CN113610645A - Method, device and equipment for evaluating risk of project data and storage medium - Google Patents
Method, device and equipment for evaluating risk of project data and storage medium Download PDFInfo
- Publication number
- CN113610645A CN113610645A CN202110927489.7A CN202110927489A CN113610645A CN 113610645 A CN113610645 A CN 113610645A CN 202110927489 A CN202110927489 A CN 202110927489A CN 113610645 A CN113610645 A CN 113610645A
- Authority
- CN
- China
- Prior art keywords
- project data
- label
- scoring
- project
- main
- 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
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- 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
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a data processing technology, and discloses a risk assessment method for project data, which comprises the following steps: acquiring original project data and project characteristics, and selecting a pre-constructed scoring card system according to the project characteristics; calling a main label set pre-constructed in the label card system according to the original project data, and constructing a main label calculation model according to the main label set; calculating to obtain the main label evaluation of the original project data by using the main label calculation model; obtaining a feature vector by using historical project data, and constructing a scoring model according to the feature vector and the scoring card system; and evaluating the nonlinear dimensionality reduction of the main label by using the scoring model to obtain a scoring result. In addition, the invention also relates to a block chain technology, and the scoring result can be stored in a node of the block chain. The invention also provides a risk assessment device of the project data, electronic equipment and a storage medium. The invention can solve the problems of inaccurate risk scoring and low efficiency.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method and an apparatus for risk assessment of project data, an electronic device, and a computer-readable storage medium.
Background
With the development of science and technology, data explosively grows, the analysis and evaluation of the data become more and more important, and the data needs to be specifically analyzed when projects in various fields fall to the ground. For example, for a non-standard investment financing financial project of a trust company, a worker is required to actually investigate the project situation.
In the prior art, the risk assessment method of project data has the following problems: the scoring system for the project is not complete, which results in too complex scoring process and low scoring efficiency. And the scoring system has no pertinence, so that the finally obtained score is not accurate enough.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for risk assessment of project data, and mainly aims to improve the risk assessment efficiency and scoring accuracy of the project data.
In order to achieve the above object, the present invention provides a method for risk assessment of project data, comprising:
acquiring pre-constructed original project data and project characteristics, and selecting a pre-constructed scoring card system according to the project characteristics;
calling a main label set pre-constructed in the label card system according to the original project data, and constructing a main label calculation model according to the main label set;
calculating the original project data by using the main label calculation model to obtain a main label evaluation of the original project data;
receiving historical project data, converting the historical project data to obtain a feature vector, and constructing a scoring model according to the feature vector and the scoring card system;
and performing nonlinear dimensionality reduction on the main label evaluation by using the scoring model to obtain a project score, and obtaining a scoring result according to the project score.
Optionally, the obtaining of the pre-constructed original project data and project characteristics, and selecting the pre-constructed scoring card system according to the project characteristics, includes:
matching the project characteristics with a pre-constructed scoring card system set;
matching the tag card system containing the item characteristics from the scoring card system set.
Optionally, the invoking a pre-constructed main tag set in the tag card system according to the original item data, and constructing a main tag calculation model according to the main tag set includes:
calling a main label set pre-constructed in the label card system according to the original project data, decomposing each main label in the main label set to obtain m secondary labels corresponding to the main label, and integrating all the secondary labels to obtain a secondary label set of each main label. Wherein m is a positive integer;
decomposing each secondary label in the secondary label set according to a preset analysis mode to obtain n decision factors corresponding to each secondary label, and integrating all the decision factors to obtain a decision factor set, wherein n is a positive integer;
and integrating the primary label set, the secondary label set and the decision factor set to obtain the primary label calculation model.
Optionally, the calculating the original item data by using the primary tag calculation model to obtain the primary tag evaluation of the original item data includes:
calling a pre-constructed integer system rule according to the original project data;
calculating to obtain the score of each decision factor by using the main label calculation model according to the integer rule and the original project data, and accumulating the n decision factor scores corresponding to each secondary label to obtain a secondary label score;
and accumulating the m secondary label scores corresponding to each main label to obtain the main label evaluation.
Optionally, the converting the historical project data to obtain a feature vector, and constructing a scoring model according to the feature vector and the scoring card system includes:
constructing a linear matrix by using the historical project data;
calculating the eigenvalue of the linear matrix and converting the eigenvalue into an eigenvector;
performing calculation on the feature vectors by using a pre-constructed kernel function to obtain grading model construction data;
and constructing the grading model according to the grading model construction data.
