CN111898970A - Authentication method and device for product application qualification - Google Patents
Authentication method and device for product application qualification Download PDFInfo
- Publication number
- CN111898970A CN111898970A CN202010612218.8A CN202010612218A CN111898970A CN 111898970 A CN111898970 A CN 111898970A CN 202010612218 A CN202010612218 A CN 202010612218A CN 111898970 A CN111898970 A CN 111898970A
- Authority
- CN
- China
- Prior art keywords
- epidemic situation
- variance
- feature
- historical
- application object
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012797 qualification Methods 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000009826 distribution Methods 0.000 claims abstract description 40
- 239000000126 substance Substances 0.000 claims description 9
- 238000009877 rendering Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 230000006399 behavior Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- 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
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the invention relates to the field of science and technology finance (Fintech), in particular to a method and a device for authenticating product application qualification, which are used for increasing the accuracy of product application qualification authentication and improving the authentication efficiency. The embodiment of the invention comprises the following steps: receiving an epidemic situation special loan request which comprises loan qualification information of an application object; determining the characteristic data of the application object according to the loan qualification information; based on a mean variance model, obtaining the feature item combination variance of the application object according to the feature data of the application object; if the feature item combination variance of the application object is determined to be within the confidence interval of the epidemic situation feature item combination distribution curve, sending an authentication passing message to the application object; the epidemic situation characteristic item combined distribution curve is drawn according to the characteristic data and the characteristic item combined variance of the historical epidemic situation sample based on a mean variance model.
Description
Technical Field
The invention relates to the field of science and technology finance (Fintech), in particular to a method and a device for authenticating product application qualification.
Background
With the continuous development of financial technologies, especially internet technology and finance, more and more technologies (such as distributed, Blockchain, artificial intelligence, etc.) are applied to the financial field, but the financial industry also puts higher demands on the technologies.
In order to solve the problem of the mobile capital tension of small and micro enterprises, the nation issues special epidemic loan. The existing special loan for epidemic situation is an application, and a client needs to complete application and approval of various data online and go to a bank outlet online to apply for loan. After the banking department collects the materials, the manual examination is carried out: auditing unqualified customers and returning the customer data; and (5) checking the approved client, and performing contract signing and loan issuing processes.
Disclosure of Invention
The application provides an authentication method and device for product application qualification, which are used for increasing the accuracy of product application qualification authentication and improving the authentication efficiency.
The authentication method for the product application qualification provided by the embodiment of the invention comprises the following steps:
receiving an epidemic situation special loan request which comprises loan qualification information of an application object;
determining the characteristic data of the application object according to the loan qualification information;
based on a mean variance model, obtaining the feature item combination variance of the application object according to the feature data of the application object;
if the feature item combination variance of the application object is determined to be within the confidence interval of the epidemic feature item combination distribution curve, sending epidemic special loan data to the application object;
the epidemic situation characteristic item combined distribution curve is drawn according to the characteristic data and the characteristic item combined variance of the historical epidemic situation sample based on a mean variance model.
In an alternative embodiment, the loan eligibility information includes numeric class information and text class information;
determining characteristic data of the application object according to the loan qualification information, wherein the characteristic data comprises:
determining digital data corresponding to the text type information of the application object according to the corresponding relation between the text and the number;
and determining the grade identification corresponding to the digital class information of the application object according to the corresponding relation between the number and the grade.
In an optional embodiment, before receiving the request for special loan for epidemic situation, the method further includes;
obtaining loan qualification information of a plurality of historical epidemic situation objects;
taking N historical epidemic situation objects as a historical epidemic situation sample, and determining the characteristic data of the corresponding historical epidemic situation sample according to the loan qualification information of the N historical epidemic situation objects;
calculating the feature item combination variance of the historical epidemic situation samples according to the feature data of the historical epidemic situation samples based on the mean variance model and each historical epidemic situation sample;
drawing a combined distribution curve of the epidemic situation characteristic items by using the characteristic data of all the historical epidemic situation samples and the corresponding characteristic item combined variances;
and determining the confidence interval according to the epidemic situation characteristic item combined distribution curve.
In an optional embodiment, calculating the feature item combined variance of the historical epidemic situation sample according to the feature data of the historical epidemic situation sample based on the mean variance model includes:
calculating the variance and the weight of each feature item according to the feature data of the historical epidemic situation sample;
calculating the incidence relation between every two feature items according to the variance of the feature items;
and obtaining the optimal solution of the feature item combined variance of the historical epidemic situation sample based on the mean variance model according to the calculated variance, weight and incidence relation among the feature items.
In an alternative embodiment, the variance of the combination of the feature items of the historical epidemic situation sample is calculated according to the following formula:
wherein the content of the first and second substances,2representing the combined variance of the feature items of the historical epidemic situation samples;
representing the variance of the ith feature item; w is aiRepresenting the weight of the ith characteristic item in the historical epidemic situation sample; e (a) represents the mean of all feature terms; r isiAnd rjRepresenting the values of the ith and jth feature terms.
