CN114881765A - Credit item risk identification method and device - Google Patents
Credit item risk identification method and device Download PDFInfo
- Publication number
- CN114881765A CN114881765A CN202210550953.XA CN202210550953A CN114881765A CN 114881765 A CN114881765 A CN 114881765A CN 202210550953 A CN202210550953 A CN 202210550953A CN 114881765 A CN114881765 A CN 114881765A
- Authority
- CN
- China
- Prior art keywords
- credit
- green
- identified
- item
- project
- 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
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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Abstract
The invention provides a credit high-risk project identification method and a credit high-risk project identification device, which can be applied to the field of artificial intelligence or the field of finance.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a credit project risk identification method and device.
Background
In recent years, the development of green finance is greatly promoted in China, wherein the green finance refers to financial services provided for project investment and financing, project operation, risk management and the like in the fields of environmental protection, energy conservation, clean energy, green traffic, green buildings and the like, and the economic activities are used for supporting environment improvement, coping with climate change and saving resources and efficiently utilizing the resources.
At present, banks generally adopt the mode of subjective judgement to discern green financial project, and the error rate is high, and the bank generally can not effectively discern whether this green financial project has the risk after discerning green financial project.
Disclosure of Invention
In view of the above, the invention provides a credit item risk identification method and device, which can automatically identify a green credit item and realize accurate identification of credit item risks to be identified.
In order to achieve the above purpose, the invention provides the following specific technical scheme:
a method of risk identification of a credit item, comprising:
acquiring a credit item to be identified;
calling a pre-constructed green credit project identification model, and judging whether the credit project to be identified is a green credit project or not;
if the credit project to be identified is a green credit project, matching a pre-constructed risk keyword library with the information of the credit project to be identified to obtain a risk matching degree;
and if the risk matching degree is smaller than a preset standard value, determining that the credit item to be identified is not a high-risk credit item.
Optionally, constructing the green credit item identification model comprises:
acquiring all characters in a green credit project requirement file;
extracting high-frequency keywords in all characters in the green credit project requirement file;
matching the information of each industry type with the high-frequency keywords to obtain the matching degree of each industry type;
adding the industry type with a matching degree greater than a threshold value into a green industry type list in the green credit project identification model.
Optionally, the invoking a pre-constructed green credit item identification model, and determining whether the credit item to be identified is a green credit item, includes:
acquiring the industry type of the credit project to be identified;
judging whether the industry type of the credit project to be identified belongs to is in a green industry type list in the green credit project identification model;
if the credit item to be identified is in the green industry type list, determining that the credit item to be identified is a green credit item;
and if the credit item to be identified is not in the green industry type list, determining that the credit item to be identified is not a green credit item.
Optionally, constructing the green industry mapping model includes:
acquiring all characters in a green credit project requirement file;
extracting high-frequency keywords in all characters in the green credit project requirement file;
adding the high frequency keyword to the green credit item identification model.
Optionally, the invoking a pre-constructed green credit item identification model, and determining whether the credit item to be identified is a green credit item, includes:
matching the information of the credit project to be identified with the high-frequency keywords in the green credit project identification model to obtain green project matching degree;
if the matching degree of the green item is larger than a threshold value, determining that the credit item to be identified is a green credit item;
and if the green item matching degree is not greater than the threshold value, determining that the credit item to be identified is not a green credit item.
Optionally, constructing the risk keyword library includes:
obtaining environmental security violation information and eliminating out-dated capacity information;
and extracting the environmental security violation information and the risk keywords in the obsolete backward productivity information to form the risk keyword library.
Optionally, the method further includes:
acquiring a plurality of historical high-risk credit item information;
matching each piece of historical high-risk credit project information with the risk keyword library respectively to obtain the risk matching degree of each historical high-risk credit project;
and determining the risk matching degree of a plurality of historical high-risk credit items as the standard value.
A risk identification apparatus for a credit item, comprising:
the credit item identification unit is used for identifying a credit item to be identified;
the green credit item determination unit is used for calling a pre-constructed green credit item identification model and determining whether the credit item to be identified is a green credit item;
the risk identification unit is used for matching a pre-constructed risk keyword library with the information of the credit project to be identified to obtain a risk matching degree if the credit project to be identified is a green credit project; and if the risk matching degree is smaller than a preset standard value, determining that the credit item to be identified is not a high-risk credit item.
