CN112801773A - Enterprise risk early warning method, device, equipment and storage medium - Google Patents
Enterprise risk early warning method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112801773A CN112801773A CN202110080220.XA CN202110080220A CN112801773A CN 112801773 A CN112801773 A CN 112801773A CN 202110080220 A CN202110080220 A CN 202110080220A CN 112801773 A CN112801773 A CN 112801773A
- Authority
- CN
- China
- Prior art keywords
- transaction
- risk
- enterprise
- target
- risk detection
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000001514 detection method Methods 0.000 claims abstract description 159
- 230000002159 abnormal effect Effects 0.000 claims abstract description 74
- 238000012549 training Methods 0.000 claims description 64
- 239000013598 vector Substances 0.000 claims description 61
- 238000003066 decision tree Methods 0.000 claims description 42
- 238000012216 screening Methods 0.000 claims description 15
- 238000010276 construction Methods 0.000 claims description 14
- 238000007781 pre-processing Methods 0.000 claims description 8
- 239000013604 expression vector Substances 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 5
- 230000009467 reduction Effects 0.000 claims description 5
- 238000012502 risk assessment Methods 0.000 abstract description 15
- 230000008569 process Effects 0.000 description 13
- 238000004891 communication Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 230000009466 transformation Effects 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
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application discloses an enterprise risk early warning method, an enterprise risk early warning device, enterprise risk early warning equipment and a storage medium, wherein the method comprises the following steps: acquiring transaction flow information corresponding to a target enterprise, and constructing transaction characteristic data corresponding to the transaction flow information; performing risk detection on the target enterprise based on the transaction characteristic data and a preset abnormal repayment and information source identification model to obtain a first risk detection result; and obtaining a target risk result of the target enterprise based on the first risk detection result. In the application, the borrowing transaction of the target enterprise and the small loan company and the abnormal repayment and repayment source of the enterprise can be identified through the preset abnormal repayment and repayment source identification model, so that the coverage range of transaction data early warning is enlarged, and the accuracy of risk assessment is improved.
Description
Technical Field
The application relates to the technical field of artificial intelligence of financial technology (Fintech), in particular to an enterprise risk early warning method, device, equipment and storage medium.
Background
With the continuous development of financial science, especially internet science and technology finance, more and more technologies (such as distributed, block chain Blockchain, artificial intelligence and the like) are applied to the financial field, but the financial industry also puts higher requirements on the technologies, and for example, the financial industry also has higher requirements on enterprise risk early warning.
Currently, a bank generally needs to perform risk assessment on each enterprise, specifically, the bank generally performs risk assessment on the enterprise through bank transaction running data to ensure whether the enterprise is borrowed and credited to a corresponding enterprise, and currently, aiming at the bank transaction running data, the bank transaction running data mainly focuses on analyzing whether abnormal phenomena such as fraud and the like are involved in transactions, so that abnormal transactions are intercepted in time, and only abnormal transactions are intercepted, so that bank risk assessment is inaccurate, if a small loan company has a high interest rate, the risk control capability is poor, and companies repayment banks after borrowing from the small loan company by the enterprise often cannot be identified accurately.
Disclosure of Invention
The application mainly aims to provide an enterprise risk early warning method, device, equipment and storage medium, and aims to solve the technical problem that in the process of risk assessment of an enterprise by an existing bank, the risk assessment accuracy is low.
In order to achieve the above object, the present application provides an enterprise risk early warning method, including:
acquiring transaction flow information corresponding to a target enterprise, and constructing transaction characteristic data corresponding to the transaction flow information;
performing risk detection on the target enterprise based on the transaction characteristic data and a preset abnormal repayment and information source identification model to obtain a first risk detection result;
and obtaining a target risk result of the target enterprise based on the first risk detection result.
Optionally, the step of obtaining a target risk result of the target enterprise based on the first risk detection result includes:
inputting the transaction characteristic data into the abnormal transaction identification model so as to perform abnormal transaction detection on the target enterprise based on the transaction characteristic data and obtain a second risk detection result;
and acquiring weight information corresponding to the first risk detection result and the second risk detection result, and generating a target risk result of the target enterprise based on the weight information, the first risk detection result and the second risk detection result.
Optionally, before the step of performing risk detection on the target enterprise based on the transaction characteristic data and a preset abnormal repayment and reimbursement source identification model to obtain a first risk detection result, the enterprise risk early warning method further includes:
acquiring a training data set, and constructing a training characteristic data set corresponding to the training data set;
constructing a decision tree model based on the training feature data set;
based on the decision tree model, carrying out feature screening on the training feature data set to obtain a target feature data set;
and constructing the preset abnormal repayment and interest reduction source identification model based on the target characteristic data set.
Optionally, the decision tree model comprises at least one decision tree,
the step of performing feature screening on the training feature data set based on the decision tree model to obtain a target feature data set includes:
determining each initial transaction flow characteristic corresponding to the training characteristic data set, and acquiring the number of non-leaf nodes corresponding to each initial transaction flow characteristic in each decision tree;
based on the number of the non-leaf nodes, performing feature importance ranking on the initial transaction flow features to obtain a feature importance ranking result;
selecting a preset number of target transaction flow characteristics from each initial transaction flow characteristic based on the characteristic importance sorting result;
and selecting feature data corresponding to the target transaction running features from the training feature data set as the target feature data set.
Optionally, the transaction flow information comprises transaction flow text, the transaction characteristic data comprises a transaction flow characteristic representation vector,
the step of constructing the transaction characteristic data corresponding to the transaction flow information includes:
extracting target characteristic values corresponding to a preset number of construction features from the transaction flow text, and combining the target characteristic values into construction characteristic vectors;
mapping the transaction flow text to a preset data dimension space to obtain a text low-dimension space expression vector;
and splicing the constructed feature vector and the text low-dimensional space representation vector to obtain the transaction flow feature representation vector.