Optionally, the performing, by using the scoring model, nonlinear dimensionality reduction on the main label evaluation to obtain a risk assessment of the project data, and obtaining a scoring result according to the risk assessment of the project data includes:
reducing the dimension of the main label evaluation through the grading model to obtain a final grade;
and associating the final score with a pre-constructed reliability evaluation standard, and integrating the projects with the final scores reaching the reliability evaluation standard to obtain the scoring result.
Optionally, the performing, by the scoring model, the dimensionality reduction on the main label evaluation to obtain a final score includes:
mapping the main label evaluation to different dimensions by using the scoring model to obtain different dimension sets;
and taking the set of the main label evaluation which is the largest in different dimensions as the final score.
In order to solve the above problem, the present invention further provides a database script issuing apparatus, including:
the main tag calculation model construction module is used for acquiring pre-constructed original project data and project characteristics, selecting a pre-constructed scoring card system according to the project characteristics, calling a pre-constructed main tag set in the scoring card system according to the original project data, and constructing a main tag calculation model according to the main tag set;
the main label evaluation calculation module is used for calculating the original project data by using the main label calculation model to obtain a main label evaluation of the original project data;
the scoring model building module is used for receiving historical project data, converting the historical project data to obtain a feature vector, and building a scoring model according to the feature vector and the scoring card system;
and the scoring result calculation module is used for performing nonlinear dimensionality reduction on the main label evaluation by using the scoring model to obtain the risk assessment of the project data, and obtaining a scoring result according to the risk assessment of the project data.
In order to solve the above problem, the present invention also 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 for risk assessment of project data described above.
In order to solve the above problem, the present invention further provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the risk assessment method for project data described above.
According to the invention, the scoring card system is selected according to the project characteristics, the main tag calculation model is constructed according to the scoring card system, the scoring model is further constructed according to the historical project data and the scoring card system, the historical data and the existing project are connected and mapped by using the scoring model, the accuracy of the scoring result is improved, the project data can be automatically scored, and the manual scoring by a tester is not needed. Therefore, the risk assessment method and device for project data, the electronic equipment and the computer readable storage medium provided by the invention can solve the problem of low project reliability scoring efficiency.
Drawings
Fig. 1 is a schematic flow chart of a risk assessment method for project data according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart showing a detailed implementation of one of the steps in FIG. 1;
FIG. 3 is a functional block diagram of a risk assessment apparatus for project data according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device for implementing the risk assessment method for project data according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the application provides a risk assessment method for project data. The execution subject of the risk assessment method for project data includes, but is not limited to, at least one of electronic devices that can be configured to execute the method provided by the embodiments of the present application, such as a server and a terminal. In other words, the risk assessment method for project data may be performed by software or hardware installed in a terminal device or a server device, and the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Fig. 1 is a schematic flow chart of a risk assessment method for project data according to an embodiment of the present invention. In this embodiment, the method for risk assessment of project data includes:
s1, acquiring pre-constructed original project data and project characteristics, and selecting a pre-constructed scoring card system according to the project characteristics;
in one application scenario of the present invention, the original project data may be financial and newspaper data of a non-bidding financing project, and the project characteristics may include, but are not limited to, project basic information, business classification information, investing and financing scheme information, repayment source information, transaction structure information, and warranty measure information.
Further, the scoring card system is a system for scoring the main label of the project, and comprises a pre-constructed main label set, a secondary label set and a decision factor set. In one implementation of the present invention, the main label may be divided into 5 regions, and each region has a score value ([0,1], [1,2], [2,3], [3,4], [4,5 ]). In the scoring card system, each primary label corresponds to m secondary labels, and each secondary label corresponds to n decision factors.
Specifically, the project characteristics are matched with a pre-constructed scoring card system set in the embodiment of the invention; matching the tag card system containing the item characteristics from the scoring card system set.
S2, calling a main label set which is pre-constructed in the label card system according to the original project data, and constructing a main label calculation model according to the main label set;
in the embodiment of the present invention, the main tag is extracted from the project, for example, in the application scenario of the trust company, the non-standard investment financing project may be divided into eight main tags: debt paying subject, mortgage guarantee, bottom layer project, industry evaluation, transaction structure, post-investment management, investment pricing and credit increase party guarantee. The set of primary labels is a set of the primary labels.
