CN113793007A - Data transaction authority control method, device and equipment - Google Patents
Data transaction authority control method, device and equipment Download PDFInfo
- Publication number
- CN113793007A CN113793007A CN202111040178.5A CN202111040178A CN113793007A CN 113793007 A CN113793007 A CN 113793007A CN 202111040178 A CN202111040178 A CN 202111040178A CN 113793007 A CN113793007 A CN 113793007A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- initial credit
- initial
- credit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000011156 evaluation Methods 0.000 claims description 66
- 238000007637 random forest analysis Methods 0.000 claims description 30
- 230000006870 function Effects 0.000 claims description 29
- 230000006399 behavior Effects 0.000 claims description 23
- 238000004891 communication Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 11
- 238000012935 Averaging Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000005314 correlation function Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0609—Buyer or seller confidence or verification
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the invention relates to the technical field of data transaction, and particularly provides a data transaction authority control method, a device and equipment.
Description
Technical Field
The embodiment of the invention belongs to the technical field of data transaction, and particularly relates to a method, a device and equipment for controlling data transaction permission.
Background
With the development of big data and artificial intelligence, data transaction needs are more and more, and transaction behaviors are more and more active. At present, in the process of member authentication, a data transaction platform mainly authenticates identity data attributes provided during user registration, and divides users into a set grade and a set classification so as to open data purchase and use permission of the users.
The inventor of the application finds in research that with the rapid development of data transaction, more small and medium-sized enterprises participate in the data transaction market, the types of data are increasingly abundant, data transaction users and data types show a trend of dual growth and composition, and a relatively simple and accessible user examination and classification method cannot meet the safety requirements of a data transaction platform.
Disclosure of Invention
In view of the above problems, embodiments of the present invention provide a method, an apparatus, and a device for controlling data transaction permission, which solve the above technical problems in the prior art.
According to an aspect of an embodiment of the present invention, there is provided a data transaction authority control method, including:
acquiring initial credit data of a user;
determining an initial credit evaluation value of the user through a preset random forest feature model according to the initial credit data of the user;
determining initial data transaction authority according to the initial credit evaluation value of the user;
monitoring the change information of the initial credit data of the user;
generating a user risk rating through a preset credit rating prediction model according to the change information;
and controlling the data transaction authority according to the user risk rating.
In some embodiments, the user-initiated credit data includes credit data weight information;
the method for determining the initial credit evaluation value of the user through the preset random forest feature model according to the initial credit data of the user comprises the following steps:
screening the initial credit data of the user according to the weight information;
inputting the screened initial user credit data serving as a sample into the random forest characteristic model for model training;
and determining an initial credit evaluation value of the user through the trained random forest feature model.
In some embodiments, the change information of the user initial credit data includes: changing the initial credit data of the user and data access behavior;
the generating of the user risk rating through a preset credit rating prediction model according to the change information comprises the following steps:
inputting the changed initial credit data and data access behavior data of the user into a gradient descent tree model for modeling;
and generating a user risk rating through the trained gradient descent tree model.
In some embodiments, the modeling the gradient descent tree model includes:
inputting a sample data set and a loss function, wherein the loss function represents a loss function of a corresponding class;
calculating the probability of the sample point belonging to each category according to the input training data set and the loss function;
and determining the user risk rating of the corresponding category of the user according to the probability that the sample point belongs to each category.
In some embodiments, before controlling the data transaction right according to the user risk rating, the method further includes:
constructing a user feature data set according to the initial credit assessment value and the user risk rating;
clustering by a distance nearest method according to the user characteristic data set;
and when the Euclidean distances between the clusters are not less than a preset threshold value, outputting a user risk classification and grading result.
In some embodiments, the controlling the data transaction right according to the user risk rating further comprises:
averaging the initial credit assessment value, the user risk rating and the user risk classification grading result;
taking the average value as a final credit classification grading result of the user;
and controlling the data transaction authority according to the final credit classification grading result.
An embodiment of the present application further provides a data transaction authority control device, including:
the user initial credit data acquisition module: the system is used for acquiring user initial credit data;
an initial credit evaluation value determination module: the system comprises a user initial credit evaluation value determination module, a user initial credit evaluation value determination module and a user initial credit evaluation value determination module, wherein the user initial credit evaluation value determination module is used for determining an initial credit evaluation value of a user through a preset random forest feature model according to the user initial credit data;
an initial data transaction authority determination module: the system is used for determining initial data transaction authority according to the initial credit evaluation value of the user;
a monitoring module: the change information is used for monitoring the initial credit data of the user;
a user risk level generation module: the system is used for generating a user risk rating through a preset credit rating prediction model according to the change information;
the data transaction authority control module: for controlling the data transaction right according to the user risk rating.
