CN116703555A - Early warning method, early warning device, electronic equipment and computer readable medium - Google Patents
Early warning method, early warning device, electronic equipment and computer readable medium Download PDFInfo
- Publication number
- CN116703555A CN116703555A CN202211534886.9A CN202211534886A CN116703555A CN 116703555 A CN116703555 A CN 116703555A CN 202211534886 A CN202211534886 A CN 202211534886A CN 116703555 A CN116703555 A CN 116703555A
- Authority
- CN
- China
- Prior art keywords
- early warning
- entity
- transaction data
- generating
- portrait
- 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 45
- 238000012549 training Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000003062 neural network model Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 14
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000013145 classification model Methods 0.000 claims description 7
- 230000004044 response Effects 0.000 claims description 6
- 239000010419 fine particle Substances 0.000 claims 1
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000007418 data mining Methods 0.000 abstract description 2
- 238000011161 development Methods 0.000 description 21
- 238000010586 diagram Methods 0.000 description 15
- 230000008859 change Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 241000605059 Bacteroidetes Species 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008014 freezing Effects 0.000 description 1
- 238000007710 freezing Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses an early warning method, an early warning device, electronic equipment and a computer readable medium, and relates to the technical field of big data analysis and mining; carrying out fine granularity classification on historical transaction data based on a preset dimension to obtain corresponding fine granularity; generating a corresponding entity portrait based on the fine granularity; generating an early warning model according to entity portrait training, acquiring current transaction data corresponding to the entity identifier, generating early warning information according to the current transaction data and the early warning model, and sending the early warning information to a preset processing node. Therefore, the risk after the lending can be accurately predicted, and the loss is reduced.
Description
Technical Field
The present application relates to the field of big data analysis and mining technologies, and in particular, to an early warning method, an early warning device, an electronic device, and a computer readable medium.
Background
The enterprise is used as an important client of bank loan business, has the characteristics of high credit limit, large loan amount, difficult assessment, high risk and the like, and once the enterprise generates bad account, the enterprise generates larger loss to the bank. In order to make post-loan early warning of an enterprise, the enterprise needs to be monitored in multiple dimensions, multiple scenes and multiple angles. However, most of the existing post-credit early warning systems of banks do not perform systematic analysis on business characteristics and current situations of industries of enterprises during development, so that the existing post-credit early warning systems often cannot accurately identify the enterprises which possibly generate problems, and therefore the risks cannot be prejudged in advance.
Disclosure of Invention
In view of the above, embodiments of the present application provide an early warning method, apparatus, electronic device, and computer readable medium, which can solve the problem that the existing post-loan early warning system cannot accurately identify an enterprise that may be problematic, so that the risk cannot be predicted in advance.
In order to achieve the above object, according to an aspect of the embodiments of the present application, there is provided an early warning method, including:
receiving an early warning request, acquiring a corresponding entity identifier, and further acquiring corresponding historical transaction data according to the entity identifier;
carrying out fine granularity classification on historical transaction data based on a preset dimension to obtain corresponding fine granularity;
generating a corresponding entity portrait based on the fine granularity;
generating an early warning model according to entity portrait training, acquiring current transaction data corresponding to the entity identifier, generating early warning information according to the current transaction data and the early warning model, and sending the early warning information to a preset processing node.
Optionally, fine-grained classification of the historical transaction data based on the preset dimension includes:
the historical transaction data is input into a classification model to output fine-grained classifications corresponding to the preset dimensions.
Optionally, generating the corresponding entity representation based on the fine granularity includes:
Extracting high-level features and low-level features in corresponding historical transaction data based on fine granularity;
and generating corresponding entity portraits according to the high-level features and the low-level features.
Optionally, generating the corresponding entity representation based on the fine granularity includes:
determining a corresponding risk level according to the fine granularity;
and generating a corresponding entity portrait according to the risk level, the fine granularity and the preset monitoring object type.
Optionally, generating the early warning model according to entity portrait training includes:
acquiring an initial neural network model;
acquiring a training sample set, wherein the training sample set comprises entity portraits and early warning information corresponding to the entity portraits;
and taking the entity portraits as input of an initial neural network model, taking early warning information corresponding to the entity portraits as expected output, and training the initial neural network model to obtain an early warning model.
Optionally, generating the early warning information according to the current transaction data and the early warning model includes:
generating a current transaction representation based on the current transaction data;
and inputting the current transaction portrait to the early warning model for analysis, generating early warning information and outputting the early warning information in response to the corresponding risk items of the analysis result corresponding to the current transaction portrait.
Optionally, generating the early warning information includes:
determining the number of risk items corresponding to the current transaction data;
and generating early warning information according to the quantity and the corresponding risk items.
