CN112116245A - Credit risk assessment method, credit risk assessment device, computer equipment and storage medium - Google Patents
Credit risk assessment method, credit risk assessment device, computer equipment and storage mediumDownload PDFInfo
- Publication number
- CN112116245A CN112116245ACN202010984025.5ACN202010984025ACN112116245ACN 112116245 ACN112116245 ACN 112116245ACN 202010984025 ACN202010984025 ACN 202010984025ACN 112116245 ACN112116245 ACN 112116245A
- Authority
- CN
- China
- Prior art keywords
- user
- attribute
- consumption behavior
- data
- evaluated
- 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 OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Finance (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Accounting & Taxation (AREA)
- Technology Law (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a credit risk assessment method, a credit risk assessment device, computer equipment and a storage medium.
Background
The credit is a value movement form taking repayment and interest as conditions, and generally comprises credit activities such as bank deposit, loan and the like, the loan is necessarily accompanied by risks, before the repayment deadline expires, the great change of the financing condition of a borrower possibly affects the performance capability of the borrower, so that the risks such as bad account and the like occur, and therefore, the credit has great significance for credit risk assessment of the borrower in advance.
Currently, credit risk of a borrower is generally evaluated according to personal information of the borrower, value data, credit investigation data and the like, wherein the personal information comprises information such as gender, academic calendar and the like of the borrower, the value data comprises monthly income, fixed assets and the like of the borrower, and the credit investigation data comprises the number of credit cards of the borrower, the number of overdue credit and the like. However, the value data and credit investigation data of the borrower are static data, and the static data is characterized by being stable and not easy to change or changing slowly, and cannot reflect the future change trend of the borrower, so that if credit risk assessment is performed only according to the static data of the borrower, an accurate credit risk assessment result cannot be obtained, and the accuracy rate of credit risk assessment is low.
Disclosure of Invention
The invention provides a credit risk assessment method, a credit risk assessment device, computer equipment and a storage medium, which mainly can improve the accuracy of credit risk assessment and ensure the reliability of a credit risk assessment result.
According to a first aspect of the present invention, there is provided a credit risk assessment method, comprising:
acquiring consumption behavior time sequence data and attribute data corresponding to a user to be evaluated;
inputting the consumption behavior time sequence data into a preset consumption behavior feature extraction model for feature extraction to obtain consumption behavior feature vectors corresponding to the consumption behavior time sequence data;
inputting the attribute data into a preset attribute feature extraction model for feature extraction to obtain an attribute feature vector corresponding to the user to be evaluated;
and determining a credit risk evaluation result corresponding to the user to be evaluated according to the consumption behavior feature vector and the attribute feature vector.
According to a second aspect of the present invention, there is provided a credit risk assessment apparatus including:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring consumption behavior time sequence data and attribute data corresponding to a user to be evaluated;
the first extraction unit is used for inputting the consumption behavior time sequence data into a preset consumption behavior feature extraction model for feature extraction to obtain a consumption behavior feature vector corresponding to the consumption behavior time sequence data;
the second extraction unit is used for inputting the attribute data into a preset attribute feature extraction model for feature extraction to obtain an attribute feature vector corresponding to the user to be evaluated;
and the determining unit is used for determining a credit risk evaluation result corresponding to the user to be evaluated according to the consumption behavior feature vector and the attribute feature vector.
According to a third aspect of the present invention, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
acquiring consumption behavior time sequence data and attribute data corresponding to a user to be evaluated;
inputting the consumption behavior time sequence data into a preset consumption behavior feature extraction model for feature extraction to obtain consumption behavior feature vectors corresponding to the consumption behavior time sequence data;
inputting the attribute data into a preset attribute feature extraction model for feature extraction to obtain an attribute feature vector corresponding to the user to be evaluated;
and determining a credit risk evaluation result corresponding to the user to be evaluated according to the consumption behavior feature vector and the attribute feature vector.
According to a fourth aspect of the present invention, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the program:
acquiring consumption behavior time sequence data and attribute data corresponding to a user to be evaluated;
inputting the consumption behavior time sequence data into a preset consumption behavior feature extraction model for feature extraction to obtain consumption behavior feature vectors corresponding to the consumption behavior time sequence data;
inputting the attribute data into a preset attribute feature extraction model for feature extraction to obtain an attribute feature vector corresponding to the user to be evaluated;
and determining a credit risk evaluation result corresponding to the user to be evaluated according to the consumption behavior feature vector and the attribute feature vector.
