality of index dimensions and setting a monitoring index in the plurality of index dimensions; and, data cleaning is carried out on the collected transaction data. The duration and frequency of collecting the transaction data can be set according to actual conditions, for example, within the last year, the collection period is every day, and the disclosure includes, but is not limited to, the duration and frequency of collecting the transaction data; the data cleaning is a process of rechecking and checking data, aims to delete repeated information, correct existing errors and provide data consistency, ensures that key fields of the cleaned transaction data do not contain abnormal values, missing values and repeated values which should not appear through data cleaning, and sets monitoring data in multiple index dimensions based on the cleaned transaction data to obtain images of the account in each index dimension.
In step S120, a sub-evaluation model corresponding to each index dimension is established according to the monitoring index in each index dimension.
In an exemplary embodiment of the present disclosure, the structure and parameter values of the sub-evaluation model are constructed according to the monitoring indexes in each index dimension, wherein the sub-evaluation model corresponds to the index dimension one to one. Specifically, fig. 2 shows a flow chart of sub-evaluation model establishment according to an exemplary embodiment of the present disclosure, and as shown in fig. 2, the process of the sub-evaluation model includes the following steps:
step S210, constructing the structure of the sub-evaluation model corresponding to each index dimension according to a preset construction rule;
in an exemplary embodiment of the present disclosure, a sub-evaluation model corresponding to an index dimension may be constructed according to the attribute and the number of monitoring indexes in the index dimension. Optionally, in a preset structure of a plurality of sub-evaluation models, the available sub-evaluation model structures of the current index dimension can be directly called according to the attribute and the number of the monitoring index; optionally, the sub-evaluation model corresponding to the current index dimension may be generated in response to a model building operation (e.g., a selection operation or an input operation) of an operation user.
Step S220, setting the parameter values of the corresponding sub-evaluation model structures according to the monitoring indexes in the index dimensions to obtain the sub-evaluation models corresponding to the index dimensions.
In an exemplary embodiment of the present disclosure, parameter values of corresponding sub-evaluation models are set according to monitoring indexes in each index dimension; taking a sub-evaluation model as a decision tree model as an example, the depth, the number of nodes and the node hierarchical relationship of the decision tree model can be determined according to the attributes and the number of monitoring indexes in each index dimension; the monitoring indexes in the index dimensionality can be used as nodes corresponding to the decision tree model, the node risk probability of the decision tree model is set, and finally the node threshold values in the decision tree model are calculated according to the monitoring indexes, so that a complete decision tree model is obtained.
The process of constructing a sub-evaluation model (taking a decision tree model as an example) is described in detail below, taking the identification of illegal funding enterprises as an example. Fig. 3 shows a modeling schematic diagram of a sub-evaluation model (decision tree model) according to an exemplary embodiment of the present disclosure, as shown in fig. 3, taking the above example that eight monitoring indexes can be set under the index dimension "account to account transfer to trade ratio", the eight monitoring indexes are account X time in the past versus account number to account to transfer to private, account X time in the past versus account number to transaction number to account to transfer to private, enterprise X time in the past versus account number to account to average transaction amount, enterprise X time in the past versus pen to average transaction amount, account X time in the past versus account number to account to transfer to private, account X time in the past versus account number to account to transaction number ratio, and account X time in the past versus account number to account to transaction amount to transfer to account to trade ratio.
Firstly, when a decision tree model is constructed, according to the attribute of the index dimension of 'account-private transfer-transaction duty' and the monitoring index number in the index dimension of eight, determining the depth and the node number of the decision tree, such as a decision tree structure shown in fig. 3;
secondly, determining the hierarchical relationship of each node (monitoring index) according to the discrimination of each monitoring index, for example, selecting the monitoring index from the root node of the decision tree, taking the account with the most discrimination, such as the number of accounts in the past X time, as the root node, and then selecting the monitoring index as a leaf node according to the discrimination of the monitoring index in sequence until the monitoring index in the index dimension is completely selected, so as to obtain a complete decision tree model structure;
next, node risk probabilities in the decision tree model structure are set according to the monitoring indexes in the index dimension, wherein the node risk probabilities may be automatically set according to a preset node risk probability rule, or may be set in response to a selection or input operation of a user, such as P being 0.05, P being 0.1, and so on, as shown in fig. 3. The setting principle of the node risk probability of the child node may be smooth increase, and the node risk probability of the decision tree model which goes down is larger, as shown in fig. 3, of course, the corresponding node risk probability may also be set according to actual requirements, which is not particularly limited by the present disclosure;
and finally, determining the corresponding node threshold according to the quantiles of the monitoring indexes, for example, calculating the quantile distribution of each monitoring index, and taking 90% quantile as the node threshold of the corresponding monitoring index. The quantile is a numerical point which divides the probability distribution range of a random variable into several equal parts, and the scheme can use 90% quantile of each monitoring index as a node threshold.