In addition, the application also provides an early warning device, which comprises:
the receiving unit is configured to receive the early warning request, acquire the corresponding entity identifier and further acquire the corresponding historical transaction data according to the entity identifier;
the fine granularity determining unit is configured to classify the historical transaction data into fine granularity based on a preset dimension so as to obtain corresponding fine granularity;
an entity representation generation unit configured to generate a corresponding entity representation based on the fine granularity;
the early warning unit is configured to generate an early warning model according to entity portrait training, acquire current transaction data corresponding to the entity identifier, generate early warning information according to the current transaction data and the early warning model, and send the early warning information to a preset processing node.
Optionally, the fine granularity determining unit is further configured to:
the historical transaction data is input into a classification model to output fine-grained classifications corresponding to the preset dimensions.
Optionally, the entity representation generation unit is further configured to:
Extracting high-level features and low-level features in corresponding historical transaction data based on fine granularity;
and generating corresponding entity portraits according to the high-level features and the low-level features.
Optionally, the entity representation generation unit is further configured to:
determining a corresponding risk level according to the fine granularity;
and generating a corresponding entity portrait according to the risk level, the fine granularity and the preset monitoring object type.
Optionally, the pre-warning unit is further configured to:
acquiring an initial neural network model;
acquiring a training sample set, wherein the training sample set is configured into an entity portrait and early warning information corresponding to the entity portrait;
and taking the entity portraits as input of an initial neural network model, taking early warning information corresponding to the entity portraits as expected output, and training the initial neural network model to obtain an early warning model.
Optionally, the pre-warning unit is further configured to:
generating a current transaction representation based on the current transaction data;
and inputting the current transaction portrait to the early warning model for analysis, generating early warning information and outputting the early warning information in response to the corresponding risk items of the analysis result corresponding to the current transaction portrait.
Optionally, the pre-warning unit is further configured to:
Determining the number of risk items corresponding to the current transaction data;
and generating early warning information according to the quantity and the corresponding risk items.
In addition, the application also provides early warning electronic equipment, which comprises: one or more processors; and the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are enabled to realize the early warning method.
In addition, the application also provides a computer readable medium, on which a computer program is stored, which when executed by a processor, implements the early warning method as described above.
To achieve the above object, according to still another aspect of an embodiment of the present application, there is provided a computer program product.
The computer program product of the embodiment of the application comprises a computer program, and the early warning method provided by the embodiment of the application is realized when the program is executed by a processor.
One embodiment of the above application has the following advantages or benefits: the method and the device acquire the corresponding entity identification by receiving the early warning request, and further acquire the corresponding historical transaction data according to the entity identification; carrying out fine granularity classification on historical transaction data based on a preset dimension to obtain corresponding fine granularity; generating a corresponding entity portrait based on the fine granularity; generating an early warning model according to entity portrait training, acquiring current transaction data corresponding to the entity identifier, generating early warning information according to the current transaction data and the early warning model, and sending the early warning information to a preset processing node. Therefore, the risk after the lending can be accurately predicted, and the loss is reduced.
Further effects of the above-described non-conventional alternatives are described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the application and are not to be construed as unduly limiting the application. Wherein:
FIG. 1 is a schematic diagram of the main flow of an early warning method according to one embodiment of the application;
FIG. 2 is a schematic diagram of the main flow of an early warning method according to one embodiment of the application;
FIG. 3 is a schematic diagram of a main flow of an early warning method according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a primary flow of an early warning method according to an embodiment of the application
FIG. 5 is a schematic diagram of the main units of the early warning device according to an embodiment of the present application;
FIG. 6 is an exemplary system architecture diagram in which embodiments of the present application may be applied;
fig. 7 is a schematic diagram of a computer system suitable for use in implementing an embodiment of the application.
Detailed Description
Exemplary embodiments of the present application will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present application are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness. In the technical scheme of the application, the aspects of acquisition, analysis, use, transmission, storage and the like of the related user personal information all meet the requirements of related laws and regulations, are used for legal and reasonable purposes, are not shared, leaked or sold outside the aspects of legal use and the like, and are subjected to supervision and management of a supervision department. Necessary measures should be taken for the personal information of the user to prevent illegal access to such personal information data, ensure that personnel having access to the personal information data comply with the regulations of the relevant laws and regulations, and ensure the personal information of the user. Once these user personal information data are no longer needed, the risk should be minimized by limiting or even prohibiting the data collection and/or deletion.
User privacy is protected by de-identifying data when used, including in some related applications, such as by removing a particular identifier, controlling the amount or specificity of stored data, controlling how data is stored, and/or other methods.
Fig. 1 is a schematic diagram of main flow of an early warning method according to an embodiment of the present application, and as shown in fig. 1, the early warning method includes:
step S101, receiving an early warning request, acquiring a corresponding entity identifier, and further acquiring corresponding historical transaction data according to the entity identifier.
