CN117808578A - Intelligent pedestrian credit information data analysis method and system - Google Patents
Intelligent pedestrian credit information data analysis method and system Download PDFInfo
- Publication number
- CN117808578A CN117808578A CN202410232695.XA CN202410232695A CN117808578A CN 117808578 A CN117808578 A CN 117808578A CN 202410232695 A CN202410232695 A CN 202410232695A CN 117808578 A CN117808578 A CN 117808578A
- Authority
- CN
- China
- Prior art keywords
- credit
- data
- features
- determining
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000007405 data analysis Methods 0.000 title claims abstract description 23
- 230000008859 change Effects 0.000 claims abstract description 48
- 238000012545 processing Methods 0.000 claims abstract description 45
- 238000004458 analytical method Methods 0.000 claims abstract description 12
- 238000011156 evaluation Methods 0.000 claims description 27
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012797 qualification Methods 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides an intelligent pedestrian credit information data analysis method and system, which belong to the technical field of data processing and specifically comprise the following steps: the credit basic characteristics of the user are constructed based on the analysis result of the pedestrian credit data, the risk rule score of the user is determined through the credit basic characteristics and the rule score model, when the fact that the credit risk exists in the user is determined based on the risk rule score, the update probability and the suspected change characteristics of different credit basic characteristics are determined through the update data of different credit basic characteristics, the feature data of the suspected change characteristics of the user and the feature data of the high-quality characteristics are obtained, whether the credit application can be processed or not is determined by combining the risk rule score of the user, and the technical problem that the processing result of the credit application is inaccurate due to untimely update of the pedestrian credit data is avoided.
Description
Technical Field
The invention belongs to the technical field of data processing, and particularly relates to an intelligent pedestrian credit information data analysis method and system.
Background
The pedestrian credit data is a credit field core data asset, and rich user personal information and credit performance are recorded. Comprehensively extracting credit investigation information, and comprehensively judging qualification and risk of service users, which is important for credit business.
In order to realize analysis processing of pedestrian credit information data, a method for analyzing and processing the pedestrian credit information data is provided in a data extraction and processing method and system based on user credit characteristics in the prior art scheme CN202210915656.0, and a method for mining credit information reporting characteristics in the prior art scheme CN202111410257.0, but the following technical problems are found through analysis:
the user's pedestrian credit data is not updated in real time, and the update period is generally fixed, so that when the approval process of the credit application is performed, the technical problem that the approval result of the credit application is not accurate enough due to the fact that the credit data is not updated timely may exist, and therefore if the evaluation of the update probability of the differentiated pedestrian credit data cannot be performed in combination with the historical update conditions of the pedestrian credit data of different users, the accurate control of the credit risk may not be realized.
Aiming at the technical problems, the invention provides an intelligent pedestrian credit information data analysis method and system.
Disclosure of Invention
In order to achieve the purpose of the invention, the invention adopts the following technical scheme:
according to one aspect of the invention, an intelligent pedestrian credit information data analysis method is provided.
An intelligent pedestrian credit information data analysis method is characterized by comprising the following steps:
s1, constructing credit basic characteristics of a user based on an analysis result of pedestrian credit information data, determining risk rule scores of the user through the credit basic characteristics and a rule score model, and entering a next step when determining that the user does not have credit risks based on the risk rule scores;
s2, determining updating conditions of credit basic features of the pedestrian credit information data of the user under different historical updating times based on the historical updating data, and determining instantaneity of the pedestrian credit information data of the user by combining time of the historical updating times of the credit basic features and updating time of the pedestrian credit information data, wherein when the instantaneity does not meet requirements, the next step is carried out;
s3, determining update probabilities and suspected change characteristics of different credit basic characteristics through update data of the different credit basic characteristics, and determining characteristic scores of the different suspected change characteristics and high-quality characteristics in the suspected change characteristics according to correlation coefficients of the different suspected change characteristics and credit application results;
s4, acquiring the feature data of the suspected change features and the feature data of the high-quality features of the user, and determining whether the processing of the credit application can be performed or not according to the risk rule score of the user.
The invention has the beneficial effects that:
1. the risk rule score of the user is determined through the credit basic characteristics and the rule score model, so that the screening of the user with credit risk based on the current credit report from the perspective of the credit basic characteristics is realized, the technical problem of low processing efficiency caused by the real-time evaluation of all credit data is avoided, and the processing efficiency of the credit application is improved.
2. The real-time performance of the pedestrian credit data of the user is determined based on the updating condition of the credit basic features, the time of the historical updating times of the credit basic features and the updating time of the pedestrian credit data, not only the updating times of different credit basic features are considered, but also the screening of users with frequent updating of the recent credit basic features is realized by considering the updating time of the credit basic features, and a foundation is laid for the differentiated determination of whether the credit application can be processed.