Compared with the conventional method for evaluating the credit risk of the user to be evaluated according to the static data of the user to be evaluated, the credit risk evaluation method, the credit risk evaluation device, the computer equipment and the storage medium can acquire the consumption behavior time sequence data and the attribute data corresponding to the user to be evaluated; inputting the consumption behavior time sequence data into a preset consumption behavior feature extraction model for feature extraction to obtain consumption behavior feature vectors corresponding to the consumption behavior time sequence data; meanwhile, inputting the attribute data into a preset attribute feature extraction model for feature extraction to obtain an attribute feature vector corresponding to the user to be evaluated; and finally, determining a credit risk assessment result corresponding to the user to be assessed according to the consumption behavior feature vector and the attribute feature vector, so that dynamic data reflecting the future change trend of the user to be assessed can be introduced by acquiring the consumption behavior time sequence data of the user to be assessed, and when the user to be assessed is subjected to risk assessment, the credit risk assessment result of the user to be assessed can be predicted according to the consumption behavior feature vector and the attribute feature vector by extracting the consumption behavior feature vector and the attribute feature vector of the user to be assessed, and the influence of static data and dynamic data on credit risk assessment can be considered at the same time, so that the reliability of the credit risk assessment result can be ensured, and the prediction precision of the credit risk assessment result can be improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a flow chart of a credit risk assessment method according to an embodiment of the invention;
FIG. 2 is a flow chart of another credit risk assessment method provided by an embodiment of the invention;
FIG. 3 is a schematic diagram illustrating the structure of a credit risk assessment device according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating another credit risk assessment device according to an embodiment of the present invention;
fig. 5 shows a physical structure diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The invention will be described in detail hereinafter with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Currently, credit risk of a borrower is generally evaluated according to personal information of the borrower, value data, credit investigation data and the like, wherein the personal information comprises information such as gender, academic calendar and the like of the borrower, the value data comprises monthly income, fixed assets and the like of the borrower, and the credit investigation data comprises the number of credit cards of the borrower, the number of overdue credit and the like. However, the value data and credit investigation data of the borrower are static data, and the static data is characterized by being stable and not easy to change or changing slowly, and cannot reflect the future change trend of the borrower, so that if credit risk assessment is performed only according to the static data of the borrower, an accurate credit risk assessment result cannot be obtained, and the accuracy rate of credit risk assessment is low.
In order to solve the above problem, an embodiment of the present invention provides a credit risk assessment method, as shown in fig. 1, the method including:
101. and acquiring consumption behavior time sequence data and attribute data corresponding to the user to be evaluated.
Wherein, the user to be evaluated is a user needing credit risk evaluation, the consumption behavior time sequence data of the user to be evaluated is established according to consumption records of the user to be evaluated in a period of time, and specifically comprises historical consumption frequency time sequence data, total consumption amount time sequence data, time sequence data of the category of commodities to which the maximum consumption amount belongs, consumption and monthly income occupation ratio time sequence data and the like of the user to be evaluated, for example, the consumption records of the user to be evaluated in one year are obtained, an equally divided time interval is determined to be one month, the historical consumption frequency time sequence data of the user to be evaluated is established to be (3,2,3,5,7,8,9,10,3,6,7,5), namely, the consumption frequency of the user to be evaluated in 1-12 months in the year, the first month is consumed for 3 times, the second month is consumed for 2 times, the third month is consumed for 3 times, the fourth month is consumed for 5 times and the like, furthermore, the attribute data of the user to be evaluated includes: the method comprises the following steps that personal information, value data and credit investigation data of a user to be evaluated are obtained, wherein the personal information comprises the sex, age, academic history, prison, marital conditions and the like of the user to be evaluated; the value data mainly refers to the personal financial condition of the user to be evaluated, and specifically comprises the following steps: monthly income, fixed assets, account balance, monthly consumption income proportion, payment amount and the like; the credit investigation data comprises: the number of credit cards, the total amount of credit, the number of successful borrowings, the number of overdue times and the like of the user to be evaluated.
For the embodiment of the invention, in order to overcome the defect that in the prior art, the credit risk is evaluated only according to the static data (attribute data) of the user to be evaluated, therefore, the embodiment of the invention adopts the machine learning technology in the field of artificial intelligence, introduces the consumption time sequence data of the user to be evaluated, the method and the device are mainly suitable for credit risk assessment, and an execution main body of the embodiment of the invention is a device or equipment capable of performing credit risk assessment on the user to be assessed, and can be arranged on one side of a client or a server.
Specifically, when a user to be evaluated applies for a loan, the user to be evaluated uploads personal information and value data in advance, a credit service worker receives and verifies the personal information and the value data of the user to be evaluated and stores the personal information and the value data in a server, meanwhile, the credit service worker also calls credit investigation data of the user to be evaluated and consumption records in a period of time to store, then, the credit evaluation service worker carries out credit risk evaluation on the user to be evaluated so as to determine whether to pay the user according to a credit risk evaluation result, the specific credit service worker can trigger a credit risk evaluation instruction by clicking a credit risk evaluation button in a server interface, after receiving the credit risk evaluation instruction of the user to be evaluated, the server calls the consumption records and attribute data of the user to be evaluated in a period of time and according to the consumption records of the user to be evaluated in a period of time, and generating consumption behavior time sequence data corresponding to the user to be evaluated so as to jointly predict the credit risk evaluation result of the user to be evaluated according to the consumption behavior time sequence data and the attribute data.
102. And inputting the consumption behavior time sequence data into a preset consumption behavior feature extraction model for feature extraction to obtain a consumption behavior feature vector corresponding to the consumption behavior time sequence data.
For the embodiment of the present invention, the Xgboost consumption behavior feature extraction model may specifically be an Xgboost consumption behavior feature extraction model, and may process time series data, the Xgboost consumption behavior feature extraction model mainly includes an input layer, a hidden layer, and an output layer, the time series data of consumption behavior corresponding to a user to be evaluated is input through the input layer, then the hidden layer is used to perform feature extraction on the time series data of consumption behavior, so as to obtain a consumption behavior feature vector corresponding to the user to be evaluated, further, the output layer may predict the consumption behavior feature vector of the user to be evaluated, so as to obtain a preliminary risk evaluation result corresponding to the user to be evaluated, so as to introduce the consumption behavior time series data, i.e. dynamic data, of the user to be evaluated, and may use the Xgboost consumption behavior feature extraction model to extract the consumption behavior feature vector of the user to be evaluated, so as to combine the static data with the user to be evaluated to jointly carry out credit risk evaluation.