In this embodiment, the execution body (for example, may be a server) of the early warning method may receive the early warning request through a wired connection or a wireless connection. The executing body may acquire the entity identifier carried in the early warning request, and specifically, the entity identifier may be a company identifier or may be a user identifier. The embodiment of the application does not limit the entity identification in detail. After the execution body obtains the corresponding entity identifier, the execution body can obtain historical transaction data corresponding to the entity identifier. The historical transaction data can be transaction data of financial product purchase of the entity corresponding to the entity identifier for n months, or loan data of the entity corresponding to the entity identifier for n months, and the type and the content of the historical transaction data are not particularly limited in the embodiment of the application.
Step S102, carrying out fine granularity classification on the historical transaction data based on the preset dimension to obtain corresponding fine granularity.
The preset dimensions may include, for example, a lawsuit dimension, an environmental violation dimension, a financial condition exception dimension, an operation condition exception dimension, a personal credit violation dimension, and the like, which are not specifically limited in the embodiments of the present application.
The execution body may perform similarity calculation on the historical transaction data and a preset dimension, so as to determine fine granularity corresponding to the historical transaction data according to the calculated similarity.
As another implementation, fine-grained classification of historical transaction data based on preset dimensions includes: the historical transaction data is input into a classification model to output fine-grained classifications corresponding to the preset dimensions.
And outputting fine granularity classification corresponding to the preset dimension in the historical transaction data. For example, the financial condition exception granularity, and the lawsuit granularity corresponding to the historical transaction data are output.
The classification model is used for representing the corresponding relation between the data and the fine granularity corresponding to the preset dimension.
Step S103, based on the fine granularity, generating a corresponding entity portrait.
Specifically, based on the fine granularity, generating the corresponding entity representation includes:
Determining a corresponding risk level according to the fine granularity; the risk level can be divided into high, medium and low. And inputting the fine granularity corresponding to the historical transaction data into a risk level assessment model to obtain a corresponding risk level.
And generating a corresponding entity portrait according to the risk level, the fine granularity and the preset monitoring object type.
The preset monitoring object types may include company class, individual human. And taking the risk level and the fine granularity as labels to generate an entity portrait corresponding to the detection object type.
Step S104, generating an early warning model according to entity portrait training, acquiring current transaction data corresponding to the entity identifier, generating early warning information according to the current transaction data and the early warning model, and sending the early warning information to a preset processing node.
Specifically, generating an early warning model according to entity portrait training comprises:
acquiring an initial neural network model, such as a convolutional neural network model (Convolutional Neural Network, CNN); acquiring a training sample set, wherein the training sample set comprises entity portraits (namely entity portraits obtained by historical transaction data) and early warning information corresponding to the entity portraits; and taking the entity portraits as input of an initial neural network model, taking early warning information corresponding to the entity portraits as expected output, and training the initial neural network model to obtain an early warning model.
Specifically, generating early warning information according to current transaction data and an early warning model includes: generating a current transaction representation based on the current transaction data; and inputting the current transaction portrait to the early warning model for analysis, generating early warning information and outputting the early warning information in response to the corresponding risk items of the analysis result corresponding to the current transaction portrait.
The current transaction data corresponding to the entity identification is input into the early warning model, whether the current transaction data has risks or not can be determined, and when the early warning model detects that the current transaction data has risks, namely, corresponding risk items exist in the current transaction data, corresponding early warning information is output. The risk prediction is carried out on the current transaction data by using the early warning model obtained by training the entity portrait generated by the historical transaction data, so that the result of the risk prediction after the lending is more accurate, and the risk prediction after the lending is more timely.
According to the embodiment, the corresponding entity identification is obtained by receiving the early warning request, and then the corresponding historical transaction data is obtained according to the entity identification; carrying out fine granularity classification on historical transaction data based on a preset dimension to obtain corresponding fine granularity; generating a corresponding entity portrait based on the fine granularity; generating an early warning model according to entity portrait training, acquiring current transaction data corresponding to the entity identifier, generating early warning information according to the current transaction data and the early warning model, and sending the early warning information to a preset processing node. Therefore, the risk after the lending can be accurately predicted, and the loss is reduced.
Fig. 2 is a schematic flow chart of an early warning method according to an embodiment of the present application, as shown in fig. 2, the early warning method includes:
step S201, receiving an early warning request, obtaining a corresponding entity identifier, and further obtaining corresponding historical transaction data according to the entity identifier.
The early warning request can be a request for early warning the risk of purchased financial products, or a request for early warning the risk after lending. After receiving the early warning request and acquiring the corresponding entity identifier, the executing body can acquire historical transaction data corresponding to the entity identifier. The historical transaction data may be transaction data of financial product purchase of the entity corresponding to the entity identifier for n months, for example, or loan data of the entity corresponding to the entity identifier for n months.
Step S202, carrying out fine granularity classification on the historical transaction data based on a preset dimension to obtain corresponding fine granularity.
