CN111784503B - Operation rendering method, system and storage medium of communication credit investigation data - Google Patents
Operation rendering method, system and storage medium of communication credit investigation data Download PDFInfo
- Publication number
- CN111784503B CN111784503B CN202010609202.1A CN202010609202A CN111784503B CN 111784503 B CN111784503 B CN 111784503B CN 202010609202 A CN202010609202 A CN 202010609202A CN 111784503 B CN111784503 B CN 111784503B
- Authority
- CN
- China
- Prior art keywords
- credit
- data
- credit investigation
- capability
- investigation
- 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
- 238000011835 investigation Methods 0.000 title claims abstract description 273
- 238000004891 communication Methods 0.000 title claims abstract description 145
- 238000009877 rendering Methods 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 80
- 238000004806 packaging method and process Methods 0.000 claims abstract description 17
- 230000010354 integration Effects 0.000 claims abstract description 14
- 238000011156 evaluation Methods 0.000 claims description 99
- 238000012549 training Methods 0.000 claims description 63
- 238000005538 encapsulation Methods 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 18
- 238000000556 factor analysis Methods 0.000 claims description 10
- 238000013077 scoring method Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 9
- 238000012847 principal component analysis method Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 239000008186 active pharmaceutical agent Substances 0.000 description 19
- 238000007726 management method Methods 0.000 description 14
- 238000011161 development Methods 0.000 description 11
- 230000009286 beneficial effect Effects 0.000 description 10
- 230000008859 change Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000005457 optimization Methods 0.000 description 6
- 230000006399 behavior Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000013475 authorization Methods 0.000 description 2
- 238000004587 chromatography analysis Methods 0.000 description 2
- 238000011157 data evaluation Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012067 mathematical method Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 210000003462 vein Anatomy 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000000586 desensitisation Methods 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention relates to an operation rendering method, a system and a storage medium of communication credit investigation data, wherein the method comprises the steps of obtaining communication source data provided by a communication operator, and carrying out data integration on the communication source data to obtain credit investigation data; constructing a credit investigation service model according to the credit investigation data; acquiring credit information to be converted, and inputting the credit information to be converted into the credit information service model to obtain a credit information capacity list corresponding to the credit information to be converted; and packaging the credit investigation capability list to obtain a credit investigation demonstration product. The invention provides the big data operation rendering capability of the communication operator, which internally meets the operation requirement of the existing big data, externally meets the strong requirement of the industries such as banks, finance, government affairs and the like on the communication credit investigation data, creates value for the credit of the user and makes up the market blank.
Description
Technical Field
The present invention relates to the field of data development in the communications industry, and in particular, to an operation rendering method, system and storage medium for communication credit investigation data.
Background
On the one hand, with the continuous development of large data platforms of large communication operators (such as mobile communication operators), the construction of enterprise data centers is basically realized, massive data assets of the operators are gathered, and in order to realize the creation and income creation of the maximum value of the massive data assets in the enterprise data centers, the communication operators face new challenges such as basic data service enhancement, large data capacity realization, accurate market positioning with open capacity and the like.
On the other hand, the credit market is an important component of the market economic system in China, and is also an important foundation for further playing the decisive role of the market and promoting the construction of the national treatment system and the treatment capability in the comprehensive and deep reform process. Under the big data age, as a comprehensive innovation of data, technology, methods and systems, the big data comprehensively reconstructs the sources and forms of credit investigation data, credit investigation processing modes, credit investigation evaluation technology, the transmission and sharing channels of credit investigation products and the credit investigation system basis, thus generating new influences on the traditional credit investigation market and providing new requirements.
Under the actions of the two aspects, the communication operators have to provide basic credit data to external capability open service functions in the face of increasingly supporting requirements of external credit data services in the credit scenes of industries such as banks, internet finance, government affairs and the like, and can realize the development and operation of credit service products such as verification products, credit knowledge products and the like, so that the capability of the credit data is realized.
However, there is a lot of market blank in the present market in terms of credit data formed based on big data of communication operators and operational variation of the credit data.
Disclosure of Invention
Aiming at the defects of the prior art, the technical problem to be solved by the invention is to provide a method, a system and a storage medium for rendering communication credit data, which provide big data operation rendering capability of a communication operator, meet the operation requirement of the existing big data, meet the strong requirement of the industries such as banks, finance, government affairs and the like on the communication credit data, and make up the market blank.
The technical scheme for solving the technical problems is as follows:
an operation rendering method of communication credit information data, comprising the following steps:
step 1: acquiring communication source data provided by a communication operator, and carrying out data integration on the communication source data to obtain credit investigation data;
step 2: constructing a credit investigation service model according to the credit investigation data;
step 3: acquiring credit information to be converted, and inputting the credit information to be converted into the credit information service model to obtain a credit information capacity list corresponding to the credit information to be converted;
Step 4: and packaging the credit investigation capability list to obtain a credit investigation demonstration product.
The beneficial effects of the invention are as follows: the method comprises the steps that large data such as communication source data of a user provided by a communication operator are obtained, the data are integrated, the obtained credit investigation data are convenient for subsequent large data analysis, and then a credit investigation service model for evaluating credit investigation conditions of the user is constructed; the credit investigation service model is utilized to obtain a credit investigation capability list corresponding to the credit investigation data of any user to be evaluated, the credit investigation capability list accurately reflects the credit investigation capability of the user to be evaluated, the subsequent personalized encapsulation is convenient, the encapsulation is carried out based on the credit investigation capability list, the obtained credit investigation product is more in line with the credit investigation capability of the user to be evaluated, the credit investigation capability of the user can be accurately carried out operation and change, and the credit creation value of the user is realized;
the operation rendering method of the communication credit information data can construct a credit ecosystem of a communication operator, provides unified credit information capability development, management and control and operation based on big data service, and the provided credit information rendering product reflects the big data operation rendering capability of the communication operator, meets the operation requirements of the existing service and data labels on the inside (i.e. the communication operator), meets the strong requirements of the industries such as banks, finance, government affairs and the like on the communication credit information data, makes up market blank, and is an important component of a new credit information market in the big data era.
On the basis of the technical scheme, the invention also has the following improvement:
further: in the step 1, the specific step of obtaining the credit investigation data includes:
step 11: extracting the communication source data according to a preset period to generate a plurality of interface files;
step 12: and loading all the interface files into a database according to preset database interface rules to obtain the credit investigation data.
The beneficial effects of the above further technical scheme are: in data integration, firstly, the data layer is utilized to acquire communication source data of a communication operator, and then the communication source data are extracted according to a preset period, so that the acquired interface file is convenient for the subsequent utilization of the database to acquire credit investigation data; according to a preset database rule, the interface file is conveniently and smoothly loaded into the database to obtain the required credit investigation data; the communication source data are big data generated by a user at a communication operator, the extracted interface file and the obtained credit investigation data comprise user information, bills, details, arrearages, payment, consumption, integration and other data, the database is a big data platform database, and the preset period can be selected and adjusted according to actual conditions.