The step of carrying out risk detection on the target enterprise based on the transaction characteristic data and a preset abnormal repayment and interest source identification model to obtain a first risk detection result comprises the following steps:
performing risk detection on the target enterprise based on the transaction characteristic data and a first sub-identification model in a preset abnormal repayment and information source identification model to obtain a first risk detection sub-result;
performing risk detection on the target enterprise based on the transaction characteristic data and a second sub-identification model in a preset abnormal repayment and information source identification model to obtain a second risk detection sub-result;
performing risk detection on the target enterprise based on the transaction characteristic data and a third sub-identification model in a preset abnormal repayment and information source identification model to obtain a third risk detection sub-result;
the basic models for training the first sub-recognition model, the second sub-recognition model and the third sub-recognition model are different;
and fusing the first risk detection sub-result, the second risk detection sub-result and the third risk detection sub-result to obtain a first risk detection result.
Optionally, the step of obtaining transaction flow information corresponding to the target enterprise includes:
acquiring original transaction data corresponding to a target enterprise;
carrying out duplicate removal and missing data cleaning treatment on the original transaction data to obtain preprocessed data;
and setting the preprocessing data as the transaction flow information corresponding to the target enterprise.
The application also provides an enterprise risk early warning device, enterprise risk early warning device includes:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring transaction flow information corresponding to a target enterprise and constructing transaction characteristic data corresponding to the transaction flow information;
the risk detection module is used for carrying out risk detection on the target enterprise based on the transaction characteristic data and a preset abnormal repayment and receipt source identification model to obtain a first risk detection result;
and the second acquisition module is used for acquiring a target risk result of the target enterprise based on the first risk detection result.
Optionally, the second obtaining module includes:
the input unit is used for inputting the transaction characteristic data into the abnormal transaction identification model so as to detect abnormal transactions of the target enterprise based on the transaction characteristic data and obtain a second risk detection result;
a first obtaining unit, configured to obtain weight information corresponding to the first risk detection result and the second risk detection result, and generate a target risk result of the target enterprise based on the weight information, the first risk detection result, and the second risk detection result.
Optionally, the apparatus further comprises:
the third acquisition module is used for acquiring a training data set and constructing a training characteristic data set corresponding to the training data set;
a first construction module for constructing a decision tree model based on the training feature data set;
the characteristic screening module is used for carrying out characteristic screening on the training characteristic data set based on the decision tree model to obtain a target characteristic data set;
and the second construction module is used for constructing the preset abnormal repayment and interest reduction source identification model based on the target characteristic data set.
Optionally, the decision tree model comprises at least one decision tree,
the feature screening module includes:
a first determining unit, configured to determine each initial transaction flow characteristic corresponding to the training characteristic data set, and obtain a corresponding number of non-leaf nodes of each initial transaction flow characteristic in each decision tree;
the sorting unit is used for sorting the feature importance of each initial transaction flow characteristic based on the number of the non-leaf nodes to obtain a feature importance sorting result;
the first selection unit is used for selecting a preset number of target transaction flow characteristics from each initial transaction flow characteristic based on the characteristic importance ranking result;
and the second selection unit is used for selecting the feature data corresponding to the target transaction running features from the training feature data set as the target feature data set.
Optionally, the transaction flow information comprises transaction flow text, the transaction characteristic data comprises a transaction flow characteristic representation vector,
the first obtaining module comprises:
the extraction unit is used for extracting target characteristic values corresponding to a preset number of construction characteristics from the transaction flow text and combining the target characteristic values into construction characteristic vectors;
the second acquisition unit is used for mapping the transaction pipeline text to a preset data dimension space to obtain a text low-dimensional space representation vector;
and the third acquisition unit is used for splicing the constructed feature vector and the text low-dimensional space representation vector to acquire the transaction flow feature representation vector.
The risk detection module includes:
the first risk detection unit is used for carrying out risk detection on the target enterprise based on the transaction characteristic data and a first sub-identification model in a preset abnormal repayment and receipt source identification model to obtain a first risk detection sub-result;
the second risk detection unit is used for carrying out risk detection on the target enterprise based on the transaction characteristic data and a second sub-identification model in a preset abnormal repayment and receipt source identification model to obtain a second risk detection sub-result;
the third risk detection unit is used for carrying out risk detection on the target enterprise based on the transaction characteristic data and a third sub-identification model in a preset abnormal repayment and receipt source identification model to obtain a third risk detection sub-result;
the basic models for training the first sub-recognition model, the second sub-recognition model and the third sub-recognition model are different;
and the fusion unit is used for fusing the first risk detection sub-result, the second risk detection sub-result and the third risk detection sub-result to obtain a first risk detection result.
Optionally, the first obtaining module includes:
the fourth acquisition unit is used for acquiring original transaction data corresponding to the target enterprise;
the preprocessing unit is used for carrying out duplicate removal and missing data cleaning treatment on the original transaction data to obtain preprocessed data;
and the setting unit is used for setting the preprocessing data as the transaction flow information corresponding to the target enterprise.
The application also provides enterprise risk early warning equipment, enterprise risk early warning equipment is entity equipment, enterprise risk early warning equipment includes: the risk early warning system comprises a memory, a processor and a program of the enterprise risk early warning method, wherein the program of the enterprise risk early warning method can realize the steps of the enterprise risk early warning method when the program of the enterprise risk early warning method is executed by the processor.
The application also provides a storage medium, wherein a program for implementing the enterprise risk early warning method is stored in the storage medium, and the program for implementing the enterprise risk early warning method implements the steps of the enterprise risk early warning method when being executed by a processor.
The present application also provides a computer program product, comprising a computer program, which when executed by a processor, implements the steps of the enterprise risk pre-warning method described above.