The preset dimensions may include: a group enterprise risk event dimension, a major external risk event dimension, and a public and private linkage credit risk dimension.
The historical transaction data is matched with preset dimensions to determine which one or more of the preset dimensions corresponds to the historical transaction data, and one or more of the preset dimensions corresponding to the historical transaction data are determined to be fine-grained corresponding to the historical transaction data.
Step S203, extracting the high-level features and the low-level features in the corresponding historical transaction data based on the fine granularity.
For example, when the fine granularity (i.e., the major class of risk types) corresponding to the historical transaction data is the dimension of the risk items of the group enterprise, the high-level features in the extracted historical transaction data may be abstract existence check risks, the extracted low-level features may be mechanisms, check dates, check condition descriptions, numbers of confirmed risk floors under the group enterprise, names of confirmed risk floors, office of confirmed risk floors, numbers of loans of confirmed risk floors, balances of loans of confirmed risk floors, descriptions of check condition floors, high risk levels, preliminary confirmed existence risks by early warning check of the group enterprise, and types of monitoring objects are company classes.
For example, when the fine granularity corresponding to the historical transaction data is a major external risk item dimension, the high-level feature in the extracted historical transaction data may be an abstract major enterprise change risk, the extracted low-level feature may be a specific high-level management change flag, a stockholder change flag, a stock right change flag, an operation range change flag, an operation place change flag, a newly added external investment flag, a trusted executor flag, a low risk level, a risk item is a change risk, and a monitoring object type is a company type.
Step S204, corresponding entity portraits are generated according to the high-level features and the low-level features.
And taking the fine granularity corresponding to the historical transaction data as a primary entity tag, taking the high-level features and the low-level features corresponding to the fine granularity as a secondary entity tag subordinate to the primary entity tag, and generating a corresponding entity portrait according to the primary entity tag and the corresponding secondary entity tag.
Step S205, generating an early warning model according to entity portrait training, acquiring current transaction data corresponding to the entity identifier, generating early warning information according to the current transaction data and the early warning model, and sending the early warning information to a preset processing node.
The early warning model can also be used for representing the corresponding relation between the data and the risk level. The execution body may input the current transaction data to the early warning model to output a corresponding risk level, and when the output risk level exceeds a threshold, for example, when the output risk level is greater than one level, for example, the output risk level may be a secondary risk or a tertiary risk, early warning information is generated based on the output risk level and sent to a preset processing node, where the preset processing node may be a node corresponding to an offline processor. Therefore, the risk after the lending can be rapidly and accurately predicted, and the loss is reduced.
Fig. 3 is a schematic flow chart of an early warning method according to an embodiment of the present application, and as shown in fig. 3, the early warning method includes:
step S301, receiving an early warning request, obtaining a corresponding entity identifier, and further obtaining corresponding historical transaction data according to the entity identifier.
The early warning request can be a request for early warning the risk of purchased financial products, or a request for early warning the risk after lending. After receiving the early warning request and acquiring the corresponding entity identifier, the executing body can acquire historical transaction data corresponding to the entity identifier. The historical transaction data may be transaction data of financial product purchase of the entity corresponding to the entity identifier for n months, for example, or loan data of the entity corresponding to the entity identifier for n months.
Step S302, carrying out fine granularity classification on the historical transaction data based on the preset dimension to obtain corresponding fine granularity.
The preset dimensions may include: a group enterprise risk event dimension, a major external risk event dimension, an external judicial litigation dimension, an environmental protection violation administrative penalty dimension, a financial condition exception dimension, an operating condition exception dimension, an associated personal credit violation dimension such as a legal representative real person, a frozen dimension for public to private customers or accounts, a checked dimension for public to private customers or accounts, an incorporated enterprise-level blacklist dimension, a transitional liability or financing dimension, an abnormal dimension for public financial data, and the like.
The historical transaction data is matched with preset dimensions to determine which one or more of the preset dimensions corresponds to the historical transaction data, and one or more of the preset dimensions corresponding to the historical transaction data are determined to be fine-grained corresponding to the historical transaction data.
Step S303, extracting the high-level features and the low-level features in the corresponding historical transaction data based on the fine granularity.
For example, when the fine granularity corresponding to the historical transaction data is a public-private linkage credit risk dimension, the high-level feature in the extracted historical transaction data may be an abstract risk of surrendering a public loan, the low-level feature may be a specific mark for a public client agency name, a public client agency code, a public client name, a public client number, a loan account number, a loan issue date, a credit amount, a loan balance, a delinquent day, a public client agency name, a public client agency code, a public client name, a public client number, a blacklist type, a blacklist inclusion date, a public bad loan balance, a credit report date, a public overdue loan balance, a credit report date, a risk item being a mark for exceeding 10 days of overdue to the public client, a risk level being high, and the type of the monitored object being a company type.