The invention provides a product application qualification authentication device, comprising:
the receiving unit is used for receiving an epidemic situation special loan request which comprises loan qualification information of an application object;
the determining unit is used for determining the characteristic data of the application object according to the loan qualification information;
the computing unit is used for obtaining the feature item combination variance of the application object according to the feature data of the application object based on a mean variance model;
the sending unit is used for sending epidemic special loan data to the application object if the feature item combination variance of the application object is determined to be within the confidence interval of the epidemic feature item combination distribution curve;
the epidemic situation characteristic item combined distribution curve is drawn according to the characteristic data and the characteristic item combined variance of the historical epidemic situation sample based on a mean variance model.
In an alternative embodiment, the loan eligibility information includes numeric class information and text class information;
the determining unit is specifically configured to:
determining digital data corresponding to the text type information of the application object according to the corresponding relation between the text and the number;
and determining the grade identification corresponding to the digital class information of the application object according to the corresponding relation between the number and the grade.
In an optional embodiment, the apparatus further includes a rendering unit configured to:
obtaining loan qualification information of a plurality of historical epidemic situation objects;
taking N historical epidemic situation objects as a historical epidemic situation sample, and determining the characteristic data of the corresponding historical epidemic situation sample according to the loan qualification information of the N historical epidemic situation objects;
calculating the feature item combination variance of the historical epidemic situation samples according to the feature data of the historical epidemic situation samples based on the mean variance model and each historical epidemic situation sample;
drawing a combined distribution curve of the epidemic situation characteristic items by using the characteristic data of all the historical epidemic situation samples and the corresponding characteristic item combined variances;
and determining the confidence interval according to the epidemic situation characteristic item combined distribution curve.
In an optional embodiment, the rendering unit is specifically configured to:
calculating the variance and the weight of each feature item according to the feature data of the historical epidemic situation sample;
calculating the incidence relation between every two feature items according to the variance of the feature items;
and obtaining the optimal solution of the feature item combined variance of the historical epidemic situation sample based on the mean variance model according to the calculated variance, weight and incidence relation among the feature items.
In an optional embodiment, the drawing unit is specifically configured to calculate a feature term combination variance of the historical epidemic situation sample according to the following formula:
wherein the content of the first and second substances,2representing the combined variance of the feature items of the historical epidemic situation samples;
representing the variance of the ith feature item; w is aiRepresenting the weight of the ith characteristic item in the historical epidemic situation sample; e (a) represents the mean of all feature terms; r isiAnd rjRepresenting the values of the ith and jth feature terms.
An embodiment of the present invention further provides an electronic device, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method as described above.
Embodiments of the present invention also provide a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method as described above.
In the embodiment of the invention, after the bank system receives the epidemic situation special loan request, the bank system can determine the characteristic data of the application object according to the loan qualification information because the epidemic situation special loan request contains the loan qualification information of the application object. And inputting the characteristic data of the application object into the mean variance model to obtain the characteristic item combination variance of the application object. And then comparing the feature item combination variance of the application object with the confidence interval of the epidemic situation feature item combination distribution curve, if the feature item combination variance of the application object is in the execution period, the application object is considered to have the special loan qualification of the epidemic situation, and an authentication passing message is sent to the application object. The epidemic situation characteristic item combined distribution curve is drawn according to the characteristic data and the characteristic item combined variance of the historical epidemic situation sample based on a mean variance model. According to the embodiment of the invention, the characteristic similarity between enterprise customers in the historical epidemic situation period and the current epidemic situation period is utilized, and the epidemic situation characteristic item combination distribution curve is drawn according to the characteristic data and the characteristic item combination variance of the historical epidemic situation sample, so that whether the characteristics of the application object meet the qualification requirements of the special loan of the epidemic situation is judged. Inputting the feature data of the application object applying for the epidemic situation special loan into the mean variance model to obtain the feature item combination variance of the application object, and if the feature item combination variance of the application object is within a preset confidence interval, considering that the application object has the qualification of the epidemic situation special loan and pushing related loan products to the application object; and if the feature item combination variance of the application object is not within the preset confidence interval, the application object is considered to have no epidemic situation special loan qualification, and the epidemic situation special loan request of the application object is rejected. The process utilizes the mean variance model, fully embodies the advantages of automatic analysis, and greatly improves the authentication efficiency. Meanwhile, the characteristic image is drawn on the client which is seriously influenced by the epidemic situation, the automatic matching authentication is carried out on the application object, the subjective influence of manual operation is avoided, and the authentication accuracy is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a schematic diagram of a possible system architecture according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a method for authenticating a product application qualification according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a combined distribution curve of epidemic situation characteristic items according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an authentication apparatus for product qualification according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
For convenience of understanding, terms that may be referred to in the embodiments of the present invention are defined and explained below.
Small and micro enterprises: the small and micro enterprises are the general names of small enterprises, micro enterprises and family workshop-type enterprises.