Compared with the existing risk assessment process of an enterprise by a bank, which only focuses on analyzing whether the transaction relates to abnormal phenomena such as fraud and the like, so that the risk assessment accuracy is low, the enterprise risk early warning method, the enterprise risk early warning device, the enterprise risk early warning equipment and the storage medium have the advantages that transaction running information corresponding to a target enterprise is obtained, and transaction characteristic data corresponding to the transaction running information is constructed; performing risk detection on the target enterprise based on the transaction characteristic data and a preset abnormal repayment and information source identification model to obtain a first risk detection result; and obtaining a target risk result of the target enterprise based on the first risk detection result. In the application, in the process of risk assessment of a target enterprise, transaction flow information corresponding to the target enterprise is obtained, and transaction characteristic data corresponding to the transaction flow information is constructed; based on the transaction characteristic data and the preset abnormal repayment and interest source identification model, the target enterprise is subjected to risk detection, and then a target risk result of the target enterprise is obtained, namely, in the embodiment, the borrowing transaction of the target enterprise and a small loan company and the abnormal repayment and interest source of the enterprise can be identified through the preset abnormal repayment and interest source identification model, so that the coverage range of transaction data early warning is widened, and the accuracy of risk assessment is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
Fig. 1 is a schematic flowchart of a first embodiment of an enterprise risk early warning method according to the present application;
fig. 2 is a detailed flowchart of the step S30 in the first embodiment of the enterprise risk early warning method of the present application;
fig. 3 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present application.
The objectives, features, and advantages of the present application will be further described with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In a first embodiment of the enterprise risk early warning method of the present application, referring to fig. 1, the enterprise risk early warning method includes:
step S10, acquiring transaction flow information corresponding to a target enterprise, and constructing transaction characteristic data corresponding to the transaction flow information;
step S20, based on the transaction characteristic data and a preset abnormal repayment and receipt source identification model, carrying out risk detection on the target enterprise to obtain a first risk detection result;
and step S30, obtaining a target risk result of the target enterprise based on the first risk detection result.
The method comprises the following specific steps:
step S10, acquiring transaction flow information corresponding to a target enterprise, and constructing transaction characteristic data corresponding to the transaction flow information;
in this embodiment, it should be noted that the enterprise risk early warning method is applied to an enterprise risk early warning device, and the enterprise risk early warning device belongs to an enterprise risk early warning device, and specifically, the application scenario of the enterprise risk early warning method lies in that: the method comprises the steps of carrying out risk detection on a target enterprise to carry out risk early warning on the target enterprise, wherein the specific application scenario can be that the target enterprise requests bank loan through a bank platform, and the bank needs to carry out risk assessment on the target enterprise.
When a loan request of a target enterprise is detected, transaction flow information corresponding to the target enterprise is extracted from the loan request, or transaction flow information corresponding to the target enterprise is directly inquired from a preset system, wherein the transaction flow information comprises information characteristics such as a name of a transaction opponent, an amount, a transaction summary, a transaction date, a repayment and rest date, a repayment amount, a deposit amount, a business category and the like, and the transaction characteristic data is coded data of the transaction flow characteristics of the target enterprise. That is, in this embodiment, the transaction flow information needs to be subjected to information encoding processing to obtain encoded data of the transaction flow characteristics of the target enterprise, i.e., the transaction characteristic data.
The step of obtaining the transaction flow information corresponding to the target enterprise includes:
step S01, acquiring original transaction data corresponding to the target enterprise;
step S02, carrying out duplicate removal and missing data cleaning processing on the original transaction data to obtain preprocessed data;
and step S03, setting the preprocessing data as the transaction flow information corresponding to the target enterprise.
In this embodiment, the original transaction data is further preprocessed, where the preprocessing process may be based on a business license of a target enterprise, a name of the target enterprise, and the like, and the original transaction data is subjected to data deduplication and missing data cleaning processing, so as to obtain transaction flow information corresponding to the target enterprise.
After the transaction flow information is obtained, acquiring the transaction flow information corresponding to the target enterprise, and constructing transaction characteristic data corresponding to the transaction flow information, specifically, acquiring the transaction flow information corresponding to the target enterprise, and performing characteristic extraction on the transaction flow information to extract the flow transaction characteristic information required in the transaction flow information, so as to obtain the transaction characteristic data corresponding to the transaction flow information.
The transaction pipeline information comprises transaction pipeline text, the transaction characteristic data comprises a transaction pipeline characteristic representation vector,
the step of constructing the transaction characteristic data corresponding to the transaction flow information includes:
step S11, extracting target characteristic values corresponding to a preset quantity of construction characteristics from the transaction flow text, and combining the target characteristic values into construction characteristic vectors;
in this embodiment, it should be noted that the transaction flow text refers to a paper document, an electronic document, and the like of a transaction flow acquired from a financial institution such as a bank, that is, the form of the transaction flow text is not limited, the transaction feature data is specifically represented by a transaction flow feature representation vector, specifically, a target feature value corresponding to a preset number of structural features is extracted from the transaction flow text, and each target feature value is combined into a structural feature vector, where the structural feature may be a manually combined feature or a manually determined feature, the structural feature includes a repayment return date, a transaction summary, and the like, that is, since the transaction flow text includes a plurality of flow columns, a preset number of structural features are extracted from the plurality of flow columns, and further a target feature value corresponding to the preset number structural features is extracted, and then the structural feature vector is obtained.
Extracting target feature values corresponding to a preset number of structural features from the transaction running text, combining the target feature values into a structural feature vector, specifically, extracting feature associated words corresponding to each structural feature from the transaction running text, performing feature coding on specific contents of the feature associated words (such as transaction amount) to generate target feature values corresponding to each structural feature, and further splicing the target feature values in a preset arrangement order to obtain a structural feature vector, for example, assuming that the structural features include a feature a, a feature B and a feature C, the feature associated word corresponding to the feature a is X, the target feature value obtained after performing feature coding on specific contents of X is a1, the feature word corresponding to the feature a is Y, and the target feature value obtained after performing feature coding on specific contents of Y is a2, the feature related word corresponding to the feature C is Z, the target feature value obtained by feature coding of the specific content of Z is a3, and the generated structural feature vector is (a1, a2, a 3).
Step S12, mapping the transaction flow text to a preset data dimension space to obtain a text low-dimensional space expression vector;
in this embodiment, the transaction running text is mapped to a preset data dimension space to obtain a text low-dimensional space representation vector, specifically, a preset vectorization module is called to vectorize each word in the transaction running text to obtain a vectorized text, and then the vectorized text is mapped to a preset data dimension space, where a data dimension of the preset data dimension space is lower than a data dimension of the vectorized text to obtain a text low-dimensional space representation vector, for example, assuming that the vectorized text is a 1024-bit vector, and after the text low-dimensional space representation vector is mapped to the preset data dimension space, the text low-dimensional space representation vector is a 72-bit vector. In this embodiment, the transaction pipeline text is mapped to a preset data dimension space, and a text low-dimensional space representation vector is obtained, so that the data processing amount can be reduced, and the data processing efficiency can be improved.