Step S304, corresponding entity portraits are generated according to the high-level features and the low-level features.
And fusing the high-level features and the low-level features corresponding to the fine grains to obtain corresponding fusion features by taking the fine grains corresponding to the historical transaction data as primary entity tags, taking the fusion features as secondary entity tags subordinate to the primary entity tags, and generating corresponding entity portraits according to the primary entity tags and the corresponding secondary entity tags.
Step S305, generating an early warning model according to entity portrait training, and acquiring current transaction data corresponding to the entity identifier.
Step S306, determining the number of risk items corresponding to the current transaction data.
For example, where the fine granularity corresponding to the current transaction data is a corporate linkage credit risk dimension, the corresponding risk items include: the method comprises the steps of conducting 7 risk items of default risks on public loans, conducting default personal credit of associated persons such as legal representatives/real control persons and the like, conducting freezing on public-private customers or accounts, conducting checking on public-private customers or accounts, being incorporated into an enterprise-level blacklist, conducting excessive liabilities or financing, conducting abnormal public financial data, namely, when the fine granularity corresponding to current transaction data is a company linkage credit risk dimension, and the number of corresponding risk items is 7.
Step S307, generating early warning information according to the number and the corresponding risk items.
And generating early warning information with the same quantity as the number of the risk items according to the specific risk items. For example, the current transaction data has risk event 1 and risk event 2. Then the early warning information 1 corresponding to the risk item 1 and the early warning information 2 corresponding to the risk item 2 are generated. And outputting early warning information 1 and early warning information 2.
Step S308, the early warning information is sent to a preset processing node.
Generating early warning information according to the current transaction data and the early warning model, and sending the early warning information to a preset processing node. And sending the early warning information 1 and the early warning information 2 to a preset processing node, wherein the preset processing node can be a node corresponding to a risk processing person. Therefore, the accuracy of information early warning can be improved, and the processing speed of the generated early warning information can be improved.
Fig. 4 is a schematic diagram of an application scenario of an early warning method according to an embodiment of the present application. The early warning method provided by the embodiment of the application is applied to an information early warning scene. As shown in fig. 4, when one development enterprise exists corresponding to item 1, item 2, and item 3, where item 1 exists a risk item 1, and item 2 exists a risk item 1 and a risk item 2. The final data output may be: item 1 corresponds output early warning information 1 and early warning information 2, wherein, early warning information 1: risk item 1, building project 1, development enterprise a, and business. Early warning information 2: risk item 2, building project 1, development enterprise a, and business. Item 2 outputs an early warning message as: risk item 1, building project 1, development enterprise a, and business. Enterprise suspicious points can be evaluated with as few fields as possible, and labor cost of business personnel is reduced.
The application completes the data extraction and processing process through the technologies of storage process, SQL, SHELL, distributed database and the like, and realizes the back-end interface and front-end interface to provide the suspicious point data for post-credit early warning service personnel for operation through the cooperation of Java language and SpringMVC and Mybatis framework.
Taking a real estate development enterprise with potential risks as an example, firstly, a building inventory to be checked needs to be carded: the embodiment of the application can provide a development enterprise selection scheme based on loan business conditions of real estate development enterprises in target units, can screen more suspicious point developer enterprises by using smaller resources, and improves the efficiency. Searching a list of cooperative building items in the lending system, and removing the completed acceptance items or the items with stage warranty periods to form a list of cooperative items. In order to improve the efficiency, only the projects with the number of the stock loan being more than or equal to 20, the newly added loan being issued in the last two years, the officially mortgage ratio of the stock loan being less than 90% and the current non-cooperation expiration date are monitored. The collaborative real estate development enterprise information is then found through the inventory of building projects. And generating a credit collaborative development enterprise list according to the collaborative project list summary. And finally searching all related enterprises through collaborative development enterprise information. And generating a to-be-monitored collaborative development enterprise association enterprise list. The specific steps of the selection of the associated enterprises are as follows: whether the development enterprise is in the basic association relation tree of the unit individual loan system 'partner group list library', if so, the enterprise or the individual with the following A, B, C type association relation is selected.
A. The stock right and control class comprises full fund, control and third party control relation. On the one hand, if the investment ratio of enterprises invested in the enterprises exceeds 50% or the investment ratio of the enterprises invested in the enterprises is 3 stakeholders in front of the position list, the invested enterprises are screened out; on the other hand, if the investment ratio of the stakeholder is more than 50% or the first 3 large stakeholders are located, the major stakeholders of the collaborative house enterprise (as the invested enterprise) are screened out (the stakeholder controlling range includes the corporate stakeholders and the natural corporate stakeholders).
B. Guarantee class including guarantee, mortgage, and guarantee deposit. Only the enterprises guaranteed by the cooperated house enterprises are used as the associated enterprises, and the guaranteed relationship is not taken.