Mean variance model: is the investment risk model proposed by harry markoviz in 1952, also called markoviz model. Markovitz defines risk as the fluctuation rate of profitability, and applies a mathematical statistical method to the research of investment portfolio selection for the first time. The method enables the multi-objective optimization of the benefits and the risks to achieve the optimal balance effect.
Confidence interval: refers to the estimation interval of the overall parameter constructed from the sample statistics. In statistics, the confidence interval for a probability sample is an interval estimate for some overall parameter of the sample. The confidence interval exhibits the degree to which the true value of the parameter has a certain probability of falling around the measurement result, which gives the confidence level of the measured value of the measured parameter, i.e. the "one probability" required above.
In the embodiment of the invention, the characteristics of each small and micro enterprise in the new crown epidemic situation are analyzed by taking the characteristics of the high-quality loan clients in the SARS epidemic situation period of 03 as a basis to determine whether the small and micro enterprise sending out the special epidemic situation loan request has special epidemic situation loan qualification or not. Specifically, the embodiment of the invention draws the epidemic situation characteristic item combination distribution curve based on the Markov mean variance model, and further sets the confidence interval as the basis for measuring whether the characteristic data of the application object meets the conditions.
The Markov mean square error model is a quadratic programming problem which takes asset weight as variable, adopts a Lagrange method in differentiation to solve, and obtains the optimal investment proportion when the variance of the combined income is minimum under the limiting condition. The investor selects the optimal investment portfolio scheme on the leading edge of the effective portfolio according to the income target and the risk preference of the investor.
In the embodiment of the invention, the distribution characteristics of each characteristic item of a high-quality client in the SARS period are analyzed through a mean variance model to obtain an optimal characteristic item combination scheme. And drawing the two-dimensional plane by taking the integral characteristic item mean value as an abscissa and taking the optimal combined solution as an ordinate to form a curve. At each point on the curve, the variance value is the smallest, which is called the minimum variance point. The curve exhibits a normal distribution characteristic, on which graph confidence intervals are set.
And then, analyzing the small micro-enterprise in the existing new crown period through a mean variance model, and if the optimal feature item combination scheme of the small micro-enterprise falls within a confidence interval, indicating that the small micro-enterprise accords with epidemic situation high-quality customer standards and has the qualification of applying for epidemic situation special loans.
As shown in fig. 1, a system architecture to which the embodiment of the present invention is applicable includes a banking system 101 and a small micro-enterprise system 102. The small-micro enterprise system 102 may be a client installed on a terminal, or may also be an operating system installed on a server, where the terminal may be an electronic device with a wireless communication function, such as a mobile phone, a tablet computer, or a dedicated handheld device, or may be a device connected to the internet in a wired access manner, such as a Personal Computer (PC), a notebook computer, or a server. The terminal may be an independent device, or a terminal cluster formed by a plurality of terminals. Preferably, the terminal can perform information processing by using a cloud computing technology.
The banking system 101 may be a network device such as a computer, may be an independent device, or may be a server cluster formed by a plurality of servers. Preferably, the account node 102 may employ cloud computing technology for information processing.
The bank System 101 may communicate with the small-sized micro enterprise System 102 through an INTERNET network, or may communicate with the small-sized micro enterprise System 102 through a Global System for Mobile Communications (GSM), a Long Term Evolution (LTE) System, or other Mobile communication systems.
Based on the above architecture, an embodiment of the present invention provides a method for authenticating a product application qualification, as shown in fig. 2, the method for authenticating a product application qualification provided by the embodiment of the present invention includes the following steps:
And 203, obtaining the feature item combination variance of the application object according to the feature data of the application object based on a mean variance model.
Step 204: and if the feature item combination variance of the application object is determined to be in the confidence interval of the epidemic situation feature item combination distribution curve, sending an authentication passing message to the application object.
The epidemic situation characteristic item combined distribution curve is drawn according to the characteristic data and the characteristic item combined variance of the historical epidemic situation sample based on a mean variance model.
Furthermore, a plurality of epidemic loan products are provided in the system background, such as delayed repayment, new loan and old loan, non-repayment and continuous loan, and when the bank system sends an authentication passing message to the client, the loan products can be pushed to the client at the same time.
In addition, if the confidence interval of the epidemic situation characteristic item combination distribution curve in the characteristic item combination variance step of the application object is determined, the application object is considered to be not qualified in the epidemic situation special loan, and therefore the authentication failure message is sent.