Optionally, the apparatus further comprises a green credit item identification model construction unit, specifically configured to:
acquiring all characters in a green credit project requirement file;
extracting high-frequency keywords in all characters in the green credit project requirement file;
matching the information of each industry type with the high-frequency keywords to obtain the matching degree of each industry type;
adding the industry type with a matching degree greater than a threshold value into a green industry type list in the green credit project identification model.
Optionally, the green credit item determination unit is specifically configured to:
acquiring the industry type of the credit project to be identified;
judging whether the industry type of the credit project to be identified belongs to is in a green industry type list in the green credit project identification model;
if the credit item to be identified is in the green industry type list, determining that the credit item to be identified is a green credit item;
and if the credit item to be identified is not in the green industry type list, determining that the credit item to be identified is not a green credit item.
Optionally, the apparatus further comprises a green credit item identification model construction unit, specifically configured to:
acquiring all characters in a green credit project requirement file;
extracting high-frequency keywords in all characters in the green credit project requirement file;
adding the high frequency keyword to the green credit item identification model.
Optionally, the green credit item determination unit is specifically configured to:
matching the information of the credit project to be identified with the high-frequency keywords in the green credit project identification model to obtain green project matching degree;
if the matching degree of the green item is greater than a threshold value, determining that the credit item to be identified is a green credit item;
and if the green item matching degree is not greater than the threshold value, determining that the credit item to be identified is not a green credit item.
Optionally, the apparatus further comprises:
the risk keyword library construction unit is used for acquiring environmental security violation information and eliminating out-dated capacity information; and extracting the environmental security violation information and the risk keywords in the obsolete backward productivity information to form the risk keyword library.
Optionally, the apparatus further comprises:
a standard value determination unit for acquiring a plurality of historical high-risk credit item information; matching each piece of historical high-risk credit project information with the risk keyword library respectively to obtain the risk matching degree of each historical high-risk credit project; and determining the risk matching degree of a plurality of historical high-risk credit items as the standard value.
Compared with the prior art, the invention has the following beneficial effects:
the invention discloses a credit project risk identification method and a credit project risk identification device, which are characterized in that whether a credit project to be identified is a green credit project is judged through a pre-constructed green credit project identification model, preliminary screening of the credit project to be identified is realized, the green credit project is automatically identified, and under the condition that the credit project to be identified is the green credit project, a pre-constructed risk keyword library is matched with information of the credit project to be identified, the credit project to be identified is further screened, and accurate identification of the credit project risk to be identified is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart illustrating a method for risk identification of credit projects according to an embodiment of the present invention;
FIG. 2 is a partial flow diagram of a credit item risk identification method according to an embodiment of the present invention;
FIG. 3 is a partial flow diagram of a credit item risk identification method according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a credit item risk identification apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a credit project risk identification method, which is used for automatically identifying a green credit project, further screening the credit project to be identified under the condition that the credit project to be identified is the green credit project, realizing accurate identification of the credit project risk to be identified and improving the intelligent level of judging the green credit project and the high-risk credit project.
Specifically, referring to fig. 1, the method for identifying a risk of a credit project disclosed in this embodiment includes the following steps:
s101: acquiring a credit item to be identified;
the credit items to be identified are the credit items to be processed submitted by the customers, and the credit items to be identified comprise the industry types, the item information and the like.
The type of the industry to which the credit project to be identified belongs may be a new energy industry, such as photovoltaic power generation, wind power generation, and the like, and the type of the industry to which the credit project to be identified belongs may be a traditional energy industry, such as coal, petroleum, and the like, which are only examples, and the invention is not limited thereto.
S102: calling a pre-constructed green credit project identification model, and judging whether the credit project to be identified is a green credit project or not;
the green credit term identification model may be implemented in a variety of ways, as set forth below by way of a few examples.