Specifically, referring to fig. 2, the S2 includes:
s20, calling a main label set pre-constructed in the label card system according to the original project data, decomposing each main label in the main label set to obtain m secondary labels corresponding to the main label, and integrating all the secondary labels to obtain a secondary label set of each main label. Wherein m is a positive integer;
for example, in the risk assessment process of the non-bid financing project data, the financial report data of the non-bid financing project is searched in the pre-constructed main label set, and the main label set containing the financial report data is selected as the main label set of the project. The secondary label set is a set of secondary labels, and the secondary labels are obtained by decomposing the primary label, for example, the secondary labels "manufacturing enterprise", "bank", and "international public welfare organization" can be obtained by decomposing the primary label "repayment subject".
S21, decomposing each secondary label in the secondary label set according to a preset analysis mode to obtain n decision factors corresponding to each secondary label, and integrating all the decision factors to obtain a decision factor set, wherein n is a positive integer.
In the embodiment of the present invention, the preset analysis manner may be a quantitative analysis method after a predetermined analysis.
The qualitative mode is to decompose according to the type of the secondary label, and the quantitative mode is to analyze according to the numerical value of the secondary label.
For example, for the sub-label "bank", the sub-label "bank" is firstly decomposed into different types of factors such as "securities" and "funds" in a qualitative manner, then the "securities" is decomposed into "small securities" and "huge securities" in a quantitative manner, the "funds" is decomposed into "small enterprise funds" and "group funds" in a quantitative manner, and the "small securities", "large securities", "small enterprise funds" and "group funds" are summarized to obtain the decision factor corresponding to the sub-label "bank".
And S22, integrating the primary label set, the secondary label set and the decision factor set to obtain the primary label calculation model.
According to the embodiment of the invention, a pre-constructed parameter b is obtained according to the number and the variety of the decision factor setsjAnd xjObtaining a pre-constructed parameter a according to the type of the secondary label setiAccording to bj、xjAnd aiAnd constructing to obtain the main label calculation model.
Wherein the master tag computation model is y ═ Σ (a)iΣbjxj),x∈[1,5],a,b∈(0,1],Σbj＝1,Σai1 is ═ 1; wherein y is the rating of each primary label, and bjIs the decision factor score, said xjIs the decision factor, said aiIs the secondary label weight.
According to the embodiment of the invention, the main label is refined by constructing the main label calculation model, so that the risk assessment of the project data is more specific, and the scoring result is more accurate.
S3, calculating the original project data by using the main label calculation model to obtain a main label evaluation of the original project data;
specifically, the calculating the original item data by using the main label calculation model to obtain the main label evaluation of the original item data includes:
calling a pre-constructed integer system rule according to the original project data;
calculating to obtain the score of each decision factor by using the main label calculation model according to the integer rule and the original project data, and accumulating the n decision factor scores corresponding to each secondary label to obtain a secondary label score;
and accumulating the m secondary label scores corresponding to each main label to obtain the main label evaluation.
In the embodiment of the present invention, the integral rule means that the decision factor maps the rating card system according to 1-point, 2-point, 3-point, 4-point and 5-point integral systems in a qualitative mode and a quantitative mode, and the decision factor is obtained by decomposing the secondary label, for example, decomposing the secondary label "production enterprise", and obtaining the decision factors "steel production enterprise" and "coal production enterprise", etc.
S4, converting the historical project data to obtain a feature vector, and constructing a grading model according to the feature vector and the grading card system;
in the embodiment of the present invention, the historical item data refers to item data that has been scored. The scoring model refers to a calculation model with a dimension reduction function.
Specifically, the converting the historical project data to obtain a feature vector, and constructing a scoring model according to the feature vector and the scoring card system includes:
constructing a linear matrix by using the historical project data;
calculating the eigenvalue of the linear matrix and converting the eigenvalue into an eigenvector;
performing calculation on the feature vectors by using a pre-constructed kernel function to obtain grading model construction data;
and constructing the grading model according to the grading model construction data and the grading card system.