In the embodiment of the invention, after the bank system receives the epidemic situation special loan request, the bank system can determine the characteristic data of the application object according to the loan qualification information because the epidemic situation special loan request contains the loan qualification information of the application object. And inputting the characteristic data of the application object into the mean variance model to obtain the characteristic item combination variance of the application object. And then comparing the feature item combination variance of the application object with the confidence interval of the epidemic situation feature item combination distribution curve, if the feature item combination variance of the application object is in the execution period, the application object is considered to have the special loan qualification of the epidemic situation, and an authentication passing message is sent to the application object. The epidemic situation characteristic item combined distribution curve is drawn according to the characteristic data and the characteristic item combined variance of the historical epidemic situation sample based on a mean variance model. According to the embodiment of the invention, the characteristic similarity between enterprise customers in the historical epidemic situation period and the current epidemic situation period is utilized, and the epidemic situation characteristic item combination distribution curve is drawn according to the characteristic data and the characteristic item combination variance of the historical epidemic situation sample, so that whether the characteristics of the application object meet the qualification requirements of the special loan of the epidemic situation is judged. Inputting the feature data of the application object applying for the epidemic situation special loan into the mean variance model to obtain the feature item combination variance of the application object, and if the feature item combination variance of the application object is within a preset confidence interval, considering that the application object has the qualification of the epidemic situation special loan and pushing related loan products to the application object; and if the feature item combination variance of the application object is not within the preset confidence interval, the application object is considered to have no epidemic situation special loan qualification, and the epidemic situation special loan request of the application object is rejected. The process utilizes the mean variance model, fully embodies the advantages of automatic analysis, and greatly improves the authentication efficiency. Meanwhile, the characteristic image is drawn on the client which is seriously influenced by the epidemic situation, the automatic matching authentication is carried out on the application object, the subjective influence of manual operation is avoided, and the authentication accuracy is improved.
In a specific embodiment, the loan qualification information in the embodiment of the present invention includes transaction behavior information, tax data information, and epidemic situation characteristic information of the application object.
Specifically, the transaction behavior data may be a large amount of financial transaction behavior data accumulated while providing financial services for the silver behavior application object. By analyzing these data, important image information such as five-level classification, overdue days, credit information, etc. can be obtained.
The tax data information is tax data generated on the tax payment information of the application object, and is important information for promoting the construction of a financial credit system to be further complete. Under the influence of epidemic situations, tax data information of an application object, such as an asset liability statement, a profit statement and the like, can obviously change. Through comparing and analyzing the change items, the situation that the application object is affected by the epidemic situation can be accurately grasped.
After the epidemic situation occurs, the affected degree of each region and each industry is different, and the epidemic situation characteristic information shows the degree of the affected degree of the epidemic situation. For example, the four industries of lodging, dining, cultural and sports entertainment, transportation and tourism are the most serious industries impacted by epidemic situations. The characteristic items related to the four industries in the national standard industry classification are recorded into an epidemic situation characteristic library and are used for supporting the epidemic situation influencing industries.
The loan qualification information can be sent to a bank system together when a client sends a special loan request for epidemic situations; or the bank system can inquire and acquire the loan from the database after receiving the special loan request of epidemic situation sent by the client. Specifically, the transaction behavior data may be stored in a feature database of the bank system itself, the tax data information is stored in a tax data feature database, and the epidemic situation feature information is stored in an epidemic situation feature database.
Further, the processing of the embodiments of the present invention may be different for different types of loan eligibility information. The loan qualification information comprises digital information and text information;
determining characteristic data of the application object according to the loan qualification information, wherein the characteristic data comprises:
determining digital data corresponding to the text type information of the application object according to the corresponding relation between the text and the number;
and determining the grade identification corresponding to the digital class information of the application object according to the corresponding relation between the number and the grade.
In the specific implementation process, the text information, such as the enterprise registration address in the tax data information and the epidemic situation influence industry level in the epidemic situation characteristic information, are all the text information, and in order to facilitate calculation, the text information needs to be assigned. The corresponding relation between the loan qualification information of each text class and the number is preset, for example, for an enterprise registration address, the assignment can be performed according to different provincial and autonomous region direct administration cities, and since 34 provincial and autonomous region direct administration cities are included, the assignment of 0 to 33 can be performed on different provincial and autonomous region direct administration cities, such as 0 for Beijing, 1 for Tianjin, 2 for Hebei, and the like.
On the other hand, for convenience of calculation, in the embodiment of the present invention, except for the logically indistinguishable categories (for example, five-level classification, which logically includes only five categories; and only 34 categories, which logically belong to municipalities and municipalities in provincial and autonomous regions), the rest of the digital category information is divided into 10 levels. For example, the credit line can be divided into 0 to 100 ten thousand yuan, 100 ten thousand to 200 ten thousand yuan, 200 ten thousand to 300 ten thousand yuan … … 900 ten thousand yuan to 1000 ten thousand yuan and more than 1000 ten thousand yuan, which are respectively assigned with 0, 1, 2 … … 8, 9, so that the subsequent calculation by using a mean variance model is convenient.
The specific characteristic comparison is shown in table 1:
TABLE 1
The following describes the calculation process using the mean-variance model.