In the process of constructing the decision tree model, the arrangement of the nodes and the setting of the parameter values in the preset construction rule from the determination of the monitoring indexes under each index dimension are determined based on the actually acquired transaction data, the attributes of the enterprise accounts and the actual business requirements, and the corresponding parameters can be adjusted by combining with the artificial actual business experience in the process, so that the obtained identification result of the decision tree model is more accurate and has more business interpretability.
Step S130: and according to a preset integration rule, carrying out integration processing on the obtained multiple sub-evaluation models to obtain a target evaluation model.
In an exemplary embodiment of the present disclosure, the number of target evaluation models is plural, and the number of target evaluation models is less than the number of sub-evaluation models. Fig. 4 shows a model integration flow chart according to an exemplary embodiment of the present disclosure, such as fig. 4, the process comprising the steps of:
step S410: determining the number of target evaluation models according to the attributes of the index dimensions;
in an exemplary embodiment of the present disclosure, it may be determined which sub-evaluation models may be combined according to the attribute of the index dimension, so as to determine the number of the obtained target evaluation models.
For example, taking illegal funding enterprise identification as an example, five index dimensions of "transfer transaction duty to private account, return of preset dedicated resources, distributed transfer to centralized transfer-out resources, centralized transfer to decentralized transfer-out resources" correspond to the first decision tree model, the second decision tree model, the third decision tree model, the fourth decision tree model and the fifth decision tree model respectively, because the combination of the monitoring index 'account ratio of private account transfer in transaction' and the monitoring index 'decentralized transfer in centralized transfer out resource' can reflect the risk of 'the business account as the collection account of illegal collection', therefore, the decision tree model 1 corresponding to the monitoring index 'account to private account transfer to transaction ratio' and the decision tree model 4 corresponding to the monitoring index 'decentralized transfer to centralized transfer out of resource' are combined, so that the obtained first evaluation model is more service explanatory. By analogy, the combination of the monitoring index 'private account transfer transaction occupation ratio' and the monitoring index 'centralized transfer to distributed transfer resources' can reflect the risk of 'an enterprise account being used as a refund account of illegal collection', so that the decision tree model 2 and the decision tree model 5 are combined to obtain a second target evaluation model, the monitoring index 'preset return of the private resources' reflects the risk of 'the enterprise account being used as a risk behavior collection account and a refund account', the decision tree model 3 is used as a third target evaluation model, and the 5 sub evaluation models are integrated into 3 target evaluation models.
The risk of each combined index (such as 'an industry account is used as a collection account for illegal collection') can be reflected more accurately through the target evaluation model obtained by integrating and processing the sub-evaluation models, and the accuracy of identifying the risk object of the target evaluation model is improved.
Step S420: the sub-evaluation models are subjected to a grouping integration process to obtain target evaluation models having the number determined in step S410.
In the exemplary embodiment of the present disclosure, according to the number of the target evaluation models determined in step S410, the sub-evaluation models are subjected to corresponding grouping and integration processing to obtain the target evaluation model. The evaluation score output by any target evaluation model is the mean value of the output scores of the sub-evaluation models corresponding to any target evaluation model, that is, the evaluation score output by the first target evaluation model integrated by the decision tree model 1 and the decision tree model 2 is the mean value of the output scores of the two decision tree models.
According to the scheme, based on sufficient transaction data as a data source, corresponding adjustment can be performed by combining manual actual business experience from division of index dimensions, determination of monitoring indexes under the index dimensions to parameter setting of the model in the process of building the model, and the risk identification accuracy of the model is improved.
Step S140: and identifying the target risk object from the risk objects to be identified based on the target evaluation model.
In an exemplary embodiment of the present disclosure, fig. 5 shows a flowchart for identifying a target risk object based on a target assessment model according to an exemplary embodiment of the present disclosure, such as fig. 5, the process comprising:
step S510, inputting the monitoring indexes corresponding to any risk object to be identified into each target evaluation model respectively, and outputting a plurality of evaluation scores; then obtaining the highest evaluation score in the plurality of evaluation scores as a risk score;
step S520, comparing the risk score with a risk threshold, and determining the risk object to be identified corresponding to the risk score larger than the risk threshold as a target risk object;
in an exemplary embodiment of the disclosure, the risk threshold may be set according to an actual situation of the risk object to be identified, and the present application is not particularly limited thereto.