Further: the specific steps of the step 2 include:
step 21: constructing a credit score basic model, and determining a plurality of evaluation dimensions of the credit score basic model and a score index set under each evaluation dimension according to the credit data;
step 22: preprocessing the credit investigation data to obtain sample data;
step 23: screening each grading index set according to the sample data by adopting a factor analysis method and a principal component analysis method to obtain a target grading index set under each evaluation dimension;
step 24: dividing the sample data into a training set and a testing set, selecting a target scoring index set with any evaluation dimension, and calculating to obtain index weight of the training set under each target scoring index in the selected target scoring index set by adopting an entropy method;
step 25: obtaining index scores of the training set under each target scoring index in the selected target scoring index set according to a preset scoring method;
step 26: calculating to obtain dimension scores corresponding to the training set under the selected evaluation dimension according to the index weights and the index scores of all target scoring indexes in the selected target scoring index set;
The specific formula for calculating the dimension score of the training set in the ith evaluation dimension is as follows:
wherein W is i Dimension score, p, for the training set in the ith evaluation dimension j And q j Respectively obtaining index weight and index score of the training set under the j-th target scoring index in the i-th target scoring index set of the evaluation dimension, wherein m is the total number of target scoring indexes in the i-th target scoring index set of the evaluation dimension;
step 27: obtaining dimension scores of the training set under each evaluation dimension according to the methods from the step 24 to the step 26;
step 28: acquiring the dimension weight of each evaluation dimension by adopting an AHP analytic hierarchy process, and obtaining the credit score of the training set according to all the dimension weights and the dimension scores of the training set under all the evaluation dimensions;
step 29: and training the credit score basic model according to the training set, all evaluation dimensions, all target score index sets and credit scores of the training set to obtain the credit service model.
The beneficial effects of the above further technical scheme are: the credit rating basic model reflects the rating condition of credit rating corresponding to credit rating data, so that the evaluation dimension of the model and a rating index set (comprising a plurality of rating indexes) contained in each evaluation dimension are firstly determined, and a framework for calculating, summarizing and rating the credit rating is conveniently initially built; the credit information data is preprocessed, so that partial data such as invalid values, missing values, error values, repeated record values and the like in the credit information data can be processed, and the data in the credit information data can be classified, so that subsequent calculation and evaluation are facilitated; continuous class indexes in sample data can be screened by adopting a factor analysis method, discrete class indexes in the sample data can be screened by adopting a principal component analysis method, so that the dimension reduction processing of each evaluation dimension is realized, the index quantity in an obtained target grading index set can be reduced on the one hand, the data evaluation precision is not lost on the other hand, and the service interpretation is convenient; through an entropy method, the index weight of the training set under each target scoring index can be guaranteed to be more reasonable and accurate, the accuracy of each dimension score calculated subsequently can be guaranteed based on all index weights and index scores of the training set under each evaluation dimension, and further the obtained credit score can reflect the comprehensive credit level of a user more based on the dimension score and the dimension weight; the AHP analytic hierarchy process (Analytic Hierarchy Process, AHP for short) is a simple, flexible and practical multi-criterion decision method for quantitatively analyzing qualitative problems, various factors in complex problems are divided into mutually connected ordered layers to lead the factors to be physicochemical, expert opinions and objective judgment results of analyzers are directly and effectively combined according to a subjective judgment structure (mainly comprising pairwise comparison) of certain objective reality, the importance of each layer element is quantitatively described in pairwise comparison, then the weight reflecting the relative importance sequence of each layer element is calculated by using a mathematical method, and the relative weights of all elements are calculated and sequenced through the total sequencing among all layers; according to the invention, the relation among the evaluation dimensions can be accurately and clearly presented through the AHP analytic hierarchy process, so that the importance of the evaluation dimensions is obtained, namely, more accurate dimension indexes are obtained, and more accurate credit scores which are more in line with actual conditions are conveniently obtained;
Therefore, through the training set, the evaluation dimension, the target score index set and the credit score, a multi-dimensional dynamic credit evaluation system (namely a credit investigation service model) can be formed, and the credit investigation capability of the user can be accurately reflected; the preset scoring method is set before the model is built, and meanwhile, the scoring method can be adjusted according to actual conditions; the specific operation steps of the entropy method, the factor analysis method, the principal component analysis method and the AHP chromatography are all prior art, and specific details are not described herein.
Further: the method further comprises the following steps before the step 3:
and optimizing the credit investigation service model by using the test set to obtain the optimized credit investigation service model.
The beneficial effects of the above further technical scheme are: through the optimization process, the accuracy of evaluating the credit investigation capability of the user by the credit investigation service model can be improved, so that credit investigation products which more accord with the credit investigation capability of the user can be obtained, and value is created for credit investigation data of the user.
Further: the specific steps of the step 3 include:
step 31: obtaining the credit investigation data to be changed from the database;
step 32: inputting the credit information to be converted into the optimized credit information service model to obtain a target credit score of the credit information to be converted and a target dimension score of the credit information to be converted under each evaluation dimension;
Step 33: and obtaining the credit rating capability list corresponding to the credit rating data to be converted according to the target credit score and the dimension scores under all evaluation dimensions.
The beneficial effects of the above further technical scheme are: the credit investigation service model is used for evaluating the credit investigation data to be changed, so that a final target credit score can be output at the same time, a target dimension score under each evaluation dimension output by the intermediate node can be output, and a credit investigation capability list is obtained according to the target credit score and the target dimension scores under all the evaluation dimensions, and the credit investigation capability of a user can be reflected from multiple dimensions; based on the credit investigation capability list, the big data operation rendering capability of the communication operator can be comprehensively embodied, on one hand, the operation requirements of the existing service and data labels are met, namely, the operation rendering capability of the communication credit investigation data is provided, on the other hand, the strong requirements of the industries such as banks, finance, government affairs and the like on the communication credit investigation data are met, so that the service scene requirements of the industries are supported, namely, the operation rendering capability of the communication credit investigation data is also provided, the credit of the user is fully created, and the market blank is effectively made up.
Further: the specific steps of the step 4 include:
sending the credit investigation capability list to a capability opening platform of the communication operator, and carrying out capability encapsulation and capability opening on the credit investigation capability list by utilizing the capability opening platform to obtain the credit investigation rendering product;
wherein, carrying out capability encapsulation and capability opening on the credit investigation capability list comprises the following steps:
API packaging is carried out on the credit investigation capability list;
registering the credit investigation capability list packaged by the API into a capability store of the capability open platform, and setting a commodity browsing function, a searching function, a subscribing function and a using function for the registered credit investigation capability list.
The beneficial effects of the above further technical scheme are: because the capability open platform of the communication operator has the services of capability encapsulation, capability opening and the like, the virtual credit investigation capability list can be conveniently encapsulated into an actual credit investigation rendering product which can be opened to the outside by sending the credit investigation capability list to the capability open platform, so that the operation rendering of credit investigation data is truly realized, the opening capability of the existing business and data labels is met, and the operation rendering capability is provided to the outside; on the other hand, the service life cycle management of the credit investigation service is convenient to realize, and the healthy operation of the operation and the appearance of the whole credit investigation data is ensured; the credit investigation product comprises credit investigation products, credit investigation products and the like.