103. And inputting the attribute data into a preset attribute feature extraction model for feature extraction to obtain an attribute feature vector corresponding to the user to be evaluated.
In order to combine attribute data (static data) of a user to be evaluated with consumption behavior time sequence data (dynamic data) and jointly evaluate loan risk of the user to be evaluated, the attribute data of the user to be evaluated needs to be subjected to feature extraction.
104. And determining a credit risk evaluation result corresponding to the user to be evaluated according to the consumption behavior feature vector and the attribute feature vector.
The credit risk assessment result of the user to be assessed includes default and non-default of the user to be assessed, for example, if the output credit risk assessment result is 0, the user to be assessed will default, that is, if the user to be assessed is lended, the user to be assessed is likely to default and cannot be repayment on time; if the output credit risk assessment result is 1, the user to be assessed does not default, namely if the user to be assessed puts the loan, the user to be assessed is likely not default, and the loan can be repacked on time. For the embodiment of the invention, in order to improve the credit risk assessment accuracy of the user to be assessed, the risk assessment needs to be carried out on the user to be assessed according to the static data and the dynamic data.
Specifically, a preliminary risk assessment result corresponding to the user to be assessed is determined according to the consumption behavior feature vector, the preliminary risk assessment result is a preliminary risk assessment result obtained only according to the consumption behavior time sequence data of the user to be assessed, and a response brought by the attribute data of the user needs to be considered, so that a final credit risk assessment result corresponding to the user to be assessed is determined according to the preliminary risk assessment result, the consumption behavior feature vector and the attribute feature vector, and specifically, the preliminary risk assessment result, the consumption behavior feature vector and the attribute feature vector can be jointly used as input vectors and input into a preset credit risk assessment model for credit risk assessment to obtain a credit risk assessment result corresponding to the user to be assessed, wherein the preset credit risk assessment model can be a preset logistic regression model, and whether the user to be assessed is credited is determined according to the credit risk assessment result output by the preset logistic regression model, for example, if the credit risk assessment result output by the preset logistic regression model is 0, it is determined that the user to be assessed is likely to default, and therefore the user is not credited; and if the credit risk assessment result output by the preset logistic regression model is 1, determining that the user to be assessed is probably not default, and therefore lending the user.
Compared with the conventional method for evaluating the credit risk of the user to be evaluated according to the static data of the user to be evaluated, the credit risk evaluation method provided by the embodiment of the invention can acquire the consumption behavior time sequence data and the attribute data corresponding to the user to be evaluated; inputting the consumption behavior time sequence data into a preset consumption behavior feature extraction model for feature extraction to obtain consumption behavior feature vectors corresponding to the consumption behavior time sequence data; meanwhile, inputting the attribute data into a preset attribute feature extraction model for feature extraction to obtain an attribute feature vector corresponding to the user to be evaluated; and finally, determining a credit risk assessment result corresponding to the user to be assessed according to the consumption behavior feature vector and the attribute feature vector, so that dynamic data reflecting the future change trend of the user to be assessed can be introduced by acquiring the consumption behavior time sequence data of the user to be assessed, and when the user to be assessed is subjected to risk assessment, the credit risk assessment result of the user to be assessed can be predicted according to the consumption behavior feature vector and the attribute feature vector by extracting the consumption behavior feature vector and the attribute feature vector of the user to be assessed, and the influence of static data and dynamic data on credit risk assessment can be considered at the same time, so that the reliability of the credit risk assessment result can be ensured, and the prediction precision of the credit risk assessment result can be improved.
Further, in order to better explain the above credit risk assessment process, as a refinement and extension to the above embodiment, another credit risk assessment method is provided in an embodiment of the present invention, as shown in fig. 2, the method includes:
201. and acquiring consumption behavior time sequence data and attribute data corresponding to the user to be evaluated.
For the embodiment of the present invention, in order to obtain the consumption behavior time series data,step 201 specifically includes: acquiring consumption records of the user to be evaluated in a preset time period and consumption time corresponding to the consumption records; and determining the consumption behavior time sequence data corresponding to the user to be evaluated according to the consumption record and the consumption time. Wherein, the preset time period can be set according to the business requirement, and it should be noted that, in order to ensure the accuracy of credit risk assessment of the user to be assessed, the preset time period should not be set too short, for example, all consumption records of the user to be assessed in the last year from 1 month to 12 months and the corresponding consumption time are obtained, and according to the consumption time corresponding to a plurality of consumption records of the user to be assessed in one year, the historical consumption frequency time series data of the user to be assessed, the customer consumption amount time series data, the time series data of the category of the commodity to which the maximum consumption amount belongs, and the consumption and monthly income proportion time series data are respectively counted, for example, the consumption and income monthly proportion time series data of the user to be assessed in the last year from 1 month to 12 months are counted as (0.5,0.3,0.8,0.2,0.5,0.9,0.7,0.9,0.8,0.6,0.7,0.5), and further, when the user to be assessed applies for loan, the personal information and the value data are filled in, the credit business personnel verify the personal information and the value data of the user to be evaluated and then store the personal information and the value data in the server, and meanwhile, credit investigation data related to the user to be evaluated are called to be stored in the server, so that when the credit risk evaluation is carried out on the user to be evaluated, the risk evaluation is carried out together according to the consumption behavior time sequence data and the attribute data of the user to be evaluated, and the accuracy rate of the credit risk evaluation of the user to be evaluated is improved.