C. Group association class. And selecting ancestor nodes step by step upwards in the enterprise group membership tree to which the cooperation enterprise belongs until reaching the top node. And selecting all the offspring nodes step by step downwards in the enterprise group membership tree to which the cooperation enterprise belongs until reaching each node at the bottommost layer.
Searching natural person associated person information through a collaborative development enterprise and associated enterprise list: the real estate development enterprises have the characteristics of huge fund amount, longer service period, more service flows and links, more and trivial service related supply chains, easiness in influence of various external factors and the like, and in order to discover the real estate development enterprises with potential risks, the embodiment of the application introduces the influence of related persons of the real estate development enterprises on the risks of the real estate development enterprises.
According to the embodiment of the application, three kinds of related persons, namely an actual control person, a legal representative person and a stockholder of a first 3 large-control natural person, related to enterprises are screened through the collaborative development enterprise list and the collaborative development enterprise related enterprise list, and a private client list to be checked is generated. And acquiring corresponding current transaction data from the private client list according to the generated to-be-checked, and further generating early warning information to perform early warning according to the current transaction data and the early warning model. The early warning device can quickly and accurately early warn the risky clients to avoid loss. The accuracy and recall rate of real estate early warning service can be improved, and loss caused by failure of timely identifying risks of real estate development enterprises in loan service is avoided.
Fig. 5 is a schematic diagram of main units of the early warning device according to the embodiment of the application. As shown in fig. 5, the early warning apparatus 500 includes a receiving unit 501, a fine granularity determining unit 502, an entity representation generating unit 503, and an early warning unit 504.
The receiving unit 501 is configured to receive the early warning request, obtain the corresponding entity identifier, and further obtain the corresponding historical transaction data according to the entity identifier.
The fine granularity determining unit 502 is configured to classify the historical transaction data into fine granularity based on a preset dimension to obtain the corresponding fine granularity.
The entity representation generation unit 503 is configured to generate a corresponding entity representation based on the fine granularity.
The early warning unit 504 is configured to generate an early warning model according to entity portrait training, acquire current transaction data corresponding to the entity identifier, generate early warning information according to the current transaction data and the early warning model, and send the early warning information to a preset processing node.
In some embodiments, the fine granularity determination unit 502 is further configured to: the historical transaction data is input into a classification model to output fine-grained classifications corresponding to the preset dimensions.
In some embodiments, entity representation generation unit 503 is further configured to: extracting high-level features and low-level features in corresponding historical transaction data based on fine granularity; and generating corresponding entity portraits according to the high-level features and the low-level features.
In some embodiments, entity representation generation unit 5033 is further configured to: determining a corresponding risk level according to the fine granularity; and generating a corresponding entity portrait according to the risk level, the fine granularity and the preset monitoring object type.
In some embodiments, the pre-warning unit 504 is further configured to: acquiring an initial neural network model; acquiring a training sample set, wherein the training sample set is configured into an entity portrait and early warning information corresponding to the entity portrait; and taking the entity portraits as input of an initial neural network model, taking early warning information corresponding to the entity portraits as expected output, and training the initial neural network model to obtain an early warning model.
In some embodiments, the pre-warning unit 504 is further configured to: generating a current transaction representation based on the current transaction data; and inputting the current transaction portrait to the early warning model for analysis, generating early warning information and outputting the early warning information in response to the corresponding risk items of the analysis result corresponding to the current transaction portrait.
In some embodiments, the pre-warning unit 504 is further configured to: determining the number of risk items corresponding to the current transaction data; and generating early warning information according to the quantity and the corresponding risk items.
It should be noted that, the early warning method and the early warning device of the present application have a corresponding relationship in the specific implementation content, so the repeated content will not be described.
Fig. 6 illustrates an exemplary system architecture 600 in which the early warning method or apparatus of embodiments of the present application may be applied.
As shown in fig. 6, the system architecture 600 may include terminal devices 601, 602, 603, a network 604, and a server 605. The network 604 is used as a medium to provide communication links between the terminal devices 601, 602, 603 and the server 605. The network 604 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
A user may interact with the server 605 via the network 604 using the terminal devices 601, 602, 603 to receive or send messages, etc. Various communication client applications such as shopping class applications, web browser applications, search class applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only) may be installed on the terminal devices 601, 602, 603.
The terminal devices 601, 602, 603 may be various electronic devices having an early warning processing screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.
The server 605 may be a server providing various services, such as a background management server (by way of example only) that provides support for early warning requests submitted by users using the terminal devices 601, 602, 603. The background management server can receive the early warning request, acquire the corresponding entity identifier, and further acquire the corresponding historical transaction data according to the entity identifier; carrying out fine granularity classification on historical transaction data based on a preset dimension to obtain corresponding fine granularity; generating a corresponding entity portrait based on the fine granularity; generating an early warning model according to entity portrait training, acquiring current transaction data corresponding to the entity identifier, generating early warning information according to the current transaction data and the early warning model, and sending the early warning information to a preset processing node. Therefore, the risk after the lending can be accurately predicted, and the loss is reduced.