Further: the method further comprises the following steps after the step 4:
step 5: setting a calling API interface and scene parameters of the credit investigation rendering product, and constructing an operation scene of the credit investigation rendering product according to the calling API interface and the scene parameters;
wherein the credit investigation rendering product operates in the operation scene.
The beneficial effects of the above further technical scheme are: the operation scene built by the set calling API interface and scene parameters is convenient for providing the scene support of credit investigation and rendering products, and the operation support of credit investigation capability rendering of credit investigation data is truly realized so as to support the business scene requirements of industries such as banks, finance, government affairs and the like on the credit investigation data.
According to another aspect of the present invention, there is further provided an operation rendering system of communication credit information data, which is applied to the operation rendering method of communication credit information data of the present invention, and includes a data acquisition module, a model construction module, a capability evaluation module and a package rendering module;
the data acquisition module is used for acquiring communication source data provided by a communication operator, and carrying out data integration on the communication source data to obtain credit investigation data;
the model construction module is used for constructing a credit investigation service model according to the credit investigation data;
The capability evaluation module is used for acquiring credit information to be converted, inputting the credit information to be converted into the credit information service model and obtaining a credit information capability list corresponding to the credit information to be converted;
and the packaging rendering module is used for packaging the credit investigation capability list to obtain credit investigation rendering products.
The beneficial effects of the invention are as follows: the credit ecological system of the communication operator can be constructed, unified credit investigation capability development, management and control and operation are provided based on the big data service, the provided credit investigation product reflects the big data operation investigation capability of the communication operator, the operation requirements of the existing service and data labels are met for the internal (i.e. the communication operator), the strong requirements of the industries such as banks, finance, government affairs and the like on the communication credit investigation data are met, market blank is made up, and the credit investigation ecological system is an important component of a new credit investigation market in the big data era.
According to another aspect of the present invention there is provided an operation rendering system for communication credit data, comprising a processor, a memory and a computer program stored in the memory and operable on the processor, the computer program when run implementing the steps in an operation rendering method for communication credit data of the present invention.
The beneficial effects of the invention are as follows: through the computer program stored in the memory and running on the processor, the credit ecological system of the communication carrier can be constructed, the unified credit investigation capability is externally provided for development, management and control and operation based on the big data service, the provided credit investigation and realization product reflects the big data operation and realization capability of the communication carrier, the operation requirements of the existing service and data labels are met for the internal (i.e. the communication carrier), the strong requirements of the industries such as banks, finance, government affairs and the like for the communication credit investigation data are externally met, market blank is made up, and the credit investigation and communication system is an important component of a new credit investigation market in the big data age.
According to another aspect of the present invention, there is provided a computer storage medium including: at least one instruction, when executed, implements the steps in an operational rendering method of communication credit data of the invention.
The beneficial effects of the invention are as follows: by executing the computer storage medium containing at least one instruction, a credit ecological system of a communication carrier can be built, unified credit investigation capability development, management and control and operation are provided based on big data service, the provided credit investigation product embodies the big data operation investigation capability of the communication carrier, the operation requirements of the existing service and data labels are met for the internal (i.e. the communication carrier), the strong requirements of the industries such as banks, finance, government affairs and the like on communication credit investigation data are met, market blank is made up, and the communication carrier is an important component of a new generation credit investigation market in the big data age.
Drawings
Fig. 1 is a flow chart of an operation and change method of communication credit information data in a first embodiment of the invention;
FIG. 2 is a flow chart of obtaining credit investigation data according to the first embodiment of the present invention;
FIG. 3 is a schematic flow chart of constructing a credit investigation service model in the first embodiment of the invention;
FIG. 4 is a schematic diagram of a modeling of credit investigation service in accordance with the first embodiment of the present invention;
FIG. 5 is a flow chart of a credit investigation capability list according to the first embodiment of the present invention;
fig. 6 is a flow chart of another operation change method of communication credit information data according to the first embodiment of the invention;
FIG. 7 is a schematic diagram of a complete model of an operation rendering method of communication credit data according to the first embodiment of the invention;
fig. 8 is a schematic structural diagram of an operation and rendering system for communication credit information data in the second embodiment of the present invention;
fig. 9 is a schematic structural diagram of another operation and change system for communication credit information data in the second embodiment of the present invention.
Detailed Description
The principles and features of the present invention are described below with reference to the drawings, the examples are illustrated for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
The present invention will be described below with reference to the accompanying drawings.
In a first embodiment, as shown in fig. 1, an operation rendering method for communication credit information data includes the following steps:
S1: acquiring communication source data provided by a communication operator, and carrying out data integration on the communication source data to obtain credit investigation data;
s2: constructing a credit investigation service model according to the credit investigation data;
s3: acquiring credit information to be converted, and inputting the credit information to be converted into the credit information service model to obtain a credit information capacity list corresponding to the credit information to be converted;
s4: and packaging the credit investigation capability list to obtain a credit investigation demonstration product.
The method comprises the steps that large data such as communication source data of a user provided by a communication operator are obtained, the data are integrated, the obtained credit investigation data are convenient for subsequent large data analysis, and then a credit investigation service model for evaluating credit investigation conditions of the user is constructed; the credit investigation service model is utilized to obtain a credit investigation capability list corresponding to the credit investigation data of any user to be evaluated, the credit investigation capability list accurately reflects the credit investigation capability of the user to be evaluated, the subsequent personalized encapsulation is convenient, the encapsulation is carried out based on the credit investigation capability list, the obtained credit investigation product is more in line with the credit investigation capability of the user to be evaluated, the credit investigation capability of the user can be accurately carried out operation and change, and the credit creation value of the user is realized;
The operation rendering method of the communication credit data can construct a credit ecosystem of a communication operator, provides unified credit capability development, management and control and operation based on big data service, the provided credit rendering product reflects big data operation rendering capability of the communication operator, meets operation requirements of the existing service and data labels on the inside (namely the communication operator), meets strong requirements of industries such as banks, finance and government affairs on the communication credit data, makes up market blank, and is an important component of a new credit market in the big data era.
Preferably, as shown in fig. 2, in S1, the specific step of obtaining the credit data includes:
s11: extracting the communication source data according to a preset period to generate a plurality of interface files;
s12: and loading all the interface files into a database according to preset database interface rules to obtain the credit investigation data.
In data integration, firstly, the data layer is utilized to acquire communication source data of a communication operator, and then the communication source data are extracted according to a preset period, so that the acquired interface file is convenient for the subsequent utilization of the database to acquire credit investigation data; according to a preset database rule, the interface file is conveniently and smoothly loaded into the database to obtain the required credit investigation data; the communication source data are big data generated by a user at a communication operator, the extracted interface file and the obtained credit investigation data comprise user information, bills, details, arrearages, payment, consumption, integration and other data, the database is a big data platform database, and the preset period can be selected and adjusted according to actual conditions.