And step S13, splicing the constructed feature vector and the text low-dimensional space representation vector to obtain the transaction flow feature representation vector.
And splicing the constructed feature vector and the text low-dimensional space representation vector to obtain the transaction flow feature representation vector, specifically, sequentially splicing the constructed feature vector and the text low-dimensional space representation vector to obtain a target splicing vector, that is, if the constructed feature vector is M1 and the text low-dimensional space representation vector is N1, the target splicing vector is (M1, N1), and using the target splicing vector as the transaction flow feature representation vector.
Step S20, based on the transaction characteristic data and a preset abnormal repayment and receipt source identification model, carrying out risk detection on the target enterprise to obtain a first risk detection result;
based on the transaction characteristic data and a preset abnormal repayment and interest source identification model, performing risk detection on the target enterprise to obtain a first risk detection result, specifically, inputting the transaction flow characteristic representation vector into the preset abnormal repayment and interest source identification model, performing vector transformation on the transaction flow characteristic representation vector to transform the transaction flow characteristic representation vector into a classification probability vector with a preset length, wherein the classification label vector is a vector formed by classification probabilities of the target enterprise belonging to each preset classification category, selecting the maximum target classification probability from the classification probability vector, taking the preset classification category corresponding to the target classification probability as the classification category of the target enterprise to obtain a classification result, and taking the classification result as the first risk detection result.
The step of carrying out risk detection on the target enterprise based on the transaction characteristic data and a preset abnormal repayment and interest source identification model to obtain a first risk detection result comprises the following steps:
step S21, based on the transaction characteristic data and a first sub-identification model in a preset abnormal repayment and receipt source identification model, carrying out risk detection on the target enterprise to obtain a first risk detection sub-result;
step S22, based on the transaction characteristic data and a second sub-recognition model in a preset abnormal repayment and interest source recognition model, carrying out risk detection on the target enterprise to obtain a second risk detection sub-result;
step S23, based on the transaction characteristic data and a third sub-recognition model in a preset abnormal repayment and interest source recognition model, carrying out risk detection on the target enterprise to obtain a third risk detection sub-result;
the basic models for training the first sub-recognition model, the second sub-recognition model and the third sub-recognition model are different;
step S24, the first risk detector result, the second risk detector result, and the third risk detector result are fused to obtain a first risk detection result.
Specifically, in this embodiment, the preset abnormal repayment source identification model includes different sub-identification models, which are specifically a first sub-identification model, a second sub-identification model and a third sub-identification model, the first sub-identification model, the second sub-identification model and the third sub-identification model are different from each other in training basic models, specifically, the basic models of the different sub-identification models may be random forest, GBDTX and gboost models, respectively, because the basic models are different, the processes of data processing performed by the different sub-identification models are different, and because the processes of data processing performed by the different sub-identification models are different, the influence of accidental factors is avoided, the prediction accuracy is improved, that is, the target enterprise is risk-detected based on the transaction characteristic data and the first sub-identification model in the preset abnormal repayment source identification model, obtaining a first risk detection sub-result, and carrying out risk detection on the target enterprise based on the transaction characteristic data and a second sub-identification model in a preset abnormal repayment and information source identification model to obtain a second risk detection sub-result; and carrying out risk detection on the target enterprise based on the transaction characteristic data and a third sub-identification model in a preset abnormal repayment and interest source identification model to obtain a third risk detection sub-result, and fusing results after the first risk detection sub-result, the second risk detection sub-result and the third risk detection sub-result are obtained, wherein the specific fusion mode can be that a risk probability mean value is taken or a risk probability maximum value is taken to further obtain a first risk detection result.
And step S30, obtaining a target risk result of the target enterprise based on the first risk detection result.
In this embodiment, a target risk result of the target enterprise is obtained based on the first risk detection result. That is, after the first risk detection result is obtained, the first risk detection result is combined with other detection results to obtain a target risk result of the target enterprise.
Referring to fig. 2, the step of obtaining the target risk result of the target enterprise based on the first risk detection result includes:
step S31, inputting the transaction characteristic data into the abnormal transaction identification model, so as to detect abnormal transactions of the target enterprise based on the transaction characteristic data and obtain a second risk detection result;
in this embodiment, the transaction feature data is input into the abnormal transaction identification model to perform abnormal transaction detection on the target enterprise based on the transaction feature data, so as to obtain a second risk detection result, specifically, based on the abnormal transaction identification model, the transaction flow feature expression vector is mapped to a second risk score to perform abnormal transaction risk detection on the target enterprise, and the second risk score is used as the second risk detection result.
Step S32, obtaining weight information corresponding to the first risk detection result and the second risk detection result, and generating a target risk result of the target enterprise based on the weight information, the first risk detection result, and the second risk detection result.
In this embodiment, the first risk detection result and the weight information corresponding to the second risk detection result are obtained, and the target risk result of the target enterprise is generated based on the weight information, the first risk detection result and the second risk detection result, specifically, for example, the second risk score and the second weight corresponding to the second risk score are subjected to quadrature to obtain a second quadrature result, the first risk score and the first weight corresponding to the first risk score are subjected to quadrature to obtain a first quadrature result, and the first quadrature result and the second quadrature result are added to obtain the target risk result of the target enterprise, so that the purpose of performing targeted risk detection on the target enterprise based on the transaction characteristic data of the target enterprise is achieved.