In some embodiments, the apparatus further comprises:
and a final credit classification grading result determining module: the system is used for constructing a user characteristic data set according to the initial credit evaluation value and the user risk rating, and clustering according to the user characteristic data set by a distance nearest method; when the Euclidean distances among the clusters are not smaller than a preset threshold value, outputting a user risk classification and grading result; and averaging the initial credit evaluation value, the user risk rating and the user risk classification grading result, and taking the average value as a final credit classification grading result of the user.
An embodiment of the present application further provides a server, including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation of the data transaction authority control method in the embodiment.
The embodiment of the present application further provides a computer-readable storage medium, where at least one executable instruction is stored in the storage medium, and when the executable instruction runs on the data transaction right control device, the data transaction right control device is enabled to execute the operation of the data transaction right control method in the foregoing embodiment.
According to the data transaction authority control method provided by the embodiment, on the basis of determining the initial credit evaluation value of the user based on the initial credit data of the user, the risk of the user is evaluated again based on the initial credit data after the user changes through the credit grade prediction model, the user risk rating can be generated in real time according to the data change and the operation behavior of the user, and the data transaction authority of the user is controlled according to the user risk rating, so that the control of the data transaction authority is more refined, and the real situation of the user can be reflected in real time.
The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and the embodiments of the present invention can be implemented according to the content of the description in order to make the technical means of the embodiments of the present invention more clearly understood, and the detailed description of the present invention is provided below in order to make the foregoing and other objects, features, and advantages of the embodiments of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 shows a flowchart of a data transaction right control method provided by an embodiment of the present invention;
FIG. 2 is a flow chart illustrating determination of an initial credit evaluation value according to an embodiment of the invention;
FIG. 3 is a flowchart illustrating a method for determining a user risk classification result according to an embodiment of the present invention;
FIG. 4 is a block diagram of a data transaction authority control device provided by an embodiment of the invention;
fig. 5 is a diagram illustrating a server apparatus according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
In the prior art, when a user conducts data transaction, user main body credit data needs to be submitted to a data transaction platform, a data transaction platform manager distributes corresponding authority for the user after checking and confirming the user main body credit data, and a system manages data transaction behaviors of the user according to the user authority. Once the corresponding authority is allocated to the user, the trading platform cannot know the change of the user body and cannot change the trading authority of the user body unless the user actively submits credit change data of the user body. And often the user's body is very variable, such as: when the main user has illegal behaviors or data transaction illegal behaviors, the authority of the main user needs to be locked or changed to avoid illegal use of data, and the existing data transaction behavior control mode has no way of fine control and has many hidden dangers.
In order to solve the above problems in the prior art, an embodiment of the present application provides a data transaction authority control method, as shown in fig. 1, the method includes:
step 101: acquiring initial credit data of a user;
when the user is admitted, the trading platform will require the user to provide qualification-class static data as the basis for examination and evaluation, including but not limited to: the method comprises the following steps of providing data indexes such as user address areas, address types, established dates, industry classifications, the number of changes of stakeholders of law people in nearly 3 months, address changes, enterprise scale, social security payment number, tax payment amount, continuous tax payment month number, whether to go to a market company and the like.
The data acquisition can require the user to directly input through the data transaction platform, or the transaction platform can automatically synchronize the user main name database after the user inputs the main name, and acquire the static data related to the main name from the user main name database.
Step 102: determining an initial credit evaluation value of the user through a preset random forest feature model according to the initial credit data of the user;
taking the initial credit data in the data transaction platform as a sample, and constructing a user admission data feature model by using a random forest feature model, specifically, as shown in fig. 2, the method includes:
step 1021: screening the initial credit data of the user according to the weight information;
and after the initial credit data of the user is acquired, performing primary processing on the initial credit data of the user according to a preset rule, wherein the primary processing comprises dirty data cleaning, data format sorting and the like, so that the initial credit data of the user meets the requirements of primary data processing.