Specifically, in the data integration of the embodiment, the data layer is utilized to obtain communication source data of a communication operator, specifically a mobile operator, from systems such as a BOSS system, a CRM system, an O domain system and the like, and the communication operator generates an interface file according to a preset period; the database is specifically a large data platform database, and then the interface file is loaded by utilizing the data service interface according to the interface rule of the large data platform database; the data loaded into the big data platform database is credit investigation data.
Preferably, as shown in fig. 3, the specific steps of S2 include:
s21: constructing a credit score basic model, and determining a plurality of evaluation dimensions of the credit score basic model and a score index set under each evaluation dimension according to the credit data;
s22: preprocessing the credit investigation data to obtain sample data;
s23: screening each grading index set according to the sample data by adopting a factor analysis method and a principal component analysis method to obtain a target grading index set under each evaluation dimension;
s24: dividing the sample data into a training set and a testing set, selecting a target scoring index set with any evaluation dimension, and calculating to obtain index weight of the training set under each target scoring index in the selected target scoring index set by adopting an entropy method;
S25: obtaining index scores of the training set under each target scoring index in the selected target scoring index set according to a preset scoring method;
s26: calculating to obtain dimension scores corresponding to the training set under the selected evaluation dimension according to the index weights and the index scores of all target scoring indexes in the selected target scoring index set;
the specific formula for calculating the dimension score of the training set in the ith evaluation dimension is as follows:
wherein W is i Dimension score, p, for the training set in the ith evaluation dimension j And q j Respectively obtaining index weight and index score of the training set under the j-th target scoring index in the i-th target scoring index set of the evaluation dimension, wherein m is the total number of target scoring indexes in the i-th target scoring index set of the evaluation dimension;
s27: obtaining dimension scores of the training set under each evaluation dimension according to the methods from S24 to S26;
s28: acquiring the dimension weight of each evaluation dimension by adopting an AHP analytic hierarchy process, and obtaining the credit score of the training set according to all the dimension weights and the dimension scores of the training set under all the evaluation dimensions;
S29: and training the credit score basic model according to the training set, all evaluation dimensions, all target score index sets and credit scores of the training set to obtain the credit service model.
The credit rating basic model reflects the rating condition of credit rating corresponding to credit rating data, so that the evaluation dimension of the model and a rating index set (comprising a plurality of rating indexes) contained in each evaluation dimension are firstly determined, and a framework for calculating, summarizing and rating the credit rating is conveniently initially built; the credit information data is preprocessed, so that partial data such as invalid values, missing values, error values, repeated record values and the like in the credit information data can be processed, and the data in the credit information data can be classified, so that subsequent calculation and evaluation are facilitated; continuous class indexes in sample data can be screened by adopting a factor analysis method, discrete class indexes in the sample data can be screened by adopting a principal component analysis method, so that the dimension reduction processing of each evaluation dimension is realized, the index quantity in an obtained target grading index set can be reduced on the one hand, the data evaluation precision is not lost on the other hand, and the service interpretation is convenient; through an entropy method, the index weight of the training set under each target scoring index can be guaranteed to be more reasonable and accurate, the accuracy of each dimension score calculated subsequently can be guaranteed based on all index weights and index scores of the training set under each evaluation dimension, and further the obtained credit score can reflect the comprehensive credit level of a user more based on the dimension score and the dimension weight; the AHP analytic hierarchy process (Analytic Hierarchy Process, AHP for short) is a simple, flexible and practical multi-criterion decision method for quantitatively analyzing qualitative problems, various factors in complex problems are divided into mutually connected ordered layers to lead the factors to be physicochemical, expert opinions and objective judgment results of analyzers are directly and effectively combined according to a subjective judgment structure (mainly comprising pairwise comparison) of certain objective reality, the importance of each layer element is quantitatively described in pairwise comparison, then the weight reflecting the relative importance sequence of each layer element is calculated by using a mathematical method, and the relative weights of all elements are calculated and sequenced through the total sequencing among all layers; according to the invention, the relation among the evaluation dimensions can be accurately and clearly presented through the AHP analytic hierarchy process, so that the importance of the evaluation dimensions is obtained, namely, more accurate dimension indexes are obtained, and more accurate credit scores which are more in line with actual conditions are conveniently obtained;
Therefore, through the training set, the evaluation dimension, the target score index set and the credit score, a multi-dimensional dynamic credit evaluation system (namely a credit investigation service model) can be formed, and the credit investigation capability of the user can be accurately reflected; the preset scoring method is set before the model is built, and meanwhile, the scoring method can be adjusted according to actual conditions; the specific operation steps of the entropy method, the factor analysis method, the principal component analysis method and the AHP chromatography are all prior art, and specific details are not described herein.
Specifically, a calculation module in the credit score basic model of the embodiment is developed in a large data platform of an operator, and is realized by using an HIVE component to schedule a work flow, so that calculation and summarization of each credit data are completed; the method also comprises a build model service center used for managing credit information data, outputting control and managing model algorithm in the whole build process of the credit information service model.
Specifically, the method for preprocessing the credit information data in the embodiment S22 includes, but is not limited to, data binning (for removing outliers), correlation analysis (for removing index collinearity), IV analysis (for selecting indexes with greater importance), and the like, and specific operation steps of the preprocessing method are all in the prior art, and specific details are not repeated here.
Specifically, the evaluation dimensions in the credit score basic model in the embodiment S21 include 5 evaluation dimensions in total of identity characteristics, performance capability, behavior preference, historical credit and vein relation; the identity characteristics are mainly analyzed based on user information (occupation, gender, online time and the like); the performance capability is mainly analyzed based on data such as pre-stored, paid, arrearage, consumption, integration and the like of a user; the behavior preference is mainly analyzed based on data such as user communication, service use, terminals and the like; the historical credit is mainly analyzed based on data such as payment, arrearage, bill and the like; the relationship between the human veins is mainly analyzed based on data such as a detailed list. Each evaluation dimension includes a corresponding scoring index set, each scoring index set includes a plurality of scoring indexes, and in this embodiment, 60 scoring indexes are counted. For example, the scoring index set corresponding to the identity feature includes a plurality of scoring indexes, which is specifically as follows: authentication service, black and white list service, real-name client authentication, group client, gold card and silver card, gender, age, online time, mobile phone state, number attribution, member star level, number of machine disassembly numbers, number recovery or not, number of online numbers, online time level, user's no disturbance, user abnormal state duration, etc.
Specifically, in the present embodiment S23, when the continuous class index is screened by the factor analysis method, the index is screened by KMO and bat Li Qiu inspection and using the cumulative contribution index; screening discrete indexes by adopting a principal component analysis method; after the factor analysis and the principal component analysis, the original 60 or more scoring indexes were reduced to 13 target scoring indexes as shown in table 1.
Table 1 evaluation dimension and target score index in this example
Specifically, in the embodiment S25, the data of the training set under each target scoring index is scored in a grading manner according to the data distribution of the training set under each target scoring index, for example, the situation of scoring the training set in a grading manner under two target scoring indexes of identity features is shown in table 2; the grading scoring condition under other target scoring indexes is similar to the grading scoring condition, and can be adjusted according to the actual condition, and the description is omitted here.