For example, in an application scenario of a trust company, project data of which decision making and payment paying are normally completed historically can be used as the pre-constructed training sample, a feature vector parameter | Y | is constructed through the project data of which decision making and payment paying are normally completed historically and the main label, the feature vector parameter | Y | is input into a radial-entering gaussian kernel function, and pre-constructed parameters α and β are solved, so that the scoring model can be obtained;
in the embodiment of the present invention, the pre-constructed kernel function may be a gaussian kernel function, and the function of the pre-constructed kernel function is to simplify the calculation steps. The scoring model may be:
f(Y)＝sign((∑_(i＝1)^nα_i exp(-|||Y|-|Y^'|||/σ2+β_i)；
wherein α, β, σ, and n are the scoring model construction data obtained by the feature vectors, Y, i and n are provided by the scoring card system, and Y is the main label evaluation. Wherein i is a continuous variable ranging from 1 to n. The value of n is obtained from the number of the decision factors and represents the number of the decision factors.
According to the embodiment of the invention, the scoring model is obtained by construction, and historical data and the existing project are connected and mapped, so that the scoring accuracy is improved.
And S5, performing nonlinear dimensionality reduction on the main label evaluation by using the scoring model to obtain the risk evaluation of the project data, and obtaining a scoring result according to the risk evaluation of the project data.
In the embodiment of the invention, the nonlinear dimensionality reduction refers to mapping the main label evaluation to a high-dimensional space, and finding the most aggregated data as the risk evaluation of the project data, the risk evaluation of the project data refers to the risk evaluation of the project data obtained through the scoring model, and the scoring result can be project reliable and project unreliable.
Specifically, the embodiment of the invention performs nonlinear dimensionality reduction on the main label evaluation through the scoring model to obtain the risk assessment of the project data, including;
and comparing the risk evaluation of the project data with a pre-constructed reliability evaluation standard to obtain the scoring result.
For example, the risk assessment of the project data is compared with a pre-constructed reliability evaluation criterion, and if the risk assessment of the project data is greater than the reliability evaluation criterion, the scoring result is reliable, and if the risk assessment of the project data is less than the reliability evaluation criterion, the scoring result is unreliable.
In detail, the embodiment of the invention maps the main label evaluation to different dimensions by using the scoring model to obtain different dimension sets; and taking the set of the main label evaluation which is the largest in different dimensions as the risk assessment of the project data.
In the embodiment of the invention, the scoring result can be the scoring of the project risk, and can be high risk and low risk.
According to the method, the evaluation of the main label is subjected to nonlinear dimension reduction by using the scoring model, so that the risk evaluation of the project data is more specific, the scoring result is more accurate, and the reliability scoring efficiency is improved by automatically performing scoring calculation. Therefore, the embodiment of the invention can solve the problem of low reliability scoring efficiency.
Fig. 3 is a functional block diagram of a risk assessment apparatus for project data according to an embodiment of the present invention.
The risk assessment apparatus 100 for project data according to the present invention may be installed in an electronic device. According to the implemented functions, the risk assessment apparatus 100 for project data may include a main tag calculation model building module 101, a main tag evaluation calculation module 102, a scoring model building module 103, and a scoring result calculation module 104. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the main tag calculation model construction module 101 is configured to obtain pre-constructed original project data and project characteristics, select a pre-constructed scoring card system according to the project characteristics, call a pre-constructed main tag set in the scoring card system according to the original project data, and construct a main tag calculation model according to the main tag set.
In one application scenario of the present invention, the original project data may be financial and newspaper data of a non-bidding financing project, and the project characteristics may include, but are not limited to, project basic information, business classification information, investing and financing scheme information, repayment source information, transaction structure information, and warranty measure information.
Further, the scoring card system is a system for scoring the project main tags and comprises a pre-constructed main tag set, a secondary tag set and a decision factor set. In one implementation of the present invention, the main label may be divided into 5 regions, and each region has a score value ([0,1], [1,2], [2,3], [3,4], [4,5 ]). In the scoring card system, each primary label corresponds to m secondary labels, and each secondary label corresponds to n decision factors.
Specifically, the embodiment of the present invention matches the project characteristics with a pre-constructed scoring card system set: matching the tag card system containing the item characteristics from the scoring card system set.
Further, in the embodiment of the present invention, the main tag is extracted from the item, for example, in an application scenario of a trust company, a non-standard investment and financing item may be divided into eight main tags: debt paying subject, mortgage guarantee, bottom layer project, industry evaluation, transaction structure, post-investment management, investment pricing and credit increase party guarantee. The set of primary labels is a set of the primary labels.