3. Whether the processing of the credit application can be performed is determined by the feature data of the suspected change features, the feature data of the high-quality features and the risk rule scores of the users, the difference of the processing risks of the credit application caused by the difference of the risk rule scores is simply considered, and meanwhile, the technical problem that the processing risk of the credit application is high due to untimely updating of the pedestrian credit data is avoided by comprehensively considering the change probability of the suspected change features and the change probability of the high-quality features.
The further technical scheme is that the pedestrian credit information data are determined according to the analysis result of the pedestrian credit information report of the user.
The further technical scheme is that the method for constructing the credit basic characteristics comprises the following steps:
and transmitting the pedestrian credit information data of the user to an existing automatic feature deriving system, and constructing credit basic features based on the automatic feature deriving system.
The further technical scheme is that the method for determining the risk rule score of the user comprises the following steps:
and determining feature scores corresponding to different credit basic features of the user based on the rule score model, and determining the risk rule score of the user according to the feature scores corresponding to the different credit basic features of the user.
A further technical solution is to determine that the user has credit risk when the risk rule score of the user does not meet the requirements.
The further technical scheme is that when the user has credit risk, the user is determined that the processing of the credit application cannot be performed.
The further technical scheme is that when the instantaneity meets the requirement, the processing of the credit application can be determined.
The further technical scheme is that the updating data of the credit basic feature comprises the updating times of the credit basic feature and the updating time of different updating times.
The further technical scheme is that when the feature score of the suspected variation feature is within a preset score interval, the suspected variation feature is determined to be a high-quality feature.
In a second aspect, the present invention provides a computer system comprising: a communicatively coupled memory and processor, and a computer program stored on the memory and capable of running on the processor, characterized by: and executing the intelligent pedestrian credit information data analysis method when the processor runs the computer program.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the invention as set forth hereinafter.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings;
FIG. 1 is a flow chart of an intelligent pedestrian credit data analysis method;
FIG. 2 is a flow chart of a method of determining the real-time nature of user pedestrian credit data;
FIG. 3 is a flow chart of a method of determining the real-time nature of user's pedestrian credit data;
FIG. 4 is a flow chart of a method of determining whether processing of a trusted application is enabled;
FIG. 5 is a block diagram of a computer system.
Detailed Description
In order to make the technical solutions in the present specification better understood by those skilled in the art, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present disclosure.
When the credit application of the credit applicant is processed, the credit risk is often required to be evaluated by means of the data analysis result of the pedestrian credit data of the user, but the pedestrian credit data of the user is not updated in real time, and the updating period is generally about one month, so that if the evaluation of the variation probability of the pedestrian credit data cannot be comprehensively performed according to the historical variation condition and the un-updated time of the pedestrian credit data of the user, the credit risk may be increased.
In order to solve the technical problems, the following technical scheme is adopted:
firstly, constructing credit basic characteristics of a user through an analysis result of pedestrian credit information data, so that a preset rule scoring model can be adopted to determine the risk rule score of the user, when the risk rule score of the user is large, credit risks exist at the moment, a credit rejection application is directly output, when the risk rule score of the user is small, it is determined that the user does not have credit risks, and the next step is carried out;
then, updating credit basic characteristics of the user under different historical updating times, determining the instantaneity of the credit basic characteristics of the user by combining the time of the historical updating times of the credit basic characteristics and the updating time of the credit basic characteristics, specifically determining the variation probability by the product of the variation quantity ratio of the credit basic characteristics and the latest time of the historical updating times of the credit basic characteristics, and then determining the instantaneity according to the weight and the real-time of the ratio of the variation probability to the non-updated time and the updating period, wherein when the instantaneity is smaller, the variation risk of the credit basic characteristics possibly exists at the moment, and entering the next step;
then determining different credit basic characteristics updating probabilities and suspected change characteristics according to different credit basic characteristics updating times and pedestrian credit data updating times, determining the updating probabilities according to the ratio of different credit basic characteristics updating times to pedestrian credit data updating times, taking the credit basic characteristics with larger updating probabilities as suspected change characteristics, and determining different suspected change characteristics feature scores and high-quality characteristics in the suspected change characteristics according to different suspected change characteristics and correlation coefficients of credit application results;
and finally, determining whether the credit application can be processed according to the number and the fluctuation probability of the suspected fluctuation features of the user, the number and the fluctuation probability of the high-quality features and the risk rule score of the user, specifically determining the sum of the fluctuation probabilities of the suspected fluctuation features according to the number and the fluctuation probability of the suspected fluctuation features, obtaining the sum of the fluctuation probabilities of the high-quality features according to the number and the fluctuation probability of the high-quality features, and finally determining the processing risk of the credit application according to the sum of the fluctuation probabilities of the suspected fluctuation features, the sum of the fluctuation probabilities of the high-quality features and the weight of the risk rule score and the processing risk of the credit application, wherein the credit application cannot be processed when the processing risk is large.