Table 2 grading scoring of two target scoring indicators under identity attributes in this embodiment
Specifically, a schematic model diagram of the entire modeling process described in the present embodiment S2 is shown in fig. 4.
Preferably, the following steps are further included before S3:
and optimizing the credit investigation service model by using the test set to obtain the optimized credit investigation service model.
Through the optimization process, the accuracy of evaluating the credit investigation capability of the user by the credit investigation service model can be improved, so that credit investigation products which more accord with the credit investigation capability of the user can be obtained, and value is created for credit investigation data of the user.
Specifically, in the present embodiment, the optimization process mainly optimizes training parameters of the entire credit investigation service model, including iteration times, learning rate, and the like.
Preferably, as shown in fig. 5, the specific steps of S3 include:
s31: obtaining the credit investigation data to be changed from the database;
s32: inputting the credit information to be converted into the optimized credit information service model to obtain a target credit score of the credit information to be converted and a target dimension score of the credit information to be converted under each evaluation dimension;
s33: and obtaining the credit rating capability list corresponding to the credit rating data to be converted according to the target credit score and the dimension scores under all evaluation dimensions.
The credit investigation service model is used for evaluating the credit investigation data to be changed, so that a final target credit score can be output at the same time, a target dimension score under each evaluation dimension output by the intermediate node can be output, and a credit investigation capability list is obtained according to the target credit score and the target dimension scores under all the evaluation dimensions, and the credit investigation capability of a user can be reflected from multiple dimensions; based on the credit investigation capability list, the big data operation rendering capability of the communication operator can be comprehensively embodied, on one hand, the operation requirements of the existing service and data labels are met, namely, the operation rendering capability of the communication credit investigation data is provided, on the other hand, the strong requirements of the industries such as banks, finance, government affairs and the like on the communication credit investigation data are met, so that the service scene requirements of the industries are supported, namely, the operation rendering capability of the communication credit investigation data is also provided, the credit of the user is fully created, and the market blank is effectively made up.
Specifically, the credit capability list finally output in the embodiment S3 is a five-dimensional credit capability list including credit scores and 5 dimension scores.
Preferably, the specific step of S4 comprises:
sending the credit investigation capability list to a capability opening platform of the communication operator, and carrying out capability encapsulation and capability opening on the credit investigation capability list by utilizing the capability opening platform to obtain the credit investigation rendering product;
wherein, carrying out capability encapsulation and capability opening on the credit investigation capability list comprises the following steps:
API packaging is carried out on the credit investigation capability list;
registering the credit investigation capability list packaged by the API into a capability store of the capability open platform, and setting a commodity browsing function, a searching function, a subscribing function and a using function for the registered credit investigation capability list.
Because the capability open platform of the communication operator has the services of capability encapsulation, capability opening and the like, the virtual credit investigation capability list can be conveniently encapsulated into an actual credit investigation rendering product which can be opened to the outside by sending the credit investigation capability list to the capability open platform, so that the operation rendering of credit investigation data is truly realized, the opening capability of the existing business and data labels is met, and the operation rendering capability is provided to the outside; on the other hand, the service life cycle management of the credit investigation service is convenient to realize, and the healthy operation of the operation and the appearance of the whole credit investigation data is ensured; the credit investigation product comprises credit investigation products, credit investigation products and the like.
Specifically, the embodiment forms credit investigation products such as verification, credit knowledge and the like by packaging the credit investigation capability list, and distributes the credit investigation products to an operator big data capability open platform so as to realize life cycle management of credit investigation service and external subscription of big data credit investigation service, thereby not only meeting the open capability of the existing service and data labels, but also providing operation appearance capability to the outside; the specific process of capability encapsulation and capability opening in this embodiment is as follows:
1) Task flow configuration
The operator big data management and control platform is responsible for unified management and control of access, arrangement, scheduling and execution, monitoring and the like of the application background task based on the big data platform.
The tenant is a user accessing the hadoop system, and the tenant information needs to be registered in the platform.
And configuring the credit tenant by a system administrator and configuring corresponding resources.
And developing and configuring the task flow by each tenant.
2) Capability providing configuration
The credit investigation service capability is provided through an operator data service capability open platform. The capability platform comprises two major services of capability packaging and capability opening (comprising capability release, capability store, system management and other functional modules).
Capability encapsulation: API encapsulation of various atomic resources such as data, services, applications, messages and the like is realized.
Capability release: the packaged APIs are registered in the capability store and are open to the outside.
Capability store: providing API commodity browsing, exploring, subscribing and using functions for the capability user. The user subscribes to the commodity and needs to be approved by the capability provider.
Two credit use modes are provided:
single query: inputting a mobile phone number and outputting a credit score;
batch query: inputting a file written with a mobile phone number and an authorization code, and supporting txt and excel formats; and outputting the direct write-back file, and downloading the file by a user after the file writing is completed.
Preferably, as shown in fig. 6, the following steps are further included after S4:
s5: setting a calling API interface and scene parameters of the credit investigation rendering product, and constructing an operation scene of the credit investigation rendering product according to the calling API interface and the scene parameters;
wherein the credit investigation rendering product operates in the operation scene.
The operation scene built by the set calling API interface and scene parameters is convenient for providing the scene support of credit investigation and rendering products, and the operation support of credit investigation capability rendering of credit investigation data is truly realized so as to support the business scene requirements of industries such as banks, finance, government affairs and the like on the credit investigation data.
Specifically, in this embodiment, a specific operation process of setting up an operation scene according to a calling API interface and a scene parameter is in the prior art, and specific details are not described herein.
The operation scenarios set up in this embodiment include, but are not limited to, the following two operation scenarios:
1) Scene one: banking credit card
In the process of applying for the credit card by the user, the credit rating of the user is required to be evaluated based on the communication source data provided by the communication carrier, a credit rating list of the user is generated, and then desensitization data such as the consumer consumption rating, the consumption behavior, the track information, the internet behavior and the like are provided for the credit card center as a data basis for evaluating the credit rating of the user of the credit card center.
2) Scene II: internet finance lending
In the process of lending customers to internet finance companies, since the credit system of the central office is not open to the outside, the finance companies need to evaluate the credit rating of the customers. According to financial service attributes, a client credit rating model is established based on communication source data (such as real client data of a Unicom) provided by a communication operator, credit is scored on a user through a big data analysis means, and after a network lending company obtains client authorization, a credit score or credit investigation capability list of the user can be obtained, so that a payment amount, period, interest rate and the like are guided.
Specifically, a schematic diagram of the operation rendering method of the entire communication credit data in this embodiment is shown in fig. 7. The operating environment requirements are as follows:
big data platform interface machine: the method is used for storing interface files, requiring 20-core CPU,128G memory and 2T data storage;
the application host computer: the tenant resource of the big data platform requires 20 cores of CPU,128G memory and 2T storage;
operating system: llinux or Unix.