Example 1
The green credit project identification model comprises a green industry type list, the industry type of the credit project to be identified is obtained, then whether the industry type of the credit project to be identified is in the green industry type list in the green credit project identification model or not is judged, and if the industry type of the credit project to be identified is in the green industry type list, the credit project to be identified is determined to be a green credit project; if not, determining that the credit item to be identified is not a green credit item.
The method for identifying the green credit item is relatively quick in application, and whether the credit item to be identified is the green credit item can be quickly judged according to the industry type of the credit item to be identified. But in the past it was necessary to build a green industry type list in the green credit project identification model.
Specifically, referring to FIG. 2, a green credit term identification model is constructed, including:
s201: acquiring all characters in a green credit project requirement file;
the green credit program requirement file may be a pedestrian green credit statistics system file and/or a bank prison green financing statistics requirement file. If the green credit project requires the text type of the file which is convenient for subsequent processing, the text recognition processing is not carried out, and if the green credit project requires the file to be the file which is inconvenient for subsequent processing, such as an image, a PDF file and the like, all characters in the green credit project requiring file need to be recognized by using an optical character recognition method.
S202: extracting high-frequency keywords in all characters in the green credit project requirement file;
the specific algorithm may be a TF-IDF algorithm.
S203: matching the information of each industry type with the high-frequency keywords to obtain the matching degree of each industry type;
s204: adding the industry type with the matching degree larger than the threshold value into a green industry type list in the green credit item identification model.
The matching degree is a ratio of the number of the high-frequency keywords matched by the industry type information to the total number of the high-frequency keywords, the threshold value may be set based on experience, or may be set based on historical experimental data, for example, if the matching degree of the information of the determined green industry type in the historical data and the high-frequency keywords is obtained, the minimum value, the average value, or the median of the matching degree may be set as the threshold value according to actual requirements, which is not specifically limited herein.
Example two
The green credit item identification model comprises high-frequency keywords of the green credit item, calls a pre-constructed green credit item identification model, and judges whether the credit item to be identified is a green credit item, and specifically comprises the following steps: matching the information of the credit project to be identified with the high-frequency keywords in the green credit project identification model to obtain a green project matching degree, and if the green project matching degree is greater than a threshold value, determining the credit project to be identified as a green credit project; and if the green item matching degree is not greater than the threshold value, determining that the credit item to be identified is not a green credit item. And the green item matching degree is the ratio of the number of the high-frequency keywords matched with the credit item information to be identified to the total number of the high-frequency keywords.
The method for identifying the green credit item has higher accuracy in application, and can accurately judge whether the credit item to be identified is the green credit item according to the specific condition of the credit item to be identified.
Constructing a green industry mapping model, comprising: and acquiring all characters in the green credit project requirement file, extracting high-frequency keywords in all the characters in the green credit project requirement file, and adding the high-frequency keywords into the green credit project identification model. The method for extracting the high-frequency keywords in all the characters in the green credit item requirement file is consistent with the principle of the first example, and is not repeated here.
Example three
The green credit project identification model is a machine learning model, such as a neural network model, the characteristic data of the credit project to be identified is input into the green credit project identification model, and whether the credit project to be identified is the green credit project or not is judged according to the identification result of the model.
The green credit project recognition model needs to be trained in advance, training samples come from determined green credit projects in historical data, feature data of the green credit projects are extracted, such as industry types and the like, to obtain the training samples, the feature data can be set according to experience, and the feature data can also be determined by analyzing the correlation between the feature data and recognition results through a naive Bayesian algorithm. And training the machine learning model by using the training samples to obtain a green credit item identification model.
If the credit item to be identified is not a green credit item, executing S103: processing the credit item to be identified according to the processing flow of the non-green credit item;
the processing flow of the non-green credit project can be the same as that of the prior art, and can also be set according to the actual application scene, and the invention is not particularly limited.
If the credit item to be identified is a green credit item, executing S104: matching the pre-constructed risk keyword library with the information of the credit project to be identified to obtain a risk matching degree;
the risk matching degree is the ratio of the number of the risk keywords matched with the information of the credit item to be identified to the total number of the risk keywords.