Compared with the existing risk assessment process of an enterprise by a bank, which only focuses on analyzing whether the transaction relates to abnormal phenomena such as fraud and the like, so that the risk assessment accuracy is low, the enterprise risk early warning method, the enterprise risk early warning device, the enterprise risk early warning equipment and the storage medium have the advantages that transaction running information corresponding to a target enterprise is obtained, and transaction characteristic data corresponding to the transaction running information is constructed; performing risk detection on the target enterprise based on the transaction characteristic data and a preset abnormal repayment and information source identification model to obtain a first risk detection result; and obtaining a target risk result of the target enterprise based on the first risk detection result. In the application, in the process of risk assessment of a target enterprise, transaction flow information corresponding to the target enterprise is obtained, and transaction characteristic data corresponding to the transaction flow information is constructed; based on the transaction characteristic data and the preset abnormal repayment and interest source identification model, the target enterprise is subjected to risk detection, and then a target risk result of the target enterprise is obtained, namely, in the embodiment, the borrowing transaction of the target enterprise and a small loan company and the abnormal repayment and interest source of the enterprise can be identified through the preset abnormal repayment and interest source identification model, so that the coverage range of transaction data early warning is widened, and the accuracy of risk assessment is improved.
An embodiment of the present application provides an enterprise risk early warning method, and provides another embodiment of the enterprise risk early warning method, where the embodiment is based on the first embodiment in the present application, and in the another embodiment, before the step of performing risk detection on the target enterprise based on the transaction characteristic data and a preset abnormal repayment and return source identification model to obtain a first risk detection result, the enterprise risk early warning method further includes:
a10, acquiring a training data set, and constructing a training feature data set corresponding to the training data set;
in this embodiment, it should be noted that the training data set may include a training transaction running text set and a verification transaction running text set, the training transaction running text set is used for training, and the verification transaction running text set is used for verification, where the specific process of constructing the training litigation characteristic data may refer to the above-mentioned refining step of step S10.
Step A20, constructing a decision tree model based on the training feature data set;
based on the training feature data set, a decision tree model is constructed, in this embodiment, it should be noted that the decision tree basic model includes a random forest, a gboost, and the like, the decision tree model includes at least one decision tree, the decision tree includes at least one non-leaf node (which may be multiple nodes), the non-leaf node corresponds to at least one feature split value, where the feature split point is a feature value range or a feature value of a transaction flow feature, and is used to indicate that the non-leaf node is split into a left child node and a right child node in a model training process, or indicate that a sample belongs to the left child node or the right child node in a model prediction process, and one of the transaction flow features may correspond to one or more feature split points, where a process of constructing the decision tree model is an existing technology and is not described herein again.
Step A30, based on the decision tree model, performing feature screening on the training feature data set to obtain a target feature data set;
in this embodiment, in an overall manner, based on the decision tree model, feature screening is performed on the training feature data set to obtain a target feature data set, specifically, each initial transaction running water feature corresponding to the training feature data set is determined, a number of non-leaf nodes corresponding to each initial transaction running water feature in the decision tree model is obtained, further, based on the number of the non-leaf nodes, a feature importance of each initial transaction running water feature is evaluated, and a feature importance evaluation value corresponding to each initial transaction running water feature is obtained, where the feature importance evaluation value is a numerical value evaluating a feature importance level, where the greater the number of the non-leaf nodes corresponding to the initial transaction running water feature is, the higher the feature importance of the initial transaction running water feature is, and further, based on each feature importance evaluation value, and carrying out feature screening on the training feature data set to obtain a target feature data set.
Wherein the decision tree model comprises at least one decision tree,
the step of performing feature screening on the training feature data set based on the decision tree model to obtain a target feature data set includes:
step A31, determining each initial transaction flow characteristic corresponding to the training characteristic data set, and obtaining the number of non-leaf nodes corresponding to each initial transaction flow characteristic in each decision tree;
in this embodiment, it should be noted that each non-leaf node of the decision tree records a feature code of a corresponding feature splitting point, where the feature code is an identity of a transaction flow feature corresponding to the feature splitting point.
Determining each initial transaction running characteristic corresponding to the training characteristic data set, and obtaining the number of non-leaf nodes corresponding to each initial transaction running characteristic in each decision tree, specifically, determining each initial transaction running characteristic corresponding to the training characteristic data set, and querying each non-leaf node corresponding to each initial transaction running characteristic in each decision tree according to the characteristic code of each initial transaction running characteristic, so as to count the number of each non-leaf node corresponding to each initial transaction running characteristic, and obtain the number of corresponding non-leaf nodes in each decision tree.
Step A32, based on the number of the non-leaf nodes, performing feature importance ranking on the initial transaction flow features to obtain a feature importance ranking result;
in this embodiment, feature importance ranking is performed on each initial transaction flow characteristic based on the number of each non-leaf node to obtain a feature importance ranking result, and specifically, feature importance ranking is performed on each initial transaction flow characteristic from large to small based on the number of each non-leaf node to obtain a feature importance ranking result.
Step A33, based on the feature importance ranking result, selecting a preset number of target transaction flow characteristics from each initial transaction flow characteristic;
in this embodiment, based on the feature importance ranking result, a preset number of target transaction flow characteristics are selected from each of the initial transaction flow characteristics, and specifically, a preset number of transaction flow characteristics at the front of the ranking are selected from the feature importance ranking result as the target transaction flow characteristics.
And A34, selecting feature data corresponding to the target transaction running features from the training feature data set as the target feature data set.
Step A40, constructing the preset abnormal repayment and interest source identification model based on the target characteristic data set.
In this embodiment, it should be noted that the target feature data set includes a sample representation vector, where the sample representation vector is composed of feature values of each of the target transaction flow features.
And constructing the preset abnormal repayment and reimbursement source identification model based on the target characteristic data set, specifically, obtaining a preset basic model, selecting a sample expression vector in the target characteristic data set, inputting the sample expression vector into the preset basic model, training and updating the preset basic model, judging whether the updated preset basic model meets a preset iteration training ending condition, if so, taking the preset basic model as the preset abnormal repayment and reimbursement source identification model, and if not, returning to the step of selecting the sample expression vector in the target characteristic data set, wherein the preset iteration training ending condition comprises loss function convergence, maximum iteration number threshold value reaching and the like.
Similarly, the abnormal transaction identification model may be constructed in the above manner, and will not be described herein again.