Further, the obtained attribute data of the user to be evaluated is likely to include a plurality of pieces of attribute data, and different pieces of attribute data are likely to have strong correlation, and in order to achieve the purpose of feature dimension reduction and over-fitting prevention, only part of attribute data can be selected from the attribute data with correlation as input variables, based on which, the method further includes: if a plurality of attribute data exist, verifying the correlation among the attribute data to obtain a correlation verification result among the attribute data; according to the correlation verification result, screening target attribute data from the attribute data, further, verifying the correlation between the attribute data to obtain the correlation verification result between the attribute data, including: calculating a correlation coefficient between the attribute data; determining a correlation verification result between the attribute data according to the calculated correlation coefficients, and screening target attribute data from the attribute data according to the correlation verification result, wherein the correlation verification result comprises: according to the correlation verification result, determining attribute data with correlation and attribute data without correlation in each attribute data; and screening a preset number of attribute data from the attribute data with the correlation, and determining the preset number of attribute data and the attribute data without the correlation as target attribute data.
Specifically, a preset correlation verification algorithm may be used to calculate a correlation coefficient between the attribute data, where a specific calculation formula of the correlation coefficient is as follows:
where ρ issFor the correlation coefficient between different attribute data, di＝xi′-yi′，xi' is a component X of attribute data XiOrder of (a), (b), (c) and (d)i' is a component Y of attribute data YiOrder of (d)iIs xi' and yi' a rank difference, n is a dimension of the attribute data X and Y, and after calculating a correlation coefficient of the attribute data X and Y, whether there is a correlation between the attribute data X and Y is judged according to a magnitude of the correlation coefficient, for example, if the calculated correlation coefficient is greater than or equal to 0.829, it is considered that there is a correlation between the attribute data X and Y; if the calculated correlation coefficient is less than 0.829, it is considered that there is no correlation between the attribute data X and Y, and thus the correlation verification result between different attribute data can be determined. Further, according to a correlation verification result between different attribute data, determining a plurality of attribute data with correlation, then screening a preset number of attribute data from the plurality of attribute data with correlation, for example, determining that 5 attribute data have correlation, in order to achieve the purpose of feature dimension reduction, screening two attribute data from the 5 attribute data with correlation, and using the screened attribute data and the attribute data without correlation as target attribute data together, so as to input the target attribute data to a preset attribute feature extraction model for feature extraction, and obtain an attribute feature vector corresponding to the user to be evaluated, thereby achieving the purposes of feature dimension reduction and over-fitting prevention.
202. And inputting the consumption behavior time sequence data into a preset consumption behavior feature extraction model for feature extraction to obtain a consumption behavior feature vector corresponding to the consumption behavior time sequence data.
For the embodiment of the invention, after dynamic data (consumption behavior time sequence data) of a user to be evaluated is introduced, the dynamic data is input into the Xgboost consumption behavior feature extraction model for feature extraction, so that a consumption behavior feature vector corresponding to the user to be evaluated is obtained, and meanwhile, credit risk of the user to be evaluated can be preliminarily evaluated according to the consumption behavior feature vector.
203. And inputting the attribute data into a preset attribute feature extraction model for feature extraction to obtain an attribute feature vector corresponding to the user to be evaluated.
For the embodiment of the invention, after the correlation verification is carried out on the multiple attribute data of the user to be evaluated, and the target attribute data in the multiple attribute data is determined, the determined target attribute data is input into the preset attribute feature extraction model for feature extraction, wherein the preset attribute feature extraction model can be a convolutional neural network model, and the attribute feature vector of the user to be evaluated is extracted through the convolutional neural network model.
204. And determining a preliminary risk evaluation result corresponding to the user to be evaluated according to the consumption behavior feature vector.
For the present embodiment, after the consumption behavior feature vector of the user to be evaluated is extracted by using the Xgboost consumption behavior feature extraction model, the credit risk of the user to be evaluated may be preliminarily evaluated by using the output layer of the Xgboost model according to the extracted consumption behavior feature vector, so as to obtain a preliminary risk evaluation result of the user to be evaluated, where the preliminary risk evaluation result includes default or non-default of the user to be evaluated.
205. And determining a credit risk evaluation result corresponding to the user to be evaluated according to the preliminary risk evaluation result, the consumption behavior feature vector and the attribute feature vector.
For the embodiment of the present invention, in order to improve the credit risk assessment accuracy of the user to be assessed, the consumption behavior time series data (dynamic data), the attribute data (static data) of the user to be assessed and the preliminary risk assessment result output by the Xgboost model need to be considered at the same time, and based on this, step 205 specifically includes: integrating the preliminary risk assessment result, the consumption behavior feature vector and the attribute feature vector to obtain an integrated feature vector; and inputting the integrated feature vectors into a preset credit risk assessment model for risk assessment to obtain a credit risk assessment result corresponding to the user to be assessed. Wherein the preset credit risk assessment model may be a preset logistic regression model.