In the second embodiment, as shown in fig. 8, an operation rendering system of communication credit information data is applied to an operation rendering method of communication credit information data in the first embodiment, and includes a data acquisition module, a model construction module, a capability evaluation module and a package rendering module;
the data acquisition module is used for acquiring communication source data provided by a communication operator, and carrying out data integration on the communication source data to obtain credit investigation data;
the model construction module is used for constructing a credit investigation service model according to the credit investigation data;
the capability evaluation module is used for acquiring credit information to be converted, inputting the credit information to be converted into the credit information service model and obtaining a credit information capability list corresponding to the credit information to be converted;
and the packaging rendering module is used for packaging the credit investigation capability list to obtain credit investigation rendering products.
The method comprises the steps that large data such as communication source data of a user provided by a communication operator are obtained through a data obtaining module, data integration is carried out on the data, and the obtained credit investigation data are convenient for subsequent large data analysis, so that a credit investigation service model for evaluating credit investigation conditions of the user is built through a model building module; the credit investigation service model is utilized by the capability evaluation module to obtain a credit investigation capability list corresponding to credit investigation data of any user to be evaluated, the credit investigation capability list accurately reflects the credit investigation capability of the user to be evaluated, the subsequent encapsulation of the encapsulation and reproduction module is convenient, the encapsulation is carried out based on the credit investigation capability list, the obtained credit investigation product better accords with the credit investigation capability of the user to be evaluated, the credit investigation capability of the user can be accurately carried out operation and reproduction, and the credit creation value of the user is realized;
the operation rendering system of the communication credit data can construct a credit ecosystem of a communication operator, provides unified credit capability development, management and control and operation based on big data service, and the provided credit rendering product reflects the big data operation rendering capability of the communication operator, meets the operation requirements of the existing service and data labels on the inner side (namely the communication operator), meets the strong requirements of the industries such as banks, finance, government affairs and the like on the communication credit data, makes up market blank, and is an important component of a new credit market in the big data era.
Preferably, the data acquisition module is specifically configured to:
extracting the communication source data according to a preset period to generate a plurality of interface files;
and loading all the interface files into a database according to preset database interface rules to obtain the credit investigation data.
The data acquisition module is used for acquiring communication source data of a communication operator by utilizing a data layer, and then extracting is carried out according to a preset period to obtain an interface file, so that the credit investigation data can be acquired by utilizing a database conveniently; according to the preset database rules, the interface file is conveniently and smoothly loaded into the database, and the required credit investigation data is obtained.
Preferably, the model building module is specifically configured to:
constructing a credit score basic model, and determining a plurality of evaluation dimensions of the credit score basic model and a score index set under each evaluation dimension according to the credit data;
preprocessing the credit investigation data to obtain sample data;
screening each grading index set according to the sample data by adopting a factor analysis method and a principal component analysis method to obtain a target grading index set under each evaluation dimension;
dividing the sample data into a training set and a testing set, selecting a target scoring index set with any evaluation dimension, and calculating to obtain index weight of the training set under each target scoring index in the selected target scoring index set by adopting an entropy method;
Obtaining index scores of the training set under each target scoring index in the selected target scoring index set according to a preset scoring method;
calculating to obtain dimension scores corresponding to the training set under the selected evaluation dimension according to the index weights and the index scores of all target scoring indexes in the selected target scoring index set;
the specific formula for calculating the dimension score of the training set in the ith evaluation dimension is as follows:
wherein W is i At the ith evaluation for the training setDimension score, p j And q j Respectively obtaining index weight and index score of the training set under the j-th target scoring index in the i-th target scoring index set of the evaluation dimension, wherein m is the total number of target scoring indexes in the i-th target scoring index set of the evaluation dimension;
obtaining dimension scores of the training set under each evaluation dimension;
acquiring the dimension weight of each evaluation dimension by adopting an AHP analytic hierarchy process, and obtaining the credit score of the training set according to all the dimension weights and the dimension scores of the training set under all the evaluation dimensions;
and training the credit score basic model according to the training set, all evaluation dimensions, all target score index sets and credit scores of the training set to obtain the credit service model.
The model construction module can form a multi-dimensional dynamic credit assessment system (namely a credit investigation service model) through the training set, the evaluation dimension, the target grading index set and the credit grading, and can accurately represent the credit investigation capability of the user; the preset scoring method is set before the model is built, and meanwhile, the scoring method can be adjusted according to actual conditions.
Preferably, as shown in fig. 9, the method further comprises a model optimization module, wherein the model optimization module is specifically used for:
and optimizing the credit investigation service model by using the test set to obtain the optimized credit investigation service model.
Through the model optimization module, the accuracy of evaluating the credit investigation capability of the user by the credit investigation service model can be improved, so that credit investigation change products which more accord with the credit investigation capability of the user can be obtained, and value is created for credit investigation data of the user.
Preferably, the capability evaluation module is specifically configured to:
obtaining the credit investigation data to be changed from the database;
inputting the credit information to be converted into the optimized credit information service model to obtain a target credit score of the credit information to be converted and a target dimension score of the credit information to be converted under each evaluation dimension;
And obtaining the credit rating capability list corresponding to the credit rating data to be converted according to the target credit score and the dimension scores under all evaluation dimensions.
The capability evaluation module is used for evaluating the credit data to be changed through the credit investigation service model, outputting a final target credit score at the same time, outputting a target dimension score under each evaluation dimension output by the intermediate node, and obtaining a credit investigation capability list according to the target credit score and the target dimension scores under all the evaluation dimensions, wherein the credit investigation capability of the user can be reflected from multiple dimensions; based on the credit investigation capability list, the big data operation rendering capability of the communication operator can be comprehensively embodied, on one hand, the operation requirements of the existing service and data labels are met, namely, the operation rendering capability of the communication credit investigation data is provided, on the other hand, the strong requirements of the industries such as banks, finance, government affairs and the like on the communication credit investigation data are met, so that the service scene requirements of the industries are supported, namely, the operation rendering capability of the communication credit investigation data is also provided, the credit of the user is fully created, and the market blank is effectively made up.
Preferably, the package rendering module is specifically configured to:
Sending the credit investigation capability list to a capability opening platform of the communication operator, and carrying out capability encapsulation and capability opening on the credit investigation capability list by utilizing the capability opening platform to obtain the credit investigation rendering product;
wherein, carrying out capability encapsulation and capability opening on the credit investigation capability list comprises the following steps:
API packaging is carried out on the credit investigation capability list;
registering the credit investigation capability list packaged by the API into a capability store of the capability open platform, and setting a commodity browsing function, a searching function, a subscribing function and a using function for the registered credit investigation capability list.
Because the capability open platform of the communication operator has the services of capability encapsulation, capability opening and the like, the credit investigation capability list is sent to the capability open platform through the encapsulation rendering module, on one hand, the virtual credit investigation capability list can be conveniently encapsulated into an actual credit investigation rendering product which can be opened to the outside, the operation rendering of credit investigation data is truly realized, the opening capability of the existing business and data labels is met, and the operation rendering capability is provided to the outside; on the other hand, the service life cycle management of the credit investigation service is convenient to realize, and the healthy operation of the operation and the appearance of the whole credit investigation data is ensured; the credit investigation product comprises credit investigation products, credit investigation products and the like.
Preferably, as shown in fig. 9, the device further comprises a scene supporting module, wherein the scene supporting module is specifically configured to:
setting a calling API interface and scene parameters of the credit investigation rendering product, and constructing an operation scene of the credit investigation rendering product according to the calling API interface and the scene parameters;
wherein the credit investigation rendering product operates in the operation scene.
The operation scene built by calling the API interface and the scene parameters set by the scene supporting module is convenient for providing the scene support of the credit investigation product, and the operation support of the credit investigation capability of the credit investigation data is truly realized so as to support the business scene requirements of industries such as banks, finance, government affairs and the like on the credit investigation data.
Details of the embodiment I and the detailed descriptions of FIGS. 1 to 7 are not repeated here.
The third embodiment also discloses an operation rendering system of communication credit information data based on the first embodiment and the second embodiment, which comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the computer program realizes the specific steps of S1 to S4 when running.
Through the computer program stored in the memory and running on the processor, the credit ecological system of the communication carrier can be constructed, the unified credit investigation capability is externally provided for development, management and control and operation based on the big data service, the provided credit investigation and realization product reflects the big data operation and realization capability of the communication carrier, the operation requirements of the existing service and data labels are met for the internal (i.e. the communication carrier), the strong requirements of the industries such as banks, finance, government affairs and the like for the communication credit investigation data are externally met, market blank is made up, and the credit investigation and communication system is an important component of a new credit investigation market in the big data age.
The present embodiment also provides a computer storage medium having at least one instruction stored thereon, which when executed, implements the specific steps of S1 to S4.
By executing the computer storage medium containing at least one instruction, a credit ecological system of a communication carrier can be built, unified credit investigation capability development, management and control and operation are provided based on big data service, the provided credit investigation product embodies the big data operation investigation capability of the communication carrier, the operation requirements of the existing service and data labels are met for the internal (i.e. the communication carrier), the strong requirements of the industries such as banks, finance, government affairs and the like on communication credit investigation data are met, market blank is made up, and the communication carrier is an important component of a new generation credit investigation market in the big data age.
Details of the embodiment I and the detailed descriptions of FIGS. 1 to 7 are not repeated here.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (9)
1. An operation rendering method of communication credit information data, which is characterized by comprising the following steps:
step 1: acquiring communication source data provided by a communication operator, and carrying out data integration on the communication source data to obtain credit investigation data;
step 2: constructing a credit investigation service model according to the credit investigation data;
step 3: acquiring credit information to be converted, and inputting the credit information to be converted into the credit information service model to obtain a credit information capacity list corresponding to the credit information to be converted;
step 4: packaging the credit investigation capability list to obtain a credit investigation demonstration product;
the specific steps of the step 2 include:
step 21: constructing a credit score basic model, and determining a plurality of evaluation dimensions of the credit score basic model and a score index set under each evaluation dimension according to the credit data;
Step 22: preprocessing the credit investigation data to obtain sample data;
step 23: screening each grading index set according to the sample data by adopting a factor analysis method and a principal component analysis method to obtain a target grading index set under each evaluation dimension;
step 24: dividing the sample data into a training set and a testing set, selecting a target scoring index set with any evaluation dimension, and calculating to obtain index weight of the training set under each target scoring index in the selected target scoring index set by adopting an entropy method;
step 25: obtaining index scores of the training set under each target scoring index in the selected target scoring index set according to a preset scoring method;
step 26: calculating to obtain dimension scores corresponding to the training set under the selected evaluation dimension according to the index weights and the index scores of all target scoring indexes in the selected target scoring index set;
the specific formula for calculating the dimension score of the training set in the ith evaluation dimension is as follows:
wherein W is i Dimension score, p, for the training set in the ith evaluation dimension j And q j Respectively the training setsIndex weight and index score under the j-th target score index in the i-th target score index set of evaluation dimensions, m being the total number of target score indexes in the i-th target score index set of evaluation dimensions;
step 27: obtaining dimension scores of the training set under each evaluation dimension according to the methods from the step 24 to the step 26;
step 28: acquiring the dimension weight of each evaluation dimension by adopting an AHP analytic hierarchy process, and obtaining the credit score of the training set according to all the dimension weights and the dimension scores of the training set under all the evaluation dimensions;
step 29: and training the credit score basic model according to the training set, all evaluation dimensions, all target score index sets and credit scores of the training set to obtain the credit service model.
2. The method for implementing operation of communication credit data according to claim 1, wherein in the step 1, the specific step of obtaining the credit data includes:
step 11: extracting the communication source data according to a preset period to generate a plurality of interface files;
step 12: and loading all the interface files into a database according to preset database interface rules to obtain the credit investigation data.
3. The method of claim 1, further comprising the step of, prior to step 3:
and optimizing the credit investigation service model by using the test set to obtain the optimized credit investigation service model.
4. The method for implementing operation of communication credit data according to claim 3, wherein the specific steps of step 3 include:
step 31: obtaining the credit investigation data to be changed from the database;
step 32: inputting the credit information to be converted into the optimized credit information service model to obtain a target credit score of the credit information to be converted and a target dimension score of the credit information to be converted under each evaluation dimension;
step 33: and obtaining the credit rating capability list corresponding to the credit rating data to be converted according to the target credit score and the dimension scores under all evaluation dimensions.
5. The method for implementing operation of communication credit data according to claim 4, wherein the specific steps of step 4 include:
sending the credit investigation capability list to a capability opening platform of the communication operator, and carrying out capability encapsulation and capability opening on the credit investigation capability list by utilizing the capability opening platform to obtain the credit investigation rendering product;
Wherein, carrying out capability encapsulation and capability opening on the credit investigation capability list comprises the following steps:
API packaging is carried out on the credit investigation capability list;
registering the credit investigation capability list packaged by the API into a capability store of the capability open platform, and setting a commodity browsing function, a searching function, a subscribing function and a using function for the registered credit investigation capability list.
6. The method of claim 5, further comprising the step of, after the step 4:
step 5: setting a calling API interface and scene parameters of the credit investigation rendering product, and constructing an operation scene of the credit investigation rendering product according to the calling API interface and the scene parameters;
wherein the credit investigation rendering product operates in the operation scene.
7. An operation rendering system of communication credit data, which is characterized by being applied to the operation rendering method of the communication credit data of any one of claims 1 to 6, and comprising a data acquisition module, a model construction module, a capability evaluation module and a packaging rendering module;
the data acquisition module is used for acquiring communication source data provided by a communication operator, and carrying out data integration on the communication source data to obtain credit investigation data;
The model construction module is used for constructing a credit investigation service model according to the credit investigation data;
the capability evaluation module is used for acquiring credit information to be converted, inputting the credit information to be converted into the credit information service model and obtaining a credit information capability list corresponding to the credit information to be converted;
and the packaging rendering module is used for packaging the credit investigation capability list to obtain credit investigation rendering products.
8. An operational rendering system for communicating credit data, comprising a processor, a memory and a computer program stored in the memory and operable on the processor, the computer program being operable to carry out the method steps of any one of claims 1 to 6.