The following will be described from two perspectives of a method class embodiment and a system class embodiment.
In order to solve the above problems, according to one aspect of the present invention, as shown in fig. 1, an intelligent pedestrian sign data analysis method is provided, which is characterized in that the method specifically includes:
s1, constructing credit basic characteristics of a user based on an analysis result of pedestrian credit information data, determining risk rule scores of the user through the credit basic characteristics and a rule score model, and entering a next step when determining that the user does not have credit risks based on the risk rule scores;
further, the pedestrian credit information data is determined according to the analysis result of the pedestrian credit information report of the user.
Specifically, the method for constructing the credit basic feature comprises the following steps:
and transmitting the pedestrian credit information data of the user to an existing automatic feature deriving system, and constructing credit basic features based on the automatic feature deriving system.
It can be appreciated that the method for determining the risk rule score of the user is as follows:
and determining feature scores corresponding to different credit basic features of the user based on the rule score model, and determining the risk rule score of the user according to the feature scores corresponding to the different credit basic features of the user.
It should be noted that, when the risk rule score of the user does not meet the requirement, it is determined that the user has a credit risk.
Further, when the user has credit risk, it is determined that the processing of the credit application cannot be performed.
Specifically, when the user has credit risk, the processing result of the credit application is directly output based on the risk rule score of the user.
In the embodiment, the risk rule score of the user is determined through the credit basic feature and the rule score model, so that the screening of the user with credit risk based on the current credit report from the perspective of the credit basic feature is realized, the technical problem of low processing efficiency caused by the real-time evaluation of all credit data is avoided, and the processing efficiency of the credit application is improved.
S2, determining updating conditions of credit basic features of the pedestrian credit information data of the user under different historical updating times based on the historical updating data, and determining instantaneity of the pedestrian credit information data of the user by combining time of the historical updating times of the credit basic features and updating time of the pedestrian credit information data, wherein when the instantaneity does not meet requirements, the next step is carried out;
it will be appreciated that the updated status of the credit base feature includes the updated number of the credit base feature.
Specifically, for example, the method for determining the real-time performance of the pedestrian credit information data of the user in the step S2 includes:
determining the non-updated time length of the pedestrian credit data based on the latest updating time and the current time of the pedestrian credit data, and determining that the real-time performance meets the requirement when the non-updated time length is smaller than the preset updating time length;
when the non-updated time length is smaller than a preset updated time length, determining the basic instantaneity of the pedestrian credit information data of the user through the non-updated time length, and when the basic instantaneity of the pedestrian credit information data of the user does not meet the requirement, determining that the instantaneity does not meet the requirement;
when the basic real-time performance of the pedestrian credit information data of the user meets the requirement, determining the data update times according to the update conditions of credit characteristics of the pedestrian credit information data under different historical update times, and when the data update times are larger than the preset update times, determining that the real-time performance does not meet the requirement;
when the number of data updating times is not more than the preset number of updating times, determining data fluctuation assessment values in different time division intervals according to the number of data updating times in different time division intervals, the updating time of the different data updating times and the updating number of credit basic features under the different data updating times, determining data fluctuation assessment values in adjacent time periods according to the data fluctuation assessment values in the different time division intervals, and determining that the instantaneity does not meet the requirement when the data fluctuation assessment values in the adjacent time periods do not meet the requirement;
when the data fluctuation estimated quantity in the adjacent time period meets the requirement, the basic instantaneity of the pedestrian credit data of the user is corrected based on the basic weight values of different time division intervals and the data fluctuation estimated quantity to obtain the instantaneity of the pedestrian credit data of the user.
Further, the real-time value range of the pedestrian credit data of the user is between 0 and 1, wherein when the real-time value of the pedestrian credit data of the user is smaller than the real-time limit value, the real-time value of the pedestrian credit data of the user is determined to not meet the requirement.
In another embodiment, as shown in fig. 2, the method for determining the real-time performance of the pedestrian sign data of the user in the step S2 is as follows:
determining the non-updated time length of the pedestrian credit data based on the latest updating time and the current time of the pedestrian credit data, and determining the basic real-time performance of the pedestrian credit data of the user through the non-updated time length;
determining data updating times according to the updating conditions of credit features of the pedestrian credit information data under different historical updating times, and determining data fluctuation evaluation values in different time division intervals according to the data updating times in different time division intervals, the updating time of different data updating times and the updating quantity of credit basic features under different data updating times;
and correcting the basic instantaneity of the pedestrian credit data of the user based on the basic weight values and the data variation evaluation values of different time division intervals to obtain the instantaneity of the pedestrian credit data of the user.