The method comprises the steps of obtaining a training data set, and constructing a training characteristic data set corresponding to the training data set; constructing a decision tree model based on the training feature data set; based on the decision tree model, carrying out feature screening on the training feature data set to obtain a target feature data set; and constructing the preset abnormal repayment and interest reduction source identification model based on the target characteristic data set. In the embodiment, the preset abnormal repayment and interest returning source identification model is accurately constructed, and a foundation is laid for improving the accuracy of risk detection.
Referring to fig. 3, fig. 3 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present application.
As shown in fig. 3, the enterprise risk early warning device may include: a processor 1001, such as a CPU, a memory 1005, and a communication bus 1002. The communication bus 1002 is used for realizing connection communication between the processor 1001 and the memory 1005. The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a memory device separate from the processor 1001 described above.
Optionally, the enterprise risk early warning device may further include a rectangular user interface, a network interface, a camera, a Radio Frequency (RF) circuit, a sensor, an audio circuit, a WiFi module, and the like. The rectangular user interface may comprise a Display screen (Display), an input sub-module such as a Keyboard (Keyboard), and the optional rectangular user interface may also comprise a standard wired interface, a wireless interface. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface).
Those skilled in the art will appreciate that the configuration of the enterprise risk early warning device illustrated in fig. 3 is not intended to be limiting, and may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components.
As shown in fig. 3, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, and an enterprise risk early warning program. The operating system is a program for managing and controlling hardware and software resources of the enterprise risk early warning device, and supports the operation of the enterprise risk early warning program and other software and/or programs. The network communication module is used for realizing communication among the components in the storage 1005 and communication with other hardware and software in the enterprise risk early warning system.
In the enterprise risk early warning apparatus shown in fig. 3, the processor 1001 is configured to execute an enterprise risk early warning program stored in the storage 1005, so as to implement any of the steps of the enterprise risk early warning method described above.
The specific implementation of the enterprise risk early warning device is basically the same as that of each embodiment of the enterprise risk early warning method, and is not described herein again.
The application also provides an enterprise risk early warning device, enterprise risk early warning device includes:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring transaction flow information corresponding to a target enterprise and constructing transaction characteristic data corresponding to the transaction flow information;
the risk detection module is used for carrying out risk detection on the target enterprise based on the transaction characteristic data and a preset abnormal repayment and receipt source identification model to obtain a first risk detection result;
and the second acquisition module is used for acquiring a target risk result of the target enterprise based on the first risk detection result.
Optionally, the second obtaining module includes:
the input unit is used for inputting the transaction characteristic data into the abnormal transaction identification model so as to detect abnormal transactions of the target enterprise based on the transaction characteristic data and obtain a second risk detection result;
a first obtaining unit, configured to obtain weight information corresponding to the first risk detection result and the second risk detection result, and generate a target risk result of the target enterprise based on the weight information, the first risk detection result, and the second risk detection result.
Optionally, the apparatus further comprises:
the third acquisition module is used for acquiring a training data set and constructing a training characteristic data set corresponding to the training data set;
a first construction module for constructing a decision tree model based on the training feature data set;
the characteristic screening module is used for carrying out characteristic screening on the training characteristic data set based on the decision tree model to obtain a target characteristic data set;
and the second construction module is used for constructing the preset abnormal repayment and interest reduction source identification model based on the target characteristic data set.
Optionally, the decision tree model comprises at least one decision tree,
the feature screening module includes:
a first determining unit, configured to determine each initial transaction flow characteristic corresponding to the training characteristic data set, and obtain a corresponding number of non-leaf nodes of each initial transaction flow characteristic in each decision tree;
the sorting unit is used for sorting the feature importance of each initial transaction flow characteristic based on the number of the non-leaf nodes to obtain a feature importance sorting result;
the first selection unit is used for selecting a preset number of target transaction flow characteristics from each initial transaction flow characteristic based on the characteristic importance ranking result;
and the second selection unit is used for selecting the feature data corresponding to the target transaction running features from the training feature data set as the target feature data set.
Optionally, the transaction flow information comprises transaction flow text, the transaction characteristic data comprises a transaction flow characteristic representation vector,
the first obtaining module comprises:
the extraction unit is used for extracting target characteristic values corresponding to a preset number of construction characteristics from the transaction flow text and combining the target characteristic values into construction characteristic vectors;
the second acquisition unit is used for mapping the transaction pipeline text to a preset data dimension space to obtain a text low-dimensional space representation vector;
and the third acquisition unit is used for splicing the constructed feature vector and the text low-dimensional space representation vector to acquire the transaction flow feature representation vector.
The risk detection module includes:
the first risk detection unit is used for carrying out risk detection on the target enterprise based on the transaction characteristic data and a first sub-identification model in a preset abnormal repayment and receipt source identification model to obtain a first risk detection sub-result;
the second risk detection unit is used for carrying out risk detection on the target enterprise based on the transaction characteristic data and a second sub-identification model in a preset abnormal repayment and receipt source identification model to obtain a second risk detection sub-result;
the third risk detection unit is used for carrying out risk detection on the target enterprise based on the transaction characteristic data and a third sub-identification model in a preset abnormal repayment and receipt source identification model to obtain a third risk detection sub-result;
the basic models for training the first sub-recognition model, the second sub-recognition model and the third sub-recognition model are different;
and the fusion unit is used for fusing the first risk detection sub-result, the second risk detection sub-result and the third risk detection sub-result to obtain a first risk detection result.
Optionally, the first obtaining module includes:
the fourth acquisition unit is used for acquiring original transaction data corresponding to the target enterprise;
the preprocessing unit is used for carrying out duplicate removal and missing data cleaning treatment on the original transaction data to obtain preprocessed data;
and the setting unit is used for setting the preprocessing data as the transaction flow information corresponding to the target enterprise.
The specific implementation of the enterprise risk early warning device is basically the same as that of the embodiments of the enterprise risk early warning method, and is not described herein again.
The embodiment of the present application provides a storage medium, and the storage medium stores one or more programs, and the one or more programs are further executable by one or more processors for implementing the steps of the enterprise risk early warning method described in any one of the above.
The specific implementation of the storage medium of the present application is substantially the same as that of each embodiment of the enterprise risk early warning method, and is not described herein again.