For example, the consumption behavior feature vector of the user to be evaluated is (x1, x2, x3), the attribute feature vector is (x4, x5, x6, x7), the preliminary risk assessment result obtained by using the Xgboost model is u, the vectors are integrated to obtain the integrated feature vector which is (x1, x2, x3, x4, x5, x6, x7, u), and the integrated feature vector (x1, x2, x3, y1, y2, y3, y4, u) is used as an input variable of a preset logistic regression model, the credit risk of the user to be evaluated is evaluated, and when the credit risk of the user to be evaluated is evaluated specifically, the probability that the user to be evaluated will not violate may be calculated, and a specific calculation formula is as follows:
wherein, alpha and beta are estimation parameters of a preset logistic regression model, (x)1,x2,…,xnU) is the integrated variable, E (y) is the probability that the user to be evaluated will not default, and whether the user to be evaluated will default is determined according to the calculated probability.
For the embodiment of the invention, when the preset consumption behavior feature extraction model, the preset attribute feature extraction model and the preset credit risk assessment model are constructed, the preset consumption behavior feature extraction model, the preset attribute feature extraction model and the preset credit risk assessment model can be used as a whole for training, consumption behavior time sequence data and attribute data of a large number of users and corresponding repayment conditions are collected, a sample data set is determined, the sample data set is trained, the preset consumption behavior feature extraction model, the preset attribute feature extraction model and the preset credit trend assessment model are constructed, and when the preset credit risk assessment model is specifically a logistic regression model, parameters of the logistic regression model are adjusted by using a preset maximum likelihood algorithm, so that optimal assessment parameters are obtained.
Compared with the conventional method for evaluating the credit risk of the user to be evaluated according to the static data of the user to be evaluated, the credit risk evaluation method provided by the embodiment of the invention can acquire the consumption behavior time sequence data and the attribute data corresponding to the user to be evaluated; inputting the consumption behavior time sequence data into a preset consumption behavior feature extraction model for feature extraction to obtain consumption behavior feature vectors corresponding to the consumption behavior time sequence data; meanwhile, inputting the attribute data into a preset attribute feature extraction model for feature extraction to obtain an attribute feature vector corresponding to the user to be evaluated; and finally, determining a credit risk assessment result corresponding to the user to be assessed according to the consumption behavior feature vector and the attribute feature vector, so that dynamic data reflecting the future change trend of the user to be assessed can be introduced by acquiring the consumption behavior time sequence data of the user to be assessed, and when the user to be assessed is subjected to risk assessment, the credit risk assessment result of the user to be assessed can be predicted according to the consumption behavior feature vector and the attribute feature vector by extracting the consumption behavior feature vector and the attribute feature vector of the user to be assessed, and the influence of static data and dynamic data on credit risk assessment can be considered at the same time, so that the reliability of the credit risk assessment result can be ensured, and the prediction precision of the credit risk assessment result can be improved.
Further, as a specific implementation of fig. 1, an embodiment of the present invention provides a credit risk assessment apparatus, as shown in fig. 3, the apparatus including: anacquisition unit 31, afirst extraction unit 32, asecond extraction unit 33, and adetermination unit 34.
The obtainingunit 31 may be configured to obtain consumption behavior time series data and attribute data corresponding to a user to be evaluated. The acquiringunit 31 is a main functional module in the device for acquiring consumption behavior time series data and attribute data corresponding to a user to be evaluated.
The first extractingunit 32 may be configured to input the consumption behavior time series data into a preset consumption behavior feature extraction model for feature extraction, so as to obtain a consumption behavior feature vector corresponding to the consumption behavior time series data. Thefirst extraction unit 32 is a main function module, which inputs the consumption behavior time series data into a preset consumption behavior feature extraction model for feature extraction to obtain a consumption behavior feature vector corresponding to the consumption behavior time series data, and is also a core module.
The second extractingunit 33 may be configured to input the attribute data to a preset attribute feature extraction model for feature extraction, so as to obtain an attribute feature vector corresponding to the user to be evaluated. Thesecond extraction unit 33 is a main function module in the present apparatus that inputs the attribute data to a preset attribute feature extraction model to perform feature extraction, so as to obtain an attribute feature vector corresponding to the user to be evaluated.
The determiningunit 34 may be configured to determine a credit risk assessment result corresponding to the user to be assessed according to the consumption behavior feature vector and the attribute feature vector. The determiningunit 34 is a main functional module, which is also a core module, in the present apparatus, for determining a credit risk assessment result corresponding to the user to be assessed according to the consumption behavior feature vector and the attribute feature vector.
Further, in order to determine the credit risk assessment result corresponding to the user to be assessed, as shown in fig. 4, the determiningunit 34 includes a first determining module 341 and a second determining module 342.
The first determining module 341 may be configured to determine a preliminary risk assessment result corresponding to the user to be assessed according to the consumption behavior feature vector.
The second determining module may be configured to determine, according to the preliminary risk assessment result, the consumption behavior feature vector, and the attribute feature vector, a credit risk assessment result corresponding to the user to be assessed.
Further, in order to determine the credit risk assessment result corresponding to the user to be assessed, the second determining module 341 includes: an integration submodule and an evaluation submodule.
The integration submodule may be configured to integrate the preliminary risk assessment result, the consumption behavior feature vector, and the attribute feature vector to obtain an integrated feature vector.
The evaluation submodule may be configured to input the integrated feature vector to a preset credit risk evaluation model for risk evaluation, so as to obtain a credit risk evaluation result corresponding to the user to be evaluated.
Further, for performing correlation verification on the attribute data, the apparatus further includes: averification unit 35 and ascreening unit 36.
The verifyingunit 35 may be configured to verify the correlation between the attribute data if there are multiple attribute data, and obtain a correlation verification result between the attribute data.
Thescreening unit 36 may be configured to screen target attribute data from the attribute data according to the correlation verification result.