Further, before receiving the special epidemic loan request, the method also comprises the following steps;
obtaining loan qualification information of a plurality of historical epidemic situation objects;
taking N historical epidemic situation objects as a historical epidemic situation sample, and determining the characteristic data of the corresponding historical epidemic situation sample according to the loan qualification information of the N historical epidemic situation objects;
calculating the feature item combination variance of the historical epidemic situation samples according to the feature data of the historical epidemic situation samples based on the mean variance model and each historical epidemic situation sample;
drawing a combined distribution curve of the epidemic situation characteristic items by using the characteristic data of all the historical epidemic situation samples and the corresponding characteristic item combined variances;
and determining the confidence interval according to the epidemic situation characteristic item combined distribution curve.
In a specific implementation process, in order to make the sample more representative, the N historical epidemic situation objects are used as one historical epidemic situation sample. For example, 30 million SARS epidemic good clients are randomly drawn and grouped into samples, and every 100 loan enterprises are randomly divided into one sample, and 3000 samples are formed.
For each historical epidemic sample, the characteristic data is the mean value of loan qualification information of each historical epidemic object contained in the sample. The mean of the feature data is specifically calculated according to the following formula:
wherein, XiIs the value corresponding to the ith characteristic item in the historical epidemic situation sample,
the number N is the average value of the characteristics in the historical epidemic situation sample, and the number N is the number of the historical epidemic situation objects contained in the historical epidemic situation sample.
And then, calculating the feature item combination variance of each historical epidemic situation sample based on the mean variance model.
Specifically, based on the mean variance model, according to the feature data of the historical epidemic situation sample, calculating the feature item combined variance of the historical epidemic situation sample, including:
calculating the variance and the weight of each feature item according to the feature data of the historical epidemic situation sample;
calculating the incidence relation between every two feature items according to the variance of the feature items;
and obtaining the optimal solution of the feature item combined variance of the historical epidemic situation sample based on the mean variance model according to the calculated variance, weight and incidence relation among the feature items.
Specifically, the variance of each feature term is calculated according to the value of the feature term and the mean of the feature term, and specifically calculated according to the following formula:
wherein σ2The variance of the feature item is obtained; xiThe characteristic value of the ith historical epidemic situation sample for the characteristic item is obtained;
the average value of the characteristics in the historical epidemic situation sample is calculated by a formula 1; and N is the number of the historical epidemic objects contained in one historical epidemic sample.
The weight of the feature item is also calculated according to the feature data of the feature item. Assume that there are two characteristic items in the historical epidemic sample: five-level classification and tax payment level.
And assigning in the five-level classification, which respectively comprises the following steps: normal-0, concern-1, Secondary-2, suspicious-3, loss-4.
If 100 enterprises in the historical epidemic sample 1 exist, the mean value of the five-level classification is 0.3. And 0.3 is rounded off and taken as 0, namely the characteristic value of the five-level classification corresponding to the historical epidemic situation sample 1 is 0. And counting the number of enterprises of which the five-level classification is normal in 100 enterprises to obtain a value M.
Taking the tax payment grade as an example, there are four categories, which are respectively: a-0, B-1, C-2, D-3.
After the same calculation, the value L is obtained.
Then in the historical epidemic situation sample 1, the weight of the five-level classification feature item is: M/(M + L), the tax rate grade characteristic item weight is: L/(M + L).
When there are multiple feature items in a sample set, and so on.
For the association relationship between two feature terms, it can be calculated by the following formula:
wherein σx、σyCan be calculated by formula 2; cov (x, y) is a covariance formula between feature term x and feature term y; rhox,yIs the incidence relation between the characteristic item x and the characteristic item y.
And then substituting the variance and the weight of the characteristic items and the incidence relation among the characteristic items into a Markov mean variance formula, and calculating to obtain the optimal solution of the characteristic item combination variance of the historical epidemic situation sample.
Specifically, the markov mean variance model satisfies the following formula:
wherein wxRepresenting the weight of the characteristic item X in the historical epidemic situation sample; w is ayRepresenting the weight of the characteristic item Y in the historical epidemic situation sample;
represents the variance of the feature item X;
represents the variance of the feature item Y; rhox,yRepresenting the incidence relation between the characteristic item X and the characteristic item Y;2represents the combined variance optimal solution of both the feature item X and the feature item Y.
When there are a plurality of characteristic items corresponding to the historical epidemic situation sample, the above formula can be converted into:
wherein the content of the first and second substances,
wi≥0，i＝1,2,......n。2feature item combination calculated by representing historical epidemic situation sampleVariance;
representing the variance of the ith feature item; w is aiRepresenting the weight of the ith characteristic item in the historical epidemic situation sample; rhoi,jAnd representing the association relationship between the ith characteristic item and the jth characteristic item.
Equation 5 above can be further equivalently converted to the following equation:
wherein the content of the first and second substances,2representing the calculated feature item combination variance of the sample set;
representing the variance of the ith feature item; w is aiRepresenting the weight of the ith characteristic item in the historical epidemic situation sample; e (a) represents the mean of all feature terms; r isiAnd rjRepresenting the values of the ith and jth feature terms.