In order to improve the accuracy of the data model, the initial credit data of the user needs to be divided into different weights, the weights of some items are high, the weights of some items are low, and the transaction platform can set the weights of the items in advance to automatically perform item matching. And selecting a transaction data value with a data weight value exceeding a preset threshold value, and inputting the part of data value serving as a characteristic index into the random forest characteristic model.
By screening the weight of the initial credit data of the user, the accuracy of data prediction is improved.
Step 1022: inputting the screened initial user credit data serving as a sample into the random forest characteristic model for model training;
the random forest feature model is a classifier including a plurality of decision trees, the output class of the random forest feature model is determined by the mode of the class output by individual trees, each decision tree is a classifier, and for an input sample, N trees have N classification results, which is similar to the random forest feature model in the prior art and is not described herein again.
Step 1023: determining an initial credit evaluation value of a user through the trained random forest characteristic model;
and performing initial credit evaluation on the newly admitted user according to the trained random forest characteristic model, and determining the initial credit evaluation value of the user.
Step 103: determining initial data transaction authority according to the initial credit evaluation value of the user;
the data trading platform sets a mapping relation between the initial credit evaluation value and the initial data trading authority in advance, and when the initial credit evaluation value of the user is obtained, the data trading platform automatically matches the corresponding initial data trading authority for the user.
Step 104: monitoring the change information of the initial credit data of the user;
for an admitted subject user, the data transaction platform monitors the change information of the initial credit data of the user, wherein the change information of the initial credit data of the user comprises the following steps: and (3) changing the initial credit data of the user and data access behaviors, and taking the changed information as a data basis of the risk rating of the user.
Step 105: generating a user risk rating through a preset credit rating prediction model according to the change information;
and inputting the changed initial credit data and data access behavior data of the user into a gradient descent tree model for modeling. And generating a user risk rating through the trained gradient descent tree model.
Due to the difference of industries and types, the data of users have the missing conditions of different degrees, so the gradient descent tree algorithm with low requirement on the integrity of the data is modeled by sampling, and the basic process is as follows:
assuming f (x) represents the learner's correlation function, then ft-1(x) It represents the strong learner from the previous round, so that L (y, f) is usedt-1(x) To represent the loss function, the objective of the algorithm is to find a weak learner ht(x) Further, the loss function L (y, f)t-1(x))=L(y,ft-1(x)+ht(x) To a minimum).
In the application scenario, the initial credit evaluation value and the risk classification of the user are discrete samples, the output is discontinuous, and the direct output class cannot be used for fitting the error of class output. Therefore, using the logistic regression log-likelihood loss function method, the predicted probability values of the classes are used to fit the losses.
The algorithm is implemented as follows:
inputting a sample data set and a loss function, wherein the loss function represents a loss function of the class, and setting the input sample data set as T { (x)1,y1),(x2,y2),...,(xN,yN) A loss function ofIndicates whether or not the classification belongs to the kth class, 1 indicates that the classification belongs to the class, and 0 indicates that the classification does not belong to the class. K is 1,2, …, K, indicating the total number of classification categories. The output classification tree is F (x).
(1) Initialization:
fk0(x)=0,k=1,2,…,K
(2) for M ═ 1,2, …, M:
(a) calculate the probability that a sample point belongs to each category:
(b) for K ═ 1,2, …, K:
rki=yki-Pk(xi),i=1,2,…,N
for probabilistic pseudo-residual { (x)1,rk1),...,(xN,rkN) Fitting a classification tree
(3) The final classification tree is obtained as:
calculating the probability of the sample point belonging to each category according to the input training data set and the loss function to obtain FMk(x) Can be used to derive a corresponding probability P that is classified into the kth classMk(x):
And determining the user risk rating of the corresponding category of the user according to the probability of the sample point belonging to each category, and finally converting the probability into the category as follows because the difference between the predicted probability value and the real probability value of the category is used for fitting loss:
for the final output class, c (k, k ') is the joint cost when the k-th class is predicted when the real value is k', i.e. the class with the highest probability is the class we predict.
On the basis, the user risk classification is divided, the classification is determined as the classification with the high probability, and different classification groups are defined as different credit grades.
Step 106: and controlling the data transaction authority according to the user risk rating.
After the initial credit evaluation value of the user is determined, change information of initial credit data of the user is further monitored, a user risk rating is generated according to the change information, and the data transaction authority is controlled according to the updated user risk rating.