It should be noted that, the early warning method provided in the embodiment of the present application is generally executed by the server 605, and accordingly, the early warning device is generally disposed in the server 605.
It should be understood that the number of terminal devices, networks and servers in fig. 6 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 7, there is illustrated a schematic diagram of a computer system 700 suitable for use in implementing an embodiment of the present application. The terminal device shown in fig. 7 is only an example, and should not impose any limitation on the functions and the scope of use of the embodiment of the present application.
As shown in fig. 7, the computer system 700 includes a Central Processing Unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM703, various programs and data required for the operation of the computer system 700 are also stored. The CPU701, ROM702, and RAM703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
The following components are connected to the I/O interface 705: an input section 706 including a keyboard, a mouse, and the like; an output section 707 including a Cathode Ray Tube (CRT), a liquid crystal credit authorization query processor (LCD), and the like, and a speaker, and the like; a storage section 708 including a hard disk or the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. The drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read therefrom is mounted into the storage section 708 as necessary.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 709, and/or installed from the removable medium 711. The above-described functions defined in the system of the present application are performed when the computer program is executed by a Central Processing Unit (CPU) 701.
The computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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. In the context of this document, a computer 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. In the present application, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer 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 computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present application may be implemented in software or in hardware. The described units may also be provided in a processor, for example, described as: a processor includes a receiving unit, a fine granularity determining unit, an entity representation generating unit, and an early warning unit. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.
As another aspect, the present application also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be present alone without being fitted into the device. The computer readable medium carries one or more programs, and when the one or more programs are executed by one device, the device receives an early warning request, acquires a corresponding entity identifier, and further acquires corresponding historical transaction data according to the entity identifier; carrying out fine granularity classification on historical transaction data based on a preset dimension to obtain corresponding fine granularity; generating a corresponding entity portrait based on the fine granularity; generating an early warning model according to entity portrait training, acquiring current transaction data corresponding to the entity identifier, generating early warning information according to the current transaction data and the early warning model, and sending the early warning information to a preset processing node.
The computer program product of the present application comprises a computer program which, when executed by a processor, implements the pre-warning method of the embodiments of the present application.
According to the technical scheme provided by the embodiment of the application, the risk after the lending can be accurately prejudged, and the loss is reduced.
The above embodiments do not limit the scope of the present application. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives can occur depending upon design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of the present application.
Claims (16)
1. An early warning method is characterized by comprising the following steps:
receiving an early warning request, acquiring a corresponding entity identifier, and further acquiring corresponding historical transaction data according to the entity identifier;
carrying out fine granularity classification on the historical transaction data based on a preset dimension to obtain corresponding fine granularity;
based on the fine granularity, generating a corresponding entity portrait;
generating an early warning model according to the entity portrait training, acquiring current transaction data corresponding to the entity identifier, generating early warning information according to the current transaction data and the early warning model, and sending the early warning information to a preset processing node.
2. The method of claim 1, wherein the fine-grained classification of the historical transaction data based on a preset dimension comprises:
And inputting the historical transaction data into a classification model to output fine-grained classification corresponding to a preset dimension.
3. The method of claim 1, wherein generating the corresponding physical representation based on the fine granularity comprises:
extracting high-level features and low-level features in corresponding historical transaction data based on the fine granularity;
and generating a corresponding entity portrait according to the high-level features and the low-level features.
4. The method of claim 1, wherein generating the corresponding physical representation based on the fine granularity comprises:
determining a corresponding risk level according to the fine granularity;
and generating a corresponding entity portrait according to the risk level, the fine granularity and the preset monitoring object type.
5. The method of claim 1, wherein generating an early warning model from the physical representation training comprises:
acquiring an initial neural network model;
acquiring a training sample set, wherein the training sample set comprises the entity portrait and early warning information corresponding to the entity portrait;
and taking the entity portrait as the input of the initial neural network model, taking the early warning information corresponding to the entity portrait as the expected output, and training the initial neural network model to obtain an early warning model.
6. The method of claim 1, wherein generating pre-warning information based on the current transaction data and the pre-warning model comprises:
generating a current transaction portrait based on the current transaction data;
and inputting the current transaction portrait to an early warning model for analysis, generating early warning information and outputting the early warning information in response to the corresponding risk items of the analysis result corresponding to the current transaction portrait.
7. The method of claim 1, wherein generating the pre-warning information comprises:
determining the number of risk items corresponding to the current transaction data;
and generating early warning information according to the number and the corresponding risk items.