Each historical epidemic situation sample can obtain an optimal solution of the feature item combination variance according to the formula 6, the optimal solution of the feature item combination variance is used as a vertical coordinate, and E (a) is that the average value of all feature items in the historical epidemic situation sample is used as a horizontal coordinate, so that one historical epidemic situation sample corresponds to one point on the coordinate graph. Furthermore, all historical epidemic situation samples can be mapped to a plurality of points on the coordinate graph, and the lattices are integrally distributed on the coordinate graph, namely the lattices are the combined distribution curve of the epidemic situation characteristic items, as shown in fig. 3.
In the embodiment of the invention, after the epidemic situation characteristic item combination distribution curve is drawn according to the process, a proper confidence interval is obtained according to the distribution proportion of the array.
Thus, after receiving the epidemic situation special loan request of the application object, the feature data of the application object is also input into the formula 6, and the feature item combination variance of the application object is calculated. And comparing the obtained feature item combination variance of the application object with the confidence interval, thereby authenticating the epidemic situation special loan qualification of the application object.
The embodiment of the present invention further provides an authentication apparatus for product application qualification, as shown in fig. 4, including:
the receiving unit 401 is configured to receive an epidemic situation special loan request, where the epidemic situation special loan request includes loan qualification information of an application object;
a determining unit 402, configured to determine feature data of the application object according to the loan qualification information;
a calculating unit 403, configured to obtain a feature item combination variance of the application object according to the feature data of the application object based on a mean variance model;
a sending unit 404, configured to send epidemic special loan data to the application object if it is determined that the feature item combination variance of the application object is within the confidence interval of the epidemic feature item combination distribution curve;
the epidemic situation characteristic item combined distribution curve is drawn according to the characteristic data and the characteristic item combined variance of the historical epidemic situation sample based on a mean variance model.
In an alternative embodiment, the loan eligibility information includes numeric class information and text class information;
the determining unit 402 is specifically configured to:
determining digital data corresponding to the text type information of the application object according to the corresponding relation between the text and the number;
and determining the grade identification corresponding to the digital class information of the application object according to the corresponding relation between the number and the grade.
In an alternative embodiment, the drawing unit 405 is further included to:
obtaining loan qualification information of a plurality of historical epidemic situation objects;
taking N historical epidemic situation objects as a historical epidemic situation sample, and determining the characteristic data of the corresponding historical epidemic situation sample according to the loan qualification information of the N historical epidemic situation objects;
calculating the feature item combination variance of the historical epidemic situation samples according to the feature data of the historical epidemic situation samples based on the mean variance model and each historical epidemic situation sample;
drawing a combined distribution curve of the epidemic situation characteristic items by using the characteristic data of all the historical epidemic situation samples and the corresponding characteristic item combined variances;
and determining the confidence interval according to the epidemic situation characteristic item combined distribution curve.
In an optional embodiment, the drawing unit 405 is specifically configured to:
calculating the variance and the weight of each feature item according to the feature data of the historical epidemic situation sample;
calculating the incidence relation between every two feature items according to the variance of the feature items;
and obtaining the optimal solution of the feature item combined variance of the historical epidemic situation sample based on the mean variance model according to the calculated variance, weight and incidence relation among the feature items.
In an optional embodiment, the drawing unit is specifically configured to calculate a feature term combination variance of the historical epidemic situation sample according to the following formula:
wherein the content of the first and second substances,2representing the combined variance of the feature items of the historical epidemic situation samples;
representing the variance of the ith feature item; w is aiRepresenting the weight of the ith characteristic item in the historical epidemic situation sample; e (a) represents the mean of all feature terms; r isiAnd rjRepresenting the values of the ith and jth feature terms.
Based on the same principle, the present invention also provides an electronic device, as shown in fig. 5, including:
the system comprises a processor 501, a memory 502, a transceiver 503 and a bus interface 504, wherein the processor 501, the memory 502 and the transceiver 503 are connected through the bus interface 504;
the processor 501 is configured to read the program in the memory 502, and execute the following method:
after receiving a processing request aiming at a second data field, acquiring the second data field from a storage system; the second data field is data which is determined according to the first information data in the block chain and is stored in the storage system;
checking the second data field by utilizing a pre-stored first tree; the first tree is established according to a hash value of a first data field, and the first data field is data determined according to the first information data;
determining that the second data field has not been tampered when the hash value of the second data field is consistent with the node value of the corresponding node in the first tree.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (12)
1. A method for authenticating product application qualification, comprising:
receiving an epidemic situation special loan request which comprises loan qualification information of an application object;
determining the characteristic data of the application object according to the loan qualification information;
based on a mean variance model, obtaining the feature item combination variance of the application object according to the feature data of the application object;
if the feature item combination variance of the application object is determined to be within the confidence interval of the epidemic situation feature item combination distribution curve, sending an authentication passing message to the application object;
the epidemic situation characteristic item combined distribution curve is drawn according to the characteristic data and the characteristic item combined variance of the historical epidemic situation sample based on a mean variance model.