The second extractingunit 33 may be specifically configured to input the target attribute data to a preset attribute feature extraction model for feature extraction, so as to obtain an attribute feature vector corresponding to the user to be evaluated.
Further, in order to determine a result of verifying the correlation between the attribute data, the verifyingunit 35 includes: acalculation module 351 and adetermination module 352.
The calculatingmodule 351 may be configured to calculate a correlation coefficient between the attribute data.
The determiningmodule 352 may be configured to determine a correlation verification result between the attribute data according to the calculated correlation coefficients.
Further, in order to screen the target attribute data from the attribute data, thescreening unit 36 includes:determination module 361filters module 362.
The determiningmodule 361 may be configured to determine attribute data with correlation and attribute data without correlation in the attribute data according to the correlation verification result.
Thescreening module 362 may be configured to screen a preset number of attribute data from the attribute data with correlation, and determine the preset number of attribute data and the attribute data without correlation as target attribute data.
Further, in order to obtain the consumption behavior time series data corresponding to the user to be evaluated, the obtainingunit 31 includes: anacquisition module 311 and adetermination module 312.
The obtainingmodule 311 may be configured to obtain a consumption record of the user to be evaluated within a preset time period and a consumption time corresponding to the consumption record.
The determiningmodule 312 may be configured to determine, according to the consumption record and the consumption time, consumption behavior time series data corresponding to the user to be evaluated.
It should be noted that other corresponding descriptions of the functional modules related to the credit risk assessment apparatus provided in the embodiment of the present invention may refer to the corresponding description of the method shown in fig. 1, and are not described herein again.
Based on the method shown in fig. 1, correspondingly, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the following steps: acquiring consumption behavior time sequence data and attribute data corresponding to a user to be evaluated; inputting the consumption behavior time sequence data into a preset consumption behavior feature extraction model for feature extraction to obtain consumption behavior feature vectors corresponding to the consumption behavior time sequence data; inputting the attribute data into a preset attribute feature extraction model for feature extraction to obtain an attribute feature vector corresponding to the user to be evaluated; and determining a credit risk evaluation result corresponding to the user to be evaluated according to the consumption behavior feature vector and the attribute feature vector.
Based on the above embodiments of the method shown in fig. 1 and the apparatus shown in fig. 3, an embodiment of the present invention further provides an entity structure diagram of a computer device, as shown in fig. 5, where the computer device includes: aprocessor 41, amemory 42, and a computer program stored on thememory 42 and executable on the processor, wherein thememory 42 and theprocessor 41 are both arranged on abus 43 such that when theprocessor 41 executes the program, the following steps are performed: acquiring consumption behavior time sequence data and attribute data corresponding to a user to be evaluated; inputting the consumption behavior time sequence data into a preset consumption behavior feature extraction model for feature extraction to obtain consumption behavior feature vectors corresponding to the consumption behavior time sequence data; inputting the attribute data into a preset attribute feature extraction model for feature extraction to obtain an attribute feature vector corresponding to the user to be evaluated; and determining a credit risk evaluation result corresponding to the user to be evaluated according to the consumption behavior feature vector and the attribute feature vector.
By the technical scheme, the consumption behavior time sequence data and the attribute data corresponding to the user to be evaluated can be acquired; inputting the consumption behavior time sequence data into a preset consumption behavior feature extraction model for feature extraction to obtain consumption behavior feature vectors corresponding to the consumption behavior time sequence data; meanwhile, inputting the attribute data into a preset attribute feature extraction model for feature extraction to obtain an attribute feature vector corresponding to the user to be evaluated; and finally, determining a credit risk assessment result corresponding to the user to be assessed according to the consumption behavior feature vector and the attribute feature vector, so that dynamic data reflecting the future change trend of the user to be assessed can be introduced by acquiring the consumption behavior time sequence data of the user to be assessed, and when the user to be assessed is subjected to risk assessment, the credit risk assessment result of the user to be assessed can be predicted according to the consumption behavior feature vector and the attribute feature vector by extracting the consumption behavior feature vector and the attribute feature vector of the user to be assessed, and the influence of static data and dynamic data on credit risk assessment can be considered at the same time, so that the reliability of the credit risk assessment result can be ensured, and the prediction precision of the credit risk assessment result can be improved.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A credit risk assessment method, comprising:
acquiring consumption behavior time sequence data and attribute data corresponding to a user to be evaluated;
inputting the consumption behavior time sequence data into a preset consumption behavior feature extraction model for feature extraction to obtain consumption behavior feature vectors corresponding to the consumption behavior time sequence data;
inputting the attribute data into a preset attribute feature extraction model for feature extraction to obtain an attribute feature vector corresponding to the user to be evaluated;
and determining a credit risk evaluation result corresponding to the user to be evaluated according to the consumption behavior feature vector and the attribute feature vector.
2. The method according to claim 1, wherein the determining the credit risk assessment result corresponding to the user to be assessed according to the consumption behavior feature vector and the attribute feature vector comprises:
determining a preliminary risk evaluation result corresponding to the user to be evaluated according to the consumption behavior feature vector;
and determining a credit risk evaluation result corresponding to the user to be evaluated according to the preliminary risk evaluation result, the consumption behavior feature vector and the attribute feature vector.