In another embodiment, the method for determining the real-time performance of the pedestrian credit data of the user in the step S2 is as follows:
s21, determining the non-updated time length of the pedestrian credit data based on the latest updating time and the current time of the pedestrian credit data, determining the basic real-time property of the pedestrian credit data of the user according to the non-updated time length, judging whether the basic real-time property of the pedestrian credit data of the user is greater than the preset real-time property, if so, entering the next step, and if not, entering the step S25;
s22, determining data updating times according to the credit feature updating conditions of the pedestrian credit information data under different historical updating times, judging whether the data updating times are smaller than an updating times limiting value, if so, determining that the real-time performance of the pedestrian credit information data of the user meets the requirement, and if not, entering the next step;
s23, determining the total number of updating credit basic features according to the number of updating credit basic features under different data updating times, judging whether the total number of updating credit basic features is in a preset feature number interval, if so, determining that the real-time performance of the pedestrian credit information data of the user meets the requirement, and if not, entering the next step;
s24, determining data fluctuation evaluation values in different time division intervals according to the data update times in different time division intervals, the update time of the different data update times and the update quantity of credit basic features under the different data update times, determining the data fluctuation evaluation values in adjacent time periods according to the data fluctuation evaluation values in the different time division intervals, judging whether the data fluctuation evaluation values in the adjacent time periods meet requirements, if yes, determining that the instantaneity meets the requirements, and if not, entering the next step;
and S25, correcting the basic instantaneity of the pedestrian credit data of the user based on the basic weight values and the data fluctuation evaluation values of different time division intervals to obtain the instantaneity of the pedestrian credit data of the user.
Further, when the instantaneity meets the requirement, the processing of the trusted application is determined to be capable of being performed.
In this embodiment, based on the update situation of the credit base feature, the time when the historical update times of the credit base feature are updated and the update time of the pedestrian credit data, the real-time performance of the pedestrian credit data of the user is determined, not only the update times of different credit base features are considered, but also the screening of users with frequent update of the recent credit base feature is realized by considering the update time of the credit base feature, and a foundation is laid for the differentiated determination of whether the processing of the credit application can be performed.
S3, determining update probabilities and suspected change characteristics of different credit basic characteristics through update data of the different credit basic characteristics, and determining characteristic scores of the different suspected change characteristics and high-quality characteristics in the suspected change characteristics according to correlation coefficients of the different suspected change characteristics and credit application results;
specifically, the update data of the credit base feature includes the update times of the credit base feature and the update times of different update times.
Specifically, as shown in fig. 3, the method for determining the update probability of the credit base feature in the step S3 includes:
the method comprises the steps of determining the updating times of credit basic features in different time division intervals according to the updating times of the credit basic features in different updating times, and determining updating evaluation values of the credit basic features in different time division intervals by combining the time difference between the updating times of the different updating times and the current time and the updating amplitude of the different updating times;
the update probability of the credit base feature is determined based on the update evaluation of the credit base feature in the different time division intervals and the base weight value of the different time division intervals.
In another embodiment, the method for determining the update probability of the credit base feature in the step S3 is as follows:
when the updating times of the credit basic features are smaller than the preset feature updating times, determining that the credit basic features do not belong to suspected variation features;
when the update times of the credit basic features are not less than the preset feature update times, the update times of the credit basic features in different time division intervals are determined through the update time of the credit basic features in different update times, and when the update times of the credit basic features in the adjacent time period are greater than an update times threshold, the credit basic features are determined to belong to suspected change features;
when the number of updating times of the credit base features in the adjacent time period is not more than the threshold value of the number of updating times, determining the update evaluation value of the credit base features in different time division intervals based on the number of updating times of the credit base features in different time division intervals and the time difference between the updating time of the different updating times and the current time, and determining that the credit base features belong to suspected variation features when the update evaluation value in the adjacent time period does not meet the requirement;
and when the update evaluation value in the adjacent time period meets the requirement, determining the update probability of the credit basic feature based on the update evaluation value of the credit basic feature in different time division intervals and the basic weight value of the different time division intervals.
Further, the adjacent time period is determined according to the preset time length, and specifically, the time period in the latest preset time length is taken as the adjacent time period.
Specifically, when the feature score of the suspected variation feature is within a preset score interval, determining that the suspected variation feature is a high-quality feature.
S4, acquiring the feature data of the suspected change features and the feature data of the high-quality features of the user, and determining whether the processing of the credit application can be performed or not according to the risk rule score of the user.
The feature data of the suspected variation features includes the number of the suspected variation features, the update probabilities of different suspected variation features, and feature scores.
Specifically, as shown in fig. 4, the determining in the step S4 whether the trusted application can be processed specifically includes:
determining the quantity of the high-quality features through the feature data of the high-quality features, and determining the update influence value of the high-quality features by combining the update probabilities of different high-quality features and the feature scores;
determining the quantity of the suspected variation features through the feature data of the suspected variation features, and determining update influence values of the suspected variation features by combining different update probabilities of the suspected variation features and feature scores;
and determining a credit giving risk value of the user based on the updated influence value of the high-quality feature, the updated influence value of the suspected variation feature and the risk rule score of the user, and determining whether the credit giving application can be processed or not according to the credit giving risk value.