Wherein, the construction of the risk keyword library comprises the following steps: the method comprises the steps of automatically capturing information related to environmental security violation and information of eliminated capacity behind released by a supervision department by utilizing other technologies such as web crawlers and the like, and then extracting risk keywords in the information related to environmental security violation and the information of eliminated capacity behind, wherein a specific algorithm can be a TF-IDF algorithm. In order to improve the accuracy and comprehensiveness of the risk keywords, unreasonable risk keywords can be removed and supplemented in a manual review mode, and finally extracted risk keywords form a risk keyword library.
S105: judging whether the risk matching degree is smaller than a preset standard value or not;
referring to fig. 3, the setting method of the standard value is as follows:
s301: acquiring a plurality of historical high-risk credit item information;
s302: matching each history high-risk credit item information with a risk keyword library respectively to obtain the risk matching degree of each history high-risk credit item;
s303: and determining the risk matching degree according to a plurality of historical high-risk credit items as a standard value.
The minimum value, the average value, or the median of the matching degree may be set as a threshold according to actual requirements, and is not specifically limited herein. Along with the continuous accumulation of historical high-risk credit projects, the standard value can be continuously updated, so that the identification precision of the high-risk credit projects is improved.
If the risk matching degree is smaller than the preset standard value, executing S106: determining that the credit item to be identified is not a high risk credit item;
if the risk matching degree is not less than the preset standard value, executing S107: the credit item to be identified is determined to be a high risk credit item.
And under the condition that the credit project to be identified is determined to be a high-risk credit project, sending alarm information to prompt the user that the credit project to be identified is the high-risk credit project.
It can be seen that in the credit high-risk project identification method disclosed in this embodiment, through a pre-constructed green credit project identification model, it is determined whether a credit project to be identified is a green credit project, preliminary screening of the credit project to be identified is implemented, the green credit project is automatically identified, and in the case that the credit project to be identified is the green credit project, the credit project to be identified is further screened by matching the pre-constructed risk keyword library with information of the credit project to be identified, so as to implement accurate identification of the risk of the credit project to be identified.
Based on the above-mentioned risk identification method for credit projects disclosed in the embodiments, the present embodiment correspondingly discloses a risk identification apparatus for credit projects, please refer to fig. 4, the apparatus includes:
an item to be identified acquisition unit 401 for acquiring a credit item to be identified;
a green credit item determination unit 402, configured to invoke a pre-constructed green credit item identification model, and determine whether the credit item to be identified is a green credit item;
the risk identification unit 403 is configured to, if the credit project to be identified is a green credit project, match a pre-constructed risk keyword library with information of the credit project to be identified to obtain a risk matching degree; and if the risk matching degree is smaller than a preset standard value, determining that the credit item to be identified is not a high-risk credit item.
Optionally, the apparatus further comprises a green credit item identification model construction unit, specifically configured to:
acquiring all characters in a green credit project requirement file;
extracting high-frequency keywords in all characters in the green credit project requirement file;
matching the information of each industry type with the high-frequency keywords to obtain the matching degree of each industry type;
adding the industry type with a matching degree greater than a threshold value into a green industry type list in the green credit project identification model.
Optionally, the green credit item determination unit 402 is specifically configured to:
acquiring the industry type of the credit project to be identified;
judging whether the industry type of the credit project to be identified belongs to is in a green industry type list in the green credit project identification model;
if the credit item to be identified is in the green industry type list, determining that the credit item to be identified is a green credit item;
and if the credit item to be identified is not in the green industry type list, determining that the credit item to be identified is not a green credit item.
Optionally, the apparatus further comprises a green credit item identification model construction unit, specifically configured to:
acquiring all characters in a green credit project requirement file;
extracting high-frequency keywords in all characters in the green credit project requirement file;
adding the high frequency keyword to the green credit item identification model.
Optionally, the green credit item determination unit 402 is specifically configured to:
matching the information of the credit project to be identified with the high-frequency keywords in the green credit project identification model to obtain green project matching degree;
if the matching degree of the green item is greater than a threshold value, determining that the credit item to be identified is a green credit item;
and if the green item matching degree is not greater than the threshold value, determining that the credit item to be identified is not a green credit item.