3. The method according to claim 2, wherein the determining the credit risk assessment result corresponding to the user to be assessed according to the preliminary risk assessment result, the consumption behavior feature vector and the attribute feature vector comprises:
integrating the preliminary risk assessment result, the consumption behavior feature vector and the attribute feature vector to obtain an integrated feature vector;
and inputting the integrated feature vectors into a preset credit risk assessment model for risk assessment to obtain a credit risk assessment result corresponding to the user to be assessed.
4. The method according to claim 1, wherein after the obtaining of the consumption behavior time series data and the attribute data corresponding to the user to be evaluated, the method further comprises:
if a plurality of attribute data exist, verifying the correlation among the attribute data to obtain a correlation verification result among the attribute data;
screening target attribute data from the attribute data according to the correlation verification result;
the inputting the attribute data into a preset attribute feature extraction model for feature extraction to obtain an attribute feature vector corresponding to the user to be evaluated includes:
and inputting the target attribute data into a preset attribute feature extraction model for feature extraction to obtain an attribute feature vector corresponding to the user to be evaluated.
5. The method according to claim 4, wherein the verifying the correlation between the attribute data to obtain the correlation verification result between the attribute data comprises:
calculating a correlation coefficient between the attribute data;
and determining a correlation verification result among the attribute data according to the calculated correlation coefficients.
6. The method according to claim 4, wherein the screening target attribute data from the respective attribute data according to the correlation verification result comprises:
according to the correlation verification result, determining attribute data with correlation and attribute data without correlation in each attribute data;
and screening a preset number of attribute data from the attribute data with the correlation, and determining the preset number of attribute data and the attribute data without the correlation as target attribute data.
7. The method according to any one of claims 1 to 6, wherein the obtaining of the consumption behavior time series data corresponding to the user to be evaluated comprises:
acquiring consumption records of the user to be evaluated in a preset time period and consumption time corresponding to the consumption records;
and determining the consumption behavior time sequence data corresponding to the user to be evaluated according to the consumption record and the consumption time.
8. A credit risk assessment apparatus, comprising:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring consumption behavior time sequence data and attribute data corresponding to a user to be evaluated;
the first extraction unit is used for inputting the consumption behavior time sequence data into a preset consumption behavior feature extraction model for feature extraction to obtain a consumption behavior feature vector corresponding to the consumption behavior time sequence data;
the second extraction unit is used for inputting the attribute data into a preset attribute feature extraction model for feature extraction to obtain an attribute feature vector corresponding to the user to be evaluated;
and the determining unit is used for determining a credit risk evaluation result corresponding to the user to be evaluated according to the consumption behavior feature vector and the attribute feature vector.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
10. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 7 when executed by the processor.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010984025.5ACN112116245A (en) | 2020-09-18 | 2020-09-18 | Credit risk assessment method, credit risk assessment device, computer equipment and storage medium |
| PCT/CN2020/124259WO2021159735A1 (en) | 2020-09-18 | 2020-10-28 | Credit risk assessment method and apparatus, and computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010984025.5ACN112116245A (en) | 2020-09-18 | 2020-09-18 | Credit risk assessment method, credit risk assessment device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112116245Atrue CN112116245A (en) | 2020-12-22 |
Family
ID=73801175
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010984025.5APendingCN112116245A (en) | 2020-09-18 | 2020-09-18 | Credit risk assessment method, credit risk assessment device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112116245A (en) |
| WO (1) | WO2021159735A1 (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112950354A (en)* | 2021-02-26 | 2021-06-11 | 中国光大银行股份有限公司 | Credit scoring method and device for account, storage medium and electronic device |
| CN113438075A (en)* | 2021-06-25 | 2021-09-24 | 四川新网银行股份有限公司 | Multi-head sequence diagram calculation method based on secret sharing algorithm and storage medium |
| CN114092216A (en)* | 2021-09-22 | 2022-02-25 | 金蝶征信有限公司 | Enterprise credit rating method, apparatus, computer device and storage medium |
| CN114331192A (en)* | 2021-12-29 | 2022-04-12 | 浙江惠瀜网络科技有限公司 | Credit risk identification method, device, terminal and storage medium based on consumption data |
| CN114707586A (en)* | 2022-03-24 | 2022-07-05 | 广东电网有限责任公司 | A data processing method, device, electronic device and storage medium |
| CN115545481A (en)* | 2022-10-10 | 2022-12-30 | 恒安嘉新（北京）科技股份公司 | Risk level determination method and device, electronic equipment and storage medium |
| CN117195256A (en)* | 2023-08-30 | 2023-12-08 | 无锡视美乐激光显示科技有限公司 | Financial data processing method and system |
| CN117575783A (en)* | 2024-01-16 | 2024-02-20 | 中国电信股份有限公司深圳分公司 | Multi-dimensional user credit assessment method, device, equipment and storage medium |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113781210B (en)* | 2021-09-29 | 2024-06-25 | 中国银行股份有限公司 | Automatic feature engineering method and device based on customer financial transaction data structure |