Specifically, when a pre-constructed main tag set in the tag card system is called according to the original item data, and a main tag calculation model is constructed according to the main tag set, the main tag calculation model construction module 101 is specifically configured to: calling a main label set pre-constructed in the label card system according to the original project data, decomposing each main label in the main label set to obtain m secondary labels corresponding to the main label, and integrating all the secondary labels to obtain a secondary label set of each main label, wherein m is a positive integer; decomposing each secondary label in the secondary label set according to a preset analysis mode to obtain n decision factors corresponding to each secondary label, and integrating all the decision factors to obtain a decision factor set, wherein n is a positive integer; and integrating the primary label set, the secondary label set and the decision factor set to obtain the primary label calculation model.
For example, in the risk assessment process of the non-bid financing project data, the financial report data of the non-bid financing project is searched in the pre-constructed main label set, and the main label set containing the financial report data is selected as the main label set of the project. The secondary label set is a set of secondary labels, and the secondary labels are obtained by decomposing the primary label, for example, the secondary labels "manufacturing enterprise", "bank", and "international public welfare organization" can be obtained by decomposing the primary label "repayment subject".
Further, in the embodiment of the present invention, the preset analysis method may be a quantitative analysis method after a predetermined analysis method.
The qualitative mode is to decompose according to the type of the secondary label, and the quantitative mode is to analyze according to the numerical value of the secondary label.
For example, for the sub-label "bank", the sub-label "bank" is firstly decomposed into different types of factors such as "securities" and "funds" in a qualitative manner, then the "securities" is decomposed into "small securities" and "huge securities" in a quantitative manner, the "funds" is decomposed into "small enterprise funds" and "group funds" in a quantitative manner, and the "small securities", "large securities", "small enterprise funds" and "group funds" are summarized to obtain the decision factor corresponding to the sub-label "bank".
Furthermore, in the embodiment of the present invention, a pre-constructed parameter b is obtained according to the number and the type of the decision factor setsjAnd xjObtaining a pre-constructed parameter a according to the type of the secondary label setiAccording to bj、xjAnd aiAnd constructing to obtain the main label calculation model.
Wherein the master tag computation model is y ═ Σ (a)iΣbjxj),x∈[1,5],a,b∈(0,1],Σbj＝1,Σai1 is ═ 1; wherein y is the rating of each primary label, and bjIs the decision factor score, said xjIs the decision factor, said aiIs the secondary label weight.
According to the embodiment of the invention, the main label is refined by constructing the main label calculation model, so that the risk assessment of the project data is more specific, and the scoring result is more accurate.
The main tag evaluation calculation module 102 is configured to calculate the original item data by using the main tag calculation model to obtain a main tag evaluation of the original item data.
Specifically, the main tag evaluation calculation module 102 calls a pre-constructed integer rule according to the original project data; calculating to obtain the score of each decision factor by using the main label calculation model according to the integer rule and the original project data, and accumulating the n decision factor scores corresponding to each secondary label to obtain a secondary label score; and accumulating the m secondary label scores corresponding to each main label to obtain the main label evaluation.
In the embodiment of the present invention, the integral rule means that the decision factor maps the rating card system according to 1-point, 2-point, 3-point, 4-point and 5-point integral systems in a qualitative mode and a quantitative mode, and the decision factor is obtained by decomposing the secondary label, for example, decomposing the secondary label "production enterprise", and obtaining the decision factors "steel production enterprise" and "coal production enterprise", etc.
The scoring model building module 103 is configured to receive historical project data, convert the historical project data to obtain a feature vector, and build a scoring model according to the feature vector and the scoring card system.
In the embodiment of the present invention, the historical item data refers to item data that has been scored. The scoring model refers to a calculation model with a dimension reduction function.
Specifically, the scoring model building module 103 builds a linear matrix by using the historical project data; calculating the eigenvalue of the linear matrix and converting the eigenvalue into an eigenvector; performing calculation on the feature vectors by using a pre-constructed kernel function to obtain grading model construction data; and constructing the grading model according to the grading model construction data and the grading card system.
For example, in an application scenario of a trust company, project data of which decision making and payment paying are normally completed historically can be used as the pre-constructed training sample, a feature vector parameter | Y | is constructed through the project data of which decision making and payment paying are normally completed historically and the main label, the feature vector parameter | Y | is input into a radial-entering gaussian kernel function, and pre-constructed parameters α and β are solved, so that the scoring model can be obtained;
in the embodiment of the present invention, the pre-constructed kernel function may be a gaussian kernel function, and the function of the pre-constructed kernel function is to simplify the calculation steps. The scoring model may be:
f(Y)＝sign((∑_(i＝1)^nα_i exp(-|||Y|-|Y^'|||/σ2+β_i)；
wherein α, β, σ, and n are the scoring model construction data obtained by the feature vectors, Y, i and n are provided by the scoring card system, and Y is the main label evaluation. Wherein i is a continuous variable ranging from 1 to n. The value of n is obtained from the number of the decision factors and represents the number of the decision factors.