The present application also provides a computer program product, comprising a computer program, which when executed by a processor, implements the steps of the enterprise risk pre-warning method described above.
The specific implementation of the computer program product of the present application is substantially the same as that of each embodiment of the enterprise risk early warning method, and is not described herein again.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.
Claims (10)
1. An enterprise risk early warning method is characterized by comprising the following steps:
acquiring transaction flow information corresponding to a target enterprise, and constructing transaction characteristic data corresponding to the transaction flow information;
performing risk detection on the target enterprise based on the transaction characteristic data and a preset abnormal repayment and information source identification model to obtain a first risk detection result;
and obtaining a target risk result of the target enterprise based on the first risk detection result.
2. The enterprise risk pre-warning method as claimed in claim 1, wherein the step of obtaining the target risk result of the target enterprise based on the first risk detection result comprises:
inputting the transaction characteristic data into the abnormal transaction identification model so as to perform abnormal transaction detection on the target enterprise based on the transaction characteristic data and obtain a second risk detection result;
and acquiring weight information corresponding to the first risk detection result and the second risk detection result, and generating a target risk result of the target enterprise based on the weight information, the first risk detection result and the second risk detection result.
3. The enterprise risk early warning method according to claim 1, wherein before the step of performing risk detection on the target enterprise based on the transaction characteristic data and a preset abnormal repayment and reimbursement source identification model to obtain a first risk detection result, the enterprise risk early warning method further comprises:
acquiring a training data set, and constructing a training characteristic data set corresponding to the training data set;
constructing a decision tree model based on the training feature data set;
based on the decision tree model, carrying out feature screening on the training feature data set to obtain a target feature data set;
and constructing the preset abnormal repayment and interest reduction source identification model based on the target characteristic data set.
4. The enterprise risk early warning method of claim 3, wherein the decision tree model comprises at least one decision tree,
the step of performing feature screening on the training feature data set based on the decision tree model to obtain a target feature data set includes:
determining each initial transaction flow characteristic corresponding to the training characteristic data set, and acquiring the number of non-leaf nodes corresponding to each initial transaction flow characteristic in each decision tree;
based on the number of the non-leaf nodes, performing feature importance ranking on the initial transaction flow features to obtain a feature importance ranking result;
selecting a preset number of target transaction flow characteristics from each initial transaction flow characteristic based on the characteristic importance sorting result;
and selecting feature data corresponding to the target transaction running features from the training feature data set as the target feature data set.
5. The enterprise risk early warning method of claim 1, wherein the transaction pipeline information comprises transaction pipeline text, the transaction characteristic data comprises a transaction pipeline characteristic representation vector,
the step of constructing the transaction characteristic data corresponding to the transaction flow information includes:
extracting target characteristic values corresponding to a preset number of construction features from the transaction flow text, and combining the target characteristic values into construction characteristic vectors;
mapping the transaction flow text to a preset data dimension space to obtain a text low-dimension space expression vector;
and splicing the constructed feature vector and the text low-dimensional space representation vector to obtain the transaction flow feature representation vector.
6. The enterprise risk early warning method according to claim 1, wherein the step of performing risk detection on the target enterprise based on the transaction characteristic data and a preset abnormal repayment and reimbursement source identification model to obtain a first risk detection result comprises:
performing risk detection on the target enterprise based on the transaction characteristic data and a first sub-identification model in a preset abnormal repayment and information source identification model to obtain a first risk detection sub-result;
performing risk detection on the target enterprise based on the transaction characteristic data and a second sub-identification model in a preset abnormal repayment and information source identification model to obtain a second risk detection sub-result;
performing risk detection on the target enterprise based on the transaction characteristic data and a third sub-identification model in a preset abnormal repayment and information source identification model to obtain a third risk detection sub-result;
the basic models for training the first sub-recognition model, the second sub-recognition model and the third sub-recognition model are different;
and fusing the first risk detection sub-result, the second risk detection sub-result and the third risk detection sub-result to obtain a first risk detection result.
7. The enterprise risk early warning method according to any one of claims 1-6, wherein the step of obtaining transaction flow information corresponding to the target enterprise comprises:
acquiring original transaction data corresponding to a target enterprise;
carrying out duplicate removal and missing data cleaning treatment on the original transaction data to obtain preprocessed data;
and setting the preprocessing data as the transaction flow information corresponding to the target enterprise.
8. An enterprise risk early warning device, characterized in that, enterprise risk early warning device includes:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring transaction flow information corresponding to a target enterprise and constructing transaction characteristic data corresponding to the transaction flow information;
the risk detection module is used for carrying out risk detection on the target enterprise based on the transaction characteristic data and a preset abnormal repayment and receipt source identification model to obtain a first risk detection result;
and the second acquisition module is used for acquiring a target risk result of the target enterprise based on the first risk detection result.
9. An enterprise risk early warning device, comprising: a memory, a processor, and a program stored on the memory for implementing the enterprise risk pre-warning method,
the memory is used for storing a program for realizing the enterprise risk early warning method;
the processor is used for executing the program for implementing the enterprise risk early warning method so as to implement the steps of the enterprise risk early warning method according to any one of claims 1 to 7.