| CN113888310A (en)* | 2021-10-14 | 2022-01-04 | 重庆海创云链数字科技有限公司 | Credit risk assessment method, credit risk assessment device and storage medium |
| CN114612223B (en)* | 2022-03-18 | 2024-08-13 | 上海爱富爱克斯网络科技发展有限责任公司 | Financial data information processing method |
| CN119205315A (en)* | 2024-11-27 | 2024-12-27 | 江西百电信息产业有限公司 | A loan risk control rating method and system based on big data |
| CN119671721B (en)* | 2025-02-21 | 2025-06-10 | 湖南三湘银行股份有限公司 | A credit assessment method and device based on artificial intelligence and big data technology |
| CN120355502B (en)* | 2025-06-20 | 2025-09-12 | 杭银消费金融股份有限公司 | Risk control management methods, systems and media based on the People's Bank of China's credit time series variables |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108734338A (en)* | 2018-04-24 | 2018-11-02 | 阿里巴巴集团控股有限公司 | Credit risk forecast method and device based on LSTM models |
| CN109657932A (en)* | 2018-11-29 | 2019-04-19 | 平安科技（深圳）有限公司 | Business risk analysis method, device, computer equipment and storage medium |
| CN110659513B (en)* | 2019-09-29 | 2022-12-06 | 哈尔滨工程大学 | Anonymous privacy protection method for multi-sensitive attribute data release |
| CN110738564A (en)* | 2019-10-16 | 2020-01-31 | 信雅达系统工程股份有限公司 | Post-loan risk assessment method and device and storage medium |
| CN111652627B (en)* | 2020-07-07 | 2024-04-23 | 中国银行股份有限公司 | Risk assessment method and risk assessment device |
- 2020
- 2020-09-18CNCN202010984025.5Apatent/CN112116245A/enactivePending
- 2020-10-28WOPCT/CN2020/124259patent/WO2021159735A1/ennot_activeCeased
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112950354A (en)* | 2021-02-26 | 2021-06-11 | 中国光大银行股份有限公司 | Credit scoring method and device for account, storage medium and electronic device |
| CN113438075A (en)* | 2021-06-25 | 2021-09-24 | 四川新网银行股份有限公司 | Multi-head sequence diagram calculation method based on secret sharing algorithm and storage medium |
| CN113438075B (en)* | 2021-06-25 | 2022-09-13 | 四川新网银行股份有限公司 | Multi-head sequence diagram calculation method based on secret sharing algorithm and storage medium |
| CN114092216A (en)* | 2021-09-22 | 2022-02-25 | 金蝶征信有限公司 | Enterprise credit rating method, apparatus, computer device and storage medium |
| CN114331192A (en)* | 2021-12-29 | 2022-04-12 | 浙江惠瀜网络科技有限公司 | Credit risk identification method, device, terminal and storage medium based on consumption data |
| CN114707586A (en)* | 2022-03-24 | 2022-07-05 | 广东电网有限责任公司 | A data processing method, device, electronic device and storage medium |
| CN114707586B (en)* | 2022-03-24 | 2025-09-23 | 广东电网有限责任公司 | Data processing method, device, electronic device and storage medium |
| CN115545481A (en)* | 2022-10-10 | 2022-12-30 | 恒安嘉新（北京）科技股份公司 | Risk level determination method and device, electronic equipment and storage medium |
| CN117195256A (en)* | 2023-08-30 | 2023-12-08 | 无锡视美乐激光显示科技有限公司 | Financial data processing method and system |
| CN117195256B (en)* | 2023-08-30 | 2024-05-31 | 无锡视美乐激光显示科技有限公司 | Financial data processing method and system |
| CN117575783A (en)* | 2024-01-16 | 2024-02-20 | 中国电信股份有限公司深圳分公司 | Multi-dimensional user credit assessment method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021159735A1 (en) | 2021-08-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112116245A (en) | Credit risk assessment method, credit risk assessment device, computer equipment and storage medium | |
| US7970676B2 (en) | Method and system for modeling future action impact in credit scoring | |
| US20190325514A1 (en) | Credit risk prediction method and device based on lstm model | |
| US20090276368A1 (en) | Systems and methods for providing personalized recommendations of products and services based on explicit and implicit user data and feedback | |
| EP1361526A1 (en) | Electronic data processing system and method of using an electronic processing system for automatically determining a risk indicator value | |
| CN110827143A (en) | Method, device and equipment for training credit scoring model | |
| AU2020321734A1 (en) | Indiagnostics framework for large scale hierarchical time-series forecasting models | |
| CN111242319A (en) | Model prediction result interpretation method and device | |
| CN107885754B (en) | Method and device for extracting credit variable from transaction data based on LDA model | |
| CN111754287A (en) | Article screening method, apparatus, device and storage medium | |
| CN117252677A (en) | Credit line determination method and device, electronic equipment and storage medium | |
| CN109308660B (en) | Credit assessment scoring model evaluation method, apparatus, device and storage medium | |
| CN113807943A (en) | A multi-factor valuation method and system, medium and equipment for non-performing assets | |
| CN112950225A (en) | Customer category determination method, device and storage medium | |
| CN117934154A (en) | Transaction risk prediction method, model training method, device, equipment, medium and program product | |
| CN117132317A (en) | Data processing methods, devices, equipment, media and products | |
| CN112116405B (en) | Data processing method, device, electronic equipment and medium | |
| CN111291838B (en) | Method and device for interpreting entity object classification result | |
| CN115115453A (en) | Wind control evaluation method and device | |
| CN114842237A (en) | Method and device for determining hasty receiving mode, computer equipment and storage medium | |
| CN114282992A (en) | Loan credit risk measuring and calculating method and device | |
| CN112926892A (en) | Capital matching method and device, electronic equipment and storage medium | |
| CN114240605A (en) | Loan calculation method and device, computer equipment and storage medium | |
| CN117011000A (en) | Bank product recommendation method, device, equipment and storage medium | |
| CN120807133A (en) | Cross-domain customer credit assessment method and related 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20201222 |