According to the embodiment of the invention, the scoring model is obtained by construction, and historical data and the existing project are connected and mapped, so that the scoring accuracy is improved.
The scoring result calculation module 104 is configured to perform nonlinear dimensionality reduction on the main label evaluation by using the scoring model to obtain risk assessment of the project data, and obtain a scoring result according to the risk assessment of the project data.
In the embodiment of the invention, the nonlinear dimensionality reduction refers to mapping the main label evaluation to a high-dimensional space, and finding the most aggregated data as the risk evaluation of the project data, the risk evaluation of the project data refers to the risk evaluation of the project data obtained through the scoring model, and the scoring result can be project reliable and project unreliable.
Specifically, the scoring result calculation module 104 compares the risk assessment of the project data with a pre-constructed reliability evaluation criterion to obtain the scoring result.
For example, the risk assessment of the project data is compared with a pre-constructed reliability evaluation criterion, and if the risk assessment of the project data is greater than the reliability evaluation criterion, the scoring result is reliable, and if the risk assessment of the project data is less than the reliability evaluation criterion, the scoring result is unreliable.
In detail, the scoring result calculation module 104 in the embodiment of the present invention maps the main label evaluation to different dimensions by using the scoring model, so as to obtain different dimension sets; and taking the set of the main label evaluation which is the largest in different dimensions as the risk assessment of the project data.
In the embodiment of the invention, the scoring result can be the scoring of the project risk, and can be high risk and low risk.
As shown in fig. 4, which is a schematic structural diagram of an electronic device of a risk assessment method for project data according to an embodiment of the present invention, the electronic device includes a processor 111, a communication interface 112, a memory 113, and a communication bus 114, where the processor 111, the communication interface 112, and the memory 113 complete mutual communication through the communication bus 114,
a memory 113 for storing computer programs, such as a risk assessment program for project data;
in an embodiment of the present application, when the processor 111 is configured to execute the program stored in the memory 113, the method for risk assessment of project data provided in any one of the foregoing method embodiments includes:
acquiring pre-constructed original project data and project characteristics, and selecting a pre-constructed scoring card system according to the project characteristics;
calling a main label set pre-constructed in the label card system according to the original project data, and constructing a main label calculation model according to the main label set;
calculating the original project data by using the main label calculation model to obtain a main label evaluation of the original project data;
receiving historical project data, converting the historical project data to obtain a feature vector, and constructing a scoring model according to the feature vector and the scoring card system;
and performing nonlinear dimensionality reduction on the main label evaluation by using the scoring model to obtain the risk evaluation of the project data, and obtaining a scoring result according to the risk evaluation of the project data.
The communication bus 114 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus 114 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface 112 is used for communication between the above-described electronic apparatus and other apparatuses.
The memory 113 may include a Random Access Memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory 113 may also be at least one storage device located remotely from the processor 111.
The processor 111 may be a general-purpose processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the integrated circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, or discrete hardware components.
The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device, may implement:
acquiring pre-constructed original project data and project characteristics, and selecting a pre-constructed scoring card system according to the project characteristics;
calling a main label set pre-constructed in the label card system according to the original project data, and constructing a main label calculation model according to the main label set;
calculating the original project data by using the main label calculation model to obtain a main label evaluation of the original project data;
receiving historical project data, converting the historical project data to obtain a feature vector, and constructing a scoring model according to the feature vector and the scoring card system;
and performing nonlinear dimensionality reduction on the main label evaluation by using the scoring model to obtain the risk evaluation of the project data, and obtaining a scoring result according to the risk evaluation of the project data.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A method for risk assessment of project data, the method comprising:
acquiring pre-constructed original project data and project characteristics, and selecting a pre-constructed scoring card system according to the project characteristics;
calling a main label set pre-constructed in the label card system according to the original project data, and constructing a main label calculation model according to the main label set;
calculating the original project data by using the main label calculation model to obtain a main label evaluation of the original project data;
receiving historical project data, converting the historical project data to obtain a feature vector, and constructing a scoring model according to the feature vector and the scoring card system;
and performing nonlinear dimensionality reduction on the main label evaluation by using the scoring model to obtain a project score, and obtaining a scoring result according to the project score.