In another embodiment, the determining in the step S4 whether the trusted application is enabled or not specifically includes:
s41, acquiring a risk rule score of the user, judging whether the risk rule score of the user is smaller than a preset risk score, if so, entering a next step, and if not, entering a step S45;
s42, judging whether the number of suspected variable features of the user is larger than a preset feature number limiting value, if so, determining that the processing of the credit application cannot be performed, and if not, entering the next step;
s43, determining the quantity of the high-quality features through the feature data of the high-quality features, determining the update influence value of the high-quality features by combining different update probabilities and feature scores of the high-quality features, judging whether the update influence value of the high-quality features meets the requirements, if not, determining that the processing of the credit application cannot be performed, and if so, entering the next step;
s44, determining the number of the suspected variable features through the feature data of the suspected variable features, determining the update influence value of the suspected variable features by combining different update probabilities and feature scores of the suspected variable features, judging whether the update influence value of the suspected variable features meets the requirements, if not, determining that the processing of the credit application cannot be performed, and if so, entering the next step;
s45, determining a credit giving risk value of the user based on the updated influence value of the high-quality feature, the updated influence value of the suspected change feature and the risk rule score of the user, and determining whether the credit giving application can be processed or not according to the credit giving risk value.
In another embodiment, the determining in the step S4 whether the trusted application is enabled or not specifically includes:
acquiring the number of suspected variation features of the user, and determining that the processing of the credit application can be performed when the number of the suspected variation features of the user is not more than a preset feature number limiting value;
when the number of suspected variable features of the user is larger than a preset feature number limiting value, determining the number of the high-quality features through feature data of the high-quality features, determining update influence values of the high-quality features by combining different update probabilities of the high-quality features and feature scores, and determining that the processing of the trust application cannot be performed when the update influence values of the high-quality features do not meet the requirements;
when the update influence value of the high-quality feature meets the requirement, determining the quantity of the suspected change features through the feature data of the suspected change features, determining the update influence value of the suspected change features by combining different update probabilities of the suspected change features and feature scores, judging whether the update influence value of the suspected change features meets the requirement, if not, determining that the processing of the trusted application cannot be performed, and if so, entering the next step;
and determining a credit giving risk value of the user based on the updated influence value of the high-quality feature, the updated influence value of the suspected variation feature and the risk rule score of the user, and determining whether the credit giving application can be processed or not according to the credit giving risk value.
In this embodiment, whether the processing of the credit application can be performed is determined by the feature data of the suspected variation feature, the feature data of the high-quality feature and the risk rule score of the user, which not only simply considers the difference of the processing risks of the credit application caused by the difference of the risk rule scores, but also avoids the technical problem of higher processing risks of the credit application caused by untimely updating of the original pedestrian credit data by comprehensively considering the variation probability of the suspected variation feature and the variation probability of the high-quality feature.
In another aspect, as shown in FIG. 5, the present invention provides a computer system comprising: a communicatively coupled memory and processor, and a computer program stored on the memory and capable of running on the processor, characterized by: and executing the intelligent pedestrian credit information data analysis method when the processor runs the computer program.
The intelligent pedestrian sign data analysis method specifically comprises the following steps:
constructing credit basic characteristics of a user based on an analysis result of the pedestrian credit information data, determining a risk rule score of the user through the credit basic characteristics and a rule score model, and entering a next step when the user is determined to have no credit risk based on the risk rule score;
determining the non-updated time length of the pedestrian credit data based on the latest updating time and the current time of the pedestrian credit data, and determining the basic real-time performance of the pedestrian credit data of the user through the non-updated time length;
determining data updating times according to the updating conditions of credit features of the pedestrian credit information data under different historical updating times, and determining data fluctuation evaluation values in different time division intervals according to the data updating times in different time division intervals, the updating time of different data updating times and the updating quantity of credit basic features under different data updating times;
correcting the basic instantaneity of the pedestrian credit data of the user based on the basic weight values and the data change evaluation values of different time division intervals to obtain the instantaneity of the pedestrian credit data of the user, and entering the next step when the instantaneity does not meet the requirement;
determining update probabilities and suspected change characteristics of different credit basic characteristics through update data of the different credit basic characteristics, and determining characteristic scores of the different suspected change characteristics and high-quality characteristics in the suspected change characteristics according to correlation coefficients of the different suspected change characteristics and credit application results;
acquiring the number of suspected variation features of the user, and determining that the processing of the credit application can be performed when the number of the suspected variation features of the user is not more than a preset feature number limiting value;
when the number of suspected variable features of the user is larger than a preset feature number limiting value, determining the number of the high-quality features through feature data of the high-quality features, determining update influence values of the high-quality features by combining different update probabilities of the high-quality features and feature scores, and determining that the processing of the trust application cannot be performed when the update influence values of the high-quality features do not meet the requirements;
when the update influence value of the high-quality feature meets the requirement, determining the quantity of the suspected change features through the feature data of the suspected change features, determining the update influence value of the suspected change features by combining different update probabilities of the suspected change features and feature scores, judging whether the update influence value of the suspected change features meets the requirement, if not, determining that the processing of the trusted application cannot be performed, and if so, entering the next step;
and determining a credit giving risk value of the user based on the updated influence value of the high-quality feature, the updated influence value of the suspected variation feature and the risk rule score of the user, and determining whether the credit giving application can be processed or not according to the credit giving risk value.