Based on the data, the method and the system have the advantages that the collected transaction data are used as data sources, multi-dimensional monitoring indexes are depicted, the transaction data can be directly obtained from related transaction institutions, and the method and the system have the advantages of being wide in source, high in timeliness and quality; meanwhile, the collected transaction data is used as sample data for constructing the model, and known risk objects are not used as the sample data, so that the objects do not need to be known as risk objects, and modeling can be realized under the condition that enough risk objects are not used as samples; sub-evaluation models corresponding to different index dimensions are integrated into a target evaluation model, so that the accuracy of risk object identification can be improved; in addition, the division of the index dimension, the determination of the monitoring index under the index dimension and the parameter setting of the model in the process of constructing the model can be combined with the manual actual business experience to adjust the corresponding parameters, so that the constructed model has more business interpretability.
Furthermore, in an exemplary embodiment of the present disclosure, a risk object identification system is also provided. Referring to fig. 6, the risk object recognition system 600 may include an index setting module 610, a model building module 620, a model integration module 630, and an object recognition module 640. In particular, the amount of the solvent to be used,
the index setting module 610 is configured to divide the collected transaction data into a plurality of index dimensions, and set a monitoring index in the plurality of index dimensions;
the model establishing module 620 is configured to establish a sub-evaluation model corresponding to each index dimension according to the monitoring index in each index dimension;
the model integration module 630 is configured to perform integration processing on the obtained multiple sub-evaluation models according to a preset integration rule to obtain a target evaluation model;
and the object identification module 640 is used for identifying the target risk object from the risk objects to be identified based on the target evaluation model.
In an exemplary embodiment of the present disclosure, the model building module 620 may further include:
the model structure construction unit is used for constructing the structure of the sub-evaluation model corresponding to each index dimension according to a preset construction rule;
and the parameter setting unit is used for setting the parameter values of the corresponding sub-evaluation model structures according to the monitoring indexes in the index dimensionality to obtain the sub-evaluation models corresponding to the index dimensionality.
In an exemplary embodiment of the present disclosure, the model structure construction unit may include:
the decision tree structure construction unit is used for determining the depth, the node number and the node hierarchical relation of the corresponding decision tree model according to the attribute of each index dimension and the monitoring index number in each index dimension, wherein the monitoring index in each index dimension is used as the node of the corresponding decision tree model;
the node risk probability setting unit is used for setting the node risk probability of each decision tree model;
and the node threshold value determining unit is used for determining a corresponding node threshold value according to the quantile distribution of each monitoring index.
In an exemplary embodiment of the present disclosure, the number of the target evaluation models is plural; the model integration module 630 may further include:
the quantity determining unit is used for determining the quantity of the target evaluation models according to the attributes of the index dimensions, wherein the quantity of the target evaluation models is less than that of the sub evaluation models;
and the integration unit is used for carrying out grouping integration processing on the sub-evaluation models to obtain the target evaluation model with the number determined by the number determination unit.
In an exemplary embodiment of the present disclosure, the object recognition module 640 may further include:
the evaluation score determining unit is used for respectively inputting the monitoring indexes corresponding to any risk object to be identified into each target evaluation model and outputting a plurality of evaluation scores;
a risk score acquisition unit configured to acquire a highest evaluation score among the plurality of evaluation scores as a risk score;
and the data comparison unit is used for comparing the risk score with a risk threshold value and determining the risk object to be identified corresponding to the risk score larger than the risk threshold value as the target risk object.
In an exemplary embodiment of the present disclosure, the index dimension includes a transfer duty ratio of a private account to a transaction, a return of a preset dedicated resource, a distributed transfer to a centralized transfer out resource, a centralized transfer to a distributed transfer out resource, and corresponds to the first decision tree model, the second decision tree model, the third decision tree model, the fourth decision tree model, and the fifth decision tree model, respectively;
the enterprise account corresponding to the first target evaluation model serves as a risk behavior collection account, the enterprise account corresponding to the second target evaluation model serves as a risk behavior refund account, and the enterprise account corresponding to the third target evaluation model serves as a risk behavior collection and refund account.