According to the data transaction authority control method provided by the embodiment, on the basis of determining the initial credit evaluation value of the user based on the initial credit data of the user, the risk of the user is evaluated again based on the initial credit data after the user changes through the credit grade prediction model, the user risk rating can be generated in real time according to the data change and the operation behavior of the user, and the data transaction authority of the user is controlled according to the user risk rating, so that the control of the data transaction authority is more refined, and the real situation of the user can be reflected in real time.
Furthermore, another data transaction right control method is further provided in the embodiments of the present application, as shown in fig. 3, in the above embodiments, the purpose of controlling the user data transaction right based on the user initial credit evaluation value and the user risk rating is achieved, in this embodiment, for user data transaction behaviors in different industries and fields, a user feature tagging manner is adopted, and then a clustering algorithm is used to achieve a user natural classification matching right, which specifically includes:
step 1061: constructing a user characteristic data set;
and constructing a user characteristic data set based on the initial credit data of the user, and performing natural language word segmentation processing based on the establishment time, the business scale, the business range and the requirement description of the user to form a tag characteristic data set.
Step 1062: initializing leaf nodes;
and (4) bringing the user characteristic data set into a clustering algorithm, and initializing leaf nodes.
Step 1063: combining leaf nodes with the nearest Euclidean distance;
step 1064: clustering by a distance nearest method according to the user characteristic data set;
step 1065: judging whether the Euclidean distances among the clusters are not smaller than a preset threshold value;
if the Euclidean distance between the clusters is not less than the preset threshold value, go to step 1066, otherwise go to step 1063.
Step 1066: and outputting the classification and grading result of the user risk.
Step 1067: and averaging the initial credit evaluation value, the user risk rating and the user risk classification grading result.
The initial credit evaluation value, the user risk rating and the user risk classification grading result determined in the embodiment are comprehensively considered, and the values of the initial credit evaluation value, the user risk rating and the user risk classification grading result are averaged.
Step 1068: and taking the average value as a final credit classification grading result of the user.
And controlling the data transaction authority according to the final credit classification grading result.
Therefore, in the embodiment of the application, under the condition that the user attribute information and the behavior information cannot be completed, the initial credit evaluation value, the user risk rating and the user risk classification result are comprehensively considered, the values of the initial credit evaluation value, the user risk rating and the user risk classification result are averaged, all dimensions are mutually complemented, and a final credit classification rating evaluation conclusion is finally formed, so that the biased difference of credit risk evaluation caused by the defects of single dimension and algorithm is avoided, the credit classification rating of users at all stages can be more comprehensive and suitable, the requirement of a system for immediately adjusting the data authority of data transaction users is met, and the security risk of data transaction is avoided to a certain extent.
Fig. 4 is a schematic structural diagram illustrating a data transaction right control device 200 according to an embodiment of the present invention. As shown in fig. 4, the apparatus 200 includes: a user initial credit data acquisition module 201, an initial credit evaluation value determination module 202, an initial data transaction authority determination module 203, a monitoring module 204, a user risk level generation module 205 and a data transaction authority control module 206;
the user initial credit data acquisition module 201 is configured to acquire user initial credit data;
the initial credit evaluation value determining module 202 is configured to determine an initial credit evaluation value of the user through a preset random forest feature model according to the user initial credit data;
the initial data transaction authority determining module 203 is configured to determine an initial data transaction authority according to the initial credit evaluation value of the user;
the monitoring module 204 is configured to monitor change information of the user initial credit data;
the user risk level generation module 205 is configured to generate a user risk rating according to the change information through a preset credit level prediction model;
the data transaction right control module 206 is configured to control the data transaction right according to the user risk rating.
In some embodiments, the initial credit evaluation value determining module 202 further comprises:
screening the initial credit data of the user according to the weight information;
inputting the screened initial user credit data serving as a sample into the random forest characteristic model for model training;
and determining an initial credit evaluation value of the user through the trained random forest feature model.
In some embodiments, the user risk level generation module 205 further comprises:
inputting the changed initial credit data and data access behavior data of the user into a gradient descent tree model for modeling;
and generating a user risk rating through the trained gradient descent tree model.