Through the above embodiments, the present invention has the following beneficial effects:
1. based on the recognition processing accuracy of different user groups, whether the comprehensive recognition accuracy of the external data source meets the requirement is determined, so that the reliable evaluation of the comprehensive recognition accuracy of the external data source is realized from the angles of the user groups with different confidence and passing rate, the technical problem that the evaluation result of the recognition accuracy is not reliable enough due to the adoption of single user data is avoided, and a foundation is laid for further realizing the differentiated management of the external data source.
2. The management of the external data sources is carried out according to the historical approval data and the yield of the credit application, the difference of the requirements of the processing quantity and the passing rate of the credit application on the yield of the external data sources is considered, and meanwhile, the foundation is laid for realizing the screening of the external data sources with higher yield by further combining the yields of different external data sources.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, devices, non-volatile computer storage medium embodiments, the description is relatively simple, as it is substantially similar to method embodiments, with reference to the section of the method embodiments being relevant.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing is merely one or more embodiments of the present description and is not intended to limit the present description. Various modifications and alterations to one or more embodiments of this description will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, or the like, which is within the spirit and principles of one or more embodiments of the present description, is intended to be included within the scope of the claims of the present description.
Claims (11)
1. An intelligent pedestrian credit information data analysis method is characterized by comprising the following steps:
constructing credit basic characteristics of a user based on an analysis result of the pedestrian credit information data, determining a risk rule score of the user through the credit basic characteristics and a rule score model, and entering a next step when the user is determined to have no credit risk based on the risk rule score;
determining updating conditions of credit basic characteristics of the pedestrian credit data of the user under different historical updating times based on the historical updating data, and determining instantaneity of the pedestrian credit data of the user by combining time of the historical updating times of the credit basic characteristics and the updating time of the pedestrian credit data, and entering the next step when the instantaneity does not meet the requirement;
determining update probabilities and suspected change characteristics of different credit basic characteristics through update data of the different credit basic characteristics, and determining characteristic scores of the different suspected change characteristics and high-quality characteristics in the suspected change characteristics according to correlation coefficients of the different suspected change characteristics and credit application results;
and acquiring the feature data of the suspected variation features and the feature data of the high-quality features of the user, and determining whether the processing of the credit application can be performed or not by combining the risk rule scores of the user.
2. The intelligent pedestrian credit data analysis method according to claim 1, wherein the pedestrian credit data is determined according to analysis results of a pedestrian credit report of the user.
3. The intelligent pedestrian credit information analysis method as claimed in claim 1, wherein the method for constructing the credit basic features is as follows:
and transmitting the pedestrian credit information data of the user to an existing automatic feature deriving system, and constructing credit basic features based on the automatic feature deriving system.
4. The intelligent pedestrian credit data analysis method as claimed in claim 1, wherein when the risk rule score of the user does not meet the requirement, it is determined that the user has credit risk.
5. The intelligent pedestrian credit data analysis method according to claim 1, wherein when the user has credit risk, the processing result of the credit application is output directly based on the risk rule score of the user.
6. The intelligent pedestrian credit data analysis method according to claim 1, wherein the method for determining the real-time performance of the pedestrian credit data of the user is as follows:
determining the non-updated time length of the pedestrian credit data based on the latest updating time and the current time of the pedestrian credit data, and determining the basic real-time performance of the pedestrian credit data of the user through the non-updated time length;
determining data updating times according to the updating conditions of credit features of the pedestrian credit information data under different historical updating times, and determining data fluctuation evaluation values in different time division intervals according to the data updating times in different time division intervals, the updating time of different data updating times and the updating quantity of credit basic features under different data updating times;
and correcting the basic instantaneity of the pedestrian credit data of the user based on the basic weight values and the data variation evaluation values of different time division intervals to obtain the instantaneity of the pedestrian credit data of the user.
7. The intelligent pedestrian credit data analysis method according to claim 1, wherein when the real-time performance meets the requirement, the processing of the credit application is determined to be enabled.