In an exemplary embodiment of the present disclosure, the identification system of risk objects further comprises a data collection module for collecting transaction data from the transaction institution.
In an exemplary embodiment of the present disclosure, the identification system of the risk object further includes a data cleansing module for cleansing the transaction data collected by the data collection module.
Since each functional module of the risk object identification system in the exemplary embodiment of the present disclosure is the same as that in the embodiment of the present invention of the risk object identification method, it is not described herein again.
It should be noted that although in the above detailed description several modules or units of the identification system of risk objects are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.
In addition, in the exemplary embodiments of the present disclosure, a computer storage medium capable of implementing the above method is also provided. On which a program product capable of implementing the above-described method of the present specification is stored. In some possible embodiments, aspects of the present disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the present disclosure described in the "exemplary methods" section above of this specification, when the program product is run on the terminal device.
Referring to fig. 7, a program product 700 for implementing the above method according to an exemplary embodiment of the present disclosure is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided. As will be appreciated by one skilled in the art, aspects of the present disclosure may be embodied as a system, method or program product. Accordingly, various aspects of the present disclosure may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.
An electronic device 800 according to such an embodiment of the disclosure is described below with reference to fig. 8. The electronic device 800 shown in fig. 8 is only an example and should not bring any limitations to the functionality and scope of use of the embodiments of the present disclosure.
As shown in fig. 8, electronic device 800 is in the form of a general purpose computing device. The components of the electronic device 800 may include, but are not limited to: the at least one processing unit 810, the at least one memory unit 820, a bus 830 connecting different system components (including the memory unit 820 and the processing unit 810), and a display unit 840.
Wherein the storage unit stores program code that is executable by the processing unit 810 to cause the processing unit 810 to perform steps according to various exemplary embodiments of the present disclosure as described in the "exemplary methods" section above in this specification.
The storage unit 820 may include readable media in the form of volatile memory units such as a random access memory unit (RAM)8201 and/or a cache memory unit 8202, and may further include a read only memory unit (ROM) 8203.
The storage unit 820 may also include a program/utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The electronic device 800 may also communicate with one or more external devices 900 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 800, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 800 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 850. Also, the electronic device 800 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) via the network adapter 860. As shown, the network adapter 860 communicates with the other modules of the electronic device 800 via the bus 830. It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with the electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
Furthermore, the above-described figures are merely schematic illustrations of processes included in methods according to exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is to be limited only by the terms of the appended claims.
Claims (12)
1. A method for identifying a risk object, comprising:
dividing the collected transaction data into a plurality of index dimensions, and setting monitoring indexes in the index dimensions;
establishing a sub-evaluation model corresponding to each index dimension according to the monitoring index in each index dimension;
integrating the obtained multiple sub-evaluation models according to a preset integration rule to obtain a target evaluation model;
and identifying target risk objects from the risk objects to be identified based on the target evaluation model.
2. The identification method according to claim 1, wherein the establishing of the sub-evaluation model corresponding to each index dimension according to the monitoring index in each index dimension includes:
according to a preset construction rule, constructing a structure of the sub-evaluation model corresponding to each index dimension;
and setting the parameter values of the corresponding sub-evaluation model structures according to the monitoring indexes in the index dimensions to obtain the sub-evaluation models corresponding to the index dimensions.
3. The identification method according to claim 2, wherein the sub-evaluation model is a decision tree model, and the establishing of the sub-evaluation model corresponding to each index dimension according to the monitoring index in each index dimension includes:
determining the depth, the node number and the node hierarchical relation of a corresponding decision tree model according to the attribute of each index dimension and the monitoring index number in each index dimension, wherein the monitoring index in each index dimension is used as a node of the corresponding decision tree model;
setting node risk probability of each decision tree model;
and determining a corresponding node threshold according to the quantile distribution of each monitoring index.
4. The identification method according to claim 1, wherein the number of the target evaluation models is plural;
the integrating the obtained multiple sub-evaluation models according to a preset integration rule to obtain a target evaluation model comprises the following steps:
determining the number of the target evaluation models according to the attributes of the index dimensions, wherein the number of the target evaluation models is less than the number of the sub-evaluation models;
and carrying out grouping integration processing on the sub-evaluation models to obtain the target evaluation models with the number.
5. The identification method according to claim 4, wherein the identifying a target risk object from the risk objects to be identified based on the target evaluation model comprises:
respectively inputting monitoring indexes corresponding to any risk object to be identified into each target evaluation model, and outputting a plurality of evaluation scores;
obtaining a highest evaluation score of the plurality of evaluation scores as a risk score;
and comparing the risk score with a risk threshold, and determining the risk object to be identified corresponding to the risk score larger than the risk threshold as the target risk object.