In some embodiments, the user risk level generation module 205 further comprises:
inputting a sample data set and a loss function, wherein the loss function represents a loss function of a corresponding class;
calculating the probability of the sample point belonging to each category according to the input training data set and the loss function;
and determining the user risk rating of the corresponding category of the user according to the probability that the sample point belongs to each category.
In some embodiments, the apparatus further comprises:
and a final credit classification grading result determining module: the system is used for constructing a user characteristic data set according to the initial credit evaluation value and the user risk rating, and clustering according to the user characteristic data set by a distance nearest method; when the Euclidean distances among the clusters are not smaller than a preset threshold value, outputting a user risk classification and grading result; and averaging the initial credit evaluation value, the user risk rating and the user risk classification grading result, and taking the average value as a final credit classification grading result of the user.
By the data transaction authority control device provided by the embodiment, on the basis of determining the initial credit evaluation value of the user based on the initial credit data of the user, the risk of the user is evaluated again based on the initial credit data after the user changes through the credit grade prediction model, the user risk rating can be generated in real time according to the data change and the operation behavior of the user, and the data transaction authority of the user is controlled according to the user risk rating, so that the control of the data transaction authority is more refined, and the real situation of the user can be reflected in real time.
The embodiment of the present invention further provides a non-volatile computer storage medium, where the computer storage medium stores at least one executable instruction, and the computer executable instruction may execute the data transaction right control method in any of the above method embodiments.
The executable instructions may be specifically configured to cause the processor to:
acquiring initial credit data of a user;
determining an initial credit evaluation value of the user through a preset random forest feature model according to the initial credit data of the user;
determining initial data transaction authority according to the initial credit evaluation value of the user;
monitoring the change information of the initial credit data of the user;
generating a user risk rating through a preset credit rating prediction model according to the change information;
and controlling the data transaction authority according to the user risk rating.
In some embodiments, the user-initiated credit data includes credit data weight information;
the method for determining the initial credit evaluation value of the user through the preset random forest feature model according to the initial credit data of the user comprises the following steps:
screening the initial credit data of the user according to the weight information;
inputting the screened initial user credit data serving as a sample into the random forest characteristic model for model training;
and determining an initial credit evaluation value of the user through the trained random forest feature model.
In some embodiments, the change information of the user initial credit data includes: changing the initial credit data of the user and data access behavior;
the generating of the user risk rating through a preset credit rating prediction model according to the change information comprises the following steps:
inputting the changed initial credit data and data access behavior data of the user into a gradient descent tree model for modeling;
and generating a user risk rating through the trained gradient descent tree model.
In some embodiments, the modeling the gradient descent tree model includes:
inputting a sample data set and a loss function, wherein the loss function represents a loss function of a corresponding class;
calculating the probability of the sample point belonging to each category according to the input training data set and the loss function;
and determining the user risk rating of the corresponding category of the user according to the probability that the sample point belongs to each category.
In some embodiments, before controlling the data transaction right according to the user risk rating, the method further includes:
constructing a user feature data set according to the initial credit assessment value and the user risk rating;
clustering by a distance nearest method according to the user characteristic data set;
and when the Euclidean distances between the clusters are not less than a preset threshold value, outputting a user risk classification and grading result.
In some embodiments, the controlling the data transaction right according to the user risk rating further comprises:
averaging the initial credit assessment value, the user risk rating and the user risk classification grading result;
taking the average value as a final credit classification grading result of the user;
and controlling the data transaction authority according to the final credit classification grading result.
According to the embodiment, on the basis of determining the user initial credit evaluation value based on the user initial credit data, the risk of the user is evaluated again based on the initial credit data after the user changes through the credit rating prediction model, the user risk rating can be generated in real time according to the data change and the operation behavior of the user, the user data transaction authority is controlled according to the user risk rating, the control of the data transaction authority is enabled to be more refined, and the real situation of the user can be reflected in real time.
Fig. 5 is a schematic structural diagram of a server according to the present invention, and the embodiment of the present invention does not limit the specific implementation of the server.
As shown in fig. 5, the server may include: a processor (processor)502, a Communications Interface 504, a memory 506, and a communication bus 508.
Wherein: the processor 502, communication interface 504, and memory 506 communicate with one another via a communication bus 508. A communication interface 504 for communicating with network elements of other devices, such as clients or other servers. The processor 502 is configured to execute the program 510, and may specifically execute the relevant steps in the above embodiments of the data transaction right control method.
In particular, program 510 may include program code that includes computer operating instructions.
The processor 502 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement an embodiment of the present invention. The one or more processors included in the server may be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
And a memory 506 for storing a program 510. The memory 506 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 510 may specifically be used to cause the processor 502 to perform the following operations:
acquiring initial credit data of a user;
determining an initial credit evaluation value of the user through a preset random forest feature model according to the initial credit data of the user;
determining initial data transaction authority according to the initial credit evaluation value of the user;
monitoring the change information of the initial credit data of the user;
generating a user risk rating through a preset credit rating prediction model according to the change information;
and controlling the data transaction authority according to the user risk rating.
In some embodiments, the user-initiated credit data includes credit data weight information;
the method for determining the initial credit evaluation value of the user through the preset random forest feature model according to the initial credit data of the user comprises the following steps:
screening the initial credit data of the user according to the weight information;
inputting the screened initial user credit data serving as a sample into the random forest characteristic model for model training;
and determining an initial credit evaluation value of the user through the trained random forest feature model.
In some embodiments, the change information of the user initial credit data includes: changing the initial credit data of the user and data access behavior;
the generating of the user risk rating through a preset credit rating prediction model according to the change information comprises the following steps:
inputting the changed initial credit data and data access behavior data of the user into a gradient descent tree model for modeling;
and generating a user risk rating through the trained gradient descent tree model.
In some embodiments, the modeling the gradient descent tree model includes:
inputting a sample data set and a loss function, wherein the loss function represents a loss function of a corresponding class;
calculating the probability of the sample point belonging to each category according to the input training data set and the loss function;
and determining the user risk rating of the corresponding category of the user according to the probability that the sample point belongs to each category.
In some embodiments, before controlling the data transaction right according to the user risk rating, the method further includes:
constructing a user feature data set according to the initial credit assessment value and the user risk rating;
clustering by a distance nearest method according to the user characteristic data set;
and when the Euclidean distances between the clusters are not less than a preset threshold value, outputting a user risk classification and grading result.
In some embodiments, the controlling the data transaction right according to the user risk rating further comprises:
averaging the initial credit assessment value, the user risk rating and the user risk classification grading result;
taking the average value as a final credit classification grading result of the user;
and controlling the data transaction authority according to the final credit classification grading result.
According to the embodiment, on the basis of determining the user initial credit evaluation value based on the user initial credit data, the risk of the user is evaluated again based on the initial credit data after the user changes through the credit rating prediction model, the user risk rating can be generated in real time according to the data change and the operation behavior of the user, the user data transaction authority is controlled according to the user risk rating, the control of the data transaction authority is enabled to be more refined, and the real situation of the user can be reflected in real time.
The embodiment of the present invention further provides a computer program, which is used for executing the data transaction right control method of the above embodiment, and the functions of the computer program are completely consistent with those of the above method, and are not described herein again.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.
Claims (10)
1. A data transaction authority control method is characterized by comprising the following steps:
acquiring initial credit data of a user;
determining an initial credit evaluation value of the user through a preset random forest feature model according to the initial credit data of the user;
determining initial data transaction authority according to the initial credit evaluation value of the user;
monitoring the change information of the initial credit data of the user;
generating a user risk rating through a preset credit rating prediction model according to the change information;
and controlling the data transaction authority according to the user risk rating.
2. The method of claim 1, wherein the user-initiated credit data includes credit data weight information;
the method for determining the initial credit evaluation value of the user through the preset random forest feature model according to the initial credit data of the user comprises the following steps:
screening the initial credit data of the user according to the weight information;
inputting the screened initial user credit data serving as a sample into the random forest characteristic model for model training;
and determining an initial credit evaluation value of the user through the trained random forest feature model.
3. The method of claim 2, wherein the change information of the user initial credit data comprises: changing the initial credit data of the user and data access behavior;
the generating of the user risk rating through a preset credit rating prediction model according to the change information comprises the following steps:
inputting the changed initial credit data and data access behavior data of the user into a gradient descent tree model for modeling;
and generating a user risk rating through the trained gradient descent tree model.
4. The method of claim 3, wherein modeling the gradient descent tree model comprises:
inputting a sample data set and a loss function, wherein the loss function represents a loss function of a corresponding class;
calculating the probability of the sample point belonging to each category according to the input training data set and the loss function;
and determining the user risk rating of the corresponding category of the user according to the probability that the sample point belongs to each category.
5. The method of claim 4, wherein prior to controlling the data transaction right according to the user risk rating, further comprising:
constructing a user feature data set according to the initial credit assessment value and the user risk rating;
clustering by a distance nearest method according to the user characteristic data set;
and when the Euclidean distances between the clusters are not less than a preset threshold value, outputting a user risk classification and grading result.
6. The method of claim 5, wherein the controlling the data transaction right according to the user risk rating further comprises:
averaging the initial credit assessment value, the user risk rating and the user risk classification grading result;
taking the average value as a final credit classification grading result of the user;
and controlling the data transaction authority according to the final credit classification grading result.
7. A data transaction authority control device, comprising:
the user initial credit data acquisition module: the system is used for acquiring user initial credit data;
an initial credit evaluation value determination module: the system comprises a user initial credit evaluation value determination module, a user initial credit evaluation value determination module and a user initial credit evaluation value determination module, wherein the user initial credit evaluation value determination module is used for determining an initial credit evaluation value of a user through a preset random forest feature model according to the user initial credit data;
an initial data transaction authority determination module: the system is used for determining initial data transaction authority according to the initial credit evaluation value of the user;
a monitoring module: the change information is used for monitoring the initial credit data of the user;
a user risk level generation module: the system is used for generating a user risk rating through a preset credit rating prediction model according to the change information;
the data transaction authority control module: for controlling the data transaction right according to the user risk rating.
8. The apparatus of claim 7, wherein the apparatus further comprises:
and a final credit classification grading result determining module: the system is used for constructing a user characteristic data set according to the initial credit evaluation value and the user risk rating, and clustering according to the user characteristic data set by a distance nearest method; when the Euclidean distances among the clusters are not smaller than a preset threshold value, outputting a user risk classification and grading result; and averaging the initial credit evaluation value, the user risk rating and the user risk classification grading result, and taking the average value as a final credit classification grading result of the user.
9. A server, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the operation of the data transaction authority control method according to any one of claims 1-6.
10. A computer-readable storage medium, wherein at least one executable instruction is stored in the storage medium, and when the executable instruction is executed on a data transaction right control device, the executable instruction causes the data transaction right control device to execute the operation of the data transaction right control method according to any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111040178.5A CN113793007B (en) | 2021-09-06 | 2021-09-06 | Data transaction authority control method, device and equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111040178.5A CN113793007B (en) | 2021-09-06 | 2021-09-06 | Data transaction authority control method, device and equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113793007A true CN113793007A (en) | 2021-12-14 |
CN113793007B CN113793007B (en) | 2024-02-27 |
Family
ID=78879579
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111040178.5A Active CN113793007B (en) | 2021-09-06 | 2021-09-06 | Data transaction authority control method, device and equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113793007B (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101493913A (en) * | 2008-01-23 | 2009-07-29 | 阿里巴巴集团控股有限公司 | Method and system for assessing user credit in internet |
CN103514566A (en) * | 2013-10-15 | 2014-01-15 | 国家电网公司 | Risk control system and method |
US20140237545A1 (en) * | 2013-02-19 | 2014-08-21 | Marble Security | Hierarchical risk assessment and remediation of threats in mobile networking environment |
CN108960956A (en) * | 2018-03-28 | 2018-12-07 | 翟红鹰 | A kind of digital asset risk management and control method, system and storage medium |
CN109685635A (en) * | 2018-09-11 | 2019-04-26 | 深圳平安财富宝投资咨询有限公司 | Methods of risk assessment, air control server-side and the storage medium of financial business |