2. The method of claim 1, wherein the loan eligibility information comprises numeric class information and text class information;
determining characteristic data of the application object according to the loan qualification information, wherein the characteristic data comprises:
determining digital data corresponding to the text type information of the application object according to the corresponding relation between the text and the number;
and determining the grade identification corresponding to the digital class information of the application object according to the corresponding relation between the number and the grade.
3. The method of claim 1, wherein prior to receiving the request for the epidemic situation-specific loan, further comprising;
obtaining loan qualification information of a plurality of historical epidemic situation objects;
taking N historical epidemic situation objects as a historical epidemic situation sample, and determining the characteristic data of the corresponding historical epidemic situation sample according to the loan qualification information of the N historical epidemic situation objects;
calculating the feature item combination variance of the historical epidemic situation samples according to the feature data of the historical epidemic situation samples based on the mean variance model and each historical epidemic situation sample;
drawing a combined distribution curve of the epidemic situation characteristic items by using the characteristic data of all the historical epidemic situation samples and the corresponding characteristic item combined variances;
and determining the confidence interval according to the epidemic situation characteristic item combined distribution curve.
4. The method of claim 3, wherein calculating the feature item combination variance of the historical epidemic sample based on the mean variance model and the feature data of the historical epidemic sample comprises:
calculating the variance and the weight of each feature item according to the feature data of the historical epidemic situation sample;
calculating the incidence relation between every two feature items according to the variance of the feature items;
and obtaining the optimal solution of the feature item combined variance of the historical epidemic situation sample based on the mean variance model according to the calculated variance, weight and incidence relation among the feature items.
5. The method according to any one of claims 1 to 4, wherein the feature item combined variance of the historical epidemic samples is calculated according to the following formula:
wherein the content of the first and second substances,2representing the combined variance of the feature items of the historical epidemic situation samples;
representing the variance of the ith feature item; w is aiRepresenting the weight of the ith characteristic item in the historical epidemic situation sample; e (a) represents the mean of all feature terms; r isiAnd rjRepresenting the values of the ith and jth feature terms.
6. An apparatus for authenticating a product application qualification, comprising:
the receiving unit is used for receiving an epidemic situation special loan request which comprises loan qualification information of an application object;
the determining unit is used for determining the characteristic data of the application object according to the loan qualification information;
the computing unit is used for obtaining the feature item combination variance of the application object according to the feature data of the application object based on a mean variance model;
the sending unit is used for sending epidemic special loan data to the application object if the feature item combination variance of the application object is determined to be within the confidence interval of the epidemic feature item combination distribution curve;
the epidemic situation characteristic item combined distribution curve is drawn according to the characteristic data and the characteristic item combined variance of the historical epidemic situation sample based on a mean variance model.
7. The apparatus of claim 6, wherein the loan eligibility information comprises numeric class information and text class information;
the determining unit is specifically configured to:
determining digital data corresponding to the text type information of the application object according to the corresponding relation between the text and the number;
and determining the grade identification corresponding to the digital class information of the application object according to the corresponding relation between the number and the grade.
8. The apparatus of claim 6, further comprising a rendering unit to:
obtaining loan qualification information of a plurality of historical epidemic situation objects;
taking N historical epidemic situation objects as a historical epidemic situation sample, and determining the characteristic data of the corresponding historical epidemic situation sample according to the loan qualification information of the N historical epidemic situation objects;
calculating the feature item combination variance of the historical epidemic situation samples according to the feature data of the historical epidemic situation samples based on the mean variance model and each historical epidemic situation sample;
drawing a combined distribution curve of the epidemic situation characteristic items by using the characteristic data of all the historical epidemic situation samples and the corresponding characteristic item combined variances;
and determining the confidence interval according to the epidemic situation characteristic item combined distribution curve.
9. The apparatus of claim 8, wherein the rendering unit is specifically configured to:
calculating the variance and the weight of each feature item according to the feature data of the historical epidemic situation sample;
calculating the incidence relation between every two feature items according to the variance of the feature items;
and obtaining the optimal solution of the feature item combined variance of the historical epidemic situation sample based on the mean variance model according to the calculated variance, weight and incidence relation among the feature items.
10. The apparatus according to any one of claims 6 to 9, wherein the mapping unit is specifically configured to calculate the feature term combination variance of the historical epidemic situation sample according to the following formula:
wherein the content of the first and second substances,2representing the combined variance of the feature items of the historical epidemic situation samples;
representing the variance of the ith feature item; w is aiRepresenting the weight of the ith characteristic item in the historical epidemic situation sample; e (a) represents the mean of all feature terms; r isiAnd rjRepresenting the values of the ith and jth feature terms.