6. The identification method according to claim 5, wherein the step of inputting the monitoring index corresponding to any risk object to be identified into each target evaluation model and outputting a plurality of evaluation scores comprises:
and the evaluation score output by any target evaluation model is the average value of the output scores of the sub-evaluation models corresponding to any target evaluation model.
7. The identification method according to claim 3, wherein the index dimension includes a transfer transaction duty ratio to a private account, a recurrence of a preset dedicated resource, a distributed transfer to a centralized transfer out resource, a centralized transfer to a decentralized transfer out resource, and corresponds to the first decision tree model, the second decision tree model, the third decision tree model, the fourth decision tree model, and the fifth decision tree model, respectively;
the enterprise account corresponding to the first target evaluation model in the target evaluation models serves as a risk behavior collection account, the enterprise account corresponding to the second target evaluation model serves as a risk behavior refund account, and the enterprise account corresponding to the third target evaluation model serves as a risk behavior collection and refund account.
8. The identification method according to claim 7, wherein the integrating the obtained plurality of sub-evaluation models according to a preset integration rule to obtain a target evaluation model comprises:
combining the first decision tree model and a fourth decision tree model to obtain the first target evaluation model;
combining the second decision tree model with a fifth decision tree model to obtain the second target evaluation model;
taking the third decision tree model as the third target evaluation model.
9. An identification method as claimed in any one of claims 1 to 8, wherein prior to dividing the collected transaction data into a plurality of target dimensions and setting a monitoring target in the plurality of target dimensions, the method further comprises:
transaction data is collected from a transaction institution and is cleaned.
10. A system for identifying a risk object, the system comprising:
the index setting module is used for dividing the collected transaction data into a plurality of index dimensions and setting monitoring indexes in the index dimensions;
the model establishing module is used for establishing a sub-evaluation model corresponding to each index dimension according to the monitoring index in each index dimension;
the model integration module is used for integrating the obtained multiple sub-evaluation models according to a preset integration rule to obtain a target evaluation model;
and the object identification module is used for identifying the target risk object from the risk objects to be identified based on the target evaluation model.
11. A storage medium having stored thereon a computer program which, when executed by a processor, implements a method of identifying a risk object according to any of claims 1 to 9.
12. An electronic device, comprising:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the method of risk object identification of any of claims 1 to 9 via execution of the executable instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110839297.0A CN113538154B (en) | 2021-07-23 | Risk object identification method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110839297.0A CN113538154B (en) | 2021-07-23 | Risk object identification method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113538154A true CN113538154A (en) | 2021-10-22 |
| CN113538154B CN113538154B (en) | 2024-07-05 |
Family
ID=
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114240097A (en) * | 2021-12-02 | 2022-03-25 | 支付宝(杭州)信息技术有限公司 | Risk assessment method and device |
| CN116187768A (en) * | 2023-04-26 | 2023-05-30 | 浙江电力交易中心有限公司 | Risk assessment and protection method suitable for green electricity market |
| CN117151716A (en) * | 2023-07-13 | 2023-12-01 | 杭州东骋科技有限公司 | Method for judging online fund transaction risk based on active inspection mode |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109829628A (en) * | 2019-01-07 | 2019-05-31 | 平安科技（深圳）有限公司 | Method for prewarning risk, device and computer equipment based on big data |
| CN110738565A (en) * | 2019-10-11 | 2020-01-31 | 中山市银鹿金科信息科技有限公司 | Real estate finance artificial intelligence composite wind control model based on data set |
| CN111191889A (en) * | 2019-12-17 | 2020-05-22 | 东方微银科技(北京)有限公司 | Scoring card development method based on logistic regression and voting type model integration |
| CN111950829A (en) * | 2019-05-17 | 2020-11-17 | 泰康保险集团股份有限公司 | Risk object positioning method and device, computer storage medium and electronic equipment |