Optionally, the apparatus further comprises:
the risk keyword library construction unit is used for acquiring environmental security violation information and eliminating out-dated capacity information; and extracting the environmental security violation information and the risk keywords in the eliminated backward productivity information to form the risk keyword library.
Optionally, the apparatus further comprises:
a standard value determination unit for acquiring a plurality of historical high-risk credit item information; matching each piece of historical high-risk credit project information with the risk keyword library respectively to obtain the risk matching degree of each historical high-risk credit project; and determining the risk matching degree according to a plurality of historical high-risk credit projects as the standard value.
The credit project risk identification device disclosed by the embodiment judges whether a credit project to be identified is a green credit project through a green credit project identification model which is constructed in advance, realizes preliminary screening of the credit project to be identified, automatically identifies the green credit project, and realizes accurate identification of the credit project risk to be identified by matching a risk keyword library constructed in advance with information of the credit project to be identified under the condition that the credit project to be identified is the green credit project.
It should be noted that the credit high-risk item identification method and device provided by the invention can be applied to the field of artificial intelligence or the field of finance. The above description is only an example, and does not limit the application field of the credit high-risk item identification method and apparatus provided by the present invention.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above embodiments can be combined arbitrarily, and the features described in the embodiments in the present specification can be replaced or combined with each other in the above description of the disclosed embodiments, so that those skilled in the art can implement or use the present application.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for risk identification of a credit item, comprising:
acquiring a credit item to be identified;
calling a pre-constructed green credit project identification model, and judging whether the credit project to be identified is a green credit project or not;
if the credit project to be identified is a green credit project, matching a pre-constructed risk keyword library with the information of the credit project to be identified to obtain a risk matching degree;
and if the risk matching degree is smaller than a preset standard value, determining that the credit item to be identified is not a high-risk credit item.
2. The method of claim 1 wherein building the green credit item identification model comprises:
acquiring all characters in a green credit project requirement file;
extracting high-frequency keywords in all characters in the green credit project requirement file;
matching the information of each industry type with the high-frequency keywords to obtain the matching degree of each industry type;
adding the industry type with a matching degree greater than a threshold value into a green industry type list in the green credit project identification model.
3. The method of claim 2 wherein said invoking a pre-built green credit term identification model to determine whether the credit term to be identified is a green credit term comprises:
acquiring the industry type of the credit project to be identified;
judging whether the industry type of the credit project to be identified belongs to is in a green industry type list in the green credit project identification model;
if the credit item to be identified is in the green industry type list, determining that the credit item to be identified is a green credit item;
and if the credit item to be identified is not in the green industry type list, determining that the credit item to be identified is not a green credit item.
4. The method of claim 1, wherein constructing the green industry mapping model comprises:
acquiring all characters in a green credit project requirement file;
extracting high-frequency keywords in all characters in the green credit project requirement file;
adding the high frequency keyword to the green credit item identification model.
5. The method of claim 4 wherein said invoking a pre-built green credit item identification model to determine whether said credit item to be identified is a green credit item comprises:
matching the information of the credit project to be identified with the high-frequency keywords in the green credit project identification model to obtain green project matching degree;
if the matching degree of the green item is greater than a threshold value, determining that the credit item to be identified is a green credit item;
and if the green item matching degree is not greater than the threshold value, determining that the credit item to be identified is not a green credit item.
6. The method of claim 1, wherein constructing the risk keyword library comprises:
obtaining environmental security violation information and eliminating out-dated capacity information;
and extracting the environmental security violation information and the risk keywords in the obsolete backward productivity information to form the risk keyword library.
7. The method of claim 1, further comprising:
acquiring a plurality of historical high-risk credit item information;
matching each piece of historical high-risk credit project information with the risk keyword library respectively to obtain the risk matching degree of each historical high-risk credit project;
and determining the risk matching degree of a plurality of historical high-risk credit items as the standard value.
8. A credit item risk identification apparatus, comprising:
the to-be-identified item acquiring unit is used for acquiring a to-be-identified credit item;
the green credit item determination unit is used for calling a pre-constructed green credit item identification model and determining whether the credit item to be identified is a green credit item;
the risk identification unit is used for matching a pre-constructed risk keyword library with the information of the credit project to be identified to obtain a risk matching degree if the credit project to be identified is a green credit project; and if the risk matching degree is smaller than a preset standard value, determining that the credit item to be identified is not a high-risk credit item.