11. An electronic device, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.
12. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010612218.8A CN111898970A (en) | 2020-06-30 | 2020-06-30 | Authentication method and device for product application qualification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010612218.8A CN111898970A (en) | 2020-06-30 | 2020-06-30 | Authentication method and device for product application qualification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111898970A true CN111898970A (en) | 2020-11-06 |
Family
ID=73208001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010612218.8A Pending CN111898970A (en) | 2020-06-30 | 2020-06-30 | Authentication method and device for product application qualification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111898970A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140317019A1 (en) * | 2013-03-14 | 2014-10-23 | Jochen Papenbrock | System and method for risk management and portfolio optimization |
| CN108846754A (en) * | 2018-06-14 | 2018-11-20 | 国网河南省电力公司经济技术研究院 | A kind of methods of risk assessment based on multi items electricity transaction |
| CN109034542A (en) * | 2018-06-29 | 2018-12-18 | 平安科技（深圳）有限公司 | Investment combination generation method, device and computer readable storage medium |
| CN109993652A (en) * | 2019-02-20 | 2019-07-09 | 复旦大学 | A kind of debt-credit assessing credit risks method and device |
| CN110097454A (en) * | 2019-04-03 | 2019-08-06 | 平安科技（深圳）有限公司 | Handle the method and Related product of data on line |
| CN110135850A (en) * | 2019-04-12 | 2019-08-16 | 深圳壹账通智能科技有限公司 | A kind of information processing method and relevant apparatus |
| CN110223137A (en) * | 2019-05-22 | 2019-09-10 | 平安科技（深圳）有限公司 | Product mix recommended method, device, computer equipment and storage medium |
| CN110288459A (en) * | 2019-04-24 | 2019-09-27 | 武汉众邦银行股份有限公司 | Loan prediction technique, device, equipment and storage medium |
-
2020
- 2020-06-30 CN CN202010612218.8A patent/CN111898970A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140317019A1 (en) * | 2013-03-14 | 2014-10-23 | Jochen Papenbrock | System and method for risk management and portfolio optimization |
| CN108846754A (en) * | 2018-06-14 | 2018-11-20 | 国网河南省电力公司经济技术研究院 | A kind of methods of risk assessment based on multi items electricity transaction |
| CN109034542A (en) * | 2018-06-29 | 2018-12-18 | 平安科技（深圳）有限公司 | Investment combination generation method, device and computer readable storage medium |
| CN109993652A (en) * | 2019-02-20 | 2019-07-09 | 复旦大学 | A kind of debt-credit assessing credit risks method and device |
| CN110097454A (en) * | 2019-04-03 | 2019-08-06 | 平安科技（深圳）有限公司 | Handle the method and Related product of data on line |
| CN110135850A (en) * | 2019-04-12 | 2019-08-16 | 深圳壹账通智能科技有限公司 | A kind of information processing method and relevant apparatus |
| CN110288459A (en) * | 2019-04-24 | 2019-09-27 | 武汉众邦银行股份有限公司 | Loan prediction technique, device, equipment and storage medium |
| CN110223137A (en) * | 2019-05-22 | 2019-09-10 | 平安科技（深圳）有限公司 | Product mix recommended method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108564286B (en) | Artificial intelligent financial wind-control credit assessment method and system based on big data credit investigation | |
| CN106295351B (en) | A kind of Risk Identification Method and device | |
| US8768866B2 (en) | Computer-implemented systems and methods for forecasting and estimation using grid regression | |
| CN110659961A (en) | Method and device for identifying off-line commercial tenant | |
| CN109740036B (en) | Hotel ordering method and device for OTA platform | |
| CN111160737A (en) | Adaptation method of resource allocation scheme and related equipment | |
| CN109685643A (en) | Loan audit risk grade determines method, apparatus, equipment and storage medium | |
| JP2016099915A (en) | Server for credit examination, system for credit examination, and program for credit examination | |
| CN110019774B (en) | Label distribution method, device, storage medium and electronic device | |
| CN114066606A (en) | System and method for falsely identifying data based on text escape as GPS distance | |
| US20180089774A1 (en) | Method for automatic property valuation | |
| CN112950359A (en) | User identification method and device | |
| CN116596659A (en) | Enterprise intelligent credit approval method, system and medium based on big data wind control | |
| CN111898970A (en) | Authentication method and device for product application qualification | |
| CN117252677A (en) | Credit line determination method and device, electronic equipment and storage medium | |
| WO2021129368A1 (en) | Method and apparatus for determining client type | |
| CN114240599A (en) | Loan calculation method and device, computer equipment and storage medium | |
| CN114581130A (en) | Bank website number assigning method and device based on customer portrait and storage medium | |
| Niknya et al. | Financial distress prediction of Tehran Stock Exchange companies using support vector machine | |
| CN113919934A (en) | Bank loan service scoring strategy iteration method | |
| CN113256401A (en) | Method, device, server and storage medium for intercepting user outside pre-loan domain | |
| US20170186095A1 (en) | Centralized GAAP approach for multidimensional accounting to reduce data volume and data reconciliation processing costs | |
| CN113298641A (en) | Integrity degree cognition method and device | |
| CN112184417A (en) | Business approval method, device, medium and electronic equipment | |
| CN111461863A (en) | Data processing method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201106 |