8. The intelligent pedestrian credit data analysis method as claimed in claim 1, wherein the method for determining the update probability of the credit base feature is as follows:
when the updating times of the credit basic features are smaller than the preset feature updating times, determining that the credit basic features do not belong to suspected variation features;
when the update times of the credit basic features are not less than the preset feature update times, the update times of the credit basic features in different time division intervals are determined through the update time of the credit basic features in different update times, and when the update times of the credit basic features in the adjacent time period are greater than an update times threshold, the credit basic features are determined to belong to suspected change features;
when the number of updating times of the credit base features in the adjacent time period is not more than the threshold value of the number of updating times, determining the update evaluation value of the credit base features in different time division intervals based on the number of updating times of the credit base features in different time division intervals and the time difference between the updating time of the different updating times and the current time, and determining that the credit base features belong to suspected variation features when the update evaluation value in the adjacent time period does not meet the requirement;
and when the update evaluation value in the adjacent time period meets the requirement, determining the update probability of the credit basic feature based on the update evaluation value of the credit basic feature in different time division intervals and the basic weight value of the different time division intervals.
9. The intelligent pedestrian credit data analysis method according to claim 8, wherein the adjacent time period is determined according to a preset time length, and specifically, the time period within the latest preset time length is taken as the adjacent time period.
10. The intelligent pedestrian credit data analysis method according to claim 1, wherein determining whether the credit application can be processed comprises:
acquiring the number of suspected variation features of the user, and determining that the processing of the credit application can be performed when the number of the suspected variation features of the user is not more than a preset feature number limiting value;
when the number of suspected variable features of the user is larger than a preset feature number limiting value, determining the number of the high-quality features through feature data of the high-quality features, determining update influence values of the high-quality features by combining different update probabilities of the high-quality features and feature scores, and determining that the processing of the trust application cannot be performed when the update influence values of the high-quality features do not meet the requirements;
when the update influence value of the high-quality feature meets the requirement, determining the quantity of the suspected change features through the feature data of the suspected change features, determining the update influence value of the suspected change features by combining different update probabilities of the suspected change features and feature scores, judging whether the update influence value of the suspected change features meets the requirement, if not, determining that the processing of the trusted application cannot be performed, and if so, entering the next step;
and determining a credit giving risk value of the user based on the updated influence value of the high-quality feature, the updated influence value of the suspected variation feature and the risk rule score of the user, and determining whether the credit giving application can be processed or not according to the credit giving risk value.
11. A computer system, comprising: a communicatively coupled memory and processor, and a computer program stored on the memory and capable of running on the processor, characterized by: the processor, when executing the computer program, performs an intelligent pedestrian sign data analysis method as claimed in any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410232695.XA CN117808578B (en) | 2024-03-01 | 2024-03-01 | Intelligent pedestrian credit information data analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410232695.XA CN117808578B (en) | 2024-03-01 | 2024-03-01 | Intelligent pedestrian credit information data analysis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117808578A true CN117808578A (en) | 2024-04-02 |
| CN117808578B CN117808578B (en) | 2024-07-26 |
Family
ID=90433863
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410232695.XA Active CN117808578B (en) | 2024-03-01 | 2024-03-01 | Intelligent pedestrian credit information data analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117808578B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118035322A (en) * | 2024-04-11 | 2024-05-14 | 浙江之科智慧科技有限公司 | Auxiliary intelligent auditing method and system based on rule base |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014193324A1 (en) * | 2013-05-27 | 2014-12-04 | Kkb-Kredi̇ Kayit Bürosu Anoni̇m Şi̇rketi̇ | Risk reporting system |
| US20180232805A1 (en) * | 2016-06-12 | 2018-08-16 | Tencent Technology (Shenzhen) Company Limited | User credit rating method and apparatus, and storage medium |
| CN108648072A (en) * | 2018-05-18 | 2018-10-12 | 深圳灰猫科技有限公司 | Internet finance lending risk evaluating system based on user credit dynamic grading |