10. A storage medium having a program for implementing an enterprise risk early warning method stored thereon, wherein the program is executed by a processor to implement the steps of the enterprise risk early warning method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110080220.XA CN112801773A (en) | 2021-01-20 | 2021-01-20 | Enterprise risk early warning method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110080220.XA CN112801773A (en) | 2021-01-20 | 2021-01-20 | Enterprise risk early warning method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112801773A true CN112801773A (en) | 2021-05-14 |
Family
ID=75810966
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110080220.XA Pending CN112801773A (en) | 2021-01-20 | 2021-01-20 | Enterprise risk early warning method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112801773A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113129133A (en) * | 2021-05-17 | 2021-07-16 | 无锡航吴科技有限公司 | Financing platform enterprise property classification method and system |
| CN113450215A (en) * | 2021-06-25 | 2021-09-28 | 中国工商银行股份有限公司 | Transaction data risk detection method and device and server |
| CN113506174A (en) * | 2021-08-19 | 2021-10-15 | 北京中数智汇科技股份有限公司 | Method, device and equipment for training risk early warning model of medium and small enterprises |
| CN113538154A (en) * | 2021-07-23 | 2021-10-22 | 同盾科技有限公司 | Risk object identification method and device, storage medium and electronic equipment |
| CN113689288A (en) * | 2021-08-25 | 2021-11-23 | 深圳前海微众银行股份有限公司 | Risk identification method, device and equipment based on entity list and storage medium |
| CN114372681A (en) * | 2021-12-27 | 2022-04-19 | 见知数据科技(上海)有限公司 | Enterprise classification method, device, equipment, medium and product based on pipeline data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050043961A1 (en) * | 2002-09-30 | 2005-02-24 | Michael Torres | System and method for identification, detection and investigation of maleficent acts |
| CN109389494A (en) * | 2018-10-25 | 2019-02-26 | 北京芯盾时代科技有限公司 | Borrow or lend money fraud detection model training method, debt-credit fraud detection method and device |
| CN109409677A (en) * | 2018-09-27 | 2019-03-01 | 深圳壹账通智能科技有限公司 | Enterprise Credit Risk Evaluation method, apparatus, equipment and storage medium |
| CN109657977A (en) * | 2018-12-19 | 2019-04-19 | 重庆誉存大数据科技有限公司 | A kind of Risk Identification Method and system |
| CN111383101A (en) * | 2020-03-25 | 2020-07-07 | 深圳前海微众银行股份有限公司 | Post-loan risk monitoring method, device, equipment and computer-readable storage medium |
-
2021
- 2021-01-20 CN CN202110080220.XA patent/CN112801773A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050043961A1 (en) * | 2002-09-30 | 2005-02-24 | Michael Torres | System and method for identification, detection and investigation of maleficent acts |
| CN109409677A (en) * | 2018-09-27 | 2019-03-01 | 深圳壹账通智能科技有限公司 | Enterprise Credit Risk Evaluation method, apparatus, equipment and storage medium |
| CN109389494A (en) * | 2018-10-25 | 2019-02-26 | 北京芯盾时代科技有限公司 | Borrow or lend money fraud detection model training method, debt-credit fraud detection method and device |
| CN109657977A (en) * | 2018-12-19 | 2019-04-19 | 重庆誉存大数据科技有限公司 | A kind of Risk Identification Method and system |
| CN111383101A (en) * | 2020-03-25 | 2020-07-07 | 深圳前海微众银行股份有限公司 | Post-loan risk monitoring method, device, equipment and computer-readable storage medium |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113129133A (en) * | 2021-05-17 | 2021-07-16 | 无锡航吴科技有限公司 | Financing platform enterprise property classification method and system |
| CN113129133B (en) * | 2021-05-17 | 2023-11-21 | 无锡航吴科技有限公司 | Financing platform enterprise property classification method and system |
| CN113450215A (en) * | 2021-06-25 | 2021-09-28 | 中国工商银行股份有限公司 | Transaction data risk detection method and device and server |
| CN113538154A (en) * | 2021-07-23 | 2021-10-22 | 同盾科技有限公司 | Risk object identification method and device, storage medium and electronic equipment |
| CN113506174A (en) * | 2021-08-19 | 2021-10-15 | 北京中数智汇科技股份有限公司 | Method, device and equipment for training risk early warning model of medium and small enterprises |
| CN113689288A (en) * | 2021-08-25 | 2021-11-23 | 深圳前海微众银行股份有限公司 | Risk identification method, device and equipment based on entity list and storage medium |
| CN113689288B (en) * | 2021-08-25 | 2024-05-14 | 深圳前海微众银行股份有限公司 | Risk identification method, device, equipment and storage medium based on entity list |
| CN114372681A (en) * | 2021-12-27 | 2022-04-19 | 见知数据科技(上海)有限公司 | Enterprise classification method, device, equipment, medium and product based on pipeline data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112801773A (en) | Enterprise risk early warning method, device, equipment and storage medium | |
| CN107330445B (en) | User attribute prediction method and device | |
| CA3063580A1 (en) | Classifier training method and apparatus, electronic device and computer readable medium | |
| CN109509048B (en) | Malicious order identification method and device, electronic equipment and storage medium | |
| CN111199474A (en) | Risk prediction method and device based on network diagram data of two parties and electronic equipment | |
| CN111222976A (en) | Risk prediction method and device based on network diagram data of two parties and electronic equipment | |
| CN111985937A (en) | Method, system, storage medium and computer equipment for evaluating value information of transaction traders | |
| CN113609345B (en) | Target object association method and device, computing equipment and storage medium | |
| CN111611390B (en) | Data processing method and device | |
| CN114202336A (en) | Risk behavior monitoring method and system in financial scene | |
| CN116485406A (en) | Account detection method and device, storage medium and electronic equipment | |
| CN112328869A (en) | User loan willingness prediction method and device and computer system | |
| CN111768247A (en) | Order-placing rate prediction method, device and readable storage medium | |
| CN109684198B (en) | Method, device, medium and electronic equipment for acquiring data to be tested | |
| CN112801489B (en) | Litigation case risk detection method, litigation case risk detection device, litigation case risk detection equipment and readable storage medium | |
| US20230230081A1 (en) | Account identification method, apparatus, electronic device and computer readable medium | |
| US20190114639A1 (en) | Anomaly detection in data transactions | |
| CN111245815B (en) | Data processing method and device, storage medium and electronic equipment | |
| CN111582313A (en) | Sample data generation method and device and electronic equipment | |
| CN111784053A (en) | Transaction risk detection method, device and readable storage medium | |
| CN115168509A (en) | Processing method and device of wind control data, storage medium and computer equipment | |
| CN114387089A (en) | Client credit risk assessment method, device, equipment and storage medium | |
| CN113807391A (en) | Task model training method and device, electronic equipment and storage medium | |
| CN114297235A (en) | Risk address identification method and system and electronic equipment | |
| CN110765100B (en) | Label generation method and device, computer readable storage medium and server |
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 |