| CN111967779A (en) * | 2020-08-19 | 2020-11-20 | 支付宝(杭州)信息技术有限公司 | Risk assessment method, device and equipment |
| WO2021012783A1 (en) * | 2019-07-23 | 2021-01-28 | 平安科技（深圳）有限公司 | Insurance policy underwriting model training method employing big data, and underwriting risk assessment method |
| CN112801187A (en) * | 2021-01-29 | 2021-05-14 | 广东省科学院智能制造研究所 | Hyperspectral data analysis method and system based on attention mechanism and ensemble learning |
| CN112801773A (en) * | 2021-01-20 | 2021-05-14 | 招商银行股份有限公司 | Enterprise risk early warning method, device, equipment and storage medium |
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109829628A (en) * | 2019-01-07 | 2019-05-31 | 平安科技（深圳）有限公司 | Method for prewarning risk, device and computer equipment based on big data |
| CN111950829A (en) * | 2019-05-17 | 2020-11-17 | 泰康保险集团股份有限公司 | Risk object positioning method and device, computer storage medium and electronic equipment |
| WO2021012783A1 (en) * | 2019-07-23 | 2021-01-28 | 平安科技（深圳）有限公司 | Insurance policy underwriting model training method employing big data, and underwriting risk assessment method |
| CN110738565A (en) * | 2019-10-11 | 2020-01-31 | 中山市银鹿金科信息科技有限公司 | Real estate finance artificial intelligence composite wind control model based on data set |
| CN111191889A (en) * | 2019-12-17 | 2020-05-22 | 东方微银科技(北京)有限公司 | Scoring card development method based on logistic regression and voting type model integration |
| CN111967779A (en) * | 2020-08-19 | 2020-11-20 | 支付宝(杭州)信息技术有限公司 | Risk assessment method, device and equipment |
| CN112801773A (en) * | 2021-01-20 | 2021-05-14 | 招商银行股份有限公司 | Enterprise risk early warning method, device, equipment and storage medium |
| CN112801187A (en) * | 2021-01-29 | 2021-05-14 | 广东省科学院智能制造研究所 | Hyperspectral data analysis method and system based on attention mechanism and ensemble learning |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114240097A (en) * | 2021-12-02 | 2022-03-25 | 支付宝(杭州)信息技术有限公司 | Risk assessment method and device |
| CN116187768A (en) * | 2023-04-26 | 2023-05-30 | 浙江电力交易中心有限公司 | Risk assessment and protection method suitable for green electricity market |
| CN117151716A (en) * | 2023-07-13 | 2023-12-01 | 杭州东骋科技有限公司 | Method for judging online fund transaction risk based on active inspection mode |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020249125A1 (en) | Method and system for automatically training machine learning model | |
| US20190347282A1 (en) | Technology incident management platform | |
| US20200192894A1 (en) | System and method for using data incident based modeling and prediction | |
| US9324038B2 (en) | Method and system for clustering, modeling, and visualizing process models from noisy logs | |
| CN111401777B (en) | Enterprise risk assessment method, enterprise risk assessment device, terminal equipment and storage medium | |
| CN106164896B (en) | Multi-dimensional recursion method and system for discovering counterparty relationship | |
| US20230419402A1 (en) | Systems and methods of optimizing machine learning models for automated anomaly detection | |
| US9524475B1 (en) | Presenting discriminant change history records on topology graphs | |
| CN104063450A (en) | Hot spot information analyzing method and equipment | |
| CN113177700B (en) | Risk assessment method, system, electronic equipment and storage medium | |
| US20230004979A1 (en) | Abnormal behavior detection method and apparatus, electronic device, and computer-readable storage medium | |
| CN111062600B (en) | Model evaluation method, system, electronic device, and computer-readable storage medium | |
| CN112631889A (en) | Portrayal method, device and equipment for application system and readable storage medium | |
| US11688012B2 (en) | Asset assessment via graphical encoding of liability | |
| WO2022271431A1 (en) | System and method that rank businesses in environmental, social and governance (esg) | |
| CN113538154B (en) | Risk object identification method and device, storage medium and electronic equipment | |
| CN113538154A (en) | Risk object identification method and device, storage medium and electronic equipment | |
| CN114493853A (en) | Credit rating evaluation method, credit rating evaluation device, electronic device and storage medium | |
| GB2602382A (en) | Relationship discovery and quantification | |
| Zang | Construction of Mobile Internet Financial Risk Cautioning Framework Based on BP Neural Network | |
| CN112380321A (en) | Primary and secondary database distribution method based on bill knowledge graph and related equipment | |
| CN112712270A (en) | Information processing method, device, equipment and storage medium | |
| US11971913B2 (en) | Auto-generation of support trees | |
| Wong et al. | An Efficient Risk Data Learning with LSTM RNN | |
| Fröhlich | Outlier identification and adjustment for time series |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |