CN115907971B - Data processing method and device suitable for personal credit evaluation system - Google Patents
Data processing method and device suitable for personal credit evaluation system Download PDFInfo
- Publication number
- CN115907971B CN115907971B CN202310044840.7A CN202310044840A CN115907971B CN 115907971 B CN115907971 B CN 115907971B CN 202310044840 A CN202310044840 A CN 202310044840A CN 115907971 B CN115907971 B CN 115907971B
- Authority
- CN
- China
- Prior art keywords
- credit
- preset
- credit evaluation
- evaluation
- behavior
- 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.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 296
- 238000003672 processing method Methods 0.000 title claims abstract description 15
- 230000006399 behavior Effects 0.000 claims abstract description 170
- 238000013210 evaluation model Methods 0.000 claims abstract description 86
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims description 66
- 238000012549 training Methods 0.000 claims description 50
- 238000013507 mapping Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 13
- 238000012795 verification Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 2
- 230000003542 behavioural effect Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The application provides a data processing method and device suitable for a personal credit evaluation system. According to the method, a personal credit behavior data set uploaded by a user is obtained, behavior characteristic data is extracted from the personal credit behavior data set according to preset data sorting conditions and preset characteristic classification rules to generate a characteristic data set, a credit evaluation result corresponding to a target service is determined according to the characteristic data set and a preset credit evaluation model, and the credit evaluation result corresponding to the target service is determined through the preset credit evaluation model, wherein the preset credit evaluation model comprises a plurality of preset credit evaluation sub-models, each preset credit evaluation sub-model is used for evaluating different credit behaviors, and the evaluation weight of the evaluation sub-results output by each preset credit evaluation sub-model is determined through the service type of the target service so that the comprehensiveness of credit evaluation of the user is ensured, and meanwhile the accuracy of credit evaluation of the user is also considered.
Description
Technical Field
The present disclosure relates to data processing technologies, and in particular, to a data processing method and apparatus suitable for a personal credit evaluation system.
Background
With the rapid development of social economy in China, the living standard of people is gradually improved, the income in the current period can not meet the consumption demands of people, and various credit businesses are also increased unprecedentedly.
To circumvent the credit business risk, commercial banks or application platforms need to conduct personal credit assessment on the user, and judge the likelihood of their performance, thereby making a decision whether to pay a credit or not. At present, personal credit evaluation mostly depends on professional experience of credit evaluation experts, has strong subjectivity, and cannot evaluate credit conditions of the applicant comprehensively and objectively.
Therefore, there is a need for ways to be able to comprehensively and accurately evaluate the actual personal credit behavior data of a user based thereon.
Disclosure of Invention
The application provides a data processing method and device suitable for a personal credit evaluation system, which are used for comprehensively and accurately evaluating personal credits of a user based on actual personal credit behavior data of the user.
In a first aspect, the present application provides a data processing method suitable for a personal credit assessment system, comprising:
Acquiring a personal credit behavior data set uploaded by a user, wherein the personal credit behavior data set comprises credit behavior data of the user on a plurality of application platforms, and original characteristic fields in the credit behavior data on each application platform are different;
extracting behavior feature data from the personal credit behavior data set according to preset data sorting conditions and preset feature classification rules to generate a feature data set, wherein the preset data sorting conditions comprise at least one of behavior occurrence time conditions and behavior type conditions, the preset feature classification rules are used for establishing mapping relations between original feature fields and target feature fields, and the behavior feature data comprise behavior data corresponding to the target feature fields;
and determining a credit evaluation result corresponding to the target service according to the characteristic data set and a preset credit evaluation model, wherein the preset credit evaluation model comprises a plurality of preset credit evaluation sub-models, each preset credit evaluation sub-model is used for evaluating different credit behaviors, and the service type of the target service is used for determining the evaluation weight of the evaluation sub-result output by each preset credit evaluation sub-model.
Optionally, the data processing method suitable for the personal credit evaluation system further includes:
acquiring a credit behavior original data set A, wherein the credit behavior original data set comprises credit behavior original data of different types of data sources;
splitting the credit action raw data set A into N credit action data subsets:
wherein, the method comprises the steps of, wherein,
the method comprises the steps of (1) obtaining credit behavior original data of an ith type of data source, wherein i is an integer which is greater than or equal to 1 and less than or equal to N;
generating M credit behavior training sets according to the credit behavior original data set A:
, wherein ,
j is an integer greater than or equal to 1 and less than or equal to M for the jth credit behavior training set, wherein M is the number of the preset credit evaluation submodels in the preset credit evaluation model; and, in addition, the processing unit,
, wherein ,
is that
Is a subset of the (a)
Comprises the following steps
In a preset ratio
K is an integer greater than or equal to 1 and less than or equal to N, said
Is of the value of (2) and the
The correlation between the corresponding kth type data source and the jth preset credit evaluation submodel is positive correlation;
generating M credit behavior test sets according to the credit behavior original data set A:
, wherein ,
Training set for jth credit behaviorThe method comprises the steps of carrying out a first treatment on the surface of the And, in addition, the processing unit,
, wherein ,
；
by using the said
Training the j-th credit evaluation submodel to be trained and utilizing the j-th credit evaluation submodel to be trained
And carrying out test verification on the j-th credit evaluation submodel to be trained to generate the j-th preset credit evaluation submodel.
Optionally, after the generating the jth preset credit evaluation submodel, the method further includes:
acquiring a service original data set D, wherein the service original data set D comprises the credit behavior original data set A and a service evaluation result data set E corresponding to various service types;
generating an initial result training set F according to each preset credit evaluation sub-model and the service original data set D;
training the credit evaluation model to be trained according to the F and the E to generate the preset credit evaluation model, wherein the evaluation weight of the evaluation sub-result output by each preset credit evaluation sub-model determined based on the service type of the target service is matched with the parameter corresponding to the variable corresponding to each preset credit evaluation sub-model in the credit evaluation model to be trained.
Optionally, the training the credit assessment model to be trained according to the F and the E includes:
Training the credit evaluation model to be trained based on the credit evaluation model to be trained by using the F and the E, wherein the credit evaluation model to be trained comprises:
wherein ,
the assessment sub-result output by the ith preset credit assessment sub-model in the F is given,
is a constant value, and is used for the treatment of the skin,
is said
And n is an integer greater than 2, M is equal to n, i is an integer greater than 1 and less than n, and p is the credit evaluation result.
Optionally, if the target service includes K service types, determining, according to the feature data set and a preset credit evaluation model, a credit evaluation result corresponding to the target service includes:
and respectively determining credit evaluation sub-results corresponding to the service types according to the characteristic data set and the preset credit evaluation model to form a credit evaluation sub-result set P:
；
the credit evaluation result is determined according to the following formula:
wherein ,
is a constant value, and is used for the treatment of the skin,
the average of the sub-results is evaluated for each credit in said P,
for each of the PThe maximum value in the individual credit evaluation sub-results,
the minimum of the sub-results is evaluated for each credit in the P,
and for the t-th credit evaluation sub-result in each credit evaluation sub-result in the P, t is an integer which is greater than or equal to 1 and less than or equal to the K.
Optionally, after determining the credit evaluation result corresponding to the target service according to the feature data set and the preset credit evaluation model, the method further includes:
forming a credit evaluation report for the target service according to the credit evaluation result;
storing the credit assessment result and the personal credit behavior data set into a first file of a target blockchain node, and storing the credit assessment report into a second file of the target blockchain node; the first file is a first encryption grade, and when a first call instruction of a business supervision server is responded, the credit evaluation result and the personal credit behavior data set in the first file and the credit evaluation report in the second file are fed back to the business supervision server, wherein the first encryption grade is matched with a first access authority of the business supervision server; and the second file is a second encryption grade, and when responding to a second call instruction of the service processing server, the credit evaluation report in the second file is fed back to the service processing server, and the second encryption grade is matched with a second access right of the service processing server.
Optionally, if the first file stores H historical credit evaluation results
Wherein each historical credit evaluation result corresponds to different generation time, and determining a target service according to the characteristic data set and a preset credit evaluation modelAfter the corresponding credit evaluation result, the method further comprises the following steps:
based on the credit evaluation result
And determining a final credit assessment result s by the following formula:
wherein ,
is that
The corresponding weight i is an integer greater than or equal to 1 and less than or equal to H,
value heel
Corresponding time and the said
The time difference between the corresponding times is inversely related;
is said
The corresponding weight.
In a second aspect, the present application provides a data processing apparatus adapted for use in a personal credit assessment system, comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a personal credit behavior data set uploaded by a user, the personal credit behavior data set comprises credit behavior data of the user on a plurality of application platforms, and original characteristic fields in the credit behavior data on each application platform are different;
the extraction module is used for extracting behavior feature data from the personal credit behavior data set according to preset data sorting conditions and preset feature classification rules to generate a feature data set, wherein the preset data sorting conditions comprise at least one of behavior occurrence time conditions and behavior type conditions, the preset feature classification rules are used for establishing mapping relations between each original feature field and each target feature field, and the behavior feature data comprise behavior data corresponding to each target feature field;
The processing module is used for determining a credit evaluation result corresponding to the target service according to the characteristic data set and a preset credit evaluation model, wherein the preset credit evaluation model comprises a plurality of preset credit evaluation sub-models, each preset credit evaluation sub-model is used for evaluating different credit behaviors, and the service type of the target service is used for determining the evaluation weight of the evaluation sub-result output by each preset credit evaluation sub-model.
In one possible design, the acquisition module is further configured to: acquiring a credit behavior original data set A, wherein the credit behavior original data set comprises credit behavior original data of different types of data sources;
the processing module is further configured to split the credit action raw data set a into N credit action data subsets:
, wherein ,
the method comprises the steps of (1) obtaining credit behavior original data of an ith type of data source, wherein i is an integer which is greater than or equal to 1 and less than or equal to N;
the processing module is further configured to generate M credit behavior training sets according to the credit behavior raw data set a:
, wherein ,
for the j-th credit training set, j is greater than or equal to 1 and less thanOr an integer equal to M, where M is the number of the preset credit evaluation submodels in the preset credit evaluation model; and, in addition, the processing unit, 
, wherein ,
is that
Is a subset of the (a)
Comprises the following steps
In a preset ratio
K is an integer greater than or equal to 1 and less than or equal to N, said
Is of the value of (2) and the
The correlation between the corresponding kth type data source and the jth preset credit evaluation submodel is positive correlation;
the processing module is further configured to generate M credit behavior test sets according to the credit behavior raw data set a:
, wherein ,
training a j-th credit behavior; and, in addition, the processing unit,
, wherein ,
；
the processing module is also used for utilizing the
Training the j-th credit evaluation submodel to be trained and utilizing the j-th credit evaluation submodel to be trained
And carrying out test verification on the j-th credit evaluation submodel to be trained to generate the j-th preset credit evaluation submodel.
Optionally, the acquiring module is further configured to acquire a service original data set D, where the service original data set D includes the credit behavior original data set a and a service evaluation result data set E corresponding to various service types;
the processing module is further configured to generate an initial result training set F according to each of the preset credit evaluation submodels and the service original data set D;
the processing module is further configured to train the credit evaluation model to be trained according to the F and the E, so as to generate the preset credit evaluation model, where an evaluation weight of an evaluation sub-result output by each preset credit evaluation sub-model determined based on the service type of the target service is matched with a parameter corresponding to a variable corresponding to each preset credit evaluation sub-model in the credit evaluation model to be trained.
The processing module is specifically configured to:
training the credit evaluation model to be trained based on the credit evaluation model to be trained by using the F and the E, wherein the credit evaluation model to be trained comprises:
wherein ,
the assessment sub-result output by the ith preset credit assessment sub-model in the F is given,
is a constant value, and is used for the treatment of the skin,
is said
The corresponding evaluation weight, n is an integer greater than 2, M is equal to n, i is an integer greater than 1 and less than n, and p is the credit evaluation result;
if the target service includes K service types, the processing module is specifically configured to:
respectively determining credit evaluation sub-results corresponding to each service type according to the characteristic data set and the preset credit evaluation model to form a credit evaluation sub-result set
；
The credit evaluation result is determined according to the following formula:
wherein ,
is a constant value, and is used for the treatment of the skin,
the average of the sub-results is evaluated for each credit in said P,
the maximum value of the sub-results is evaluated for each credit in the P,
the minimum of the sub-results is evaluated for each credit in the P,
and for the t-th credit evaluation sub-result in each credit evaluation sub-result in the P, t is an integer which is greater than or equal to 1 and less than or equal to the K.
Optionally, the processing module is specifically configured to:
forming a credit evaluation report for the target service according to the credit evaluation result;
storing the credit assessment result and the personal credit behavior data set into a first file of a target blockchain node, and storing the credit assessment report into a second file of the target blockchain node; the first file is a first encryption grade, and when a first call instruction of a business supervision server is responded, the credit evaluation result and the personal credit behavior data set in the first file and the credit evaluation report in the second file are fed back to the business supervision server, wherein the first encryption grade is matched with a first access authority of the business supervision server; and the second file is a second encryption grade, and when responding to a second call instruction of the service processing server, the credit evaluation report in the second file is fed back to the service processing server, and the second encryption grade is matched with a second access right of the service processing server.
Optionally, if the first file stores H historical credit evaluation results 
The processing module is specifically configured to:
based on the credit evaluation result
And determining a final credit assessment result s by the following formula:
wherein ,
is that
The weight of the corresponding weight is set to be equal to the weight,i is an integer of 1 or more and H or less,
value heel
Corresponding time and the said
The time difference between the corresponding times is inversely related;
is said
The corresponding weight.
In a third aspect, the present application provides an electronic device, comprising:
a processor; the method comprises the steps of,
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform any one of the possible methods described in the first aspect via execution of the executable instructions.
In a fourth aspect, the present application provides a computer-readable storage medium having stored therein computer-executable instructions which, when executed by a processor, are adapted to carry out any one of the possible methods described in the first aspect.
According to the data processing method and device suitable for the personal credit evaluation system, the personal credit behavior data set uploaded by the user is obtained, then the behavior characteristic data is extracted from the personal credit behavior data set according to the preset data sorting condition and the preset characteristic classification rule to generate the characteristic data set, the credit evaluation result corresponding to the target service is determined according to the characteristic data set and the preset credit evaluation model, and the credit evaluation result corresponding to the target service is determined through the preset credit evaluation model, wherein the preset credit evaluation model comprises a plurality of preset credit evaluation sub-models, each preset credit evaluation sub-model is used for evaluating different credit behaviors, so that the comprehensiveness of credit evaluation of the user is ensured through the multisource of the personal credit behavior data set, and in addition, the evaluation weight of the evaluation sub-results output by each preset credit evaluation sub-model is determined through the service type of the target service, so that the comprehensiveness of the credit evaluation of the user is ensured, and the accuracy of the credit evaluation of the user is also considered.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
FIG. 1 is a flow chart of a data processing method for a personal credit assessment system according to an example embodiment of the present application;
FIG. 2 is a flow chart illustrating a data processing method suitable for use in a personal credit assessment system according to another example embodiment of the present application;
FIG. 3 is a schematic diagram of a data processing apparatus suitable for use in a personal credit assessment system, according to an example embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an example embodiment of the present application.
Specific embodiments thereof have been shown by way of example in the drawings and will herein be described in more detail. These drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.
Fig. 1 is a flow chart illustrating a data processing method suitable for a personal credit assessment system according to an example embodiment of the present application. As shown in fig. 1, the method provided in this embodiment includes:
s101, acquiring a personal credit behavior data set uploaded by a user.
In this step, a personal credit behavioural data set uploaded by the user may be obtained, where the original feature fields in the credit behavioural data on each application platform are different. The personal credit action data set may include credit action data of the user on a plurality of application platforms, for example, may include house credit record data, consumption credit record data, credit record data, credit card repayment record data and the like of the user on a banking platform, may include consumption credit record data and flower file record data on a payment platform, and may further include consumption record data on jingdong, naught, and makeups. Because the credit behaviors corresponding to the platforms are different and the characteristic fields of the credit behaviors defined by the platforms are different, the credit evaluation method has the advantage that only credit records of banks are usually adopted when personal credit evaluation is performed at present, and comprehensive evaluation cannot be performed by combining with actual personal credit behaviors of users on other various platforms.
In this step, in order to comprehensively evaluate the user, the acquired personal credit behavior data set uploaded by the user may include credit behavior data on each application platform.
S102, extracting behavior characteristic data from the personal credit behavior data set according to a preset data sorting condition and a preset characteristic classification rule to generate a characteristic data set.
After the personal credit behavior data set uploaded by the user is obtained, behavior feature data can be extracted from the personal credit behavior data set according to preset data sorting conditions and preset feature classification rules to generate a feature data set, wherein the preset data sorting conditions comprise at least one of behavior occurrence time conditions and behavior type conditions, the preset feature classification rules are used for establishing mapping relations between each original feature field and each target feature field, and the behavior feature data comprise behavior data corresponding to each target feature field. Optionally, the preset feature classification rule may be a mapping table designed for each application platform in advance, and after determining the application platform from which the data originates, the preset feature classification rule may be corresponding to the mapping table. In addition, the mapping table can be submitted and declared to the management server by each application platform on time, so that the management server can update the application platform on time, and credit evaluation of the user can be updated on time according to the updating of the application platform.
S103, determining a credit evaluation result corresponding to the target service according to the characteristic data set and a preset credit evaluation model.
Optionally, the credit evaluation result corresponding to the target service may be determined according to the feature data set and a preset credit evaluation model, where the preset credit evaluation model includes a plurality of preset credit evaluation sub-models, each of the preset credit evaluation sub-models is used to evaluate different credit behaviors, and the service type of the target service is used to determine an evaluation weight of the evaluation sub-result output by each of the preset credit evaluation sub-models.
Specifically, the plurality of preset credit evaluation sub-models included in the preset credit evaluation model may be a consumption credit evaluation sub-model, a credit evaluation sub-model, a house credit evaluation sub-model, and the like. When the service type of the target service is credit, the evaluation sub-results can be output based on the consumption credit evaluation sub-model, the credit evaluation sub-model and the house credit evaluation sub-model, and then the evaluation weight of each evaluation sub-result is determined according to the service type, so that the comprehensiveness and the accuracy of credit evaluation are considered.
In this embodiment, a personal credit behavior data set uploaded by a user is obtained, then behavior feature data is extracted from the personal credit behavior data set according to a preset data sorting condition and a preset feature classification rule to generate a feature data set, then a credit evaluation result corresponding to a target service is determined according to the feature data set and a preset credit evaluation model, and a credit evaluation result corresponding to the target service is determined through the preset credit evaluation model, wherein the preset credit evaluation model comprises a plurality of preset credit evaluation sub-models, each preset credit evaluation sub-model is used for evaluating different credit behaviors, so that the comprehensiveness of credit evaluation of the user is ensured through the multisource of the personal credit behavior data set, and in addition, the evaluation weight of the evaluation sub-results output by each preset credit evaluation sub-model is determined through the service type of the target service, so that the comprehensiveness of credit evaluation of the user is ensured, and the accuracy of credit evaluation of the user is also considered.
On the basis of the above embodiment, in order to obtain each preset credit evaluation sub-model in the preset credit evaluation models, the credit evaluation sub-model to be trained corresponding to various service types may be trained in advance, and the accuracy of the subsequent output result of the model is extremely dependent on the training set and the test set adopted during training. In this embodiment, the credit action original data set a may be obtained, where the credit action original data set includes credit action original data of different types of data sources. Then, the credit action raw data set A is split into N credit action data subsets:
wherein, the method comprises the steps of, wherein,
the credit behavior original data of the ith type data source is that i is an integer which is more than or equal to 1 and less than or equal to N. And generating M credit behavior training sets according to the credit behavior original data set A:
, wherein ,
j is an integer greater than or equal to 1 and less than or equal to M for the jth credit behavior training set, wherein M is the number of the preset credit evaluation submodels in the preset credit evaluation model;and, in addition, the processing unit,
, wherein ,
is that
Is a subset of the set of (c),
Included
in a preset ratio
K is an integer of 1 or more and N or less, 
Is of the value of (2)
The correlation between the corresponding kth type data source and the jth preset credit evaluation submodel is positive. And generating M credit behavior test sets according to the credit behavior original data set A:
, wherein ,
training a j-th credit behavior; and, in addition, the processing unit,
, wherein ,
. Thereby utilizing
Training the j-th credit evaluation submodel to be trained and utilizing
And testing and verifying the j-th credit evaluation submodel to be trained to generate a j-th preset credit evaluation submodel. Through the classification and the setting of the training data, the accuracy of the training of each preset credit evaluation sub-model can be ensured, and the compatibility and the comprehensiveness of the training of each preset credit evaluation sub-model can be well ensured because the credit behavior training set adopted in the training process of each preset credit evaluation sub-model comprises the credit behavior original data of each type of data source.
In addition, after the j-th preset credit evaluation submodel is generated, a service original data set D may be further acquired, where the service original data set D includes a credit behavior original data set a and a service evaluation result data set E corresponding to various service types. And then, generating an initial result training set F according to each preset credit evaluation sub-model and the service original data set D. And training the credit evaluation model to be trained according to F and E to generate a preset credit evaluation model, wherein the evaluation weight of the evaluation sub-result output by each preset credit evaluation sub-model determined based on the service type of the target service is matched with the parameters corresponding to the variables corresponding to each preset credit evaluation sub-model in the credit evaluation model to be trained.
Specifically, training the credit evaluation model to be trained according to F and E may include: training a credit evaluation model to be trained based on the credit evaluation model to be trained by using F and E, wherein the credit evaluation model to be trained comprises:
wherein ,
the evaluation sub-result output by the i-th preset credit evaluation sub-model in F,
is a constant value, and is used for the treatment of the skin,
is that
The corresponding evaluation weight, n is an integer greater than 2, M is equal to n, i is an integer greater than 1 and less than n, and p is a credit evaluation result.
When the target service includes a plurality of service types, that is, the target service includes K service types, for the above-mentioned determination of the credit evaluation result corresponding to the target service according to the feature data set and the preset credit evaluation model, the respective credit evaluation sub-results corresponding to the service types may be determined according to the feature data set and the preset credit evaluation model, so as to form a credit evaluation sub-result set
The method comprises the steps of carrying out a first treatment on the surface of the And determining a credit evaluation result according to the following formula:
wherein ,
is a constant value, and is used for the treatment of the skin,
the average of the sub-results is evaluated for each credit in P,
the maximum value of the sub-results is evaluated for each credit in P,
the minimum of the sub-results is evaluated for each credit in P, 
And (3) for the t-th credit evaluation sub-result in the credit evaluation sub-results in P, t is an integer greater than or equal to 1 and less than or equal to K.
Therefore, the preset credit evaluation model determined by the training mode can comprehensively consider the results output by the preset credit evaluation sub-models according to the service type of the target service, so that the evaluation result which is more matched with the target service is output.
Fig. 2 is a flow chart illustrating a data processing method suitable for use in a personal credit assessment system according to another example embodiment of the present application. As shown in fig. 2, the method provided in this embodiment includes:
s201, acquiring a personal credit behavior data set uploaded by a user.
In this step, a personal credit behavioural data set uploaded by the user may be obtained, where the original feature fields in the credit behavioural data on each application platform are different. The personal credit action data set may include credit action data of the user on a plurality of application platforms, for example, may include house credit record data, consumption credit record data, credit record data, credit card repayment record data and the like of the user on a banking platform, may include consumption credit record data and flower file record data on a payment platform, and may further include consumption record data on jingdong, naught, and makeups. Because the credit behaviors corresponding to the platforms are different and the characteristic fields of the credit behaviors defined by the platforms are different, the credit evaluation method has the advantage that only credit records of banks are usually adopted when personal credit evaluation is performed at present, and comprehensive evaluation cannot be performed by combining with actual personal credit behaviors of users on other various platforms.
In this step, in order to comprehensively evaluate the user, the acquired personal credit behavior data set uploaded by the user may include credit behavior data on each application platform.
S202, extracting behavior feature data from the personal credit behavior data set according to preset data sorting conditions and preset feature classification rules to generate a feature data set.
After the personal credit behavior data set uploaded by the user is obtained, behavior feature data can be extracted from the personal credit behavior data set according to preset data sorting conditions and preset feature classification rules to generate a feature data set, wherein the preset data sorting conditions comprise at least one of behavior occurrence time conditions and behavior type conditions, the preset feature classification rules are used for establishing mapping relations between each original feature field and each target feature field, and the behavior feature data comprise behavior data corresponding to each target feature field. Optionally, the preset feature classification rule may be a mapping table designed for each application platform in advance, and after determining the application platform from which the data originates, the preset feature classification rule may be corresponding to the mapping table. In addition, the mapping table can be submitted and declared to the management server by each application platform on time, so that the management server can update the application platform on time, and credit evaluation of the user can be updated on time according to the updating of the application platform.
S203, determining a credit evaluation result corresponding to the target service according to the feature data set and a preset credit evaluation model.
Optionally, the credit evaluation result corresponding to the target service may be determined according to the feature data set and a preset credit evaluation model, where the preset credit evaluation model includes a plurality of preset credit evaluation sub-models, each of the preset credit evaluation sub-models is used to evaluate different credit behaviors, and the service type of the target service is used to determine an evaluation weight of the evaluation sub-result output by each of the preset credit evaluation sub-models.
Specifically, the plurality of preset credit evaluation sub-models included in the preset credit evaluation model may be a consumption credit evaluation sub-model, a credit evaluation sub-model, a house credit evaluation sub-model, and the like. When the service type of the target service is credit, the evaluation sub-results can be output based on the consumption credit evaluation sub-model, the credit evaluation sub-model and the house credit evaluation sub-model, and then the evaluation weight of each evaluation sub-result is determined according to the service type, so that the comprehensiveness and the accuracy of credit evaluation are considered.
S204, forming a credit evaluation report for the target service according to the credit evaluation result.
After the credit evaluation result corresponding to the target service is determined according to the feature data set and the preset credit evaluation model, a credit evaluation report for the target service can be formed according to the credit evaluation result, and the credit evaluation report can be used for guiding the processing result of the target service.
S205, storing the credit evaluation result and the personal credit behavior data set into a first file of the target blockchain node, and storing the credit evaluation report into a second file of the target blockchain node.
In this step, the credit assessment result and the personal credit action data set may be stored in a first file of the target blockchain node, and the credit assessment report may be stored in a second file of the target blockchain node. When responding to a first call instruction of the business supervision server, feeding back a credit evaluation result and a personal credit behavior data set in the first file and a credit evaluation report in the second file to the business supervision server, wherein the first encryption grade is matched with a first access right of the business supervision server; the second file is a second encryption level, and when responding to a second call instruction of the service processing server, the credit evaluation report in the second file is fed back to the service processing server, and the second encryption level is matched with a second access right of the service processing server. By storing the credit evaluation result and the personal credit behavior data set in the first file of the target blockchain node and storing the credit evaluation report in the second file of the target blockchain node, the safe storage of the data can be realized, the non-tamper modification of the data can be ensured, and the data safety is ensured. In addition, by distributing different encryption grades for the first file and the second file and configuring different access rights, the method can not only give consideration to the comprehensive requirements of data in supervision, but also meet the visual requirements of data at a service end.
If H historical credit evaluation results are stored in the first file
Wherein each history isThe credit evaluation results correspond to different generation times, and after the credit evaluation results corresponding to the target service are determined according to the feature data set and the preset credit evaluation model, the credit evaluation results can be further determined according to the credit evaluation results
And determining a final credit assessment result s by the following formula:
wherein ,
is that
The corresponding weight i is an integer greater than or equal to 1 and less than or equal to H,
value heel
Corresponding time and
the time difference between the corresponding times is inversely related;
is that
The corresponding weight.
By comprehensively considering the historical credit evaluation results and distributing different weights according to the time dimension, the comprehensiveness and accuracy of credit evaluation of the user in the time dimension are ensured.
Fig. 3 is a schematic diagram of a data processing apparatus suitable for use in a personal credit assessment system according to an example embodiment of the present application. As shown in fig. 3, the apparatus 300 provided in this embodiment includes:
the obtaining module 301 is configured to obtain a personal credit action data set uploaded by a user, where the personal credit action data set includes credit action data of the user on a plurality of application platforms, and original feature fields in the credit action data on each application platform are different;
The extracting module 302 is configured to extract behavior feature data from the personal credit behavior data set according to a preset data sorting condition and a preset feature classification rule, so as to generate a feature data set, where the preset data sorting condition includes at least one of a behavior occurrence time condition and a behavior type condition, the preset feature classification rule is used to establish a mapping relationship between each original feature field and a target feature field, and the behavior feature data includes behavior data corresponding to each target feature field;
the processing module 303 is configured to determine a credit evaluation result corresponding to the target service according to the feature data set and a preset credit evaluation model, where the preset credit evaluation model includes a plurality of preset credit evaluation sub-models, each of the preset credit evaluation sub-models is configured to evaluate different credit behaviors, and a service type of the target service is configured to determine an evaluation weight of the evaluation sub-result output by each of the preset credit evaluation sub-models.
In one possible design, the obtaining module 301 is further configured to: acquiring a credit behavior original data set A, wherein the credit behavior original data set comprises credit behavior original data of different types of data sources;
The processing module 303 is further configured to split the credit action raw data set a into N credit action data subsets:
, wherein ,
the method comprises the steps of (1) obtaining credit behavior original data of an ith type of data source, wherein i is an integer which is greater than or equal to 1 and less than or equal to N;
the processing module303, further configured to generate M credit action training sets according to the credit action raw data set a:
, wherein ,
j is an integer greater than or equal to 1 and less than or equal to M for the jth credit behavior training set, wherein M is the number of the preset credit evaluation submodels in the preset credit evaluation model; and, in addition, the processing unit,
, wherein ,
is that
Is a subset of the (a)
Comprises the following steps
In a preset ratio
K is an integer greater than or equal to 1 and less than or equal to N, said
Is of the value of (2) and the
The correlation between the corresponding kth type data source and the jth preset credit evaluation submodel is positive correlation;
the processing module 303 is further configured to generate M credit behavior test sets according to the credit behavior raw data set a:
, wherein ,
training a j-th credit behavior; and, in addition, the processing unit,
, wherein ,
；
the processing module 303 is further configured to utilize the
Training the j-th credit evaluation submodel to be trained and utilizing the j-th credit evaluation submodel to be trained 
And carrying out test verification on the j-th credit evaluation submodel to be trained to generate the j-th preset credit evaluation submodel.
Optionally, the acquiring module 301 is further configured to acquire a service original data set D, where the service original data set D includes the credit behavior original data set a and a service evaluation result data set E corresponding to various service types;
the processing module 303 is further configured to generate an initial result training set F according to each of the preset credit evaluation submodels and the service original data set D;
the processing module 303 is further configured to train the credit evaluation model to be trained according to the F and the E, so as to generate the preset credit evaluation model, where an evaluation weight of an evaluation sub-result output by each preset credit evaluation sub-model determined based on the service type of the target service is matched with a parameter corresponding to a variable corresponding to each preset credit evaluation sub-model in the credit evaluation model to be trained.
Optionally, the processing module 303 is specifically configured to:
training the credit evaluation model to be trained based on the credit evaluation model to be trained by using the F and the E, wherein the credit evaluation model to be trained comprises:
wherein ,
the assessment sub-result output by the ith preset credit assessment sub-model in the F is given,
is a constant value, and is used for the treatment of the skin,
is said
And n is an integer greater than 2, M is equal to n, i is an integer greater than 1 and less than n, and p is the credit evaluation result.
Optionally, if the target service includes K service types, the processing module 303 is specifically configured to:
respectively determining credit evaluation sub-results corresponding to each service type according to the characteristic data set and the preset credit evaluation model to form a credit evaluation sub-result set
；
The credit evaluation result is determined according to the following formula:
Optionally, the processing module 303 is specifically configured to:
forming a credit evaluation report for the target service according to the credit evaluation result;
Storing the credit assessment result and the personal credit behavior data set into a first file of a target blockchain node, and storing the credit assessment report into a second file of the target blockchain node; the first file is a first encryption grade, and when a first call instruction of a business supervision server is responded, the credit evaluation result and the personal credit behavior data set in the first file and the credit evaluation report in the second file are fed back to the business supervision server, wherein the first encryption grade is matched with a first access authority of the business supervision server; and the second file is a second encryption grade, and when responding to a second call instruction of the service processing server, the credit evaluation report in the second file is fed back to the service processing server, and the second encryption grade is matched with a second access right of the service processing server.
Optionally, if the first file stores H historical credit evaluation results
Wherein, the processing module 303 is specifically configured to:
based on the credit evaluation result
And determining a final credit assessment result s by the following formula:
wherein ,
is that
The corresponding weight i is an integer greater than or equal to 1 and less than or equal to H,
value heel
Corresponding time and the said
The time difference between the corresponding times is inversely related;
is said
The corresponding weight.
Fig. 4 is a schematic structural diagram of an electronic device according to an example embodiment of the present application. As shown in fig. 4, an electronic device 400 provided in this embodiment includes: a processor 401 and a memory 402; wherein:
a memory 402 for storing a computer program, which memory may also be a flash memory.
A processor 401 for executing the execution instructions stored in the memory to implement the steps in the above method. Reference may be made in particular to the description of the embodiments of the method described above.
Alternatively, the memory 402 may be separate or integrated with the processor 401.
When the memory 402 is a device separate from the processor 401, the electronic apparatus 400 may further include:
a bus 403 for connecting the memory 402 and the processor 401.
The present embodiment also provides a readable storage medium having a computer program stored therein, which when executed by at least one processor of an electronic device, performs the methods provided by the various embodiments described above.
The present embodiment also provides a program product comprising a computer program stored in a readable storage medium. The computer program may be read from a readable storage medium by at least one processor of an electronic device, and executed by the at least one processor, causes the electronic device to implement the methods provided by the various embodiments described above.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (6)
1. A data processing method suitable for use in a personal credit assessment system, comprising:
acquiring a personal credit behavior data set uploaded by a user, wherein the personal credit behavior data set comprises credit behavior data of the user on a plurality of application platforms, and original characteristic fields in the credit behavior data on each application platform are different;
extracting behavior feature data from the personal credit behavior data set according to preset data sorting conditions and preset feature classification rules to generate a feature data set, wherein the preset data sorting conditions comprise at least one of behavior occurrence time conditions and behavior type conditions, the preset feature classification rules are used for establishing mapping relations between original feature fields and target feature fields, and the behavior feature data comprise behavior data corresponding to the target feature fields;
determining a credit evaluation result corresponding to a target service according to the characteristic data set and a preset credit evaluation model, wherein the preset credit evaluation model comprises a plurality of preset credit evaluation sub-models, each preset credit evaluation sub-model is used for evaluating different credit behaviors, and the service type of the target service is used for determining the evaluation weight of the evaluation sub-result output by each preset credit evaluation sub-model;
The data processing method suitable for the personal credit evaluation system further comprises the following steps:
acquiring a credit behavior original data set A, wherein the credit behavior original data set comprises credit behavior original data of different types of data sources;
splitting the credit action raw data set A into N credit action data subsets:
, wherein ,/>
The method comprises the steps of (1) obtaining credit behavior original data of an ith type of data source, wherein i is an integer which is greater than or equal to 1 and less than or equal to N;
generating M credit behavior training sets according to the credit behavior original data set A:
, wherein ,/>
For the j-th credit training set, j is an integer greater than or equal to 1 and less than or equal to MThe M is the number of the preset credit evaluation submodels in the preset credit evaluation model; and (F)>
, wherein ,/>
Is->
Is a subset of the (a)
Comprises said->
In preset proportion->
K is an integer greater than or equal to 1 and less than or equal to N, said +.>
Is equal to the value of->
The correlation between the corresponding kth type data source and the jth preset credit evaluation submodel is positive correlation;
generating M credit behavior test sets according to the credit behavior original data set A:
, wherein ,/>
Training a j-th credit behavior; and (F)>
, wherein ,/>
；
By using the said
Training a j-th credit assessment sub-model to be trained and utilizing said +.>
Performing test verification on the j-th credit evaluation sub-model to be trained to generate the j-th preset credit evaluation sub-model;
after the generation of the jth preset credit evaluation submodel, the method further comprises:
acquiring a service original data set D, wherein the service original data set D comprises the credit behavior original data set A and a service evaluation result data set E corresponding to various service types;
generating an initial result training set F according to each preset credit evaluation sub-model and the service original data set D;
training the credit evaluation model to be trained according to the F and the E to generate the preset credit evaluation model, wherein the evaluation weight of the evaluation sub-result output by each preset credit evaluation sub-model determined based on the service type of the target service is matched with the parameter corresponding to the variable corresponding to each preset credit evaluation sub-model in the credit evaluation model to be trained;
the training of the credit assessment model to be trained according to the F and the E comprises the following steps:
Training the credit evaluation model to be trained based on the credit evaluation model to be trained by using the F and the E, wherein the credit evaluation model to be trained comprises:
wherein ,
an evaluation sub-result outputted for the ith preset credit evaluation sub-model in said F,/->
Is constant (I)>
Is said
The corresponding evaluation weight, n is an integer greater than 2, M is equal to n, i is an integer greater than 1 and less than n, and p is the credit evaluation result;
if the target service includes K service types, determining a credit evaluation result corresponding to the target service according to the feature data set and a preset credit evaluation model includes:
and respectively determining credit evaluation sub-results corresponding to the service types according to the characteristic data set and the preset credit evaluation model to form a credit evaluation sub-result set P:
；
the credit evaluation result is determined according to the following formula:
2. The data processing method for a personal credit evaluation system according to claim 1, further comprising, after determining a credit evaluation result corresponding to a target service according to the feature data set and a preset credit evaluation model:
forming a credit evaluation report for the target service according to the credit evaluation result;
storing the credit assessment result and the personal credit behavior data set into a first file of a target blockchain node, and storing the credit assessment report into a second file of the target blockchain node; the first file is a first encryption grade, and when a first call instruction of a business supervision server is responded, the credit evaluation result and the personal credit behavior data set in the first file and the credit evaluation report in the second file are fed back to the business supervision server, wherein the first encryption grade is matched with a first access authority of the business supervision server; and the second file is a second encryption grade, and when responding to a second call instruction of the service processing server, the credit evaluation report in the second file is fed back to the service processing server, and the second encryption grade is matched with a second access right of the service processing server.
3. The method of claim 2, wherein if the first file stores H historical credit evaluation results
Wherein, each historical credit evaluation result corresponds to different generation time, after the credit evaluation result corresponding to the target service is determined according to the feature data set and the preset credit evaluation model, the method further comprises:
based on the credit evaluation result
And determining a final credit assessment result s by the following formula: />
wherein ,
is->
The corresponding weights, i is an integer greater than or equal to 1 and less than or equal to H,/->
Value size->
The corresponding time is equal to said +.>
The time difference between the corresponding times is inversely related; />
For said->
The corresponding weight.
4. A data processing apparatus adapted for use in a personal credit assessment system, comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a personal credit behavior data set uploaded by a user, the personal credit behavior data set comprises credit behavior data of the user on a plurality of application platforms, and original characteristic fields in the credit behavior data on each application platform are different;
The extraction module is used for extracting behavior feature data from the personal credit behavior data set according to preset data sorting conditions and preset feature classification rules to generate a feature data set, wherein the preset data sorting conditions comprise at least one of behavior occurrence time conditions and behavior type conditions, the preset feature classification rules are used for establishing mapping relations between each original feature field and each target feature field, and the behavior feature data comprise behavior data corresponding to each target feature field;