9. A computer storage medium, the computer storage medium comprising: at least one instruction which, when executed, implements the method steps of any of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010609202.1A CN111784503B (en) | 2020-06-29 | 2020-06-29 | Operation rendering method, system and storage medium of communication credit investigation data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010609202.1A CN111784503B (en) | 2020-06-29 | 2020-06-29 | Operation rendering method, system and storage medium of communication credit investigation data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111784503A CN111784503A (en) | 2020-10-16 |
CN111784503B true CN111784503B (en) | 2023-12-05 |
Family
ID=72760074
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010609202.1A Active CN111784503B (en) | 2020-06-29 | 2020-06-29 | Operation rendering method, system and storage medium of communication credit investigation data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111784503B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20000072476A (en) * | 2000-09-06 | 2000-12-05 | 김윤호 | Method and Application Solution of on-line Cash Service for Enterprise |
JP2007115110A (en) * | 2005-10-21 | 2007-05-10 | Research Organization Of Information & Systems | Credit risk quantification model leniency/severity evaluating method, its execution program and recording medium |
CN107332844A (en) * | 2017-07-03 | 2017-11-07 | 上海路诚数据服务有限公司 | Privacy information application method and personal reference methods of marking |
CN108665184A (en) * | 2018-05-21 | 2018-10-16 | 国网陕西省电力公司咸阳供电公司 | A kind of power customer credit assessment method based on big data reference |
CN109063979A (en) * | 2018-07-13 | 2018-12-21 | 四川享宇金信金融服务外包有限公司 | A kind of air control model building method |
CN109191189A (en) * | 2018-08-20 | 2019-01-11 | 国网河南省电力公司经济技术研究院 | Power sales decontrol lower power customer value assessment method |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2009006617A1 (en) * | 2007-07-04 | 2009-01-08 | Global Analytics, Inc. | Systems and methods for making structured reference credit decisions |
US10453142B2 (en) * | 2009-02-11 | 2019-10-22 | Johnathan Mun | System and method for modeling and quantifying regulatory capital, key risk indicators, probability of default, exposure at default, loss given default, liquidity ratios, and value at risk, within the areas of asset liability management, credit risk, market risk, operational risk, and liquidity risk for banks |
AU2013221926A1 (en) * | 2012-08-28 | 2014-03-20 | Clearmatch Holdings (Singapore) PTE. LTD. | Methods and systems for consumer lending |
US11176480B2 (en) * | 2016-04-21 | 2021-11-16 | Oracle International Corporation | System and method for partitioning models in a database |
US11068496B2 (en) * | 2017-10-20 | 2021-07-20 | Jpmorgan Chase Bank, N.A. | System and method for data management |
-
2020
- 2020-06-29 CN CN202010609202.1A patent/CN111784503B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20000072476A (en) * | 2000-09-06 | 2000-12-05 | 김윤호 | Method and Application Solution of on-line Cash Service for Enterprise |
JP2007115110A (en) * | 2005-10-21 | 2007-05-10 | Research Organization Of Information & Systems | Credit risk quantification model leniency/severity evaluating method, its execution program and recording medium |
CN107332844A (en) * | 2017-07-03 | 2017-11-07 | 上海路诚数据服务有限公司 | Privacy information application method and personal reference methods of marking |
CN108665184A (en) * | 2018-05-21 | 2018-10-16 | 国网陕西省电力公司咸阳供电公司 | A kind of power customer credit assessment method based on big data reference |
CN109063979A (en) * | 2018-07-13 | 2018-12-21 | 四川享宇金信金融服务外包有限公司 | A kind of air control model building method |
CN109191189A (en) * | 2018-08-20 | 2019-01-11 | 国网河南省电力公司经济技术研究院 | Power sales decontrol lower power customer value assessment method |
Non-Patent Citations (6)
Title |
---|
基于大数据技术的个人信用动态评价指标体系研究――基于社会资本视角;王冬一;华迎;朱峻萱;;国际商务(对外经济贸易大学学报)(01);121-133 * |
基于指标相关性的网络运维质量评估模型;吴沐阳;刘峥;王洋;李云;李涛;;计算机应用(09);93-100 * |
基于改进模糊综合评价法的小微企业金融风险分析模型研究;李敬明;阮素梅;刘奎户;;运筹与管理(06);221-228 * |
电信运营商大数据资源变现模式及策略研究;陈科帆;周洪成;;移动通信(01);64-68 * |
电力客户风险评估的熵权层次分析方法研究;田廓;韩冰;贾昭华;;陕西电力(10);11-14 * |
科技型中小企业信用评价与实证分析;鲍盛祥;殷永飞;;科技进步与对策(20);149-154 * |
Also Published As
Publication number | Publication date |
---|---|
CN111784503A (en) | 2020-10-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107818344B (en) | Method and system for classifying and predicting user behaviors | |
US20170109657A1 (en) | Machine Learning-Based Model for Identifying Executions of a Business Process | |
US7574379B2 (en) | Method and system of using artifacts to identify elements of a component business model | |
US20150379429A1 (en) | Interactive interfaces for machine learning model evaluations | |
WO2022252363A1 (en) | Data processing method, computer device and readable storage medium | |
US20170109668A1 (en) | Model for Linking Between Nonconsecutively Performed Steps in a Business Process | |
US20170109667A1 (en) | Automaton-Based Identification of Executions of a Business Process | |
US20170109636A1 (en) | Crowd-Based Model for Identifying Executions of a Business Process | |
CN112288455B (en) | Label generation method and device, computer readable storage medium and electronic equipment | |
US20170109639A1 (en) | General Model for Linking Between Nonconsecutively Performed Steps in Business Processes | |
CN111210332A (en) | Method and device for generating post-loan management strategy and electronic equipment | |
US20170109640A1 (en) | Generation of Candidate Sequences Using Crowd-Based Seeds of Commonly-Performed Steps of a Business Process | |
CN113450158A (en) | Bank activity information pushing method and device | |
US20170109637A1 (en) | Crowd-Based Model for Identifying Nonconsecutive Executions of a Business Process | |
US20170109670A1 (en) | Crowd-Based Patterns for Identifying Executions of Business Processes | |
CN111784503B (en) | Operation rendering method, system and storage medium of communication credit investigation data | |
CN114374595B (en) | Event node attribution analysis method, device, electronic equipment and storage medium | |
Levus et al. | Intelligent System for Arbitrage Situations Searching in the Cryptocurrency Market. | |
US11741099B2 (en) | Supporting database queries using unsupervised vector embedding approaches over unseen data | |
CN115168848A (en) | Interception feedback processing method based on big data analysis interception | |
CN112883091A (en) | Factor data acquisition method and device, computer equipment and storage medium | |
CN111581068A (en) | Terminal workload calculation method and device, storage medium, terminal and cloud service system | |
Liermann et al. | Use Case: Optimization of Regression Tests—Reduction of the Test Portfolio Through Representative Identification | |
Choo | A Study on the Effect of Quality Factors of Smartphone 5G Technology on the Reliability of Information and Communication Policy | |
CN116800831B (en) | Service data pushing method, device, storage medium and processor |
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 |