2. The method for risk assessment of project data according to claim 1, wherein said selecting a pre-constructed scoring card system based on said project characteristics comprises:
matching the project characteristics with a pre-constructed scoring card system set;
matching the tag card system containing the item characteristics from the scoring card system set.
3. The method for risk assessment of project data according to claim 1, wherein said invoking a pre-constructed primary labelset in said labelset architecture according to said original project data and constructing a primary labelset computation model according to said primary labelset comprises:
calling a main label set pre-constructed in the label card system according to the original project data, decomposing each main label in the main label set to obtain m secondary labels corresponding to the main label, and integrating all the secondary labels to obtain a secondary label set of each main label; wherein m is a positive integer;
decomposing each secondary label in the secondary label set according to a preset analysis mode to obtain n decision factors corresponding to each secondary label, and integrating all the decision factors to obtain a decision factor set, wherein n is a positive integer;
and integrating the primary label set, the secondary label set and the decision factor set to obtain the primary label calculation model.
4. The method of risk assessment of project data of claim 3, wherein said computing said raw project data using said primary label computational model to obtain a primary label evaluation of said raw project data comprises:
calling a pre-constructed integer system rule according to the original project data;
calculating to obtain the score of each decision factor by using the main label calculation model according to the integer rule and the original project data, and accumulating the n decision factor scores corresponding to each secondary label to obtain a secondary label score;
and accumulating the m secondary label scores corresponding to each main label to obtain the main label evaluation.
5. The method for risk assessment of project data according to claim 1, wherein said transforming said historical project data into feature vectors and constructing a scoring model according to said feature vectors and said scoring card system comprises:
constructing a linear matrix by using the historical project data;
calculating the eigenvalue of the linear matrix and converting the eigenvalue into an eigenvector;
performing calculation on the feature vectors by using a pre-constructed kernel function to obtain grading model construction data;
and constructing the grading model according to the grading model construction data.
6. The method for risk assessment of project data according to any one of claims 1 to 5, wherein said performing a non-linear dimensionality reduction on said main label evaluation using said scoring model to obtain a project score, and obtaining a scoring result according to said project score comprises:
reducing the dimension of the main label evaluation through the grading model to obtain a final grade;
and associating the final score with a pre-constructed reliability evaluation standard, and integrating the projects with the final scores reaching the reliability evaluation standard to obtain the scoring result.
7. The method for risk assessment of project data according to claim 6, wherein said reducing dimensions of said main label evaluation by said scoring model to obtain a final score comprises:
mapping the main label evaluation to different dimensions by using the scoring model to obtain different dimension sets;
and taking the set of the main label evaluation which is the largest in different dimensions as the final score.
8. A risk assessment apparatus for project data, said apparatus comprising:
the main tag calculation model construction module is used for acquiring pre-constructed original project data and project characteristics, selecting a pre-constructed scoring card system according to the project characteristics, calling a pre-constructed main tag set in the scoring card system according to the original project data, and constructing a main tag calculation model according to the main tag set;
the main label evaluation calculation module is used for calculating the original project data by using the main label calculation model to obtain a main label evaluation of the original project data;
the scoring model building module is used for receiving historical project data, converting the historical project data to obtain a feature vector, and building a scoring model according to the feature vector and the scoring card system;
and the scoring result calculation module is used for performing nonlinear dimensionality reduction on the main label evaluation by using the scoring model to obtain the risk assessment of the project data, and obtaining a scoring result according to the risk assessment of the project data.