9. The method according to claim 8, characterized in that the apparatus further comprises a green credit item identification model building element, in particular for:
acquiring all characters in a green credit project requirement file;
extracting high-frequency keywords in all characters in the green credit project requirement file;
matching the information of each industry type with the high-frequency keywords to obtain the matching degree of each industry type;
adding the industry type with a matching degree greater than a threshold value into a green industry type list in the green credit project identification model.
10. The apparatus according to claim 9, wherein the green credit item determination element is specifically configured to:
acquiring the industry type of the credit project to be identified;
judging whether the industry type of the credit project to be identified belongs to is in a green industry type list in the green credit project identification model;
if the credit item to be identified is in the green industry type list, determining that the credit item to be identified is a green credit item;
and if the credit item to be identified is not in the green industry type list, determining that the credit item to be identified is not a green credit item.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210550953.XA CN114881765A (en) | 2022-05-20 | 2022-05-20 | Credit item risk identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210550953.XA CN114881765A (en) | 2022-05-20 | 2022-05-20 | Credit item risk identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114881765A true CN114881765A (en) | 2022-08-09 |
Family
ID=82678118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210550953.XA Pending CN114881765A (en) | 2022-05-20 | 2022-05-20 | Credit item risk identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114881765A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115545912A (en) * | 2022-11-30 | 2022-12-30 | 联合赤道环境评价股份有限公司 | Credit risk prediction method and device based on green identification information |
-
2022
- 2022-05-20 CN CN202210550953.XA patent/CN114881765A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115545912A (en) * | 2022-11-30 | 2022-12-30 | 联合赤道环境评价股份有限公司 | Credit risk prediction method and device based on green identification information |
| CN115545912B (en) * | 2022-11-30 | 2023-04-25 | 联合赤道环境评价股份有限公司 | Credit risk prediction method and device based on green identification information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107563757B (en) | Data risk identification method and device | |
| CN108366045B (en) | Method and device for setting wind control scoring card | |
| CN111352971A (en) | Bank system monitoring data anomaly detection method and system | |
| CN110378575B (en) | Overdue event refund collection method and device and computer readable storage medium | |
| CN105976242A (en) | Transaction fraud detection method and system based on real-time streaming data analysis | |
| CN109255000B (en) | Dimension management method and device for label data | |
| CN110807699B (en) | Overdue event payment collection method and device and computer readable storage medium | |
| CN110287292B (en) | Judgment criminal measuring deviation degree prediction method and device | |
| CN106021551A (en) | Consumption auxiliary decision making method based on screenshot information recognition | |
| CN111145027A (en) | Suspected money laundering transaction identification method and device | |
| CN114881765A (en) | Credit item risk identification method and device | |
| CN112328657A (en) | Feature derivation method, feature derivation device, computer equipment and medium | |
| CN111191720A (en) | Service scene identification method and device and electronic equipment | |
| Kim et al. | Pricing fraud detection in online shopping malls using a finite mixture model | |
| CN102467537B (en) | The method and apparatus deleting vocabulary | |
| CN112801784A (en) | Bit currency address mining method and device for digital currency exchange | |
| CN116628584A (en) | Power sensitive data processing method and device, electronic equipment and storage medium | |
| CN116342255A (en) | Internet consumption credit anti-fraud risk identification method and system | |
| CN109739840A (en) | Data processing empty value method, apparatus and terminal device | |
| CN115238815A (en) | Abnormal transaction data acquisition method, device, equipment, medium and program product | |
| CN114519605A (en) | Advertisement click fraud detection method, system, server and storage medium | |
| CN113112347A (en) | Determination method of hasty collection decision, related device and computer storage medium | |
| CN114707420A (en) | Credit fraud behavior identification method, device, equipment and storage medium | |
| CN115204923A (en) | Entity detection method, entity detection device, computer equipment and storage medium | |
| CN112614012A (en) | User electricity stealing identification method and device |
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 |