the processing module is used for determining a credit evaluation result corresponding to the target service according to the characteristic data set and a preset credit evaluation model, wherein the preset credit evaluation model comprises a plurality of preset credit evaluation sub-models, each preset credit evaluation sub-model is used for evaluating different credit behaviors, and the service type of the target service is used for determining the evaluation weight of the evaluation sub-result output by each preset credit evaluation sub-model;
the acquisition module is further configured to: acquiring a credit behavior original data set A, wherein the credit behavior original data set comprises credit behavior original data of different types of data sources;
The processing module is further configured to split the credit action raw data set a into N credit action data subsets:
, wherein ,/>
Credit behavior for an ith type of data sourceOriginal data, i is an integer greater than or equal to 1 and less than or equal to N;
the processing module is further configured to generate M credit behavior training sets according to the credit behavior raw data set a:
, wherein ,/>
J is an integer greater than or equal to 1 and less than or equal to M for the jth credit behavior training set, wherein M is the number of the preset credit evaluation submodels in the preset credit evaluation model; and, in addition, the processing unit,
, wherein ,/>
Is->
Is a subset of->
Comprises said->
In preset proportion->
K is an integer greater than or equal to 1 and less than or equal to N, said +.>
Is equal to the value of->
The correlation between the corresponding kth type data source and the jth preset credit evaluation submodel is positive correlation;
the processing module is arranged to be coupled to the processing module,and generating M credit behavior test sets according to the credit behavior original data set A:
, wherein ,/>
Training a j-th credit behavior; and (F)>
, wherein ,
；
the processing module is also used for utilizing the
Training a j-th credit assessment sub-model to be trained and utilizing said +. >
Performing test verification on the j-th credit evaluation sub-model to be trained to generate the j-th preset credit evaluation sub-model; />
The acquisition module is further configured to acquire a service original data set D, where the service original data set D includes the credit behavior original data set a and a service evaluation result data set E corresponding to various service types;
the processing module is further configured to generate an initial result training set F according to each of the preset credit evaluation submodels and the service original data set D;
the processing module is further configured to train the credit evaluation model to be trained according to the F and the E, so as to generate the preset credit evaluation model, where an evaluation weight of an evaluation sub-result output by each preset credit evaluation sub-model determined based on the service type of the target service is matched with a parameter corresponding to a variable corresponding to each preset credit evaluation sub-model in the credit evaluation model to be trained;
the processing module is specifically configured to:
training the credit evaluation model to be trained based on the credit evaluation model to be trained by using the F and the E, wherein the credit evaluation model to be trained comprises:
wherein ,
an evaluation sub-result outputted for the ith preset credit evaluation sub-model in said F,/->
Is constant (I)>
Is said
The corresponding evaluation weight, n is an integer greater than 2, M is equal to n, i is an integer greater than 1 and less than n, and p is the credit evaluation result;
if the target service includes K service types, the processing module is specifically configured to:
respectively determining credit evaluation sub-results corresponding to each service type according to the characteristic data set and the preset credit evaluation model to form a credit evaluation sub-result set
；
The credit evaluation result is determined according to the following formula:
5. An electronic device, comprising:
a processor; the method comprises the steps of,
a memory for storing executable instructions of the processor;
Wherein the processor is configured to perform the method of any one of claims 1 to 3 via execution of the executable instructions.
6. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310044840.7A CN115907971B (en) | 2023-01-30 | 2023-01-30 | Data processing method and device suitable for personal credit evaluation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310044840.7A CN115907971B (en) | 2023-01-30 | 2023-01-30 | Data processing method and device suitable for personal credit evaluation system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115907971A CN115907971A (en) | 2023-04-04 |
| CN115907971B true CN115907971B (en) | 2023-05-30 |
Family
ID=85740875
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310044840.7A Active CN115907971B (en) | 2023-01-30 | 2023-01-30 | Data processing method and device suitable for personal credit evaluation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115907971B (en) |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107451485B (en) * | 2017-06-02 | 2020-03-13 | 创新先进技术有限公司 | Data processing method and device based on block chain |
| CN108596434B (en) * | 2018-03-23 | 2019-08-02 | 卫盈联信息技术（深圳）有限公司 | Fraud detection and methods of risk assessment, system, equipment and storage medium |
| CN108596757A (en) * | 2018-04-23 | 2018-09-28 | 大连火眼征信管理有限公司 | A kind of personal credit file method and system of intelligences combination |
| CN109345374B (en) * | 2018-09-17 | 2023-04-18 | 平安科技（深圳）有限公司 | Risk control method and device, computer equipment and storage medium |
| CN112862298B (en) * | 2020-07-09 | 2024-02-27 | 北京睿知图远科技有限公司 | Credit evaluation method for user portrait |
| CN112258312A (en) * | 2020-10-16 | 2021-01-22 | 银联商务股份有限公司 | Personal credit scoring method and system, electronic device and storage medium |
| CN113177700B (en) * | 2021-04-15 | 2022-09-13 | 国任财产保险股份有限公司 | Risk assessment method, system, electronic equipment and storage medium |
| CN113177670A (en) * | 2021-05-27 | 2021-07-27 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment and readable storage medium |
-
2023
- 2023-01-30 CN CN202310044840.7A patent/CN115907971B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115907971A (en) | 2023-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6749468B2 (en) | Modeling method and apparatus for evaluation model | |
| US20160132815A1 (en) | Skill estimation method in machine-human hybrid crowdsourcing | |
| CN109816200B (en) | Task pushing method, device, computer equipment and storage medium | |
| CN109583594B (en) | Deep learning training method, device, equipment and readable storage medium | |
| CN111428448B (en) | Text generation method, device, computer equipment and readable storage medium | |
| CN109934723B (en) | Medical insurance fraud behavior identification method, device and equipment | |
| CN110377631A (en) | Case information processing method, device, computer equipment and storage medium | |
| CN114913923A (en) | Cell type identification method aiming at open sequencing data of single cell chromatin | |
| CN112884569A (en) | Credit assessment model training method, device and equipment | |
| CN111062486B (en) | Method and device for evaluating feature distribution and confidence of data | |
| CN111583024A (en) | Credit evaluation method, device, storage medium and server | |
| CN113705792A (en) | Personalized recommendation method, device, equipment and medium based on deep learning model | |
| CN111091408A (en) | User identification model creating method and device and identification method and device | |
| CN113723774A (en) | Answer scoring method and device, computer equipment and storage medium | |
| CN113962800A (en) | Model training and overdue risk prediction method, device, equipment and medium | |
| CN115907971B (en) | Data processing method and device suitable for personal credit evaluation system | |
| CN110866609B (en) | Method, device, server and storage medium for acquiring interpretation information | |
| CN111325255B (en) | Specific crowd delineating method and device, electronic equipment and storage medium | |
| CN113918471A (en) | Test case processing method and device and computer readable storage medium | |
| CN111488463B (en) | Test corpus generation method and device and electronic equipment | |
| CN113704452A (en) | Data recommendation method, device, equipment and medium based on Bert model | |
| CN113946579A (en) | Model-based data generation method and device, computer equipment and storage medium | |
| CN113657808A (en) | Personnel evaluation method, device, equipment and storage medium | |
| CN112766824A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN112001425A (en) | Data processing method and device and computer readable storage medium |
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 |