9. An electronic device, characterized in that the electronic device comprises:
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 a method of risk assessment of project data as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out a method of risk assessment of project data according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110927489.7A CN113610645A (en) | 2021-08-11 | 2021-08-11 | Method, device and equipment for evaluating risk of project data and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110927489.7A CN113610645A (en) | 2021-08-11 | 2021-08-11 | Method, device and equipment for evaluating risk of project data and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113610645A true CN113610645A (en) | 2021-11-05 |
Family
ID=78340601
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110927489.7A Pending CN113610645A (en) | 2021-08-11 | 2021-08-11 | Method, device and equipment for evaluating risk of project data and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113610645A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006164257A (en) * | 2004-11-15 | 2006-06-22 | Sbi Holdings Inc | Scoring model evaluation method using credit authorization, scoring model evaluation apparatus, authorization system, and scoring model evaluation program |
| CN111353689A (en) * | 2020-02-14 | 2020-06-30 | 北京贝壳时代网络科技有限公司 | Risk assessment method and device |
| CN111967779A (en) * | 2020-08-19 | 2020-11-20 | 支付宝(杭州)信息技术有限公司 | Risk assessment method, device and equipment |
| CN112101520A (en) * | 2020-08-10 | 2020-12-18 | 中国平安人寿保险股份有限公司 | Risk assessment model training method, business risk assessment method and other equipment |
| WO2021004550A1 (en) * | 2019-09-04 | 2021-01-14 | 深圳前海微众银行股份有限公司 | Method, apparatus, and device for generating esg scoring system, and readable storage medium |
| CN112598294A (en) * | 2020-12-25 | 2021-04-02 | 四川云从天府人工智能科技有限公司 | Method, device, machine readable medium and equipment for establishing scoring card model on line |
-
2021
- 2021-08-11 CN CN202110927489.7A patent/CN113610645A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006164257A (en) * | 2004-11-15 | 2006-06-22 | Sbi Holdings Inc | Scoring model evaluation method using credit authorization, scoring model evaluation apparatus, authorization system, and scoring model evaluation program |
| WO2021004550A1 (en) * | 2019-09-04 | 2021-01-14 | 深圳前海微众银行股份有限公司 | Method, apparatus, and device for generating esg scoring system, and readable storage medium |
| CN111353689A (en) * | 2020-02-14 | 2020-06-30 | 北京贝壳时代网络科技有限公司 | Risk assessment method and device |
| CN112101520A (en) * | 2020-08-10 | 2020-12-18 | 中国平安人寿保险股份有限公司 | Risk assessment model training method, business risk assessment method and other equipment |
| CN111967779A (en) * | 2020-08-19 | 2020-11-20 | 支付宝(杭州)信息技术有限公司 | Risk assessment method, device and equipment |
| CN112598294A (en) * | 2020-12-25 | 2021-04-02 | 四川云从天府人工智能科技有限公司 | Method, device, machine readable medium and equipment for establishing scoring card model on line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020107872A1 (en) | Company risk analyzing method, apparatus, computer device, and storage medium | |
| US20150269669A1 (en) | Loan risk assessment using cluster-based classification for diagnostics | |
| WO2020073727A1 (en) | Risk forecast method, device, computer apparatus, and storage medium | |
| CA3205732A1 (en) | Systems and methods for outlier detection of transactions | |
| CN113505936A (en) | Project approval result prediction method, device, equipment and storage medium | |
| CN112419030B (en) | Method, system and equipment for evaluating financial fraud risk | |
| CN112801498A (en) | Risk identification model training method, risk identification device and risk identification equipment | |
| CN112990281A (en) | Abnormal bid identification model training method, abnormal bid identification method and abnormal bid identification device | |
| CN113222668A (en) | Value-added service pushing method, device, equipment and storage medium | |
| CN115936895A (en) | Risk assessment method, device and equipment based on artificial intelligence and storage medium | |
| CN117155771B (en) | Equipment cluster fault tracing method and device based on industrial Internet of things | |
| CN112950347B (en) | Resource data processing optimization method and device, storage medium and terminal | |
| CN114139931A (en) | Enterprise data evaluation method and device, computer equipment and storage medium | |
| CN114398562B (en) | Shop data management method, device, equipment and storage medium | |
| CN113610645A (en) | Method, device and equipment for evaluating risk of project data and storage medium | |
| CN115796572A (en) | Risk enterprise identification method, apparatus, device and medium | |
| CN115063143A (en) | Account data processing method and device, computer equipment and storage medium | |
| CN114048330A (en) | Risk conduction probability knowledge graph generation method, device, equipment and storage medium | |
| CN115829722A (en) | Training method of credit risk scoring model and credit risk scoring method | |
| CN115170007A (en) | Enterprise associated risk identification method, device, equipment and storage medium | |
| CN115713248A (en) | Method for scoring and evaluating data for exchange | |
| CN114418776A (en) | Data processing method, device, terminal equipment and medium | |
| CN114004699A (en) | Artificial intelligence based risk management and control method, device, equipment and storage medium | |
| CN113487103A (en) | Model updating method, device, equipment and storage medium | |
| Lee et al. | Application of machine learning in credit risk scorecard |
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 |