8. An early warning device, characterized by comprising:
the receiving unit is configured to receive the early warning request, acquire a corresponding entity identifier and further acquire corresponding historical transaction data according to the entity identifier;
a fine granularity determining unit configured to classify the historical transaction data based on a preset dimension to obtain a corresponding fine granularity;
an entity representation generation unit configured to generate a corresponding entity representation based on the fine granularity;
The early warning unit is configured to generate an early warning model according to the entity portrait training, acquire current transaction data corresponding to the entity identifier, generate early warning information according to the current transaction data and the early warning model, and send the early warning information to a preset processing node.
9. The apparatus of claim 8, wherein the fine particle size determination unit is further configured to:
and inputting the historical transaction data into a classification model to output fine-grained classification corresponding to a preset dimension.
10. The apparatus of claim 8, wherein the entity representation generation unit is further configured to:
extracting high-level features and low-level features in corresponding historical transaction data based on the fine granularity;
and generating a corresponding entity portrait according to the high-level features and the low-level features.
11. The apparatus of claim 8, wherein the entity representation generation unit is further configured to:
determining a corresponding risk level according to the fine granularity;
and generating a corresponding entity portrait according to the risk level, the fine granularity and the preset monitoring object type.
12. The apparatus of claim 8, wherein the pre-warning unit is further configured to:
acquiring an initial neural network model;
acquiring a training sample set, wherein the training sample set is configured to be the entity portrait and the early warning information corresponding to the entity portrait;
and taking the entity portrait as the input of the initial neural network model, taking the early warning information corresponding to the entity portrait as the expected output, and training the initial neural network model to obtain an early warning model.
13. The apparatus of claim 8, wherein the pre-warning unit is further configured to:
generating a current transaction portrait based on the current transaction data;
and inputting the current transaction portrait to an early warning model for analysis, generating early warning information and outputting the early warning information in response to the corresponding risk items of the analysis result corresponding to the current transaction portrait.
14. An early warning electronic device, comprising:
one or more processors;
storage means for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-7.
15. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-7.
16. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211534886.9A CN116703555A (en) | 2022-12-02 | 2022-12-02 | Early warning method, early warning device, electronic equipment and computer readable medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211534886.9A CN116703555A (en) | 2022-12-02 | 2022-12-02 | Early warning method, early warning device, electronic equipment and computer readable medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116703555A true CN116703555A (en) | 2023-09-05 |
Family
ID=87843992
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211534886.9A Pending CN116703555A (en) | 2022-12-02 | 2022-12-02 | Early warning method, early warning device, electronic equipment and computer readable medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116703555A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118052558A (en) * | 2024-04-15 | 2024-05-17 | 万联易达物流科技有限公司 | Wind control model decision method and system based on artificial intelligence |
-
2022
- 2022-12-02 CN CN202211534886.9A patent/CN116703555A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118052558A (en) * | 2024-04-15 | 2024-05-17 | 万联易达物流科技有限公司 | Wind control model decision method and system based on artificial intelligence |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109564668A (en) | Electronics mortgage manager and monitoring | |
US20150154520A1 (en) | Automated Data Breach Notification | |
CN112184012A (en) | Enterprise risk early warning method, device, equipment and readable storage medium | |
CN111598713B (en) | Cluster recognition method and device based on similarity weight updating and electronic equipment | |
CN115422173A (en) | Data management method and system in financial credit field | |
US20130332374A1 (en) | Fraud prevention for real estate transactions | |
CN111210109A (en) | Method and device for predicting user risk based on associated user and electronic equipment | |
CN113139869A (en) | Credit investigation authorization query processing method and device | |
CN112241915A (en) | Loan product generation method and device | |
CN111414490A (en) | Method and device for determining lost connection restoration information, electronic equipment and storage medium | |
CN116703555A (en) | Early warning method, early warning device, electronic equipment and computer readable medium | |
CN117575775A (en) | Service risk detection method, device, equipment and storage medium | |
CN110991992B (en) | Processing method and device of business process information, storage medium and electronic equipment | |
CN115731028A (en) | Early warning method, early warning device, electronic equipment and computer readable medium | |
CN116051266A (en) | Loan data supervision method and device | |
CN110610290A (en) | Inter-connected merchant risk control method and system | |
CN113962817B (en) | Abnormal person identification method and device, electronic equipment and storage medium | |
CN115982241A (en) | Data processing method and device, electronic equipment and computer readable medium | |
CN115994819A (en) | Risk customer identification method, apparatus, device and medium | |
CN115795345A (en) | Information processing method, device, equipment and storage medium | |
CN115482094A (en) | Service processing method and device, electronic equipment and computer readable medium | |
CN114493853A (en) | Credit rating evaluation method, credit rating evaluation device, electronic device and storage medium | |
CN111429257B (en) | Transaction monitoring method and device | |
CN109377378B (en) | Industry relevancy risk determination device and system | |
CN112598499A (en) | Method and device for determining credit limit |
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 |