| CN109754135A (en) * | 2017-11-03 | 2019-05-14 | 广州腾讯科技有限公司 | Behavior of credit data processing method, device, storage medium and computer equipment |
| US20190355058A1 (en) * | 2017-04-14 | 2019-11-21 | Tencent Technology (Shenzhen) Company Ltd | Method and apparatus for processing credit score real-time adjustment, and processing server |
| CN111415247A (en) * | 2020-04-25 | 2020-07-14 | 中信银行股份有限公司 | Post-credit risk evaluation method and device, storage medium and electronic equipment |
| CN114022269A (en) * | 2021-10-28 | 2022-02-08 | 江苏未至科技股份有限公司 | Enterprise credit risk assessment method in public credit field |
| CN116258573A (en) * | 2023-02-07 | 2023-06-13 | 安徽农业大学 | Agricultural product supply chain credit risk identification and evolution prediction method |
| CN117593115A (en) * | 2023-12-07 | 2024-02-23 | 中国农业银行股份有限公司 | Feature value determining method, device, equipment and medium of credit risk assessment model |
| CN117591530A (en) * | 2024-01-17 | 2024-02-23 | 杭银消费金融股份有限公司 | Data cross section processing method and system |
-
2024
- 2024-03-01 CN CN202410232695.XA patent/CN117808578B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014193324A1 (en) * | 2013-05-27 | 2014-12-04 | Kkb-Kredi̇ Kayit Bürosu Anoni̇m Şi̇rketi̇ | Risk reporting system |
| US20180232805A1 (en) * | 2016-06-12 | 2018-08-16 | Tencent Technology (Shenzhen) Company Limited | User credit rating method and apparatus, and storage medium |
| US20190355058A1 (en) * | 2017-04-14 | 2019-11-21 | Tencent Technology (Shenzhen) Company Ltd | Method and apparatus for processing credit score real-time adjustment, and processing server |
| CN109754135A (en) * | 2017-11-03 | 2019-05-14 | 广州腾讯科技有限公司 | Behavior of credit data processing method, device, storage medium and computer equipment |
| CN108648072A (en) * | 2018-05-18 | 2018-10-12 | 深圳灰猫科技有限公司 | Internet finance lending risk evaluating system based on user credit dynamic grading |
| CN111415247A (en) * | 2020-04-25 | 2020-07-14 | 中信银行股份有限公司 | Post-credit risk evaluation method and device, storage medium and electronic equipment |
| CN114022269A (en) * | 2021-10-28 | 2022-02-08 | 江苏未至科技股份有限公司 | Enterprise credit risk assessment method in public credit field |
| CN116258573A (en) * | 2023-02-07 | 2023-06-13 | 安徽农业大学 | Agricultural product supply chain credit risk identification and evolution prediction method |
| CN117593115A (en) * | 2023-12-07 | 2024-02-23 | 中国农业银行股份有限公司 | Feature value determining method, device, equipment and medium of credit risk assessment model |
| CN117591530A (en) * | 2024-01-17 | 2024-02-23 | 杭银消费金融股份有限公司 | Data cross section processing method and system |
Non-Patent Citations (1)
| Title |
|---|
| 邓建新;苏小根;贺秋瑶;: "信用问题驱动的公路物流信息平台的交易信用评价", 物流技术, no. 01, 31 January 2020 (2020-01-31), pages 46 - 54 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118035322A (en) * | 2024-04-11 | 2024-05-14 | 浙江之科智慧科技有限公司 | Auxiliary intelligent auditing method and system based on rule base |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117808578B (en) | 2024-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106127363B (en) | User credit assessment method and device | |
| US20090043715A1 (en) | Method to Continuously Diagnose and Model Changes of Real-Valued Streaming Variables | |
| CN110738564A (en) | Post-loan risk assessment method and device and storage medium | |
| CN111275546A (en) | Financial client fraud risk identification method and device | |
| CN117808578B (en) | Intelligent pedestrian credit information data analysis method and system | |
| CN112785086A (en) | Credit overdue risk prediction method and device | |
| US8171033B2 (en) | Methods and systems for the determination of thresholds via weighted quantile analysis | |
| CN112445690B (en) | Information acquisition method and device and electronic equipment | |
| CN111932268A (en) | Enterprise risk identification method and device | |
| CN112232947A (en) | Loan risk prediction method and device | |
| CN110634060A (en) | User credit risk assessment method, system, device and storage medium | |
| CN112200659A (en) | Method and device for establishing wind control model and storage medium | |
| CN113344438A (en) | Loan system, loan monitoring method, loan monitoring apparatus, and loan medium for monitoring loan behavior | |
| CN115409518A (en) | User transaction risk early warning method and device | |
| CN110110737A (en) | The recognition methods of business life cycle stage and identifying system based on electricity consumption data | |
| CN111191722B (en) | Method and device for training prediction model through computer | |
| CN118037440B (en) | Trusted data processing method and system for comprehensive credit system | |
| CN113191880A (en) | Bank teller terminal cash adding suggestion determination method and device | |
| CN116823451B (en) | Credit risk control method and system | |
| CN112085497A (en) | User account data processing method and device | |
| CN116010228B (en) | Time estimation method and device for network security scanning | |
| CN109145207B (en) | Information personalized recommendation method and device based on classification index prediction | |
| CN109800887B (en) | Generation method and device of prediction process model, storage medium and electronic equipment | |
| CN117670359A (en) | Abnormal transaction data identification method and device, storage medium and electronic equipment | |
| CN118195756A (en) | Data analysis method for resource allocation and electronic equipment |
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 |