CN110119988A (en) * | 2019-04-19 | 2019-08-13 | 深圳壹账通智能科技有限公司 | Product trading method, device and computer equipment based on decision-tree model |
US20190294786A1 (en) * | 2018-03-26 | 2019-09-26 | Adp, Llc | Intelligent Security Risk Assessment |
CN110706090A (en) * | 2019-08-26 | 2020-01-17 | 阿里巴巴集团控股有限公司 | Credit fraud identification method and device, electronic equipment and storage medium |
CN112508580A (en) * | 2021-02-03 | 2021-03-16 | 北京淇瑀信息科技有限公司 | Model construction method and device based on rejection inference method and electronic equipment |
CN112749973A (en) * | 2021-01-12 | 2021-05-04 | 腾讯科技(深圳)有限公司 | Authority management method and device and computer readable storage medium |
-
2021
- 2021-09-06 CN CN202111040178.5A patent/CN113793007B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101493913A (en) * | 2008-01-23 | 2009-07-29 | 阿里巴巴集团控股有限公司 | Method and system for assessing user credit in internet |
US20140237545A1 (en) * | 2013-02-19 | 2014-08-21 | Marble Security | Hierarchical risk assessment and remediation of threats in mobile networking environment |
CN103514566A (en) * | 2013-10-15 | 2014-01-15 | 国家电网公司 | Risk control system and method |
US20190294786A1 (en) * | 2018-03-26 | 2019-09-26 | Adp, Llc | Intelligent Security Risk Assessment |
CN108960956A (en) * | 2018-03-28 | 2018-12-07 | 翟红鹰 | A kind of digital asset risk management and control method, system and storage medium |
CN109685635A (en) * | 2018-09-11 | 2019-04-26 | 深圳平安财富宝投资咨询有限公司 | Methods of risk assessment, air control server-side and the storage medium of financial business |
CN110119988A (en) * | 2019-04-19 | 2019-08-13 | 深圳壹账通智能科技有限公司 | Product trading method, device and computer equipment based on decision-tree model |
CN110706090A (en) * | 2019-08-26 | 2020-01-17 | 阿里巴巴集团控股有限公司 | Credit fraud identification method and device, electronic equipment and storage medium |
CN112749973A (en) * | 2021-01-12 | 2021-05-04 | 腾讯科技(深圳)有限公司 | Authority management method and device and computer readable storage medium |
CN112508580A (en) * | 2021-02-03 | 2021-03-16 | 北京淇瑀信息科技有限公司 | Model construction method and device based on rejection inference method and electronic equipment |
Non-Patent Citations (2)
Title |
---|
孔祥林;付靖国;刘文艳;: "银行在客户信用评级过程中风险的产生及其防范措施", 内蒙古科技与经济, no. 18, pages 83 - 91 * |
王海艳;戴桦;王汝传;: "基于行为持续性的电子商务信任与风险评估方法", 南通大学学报(自然科学版), no. 03, pages 6 - 8 * |
Also Published As
Publication number | Publication date |
---|---|
CN113793007B (en) | 2024-02-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107025596B (en) | Risk assessment method and system | |
US8346691B1 (en) | Computer-implemented semi-supervised learning systems and methods | |
CN109739844B (en) | Data classification method based on attenuation weight | |
CN109949154B (en) | Customer information classification method, apparatus, computer device and storage medium | |
CN109711955B (en) | Poor evaluation early warning method and system based on current order and blacklist base establishment method | |
CN110458324B (en) | Method and device for calculating risk probability and computer equipment | |
CN110084468B (en) | Risk identification method and device | |
CN111754044A (en) | Employee behavior auditing method, device, equipment and readable storage medium | |
CN112561685A (en) | Client classification method and device | |
CN112749973A (en) | Authority management method and device and computer readable storage medium | |
CN111752985B (en) | Method, device and storage medium for generating main body portrait | |
Shinde et al. | Loan prediction system using machine learning | |
Rao et al. | Integration of ARAS and MOORA MCDM techniques for measuring the performance of private sector banks in India | |
CN113947476A (en) | Method, device, equipment and storage medium for identifying lost-message client | |
Shams | Money, income, and prices in Bangladesh: A cointegration and causality analysis | |
CN111160647A (en) | Money laundering behavior prediction method and device | |
CN113793007B (en) | Data transaction authority control method, device and equipment | |
CN112926989B (en) | Bank loan risk assessment method and equipment based on multi-view integrated learning | |
CN113610504A (en) | Data processing method and device, computer equipment and storage medium | |
Vasco et al. | Segmentation of potential fraud taxpayers and characterization in personal income tax using data mining techniques | |
dos Santos et al. | Clustering of Assets: An Alternative to Assist in Financial Decisions | |
CN112819347B (en) | Industry subject auditing method and device, electronic equipment and storage medium | |
Yong et al. | Empirical study on credit classification of E-commerce sellers based on FCM algorithm | |
Rodin | Growing small businesses using software system for intellectual analysis of financial performance | |
CN110956471A (en) | Method for analyzing credit investigation data of decoration industry |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |