CN110689438A - Enterprise financial risk scoring method and device, computer equipment and storage medium - Google Patents
Enterprise financial risk scoring method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110689438A CN110689438A CN201910792029.0A CN201910792029A CN110689438A CN 110689438 A CN110689438 A CN 110689438A CN 201910792029 A CN201910792029 A CN 201910792029A CN 110689438 A CN110689438 A CN 110689438A
- Authority
- CN
- China
- Prior art keywords
- risk
- financial
- enterprise
- data
- risk score
- 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
- 238000013077 scoring method Methods 0.000 title claims abstract description 14
- 238000003860 storage Methods 0.000 title claims abstract description 10
- 230000009193 crawling Effects 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims description 64
- 239000013598 vector Substances 0.000 claims description 34
- 238000000034 method Methods 0.000 claims description 31
- 238000012545 processing Methods 0.000 claims description 23
- 238000004422 calculation algorithm Methods 0.000 claims description 20
- 238000003066 decision tree Methods 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 11
- 238000011835 investigation Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 8
- 238000007637 random forest analysis Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000012502 risk assessment Methods 0.000 claims description 5
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000012954 risk control Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 19
- 238000004140 cleaning Methods 0.000 description 12
- 230000002159 abnormal effect Effects 0.000 description 10
- 238000005070 sampling Methods 0.000 description 6
- 230000001105 regulatory effect Effects 0.000 description 5
- 238000002790 cross-validation Methods 0.000 description 4
- 230000007812 deficiency Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 230000002349 favourable effect Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 235000019013 Viburnum opulus Nutrition 0.000 description 2
- 244000071378 Viburnum opulus Species 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013210 evaluation model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction 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
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides an enterprise type financial risk scoring method, which comprises the following steps: crawling financial data of a target enterprise; determining the hit amount of the financial data in a preset keyword library; calculating a first risk score of the target enterprise according to the hit amount; acquiring basic data of the target enterprise; inputting the basic data into a pre-trained financial risk recognition model to obtain a second risk score of the target enterprise; and generating a risk score report according to the first risk score and the second risk score. The invention also provides an enterprise-class financial risk scoring device, computer equipment and a storage medium. The invention can quantitatively evaluate the similar financial risk of the enterprise, and is beneficial to the enterprise to realize effective risk control of the online similar financial service.
Description
Technical Field
The invention relates to the technical field of information security, in particular to a method and a device for scoring enterprise-like financial risks, computer equipment and a storage medium.
Background
In recent years, various financial products such as a P2P internet financial platform, a crowd funded financial platform, an e-commerce loan internet financial platform, and a supply chain financial internet financial platform have become important components of the financial industry. However, due to the ultra-conventional development of internet financial products, a large number of risk items, inauguration investments and risk assets of the internet financial products are formed. The formation of the risks is the root of the lack of effective risk control technology of internet cultural financial products, and particularly, the risk of illegal development of the financial services of the type of enterprises is difficult to judge through public financial data or regular field inspection because the development of the services of the online intelligent internet financial services is concealed. Even if the financial risk target name is found, each supervision unit can hardly determine the most risky operation subject, if the problem is not solved, the speed of distinguishing the financial risk subject can not keep up with the financial risk outbreak speed, the thunderstorm type of Chinese internet financial risk can be caused to crash, and the supervision unit, the people and the country are all greatly harmed.
Therefore, it is necessary to provide an enterprise-like financial risk scoring scheme for performing risk scoring on an enterprise developing a financial service to assist in determining a financial risk level of the enterprise.
Disclosure of Invention
In view of the above, it is necessary to provide a method, an apparatus, a computer device and a storage medium for enterprise-like financial risk scoring, which can quantitatively evaluate enterprise-like financial risks and facilitate the enterprises to implement effective risk management and control of online enterprise-like financial services.
The invention provides a method for scoring enterprise-class financial risk, which comprises the following steps:
crawling financial data of a target enterprise;
determining the hit amount of the financial data in a preset keyword library;
calculating a first risk score of the target enterprise according to the hit amount;
acquiring basic data of the target enterprise;
inputting the basic data into a pre-trained financial risk recognition model to obtain a second risk score of the target enterprise;
and generating a risk score report according to the first risk score and the second risk score.
Preferably, the determining the hit amount of the financial data in the preset keyword library includes:
traversing the financial data using an OCR recognition algorithm;
identifying whether keywords in the preset keyword library exist in the financial data;
when the keywords in the preset keyword library exist in the financial data, determining that the keywords are hit;
after traversing the financial data by adopting the OCR algorithm, calculating the times of hitting the keywords in the financial data;
and determining the times as the hit amount of the keywords.
Preferably, the calculating the first risk score of the target enterprise according to the hit amount comprises:
calculating the score of the keyword according to the hit amount of the keyword and the weight of a preset keyword;
and summing the scores of all the keywords to obtain a first risk score of the target enterprise.
Preferably, the training process of the financial risk recognition model includes:
acquiring basic data of a plurality of enterprises;
carrying out structuralization processing on the basic data to obtain a financial risk characteristic vector;
constructing a training set and a testing set according to the financial risk feature vectors;
inputting the training set into a preset random forest algorithm, and constructing a decision tree to obtain a financial risk recognition model;
inputting the test set into the financial risk assessment model, and identifying a decision rate;
judging whether the decision rate is greater than a preset decision rate threshold value or not;
when the decision rate is greater than or equal to the preset decision rate threshold, finishing the training of the financial risk recognition model;
and when the decision rate is smaller than the preset decision rate threshold value, reconstructing a training set and a testing set according to the financial risk feature vector, and training the financial risk recognition model based on the reconstructed training set.
Preferably, the target enterprise is determined by a combination of one or more of the following:
receiving a risk scoring enterprise list, and determining target enterprises needing risk scoring according to the risk scoring enterprise list;
and acquiring a historical risk scoring enterprise list, and screening out enterprises with risk scores smaller than a preset scoring threshold value from the historical risk scoring enterprise list to serve as target enterprises needing risk scoring again.
Preferably, the generating a risk score report according to the first risk score and the second risk score includes:
calculating an average risk score of the first risk score and the second risk score;
determining a risk grade corresponding to the average risk score according to a corresponding relation between preset risk scores and risk grades;
and generating a risk score report according to a preset risk score report template and the risk level.
Preferably, after the determining the risk level corresponding to the average risk score, the method further comprises:
when the risk level is a first level, sending a risk investigation mail to a supervision department; or
When the first risk score is larger than a preset first risk score threshold value, sending a first risk warning mail to the target enterprise; or
And when the second risk score is larger than a preset second risk score threshold value, sending a second risk warning mail to the target enterprise.
The invention provides a second aspect of an enterprise type financial risk scoring device, which comprises:
the crawling module is used for crawling the financial data of the target enterprise;
the determining module is used for determining the hit amount of the financial data in a preset keyword library;
the calculating module is used for calculating a first risk score of the target enterprise according to the hit amount;
the acquisition module is used for acquiring basic data of the target enterprise;
the input module is used for inputting the basic data into a pre-trained financial risk recognition model to obtain a second risk score of the target enterprise;
and the generating module is used for generating a risk score report according to the first risk score and the second risk score.
A third aspect of the invention provides a computer device comprising a processor for implementing the enterprise-wide financial risk scoring method when executing a computer program stored in a memory.
A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the enterprise-wide financial risk scoring method.
The enterprise-like financial risk scoring method, the device, the computer equipment and the storage medium of the invention can be used for calculating a first risk score based on financial data obtained by crawling the financial data of a target enterprise from the internet and obtaining the basic data of the target enterprise from an enterprise credit investigation database, calculating a second risk score based on the basic data and a pre-trained financial risk identification model, and finally forming a risk score report by combining the first risk score and the second risk score to quantitatively evaluate the similarly financial risk of the enterprise, thereby not only being beneficial to the effective risk control of the online similarly financial business of the enterprise, but also being beneficial to investors including institutions and scattered households to establish a timely loss stopping mechanism according to the actual conditions of the investors, enhancing the risk identification degree of the investors on investment products, and effectively eliminating the information asymmetry in the internet asset securitization process, maintaining the investor's underlying interests. For administrative areas which focus on developing internet information intermediary services, the supervision levels of supervision departments are more comprehensive and stereoscopic.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of an enterprise-like financial risk scoring method according to an embodiment of the present invention.
Fig. 2 is a structural diagram of an enterprise financial risk scoring device according to a second embodiment of the present invention.
Fig. 3 is a schematic structural diagram of a computer device according to a third embodiment of the present invention.
The following detailed description will further illustrate the invention in conjunction with the above-described figures.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a detailed description of the present invention will be given below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and features of the embodiments may be combined with each other without conflict.
In the following description, numerous specific details are set forth to provide a thorough understanding of the present invention, and the described embodiments are merely a subset of the embodiments of the present invention, rather than a complete embodiment. 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.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
Example one
Fig. 1 is a flowchart of an enterprise-type financial risk scoring method according to an embodiment of the present invention.
As shown in fig. 1, the enterprise-type financial risk scoring method specifically includes the following steps, and the order of the steps in the flowchart may be changed and some steps may be omitted according to different requirements.
And S11, the financial data of the target enterprise is crawled.
In this embodiment, a target enterprise needs to be determined, and then financial data of the target enterprise is crawled from a plurality of data sources by using a search engine technology, a web crawler technology, a regular expression technology and a scoring card technology. The search engine technology, the web crawler technology, the regular expression technology and the scoring card technology are all the prior art and are not described herein.
The plurality of data sources may include, but are not limited to: hundredth, google, Teng news, microblog, hot search, know any website supporting the user to search for access, and the like. The crawled internet content may include financial data such as popularity index, google trend, Tencent analysis, news information, advertising data, channel data, microblog popularity, forum public opinion information, and the like.
The financial data may include: financing data, warranty data, loan data, rigid redemption data, and any other financial information associated with the target enterprise.
Preferably, the target enterprise is determined by a combination of one or more of the following:
receiving a risk scoring enterprise list, and determining target enterprises needing risk scoring according to the risk scoring enterprise list;
and acquiring a historical risk scoring enterprise list, and screening out enterprises with risk scores smaller than a preset scoring threshold value from the historical risk scoring enterprise list to serve as target enterprises needing risk scoring again.
In this embodiment, a data interface may be provided, and receive a risk scoring enterprise list sent by a user through the data interface, where the risk scoring enterprise list lists one or more enterprise names that need risk scoring, and crawl financial information associated with an enterprise in the internet by using a web crawler technology according to the enterprise names. Or screening out enterprises with lower risk scores (for example, the risk scores are smaller than a preset score threshold value or the risk scores are ranked as the last few) from the historical risk score information, and then carrying out risk scoring again.
Preferably, after the financial data of the target enterprise is crawled, before the hit amount of the financial data in the preset keyword bank is determined, the method further comprises the following steps:
and performing data cleaning and abnormal value processing on the financial data.
Data cleansing the financial data may include: cleaning the financial data containing noise by adopting a method for removing extra-large values and negative value points; data cleaning is carried out on the financial data containing the repeated information by adopting a method of deleting repeated items; and (4) carrying out data cleaning on the incomplete financial data by adopting a method for establishing a relevant standard reference value.
Outlier processing of the financial data may include: for financial data where there is a data deficiency, the mean of the other financial data is used to fill in the deficiency.
In this embodiment, the data cleansing and the abnormal value processing are performed on the financial data, so as to eliminate redundant data in the financial data and obtain the financial data with a consistent standard format, so that the financial data after the data cleansing and the abnormal value processing can be better subjected to keyword matching.
And S12, determining the hit amount of the financial data in a preset keyword library.
In this embodiment, a keyword library may be preset, and a plurality of keywords associated with financial risk, for example, any words that may involve financial risk, such as warranty, fund pool, financing, guarantee, loan, rigid cash, etc., may be recorded in the keyword library.
It should be noted that, because the similar financial service modes in different scenes are different, the emphasis points are different, the corresponding financial data are also different, and the regulatory rules and rules are also different, different keyword libraries can be set according to the actual scenes and the similar financial service modes and according to the contents related in the regulatory rules and rules to cope with the enterprise financial risk scores in different scenes and similar financial service modes.
Preferably, the determining the hit amount of the financial data in the preset keyword library includes:
traversing the financial data using an OCR recognition algorithm;
identifying whether keywords in the preset keyword library exist in the financial data;
when the keywords in the preset keyword library exist in the financial data, determining that the keywords are hit;
after traversing the financial data by adopting the OCR algorithm, calculating the times of hitting the keywords in the financial data;
and determining the times as the hit amount of the keywords.
For example, assuming that the keywords in the preset keyword library are financing, an OCR recognition algorithm is used to start traversing the financial data, when it is recognized that financing exists in the financial data, it is determined that financing is hit once, and after the financial data is traversed, the number of times of financing is hit in the financial data is calculated, where the number of times is the hit amount of financing in the financial data.
In other embodiments, the keywords may also be recorded in memory after determining that the keywords are hit, one more keyword in the memory per hit of the keywords. And after traversing the financial data by adopting the OCR algorithm, accessing the keywords in the memory, and determining the hit quantity of the keywords in the financial data according to the number of the keywords in the memory.
It should be understood that if data cleaning and abnormal value processing are performed on the financial data after the financial data of the target enterprise is crawled, the OCR recognition algorithm is adopted to traverse the financial data after the data cleaning and the abnormal value processing are performed.
And S13, calculating a first risk score of the target enterprise according to the hit amount.
In this embodiment, after the hit amount of the keyword in the preset keyword library in the financial data is obtained, the risk score of the target enterprise is calculated according to the hit amounts.
Preferably, the calculating the first risk score of the target enterprise according to the hit amount comprises:
calculating the score of the keyword according to the hit amount of the keyword and the weight of a preset keyword;
and summing the scores of all the keywords to obtain a first risk score of the target enterprise.
In this embodiment, a weight may be set for each keyword in the preset keyword library.
The same weight may be set for each keyword, and different weights may be set for different keywords according to risk degrees corresponding to different keywords, which is not limited herein.
For example, assume that the financial data hits a keyword in the predetermined keyword library: financing and guarantee, wherein the hit amount of the financing is 10, and the hit amount of the guarantee is 7. And calculating the hit amount and the first weight of the financing to obtain a financing score, and calculating the hit amount and the second weight of the guarantee to obtain a guarantee score. And summing the financing score and the guarantee score to obtain a first risk score of the target enterprise. A higher first risk score indicates a greater risk for the target enterprise, and a smaller first risk score indicates a lesser risk for the target enterprise.
And S14, acquiring the basic data of the target enterprise.
In this embodiment, a data warehouse may be preset, and the data warehouse is used to store basic data of each enterprise. The basic data can be credit investigation data of the enterprise, and basic information of the enterprise is recorded.
A basic data table may be created in advance, where the basic data table includes several major classes, each major class includes multiple minor classes, and each minor class further has multiple items associated therewith. For example, the basic data is classified into a personnel category, a financial operation category and an illegal category, the financial category comprises a plurality of subclasses such as parking break, debt mortgage, cooperative operation, business operation and business change, and the parking break comprises a plurality of items such as closing doors, running, closing and stopping of a company.
And after acquiring the basic data of the target enterprise, storing the basic data of the target enterprise under the corresponding items of the basic data table.
And S15, inputting the basic data into a pre-trained financial risk recognition model to obtain a second risk score of the target enterprise.
In this embodiment, basic data of a plurality of enterprises needs to be acquired in advance, a financial risk recognition model is trained based on the basic data of the plurality of enterprises, the basic data of a target enterprise is subsequently input into the trained financial risk recognition model, a recognition result is input through the financial risk recognition model, and a second risk score of the target enterprise is obtained according to the recognition result.
Preferably, the training process of the financial risk recognition model includes:
acquiring basic data of a plurality of enterprises;
carrying out structuralization processing on the basic data to obtain a financial risk characteristic vector;
constructing a training set and a testing set according to the financial risk feature vectors;
inputting the training set into a preset random forest algorithm, and constructing a decision tree to obtain a financial risk recognition model;
inputting the test set into the financial risk assessment model, and identifying a decision rate;
judging whether the decision rate is greater than a preset decision rate threshold value or not;
when the decision rate is greater than or equal to the preset decision rate threshold, finishing the training of the financial risk recognition model;
and when the decision rate is smaller than the preset decision rate threshold value, reconstructing a training set and a testing set according to the financial risk feature vector, and training the financial risk recognition model based on the reconstructed training set.
Preferably, the structuring the basic data to obtain the financial risk feature vector includes:
updating each item in the basic data to a preset factor;
and associating the preset factor with a preset score value to obtain the financial characteristics of the item.
In this embodiment, the same score value may be set for each large category in the basic data, and then the score value of each item in the large category may be determined according to the total amount of the items in the large category, or the same score value may be set for each item. The financial features are formed by structuring the items in the underlying data. Specifically, the financial risk feature vector is defined as Y ═ (X1, X2, X3.., Xn), where Y is the financial risk feature vector, X1, X2, X3.., Xn is the n financial features. The n financial characteristics are data obtained by performing structuring processing according to the basic data.
It should be understood that, before the basic data of the target enterprise is input into the pre-trained financial risk recognition model, the basic data of the target enterprise also needs to be structured, and the structured basic data is input into the pre-trained financial risk recognition model.
And constructing a training set by using the financial risk characteristic vectors, and performing training of a financial risk identification model by using the training set as training data, wherein the training set comprises M financial risk characteristic vectors, M is a positive integer, the financial risk evaluation model comprises K decision trees, and K is a positive integer.
Preferably, a training set and a testing set can be constructed according to the financial risk feature vector by adopting a cross validation idea.
The idea of cross-validation is prior art.
Preferably, a plurality of financial risk feature vectors are randomly extracted from the training set, specifically, a random sampling mode can be adopted, the random sampling mode is that the random sampling mode is replaced, K rounds of extraction are repeatedly performed in the training set, the result of each round of extraction is used as a sub-training set, K sub-training sets are obtained, wherein the K sub-training sets are independent from each other, and the repeated financial risk feature vectors can exist in the sub-training sets. And constructing a decision tree by using a random forest algorithm, constructing a decision tree for each sub-training set to obtain K decision trees, and constructing a random forest according to the K decision trees to obtain a financial risk identification model.
It should be noted that, the extracted number of the financial risk feature vectors may be specifically obtained according to historical experience, or an appropriate financial risk feature vector may be extracted according to specific business needs, and the extracted financial risk feature vector is used as a sub-training set to train the financial risk recognition model, although the more the training sample data is, the more accurate the training sample data is, the higher the training cost is and the harder the implementation manner is, and the specific number may be extracted according to the needs of practical application, which is not limited herein.
And S16, generating a risk score report according to the first risk score and the second risk score.
In this embodiment, after the first risk score and the second risk score of the target enterprise are obtained, a risk score report is generated and displayed. And the risk score of the target enterprise can be obtained clearly through the intuitive display of the risk score report.
Preferably, the generating a risk score report according to the first risk score and the second risk score includes:
calculating an average risk score of the first risk score and the second risk score;
determining a risk grade corresponding to the average risk score according to a corresponding relation between preset risk scores and risk grades;
and generating a risk score report according to a preset risk score report template and the risk level.
In this embodiment, a risk score report template may be preset, that is, a presentation form of a risk score report is preset, for example, the presentation content of the risk score report may include: the business name, the first risk score, the second risk score, the risk level, the basic profile of the business, the report summary, the situation of high management personnel, the equity authority, the general association situation, the situation of business state distribution and the like. The basic general data, the report general data, the high management personnel condition data, the equity organization data, the overall association condition data and the state distribution condition data of the enterprise can be obtained through a sky-eye system. And after the data are obtained, sequentially filling the contents according to a preset risk scoring report template to generate a risk scoring report of the target enterprise.
Preferably, after the determining the risk level corresponding to the average risk score, the method further comprises:
when the risk level is a first level, sending a risk investigation mail to a supervision department; or
When the first risk score is larger than a preset first risk score threshold value, sending a first risk warning mail to the target enterprise; or
And when the second risk score is larger than a preset second risk score threshold value, sending a second risk warning mail to the target enterprise.
In this embodiment, the risk levels, for example, the first level, the second level, and the third level, may be set in advance. The risks in different levels represent different degrees of influence of the enterprises on the society and the consumers, wherein the first level represents that the enterprises have very high degree of influence on the society and the consumers, the second level represents that the enterprises have high degree of influence on the society and the consumers, and the second level represents that the enterprises have relatively low degree of influence on the society and the consumers. Of course in other embodiments, more risk levels may be set.
When the risk level is the first level, it indicates that the target enterprise has a serious violation, and the monitoring department needs to send a risk alarm to notify the monitoring department to manually check the target enterprise, so as to ensure that the current enterprise does not cause more serious financial risk to the society and consumers. And when the first risk score is larger than a preset first risk score threshold value or when the second risk score is larger than a preset second risk score threshold value, sending a risk warning mail to the target enterprise to inform the target enterprise to carry out self-checking and confirm where the risk factor comes from, so that the target enterprise is prevented from forming a snowball rolling effect, and the risk is increased more and more, so that the enterprise is prevented from closing.
In summary, the enterprise-type financial risk scoring method provided by the invention is used for calculating a first risk score based on financial data obtained by crawling the financial data of a target enterprise from the internet and obtaining basic data of the target enterprise from an enterprise credit investigation database, calculating a second risk score based on the basic data and a pre-trained financial risk identification model, and finally forming a risk scoring report by combining the first risk score and the second risk score. According to keywords in the supervision policy, risks are quantitatively processed, when a financial risk recognition model is trained, categories of basic data are structurally processed, and the model obtained through training can be finely divided in granularity. The enterprise financial risk scoring method can be particularly applied to a similar financial risk assessment system in the financial service industry and is used for quantitatively assessing similar financial risks of enterprises. In practical application, the method not only can be favorable for enterprises to realize effective risk management and control of online similar financial services, but also is favorable for investors including organizations and scattered households to establish a timely loss stopping mechanism according to the actual conditions of the investors, so that the risk identification degree of the investors on investment products is enhanced, the information asymmetry in the internet asset securitization process is effectively eliminated, and the fundamental interests of the investors are maintained. For administrative areas which focus on developing internet information intermediary services, the supervision levels of supervision departments are more comprehensive and stereoscopic.
Example two
Fig. 2 is a structural diagram of an enterprise financial risk scoring device according to a second embodiment of the present invention.
In some embodiments, the enterprise-wide financial risk scoring device 20 may include a plurality of functional modules comprised of program code segments. The program code for the various program segments of the enterprise-wide financial risk scoring apparatus 20 may be stored in a memory of a computer device and executed by the at least one processor to perform the functions of enterprise-wide financial risk scoring (described in detail with respect to fig. 1).
In this embodiment, the enterprise-based financial risk scoring device 20 may be divided into a plurality of functional modules according to the functions performed by the device. The functional module may include: crawling module 201, processing module 202, determining module 203, calculating module 204, obtaining module 205, inputting module 206, generating module 207, and sending module 208. The module referred to herein is a series of computer program segments capable of being executed by at least one processor and capable of performing a fixed function and is stored in memory. In the present embodiment, the functions of the modules will be described in detail in the following embodiments.
And the crawling module 201 is used for crawling the financial data of the target enterprise.
In this embodiment, a target enterprise needs to be determined, and then financial data of the target enterprise is crawled from a plurality of data sources by using a search engine technology, a web crawler technology, a regular expression technology and a scoring card technology. The search engine technology, the web crawler technology, the regular expression technology and the scoring card technology are all the prior art and are not described herein.
The plurality of data sources may include, but are not limited to: hundredth, google, Teng news, microblog, hot search, know any website supporting the user to search for access, and the like. The crawled internet content may include financial data such as popularity index, google trend, Tencent analysis, news information, advertising data, channel data, microblog popularity, forum public opinion information, and the like.
The financial data may include: financing data, warranty data, loan data, rigid redemption data, and any other financial information associated with the target enterprise.
Preferably, the target enterprise is determined by a combination of one or more of the following:
receiving a risk scoring enterprise list, and determining target enterprises needing risk scoring according to the risk scoring enterprise list;
and acquiring a historical risk scoring enterprise list, and screening out enterprises with risk scores smaller than a preset scoring threshold value from the historical risk scoring enterprise list to serve as target enterprises needing risk scoring again.
In this embodiment, a data interface may be provided, and receive a risk scoring enterprise list sent by a user through the data interface, where the risk scoring enterprise list lists one or more enterprise names that need risk scoring, and crawl financial information associated with an enterprise in the internet by using a web crawler technology according to the enterprise names. Or screening out enterprises with lower risk scores (for example, the risk scores are smaller than a preset score threshold value or the risk scores are ranked as the last few) from the historical risk score information, and then carrying out risk scoring again.
Preferably, after the crawling module 201 crawls the financial data of the target enterprise, before determining the hit amount of the financial data in the preset keyword library, the enterprise-type financial risk scoring apparatus 20 further includes:
and the processing module 202 is used for performing data cleaning and abnormal value processing on the financial data.
Data cleansing the financial data may include: cleaning the financial data containing noise by adopting a method for removing extra-large values and negative value points; data cleaning is carried out on the financial data containing the repeated information by adopting a method of deleting repeated items; and (4) carrying out data cleaning on the incomplete financial data by adopting a method for establishing a relevant standard reference value.
Outlier processing of the financial data may include: for financial data where there is a data deficiency, the mean of the other financial data is used to fill in the deficiency.
In this embodiment, the data cleansing and the abnormal value processing are performed on the financial data, so as to eliminate redundant data in the financial data and obtain the financial data with a consistent standard format, so that the financial data after the data cleansing and the abnormal value processing can be better subjected to keyword matching.
And the determining module 203 is used for determining the hit amount of the financial data in a preset keyword library.
In this embodiment, a keyword library may be preset, and a plurality of keywords associated with financial risk, for example, any words that may involve financial risk, such as warranty, fund pool, financing, guarantee, loan, rigid cash, etc., may be recorded in the keyword library.
It should be noted that, because the similar financial service modes in different scenes are different, the emphasis points are different, the corresponding financial data are also different, and the regulatory rules and rules are also different, different keyword libraries can be set according to the actual scenes and the similar financial service modes and according to the contents related in the regulatory rules and rules to cope with the enterprise financial risk scores in different scenes and similar financial service modes.
Preferably, the determining module 203 determines the hit amount of the financial data in a preset keyword library by:
traversing the financial data using an OCR recognition algorithm;
identifying whether keywords in the preset keyword library exist in the financial data;
when the keywords in the preset keyword library exist in the financial data, determining that the keywords are hit;
after traversing the financial data by adopting the OCR algorithm, calculating the times of hitting the keywords in the financial data;
and determining the times as the hit amount of the keywords.
For example, assuming that the keywords in the preset keyword library are financing, an OCR recognition algorithm is used to start traversing the financial data, when it is recognized that financing exists in the financial data, it is determined that financing is hit once, and after the financial data is traversed, the number of times of financing is hit in the financial data is calculated, where the number of times is the hit amount of financing in the financial data.
In other embodiments, the keywords may also be recorded in memory after determining that the keywords are hit, one more keyword in the memory per hit of the keywords. And after traversing the financial data by adopting the OCR algorithm, accessing the keywords in the memory, and determining the hit quantity of the keywords in the financial data according to the number of the keywords in the memory.
It should be understood that if data cleaning and abnormal value processing are performed on the financial data after the financial data of the target enterprise is crawled, the OCR recognition algorithm is adopted to traverse the financial data after the data cleaning and the abnormal value processing are performed.
And the calculating module 204 is used for calculating a first risk score of the target enterprise according to the hit amount.
In this embodiment, after the hit amount of the keyword in the preset keyword library in the financial data is obtained, the risk score of the target enterprise is calculated according to the hit amounts.
Preferably, the calculating module 204 calculates the first risk score of the target enterprise according to the hit amount includes:
calculating the score of the keyword according to the hit amount of the keyword and the weight of a preset keyword;
and summing the scores of all the keywords to obtain a first risk score of the target enterprise.
In this embodiment, a weight may be set for each keyword in the preset keyword library.
The same weight may be set for each keyword, and different weights may be set for different keywords according to risk degrees corresponding to different keywords, which is not limited herein.
For example, assume that the financial data hits a keyword in the predetermined keyword library: financing and guarantee, wherein the hit amount of the financing is 10, and the hit amount of the guarantee is 7. And calculating the hit amount and the first weight of the financing to obtain a financing score, and calculating the hit amount and the second weight of the guarantee to obtain a guarantee score. And summing the financing score and the guarantee score to obtain a first risk score of the target enterprise. A higher first risk score indicates a greater risk for the target enterprise, and a smaller first risk score indicates a lesser risk for the target enterprise.
An obtaining module 205, configured to obtain basic data of the target enterprise.
In this embodiment, a data warehouse may be preset, and the data warehouse is used to store basic data of each enterprise. The basic data can be credit investigation data of the enterprise, and basic information of the enterprise is recorded.
A basic data table may be created in advance, where the basic data table includes several major classes, each major class includes multiple minor classes, and each minor class further has multiple items associated therewith. For example, the basic data is classified into a personnel category, a financial operation category and an illegal category, the financial category comprises a plurality of subclasses such as parking break, debt mortgage, cooperative operation, business operation and business change, and the parking break comprises a plurality of items such as closing doors, running, closing and stopping of a company.
And after acquiring the basic data of the target enterprise, storing the basic data of the target enterprise under the corresponding items of the basic data table.
An input module 206, configured to input the basic data into a pre-trained financial risk recognition model, so as to obtain a second risk score of the target enterprise.
In this embodiment, basic data of a plurality of enterprises needs to be acquired in advance, a financial risk recognition model is trained based on the basic data of the plurality of enterprises, the basic data of a target enterprise is subsequently input into the trained financial risk recognition model, a recognition result is input through the financial risk recognition model, and a second risk score of the target enterprise is obtained according to the recognition result.
Preferably, the training process of the financial risk recognition model includes:
acquiring basic data of a plurality of enterprises;
carrying out structuralization processing on the basic data to obtain a financial risk characteristic vector;
constructing a training set and a testing set according to the financial risk feature vectors;
inputting the training set into a preset random forest algorithm, and constructing a decision tree to obtain a financial risk recognition model;
inputting the test set into the financial risk assessment model, and identifying a decision rate;
judging whether the decision rate is greater than a preset decision rate threshold value or not;
when the decision rate is greater than or equal to the preset decision rate threshold, finishing the training of the financial risk recognition model;
and when the decision rate is smaller than the preset decision rate threshold value, reconstructing a training set and a testing set according to the financial risk feature vector, and training the financial risk recognition model based on the reconstructed training set.
Preferably, the structuring the basic data to obtain the financial risk feature vector includes:
updating each item in the basic data to a preset factor;
and associating the preset factor with a preset score value to obtain the financial characteristics of the item.
In this embodiment, the same score value may be set for each large category in the basic data, and then the score value of each item in the large category may be determined according to the total amount of the items in the large category, or the same score value may be set for each item. The financial features are formed by structuring the items in the underlying data. Specifically, the financial risk feature vector is defined as Y ═ (X1, X2, X3.., Xn), where Y is the financial risk feature vector, X1, X2, X3.., Xn is the n financial features. The n financial characteristics are data obtained by performing structuring processing according to the basic data.
It should be understood that, before the basic data of the target enterprise is input into the pre-trained financial risk recognition model, the basic data of the target enterprise also needs to be structured, and the structured basic data is input into the pre-trained financial risk recognition model.
And constructing a training set by using the financial risk characteristic vectors, and performing training of a financial risk identification model by using the training set as training data, wherein the training set comprises M financial risk characteristic vectors, M is a positive integer, the financial risk evaluation model comprises K decision trees, and K is a positive integer.
Preferably, a training set and a testing set can be constructed according to the financial risk feature vector by adopting a cross validation idea.
The idea of cross-validation is prior art.
Preferably, a plurality of financial risk feature vectors are randomly extracted from the training set, specifically, a random sampling mode can be adopted, the random sampling mode is that the random sampling mode is replaced, K rounds of extraction are repeatedly performed in the training set, the result of each round of extraction is used as a sub-training set, K sub-training sets are obtained, wherein the K sub-training sets are independent from each other, and the repeated financial risk feature vectors can exist in the sub-training sets. And constructing a decision tree by using a random forest algorithm, constructing a decision tree for each sub-training set to obtain K decision trees, and constructing a random forest according to the K decision trees to obtain a financial risk identification model.
It should be noted that, the extracted number of the financial risk feature vectors may be specifically obtained according to historical experience, or an appropriate financial risk feature vector may be extracted according to specific business needs, and the extracted financial risk feature vector is used as a sub-training set to train the financial risk recognition model, although the more the training sample data is, the more accurate the training sample data is, the higher the training cost is and the harder the implementation manner is, and the specific number may be extracted according to the needs of practical application, which is not limited herein.
A generating module 207, configured to generate a risk score report according to the first risk score and the second risk score.
In this embodiment, after the first risk score and the second risk score of the target enterprise are obtained, a risk score report is generated and displayed. And the risk score of the target enterprise can be obtained clearly through the intuitive display of the risk score report.
Preferably, the generating module 207 generates a risk score report according to the first risk score and the second risk score includes:
calculating an average risk score of the first risk score and the second risk score;
determining a risk grade corresponding to the average risk score according to a corresponding relation between preset risk scores and risk grades;
and generating a risk score report according to a preset risk score report template and the risk level.
In this embodiment, a risk score report template may be preset, that is, a presentation form of a risk score report is preset, for example, the presentation content of the risk score report may include: the business name, the first risk score, the second risk score, the risk level, the basic profile of the business, the report summary, the situation of high management personnel, the equity authority, the general association situation, the situation of business state distribution and the like. The basic general data, the report general data, the high management personnel condition data, the equity organization data, the overall association condition data and the state distribution condition data of the enterprise can be obtained through a sky-eye system. And after the data are obtained, sequentially filling the contents according to a preset risk scoring report template to generate a risk scoring report of the target enterprise.
Preferably, after the determining the risk level corresponding to the average risk score, the apparatus further comprises:
a sending module 208, configured to send a risk investigation email to a regulatory authority when the risk level is a first level; or
When the first risk score is larger than a preset first risk score threshold value, sending a first risk warning mail to the target enterprise; or
And when the second risk score is larger than a preset second risk score threshold value, sending a second risk warning mail to the target enterprise.
In this embodiment, the risk levels, for example, the first level, the second level, and the third level, may be set in advance. The risks in different levels represent different degrees of influence of the enterprises on the society and the consumers, wherein the first level represents that the enterprises have very high degree of influence on the society and the consumers, the second level represents that the enterprises have high degree of influence on the society and the consumers, and the second level represents that the enterprises have relatively low degree of influence on the society and the consumers. Of course in other embodiments, more risk levels may be set.
When the risk level is the first level, it indicates that the target enterprise has a serious violation, and the monitoring department needs to send a risk alarm to notify the monitoring department to manually check the target enterprise, so as to ensure that the current enterprise does not cause more serious financial risk to the society and consumers. And when the first risk score is larger than a preset first risk score threshold value or when the second risk score is larger than a preset second risk score threshold value, sending a risk warning mail to the target enterprise to inform the target enterprise to carry out self-checking and confirm where the risk factor comes from, so that the target enterprise is prevented from forming a snowball rolling effect, and the risk is increased more and more, so that the enterprise is prevented from closing.
In summary, the enterprise-class financial risk scoring device provided by the invention is used for calculating a first risk score based on financial data obtained by crawling the financial data of a target enterprise from the internet and basic data of the target enterprise obtained from an enterprise credit investigation database, calculating a second risk score based on the basic data and a pre-trained financial risk identification model, and finally forming a risk scoring report by combining the first risk score and the second risk score. According to keywords in the supervision policy, risks are quantitatively processed, when a financial risk recognition model is trained, categories of basic data are structurally processed, and the model obtained through training can be finely divided in granularity. The enterprise similar-financial risk scoring device can be particularly applied to a similar-financial risk evaluation system in the financial service industry and is used for quantitatively evaluating the similar-financial risk of enterprises. In practical application, the method not only can be favorable for enterprises to realize effective risk management and control of online similar financial services, but also is favorable for investors including organizations and scattered households to establish a timely loss stopping mechanism according to the actual conditions of the investors, so that the risk identification degree of the investors on investment products is enhanced, the information asymmetry in the internet asset securitization process is effectively eliminated, and the fundamental interests of the investors are maintained. For administrative areas which focus on developing internet information intermediary services, the supervision levels of supervision departments are more comprehensive and stereoscopic.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a computer device according to a third embodiment of the present invention. In the preferred embodiment of the present invention, the computer device 3 includes a memory 31, at least one processor 32, at least one communication bus 33, and a transceiver 34.
It will be appreciated by those skilled in the art that the configuration of the computer device shown in fig. 3 does not constitute a limitation of the embodiments of the present invention, and may be a bus-type configuration or a star-type configuration, and that the computer device 3 may include more or less hardware or software than those shown, or a different arrangement of components.
In some embodiments, the computer device 3 includes a computer device capable of automatically performing numerical calculation and/or information processing according to instructions set or stored in advance, and the hardware includes but is not limited to a microprocessor, an application specific integrated circuit, a programmable gate array, a digital processor, an embedded device, and the like. The computer device 3 may also include a client device, which includes, but is not limited to, any electronic product capable of interacting with a client through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device, for example, a personal computer, a tablet computer, a smart phone, a digital camera, etc.
It should be noted that the computer device 3 is only an example, and other electronic products that are currently available or may come into existence in the future, such as electronic products that can be adapted to the present invention, should also be included in the scope of the present invention, and are included herein by reference.
In some embodiments, the memory 31 is used for storing program codes and various data, such as the enterprise-type financial risk scoring device 20 installed in the computer device 3, and realizes high-speed and automatic access to programs or data during the operation of the computer device 3. The Memory 31 includes a Read-Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an electronically Erasable rewritable Read-Only Memory (Electrically-Erasable Programmable Read-Only Memory (EEPROM)), an optical Read-Only Memory (CD-ROM) or other optical disk Memory, a magnetic disk Memory, a tape Memory, or any other medium readable by a computer capable of carrying or storing data.
In some embodiments, the at least one processor 32 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The at least one processor 32 is a Control Unit (Control Unit) of the computer device 3, connects various components of the entire computer device 3 by using various interfaces and lines, and executes various functions of the computer device 3 and processes data, such as a function of performing enterprise type financial risk scoring, by running or executing programs or modules stored in the memory 31 and calling data stored in the memory 31.
In some embodiments, the at least one communication bus 33 is arranged to enable connection communication between the memory 31 and the at least one processor 32 or the like.
Although not shown, the computer device 3 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 32 through a power management device, so as to implement functions of managing charging, discharging, and power consumption through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The computer device 3 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The integrated unit implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a computer device, or a network device) or a processor (processor) to execute parts of the methods according to the embodiments of the present invention.
In a further embodiment, in conjunction with fig. 2, the at least one processor 32 may execute the operating means of the computer device 3 and installed various types of applications (e.g., the enterprise-based financial risk scoring device 20), program code, and the like, such as the various modules described above.
The memory 31 has program code stored therein, and the at least one processor 32 can call the program code stored in the memory 31 to perform related functions. For example, the modules illustrated in fig. 2 are program code stored in the memory 31 and executed by the at least one processor 32, so as to implement the functions of the modules for the purpose of enterprise-wide financial risk scoring.
In one embodiment of the invention, the memory 31 stores a plurality of instructions that are executed by the at least one processor 32 to implement the functionality of enterprise-like financial risk scoring.
Specifically, the at least one processor 32 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1, and details are not repeated here.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may 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 sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or that the singular does not exclude the plural. A plurality of units or means recited in the apparatus claims may also be implemented by one unit or means in software or hardware. The terms first, 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. An enterprise-like financial risk scoring method, comprising:
crawling financial data of a target enterprise;
determining the hit amount of the financial data in a preset keyword library;
calculating a first risk score of the target enterprise according to the hit amount;
acquiring basic data of the target enterprise;
inputting the basic data into a pre-trained financial risk recognition model to obtain a second risk score of the target enterprise;
and generating a risk score report according to the first risk score and the second risk score.
2. The method of claim 1, wherein determining the hit size of the financial data in a predetermined keyword bank comprises:
traversing the financial data using an OCR recognition algorithm;
identifying whether keywords in the preset keyword library exist in the financial data;
when the keywords in the preset keyword library exist in the financial data, determining that the keywords are hit;
after traversing the financial data by adopting the OCR algorithm, calculating the times of hitting the keywords in the financial data;
and determining the times as the hit amount of the keywords.
3. The method of claim 2, wherein said calculating a first risk score for the target business as a function of the hit volume comprises:
calculating the score of the keyword according to the hit amount of the keyword and the weight of a preset keyword;
and summing the scores of all the keywords to obtain a first risk score of the target enterprise.
4. The method of claim 1, wherein the training process of the financial risk recognition model comprises:
acquiring basic data of a plurality of enterprises;
carrying out structuralization processing on the basic data to obtain a financial risk characteristic vector;
constructing a training set and a testing set according to the financial risk feature vectors;
inputting the training set into a preset random forest algorithm, and constructing a decision tree to obtain a financial risk recognition model;
inputting the test set into the financial risk assessment model, and identifying a decision rate;
judging whether the decision rate is greater than a preset decision rate threshold value or not;
when the decision rate is greater than or equal to the preset decision rate threshold, finishing the training of the financial risk recognition model;
and when the decision rate is smaller than the preset decision rate threshold value, reconstructing a training set and a testing set according to the financial risk feature vector, and training the financial risk recognition model based on the reconstructed training set.
5. The method of claim 1, wherein the target business is determined by a combination of one or more of:
receiving a risk scoring enterprise list, and determining target enterprises needing risk scoring according to the risk scoring enterprise list;
and acquiring a historical risk scoring enterprise list, and screening out enterprises with risk scores smaller than a preset scoring threshold value from the historical risk scoring enterprise list to serve as target enterprises needing risk scoring again.
6. The method of claim 1, wherein generating a risk score report based on the first risk score and the second risk score comprises:
calculating an average risk score of the first risk score and the second risk score;
determining a risk grade corresponding to the average risk score according to a corresponding relation between preset risk scores and risk grades;
and generating a risk score report according to a preset risk score report template and the risk level.
7. The method of any one of claims 1-6, wherein after said determining the risk level to which the average risk score corresponds, the method further comprises:
when the risk level is a first level, sending a risk investigation mail to a supervision department; or
When the first risk score is larger than a preset first risk score threshold value, sending a first risk warning mail to the target enterprise; or
And when the second risk score is larger than a preset second risk score threshold value, sending a second risk warning mail to the target enterprise.
8. An enterprise-wide financial risk scoring device, the device comprising:
the crawling module is used for crawling the financial data of the target enterprise;
the determining module is used for determining the hit amount of the financial data in a preset keyword library;
the calculating module is used for calculating a first risk score of the target enterprise according to the hit amount;
the acquisition module is used for acquiring basic data of the target enterprise;
the input module is used for inputting the basic data into a pre-trained financial risk recognition model to obtain a second risk score of the target enterprise;
and the generating module is used for generating a risk score report according to the first risk score and the second risk score.
9. A computer device comprising a processor configured to implement the enterprise-wide financial risk scoring method of any one of claims 1-7 when executing a computer program stored in a memory.
10. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the enterprise-wide financial risk scoring method as recited in any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910792029.0A CN110689438A (en) | 2019-08-26 | 2019-08-26 | Enterprise financial risk scoring method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910792029.0A CN110689438A (en) | 2019-08-26 | 2019-08-26 | Enterprise financial risk scoring method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110689438A true CN110689438A (en) | 2020-01-14 |
Family
ID=69108713
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910792029.0A Pending CN110689438A (en) | 2019-08-26 | 2019-08-26 | Enterprise financial risk scoring method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110689438A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111383101A (en) * | 2020-03-25 | 2020-07-07 | 深圳前海微众银行股份有限公司 | Post-loan risk monitoring method, device, equipment and computer-readable storage medium |
| CN111402054A (en) * | 2020-03-16 | 2020-07-10 | 中科天玑数据科技股份有限公司 | Risk judgment method and system for equity financing platform |
| CN111652501A (en) * | 2020-05-29 | 2020-09-11 | 泰康保险集团股份有限公司 | Financial product evaluation device and method, electronic device, and storage medium |
| CN111798246A (en) * | 2020-07-16 | 2020-10-20 | 中国工商银行股份有限公司 | Financial risk grade assessment method and device |
| CN112750029A (en) * | 2020-12-30 | 2021-05-04 | 北京知因智慧科技有限公司 | Credit risk prediction method, device, electronic equipment and storage medium |
| CN112907101A (en) * | 2021-03-09 | 2021-06-04 | 山大地纬软件股份有限公司 | Enterprise illegal funding behavior risk early warning method and system |
| CN113129120A (en) * | 2021-04-16 | 2021-07-16 | 建信金融科技有限责任公司 | Financial institution data supervision method and device |
| CN113177700A (en) * | 2021-04-15 | 2021-07-27 | 国任财产保险股份有限公司 | Risk assessment method, system, electronic equipment and storage medium |
| CN113222414A (en) * | 2021-05-14 | 2021-08-06 | 北京百度网讯科技有限公司 | Model stability evaluation method and device, electronic equipment and storage medium |
| CN113298373A (en) * | 2021-05-20 | 2021-08-24 | 中国建设银行股份有限公司 | Financial risk assessment method, device, storage medium and equipment |
| CN113313615A (en) * | 2021-06-23 | 2021-08-27 | 北京鼎泰智源科技有限公司 | Method and device for quantitatively grading and grading enterprise judicial risks |
| CN113344695A (en) * | 2021-06-21 | 2021-09-03 | 支付宝(杭州)信息技术有限公司 | Elastic wind control method, device, equipment and readable medium |
| CN113705909A (en) * | 2021-08-31 | 2021-11-26 | 平安银行股份有限公司 | Risk level prediction method and device based on prediction model and storage medium |
| CN113986843A (en) * | 2021-11-02 | 2022-01-28 | 青岛海尔工业智能研究院有限公司 | Data risk early warning processing method and device and electronic equipment |
| CN114219277A (en) * | 2021-12-14 | 2022-03-22 | 中国建设银行股份有限公司 | Credit report generation method and system based on crawler and model scoring |
| CN115205044A (en) * | 2022-07-29 | 2022-10-18 | 山东浪潮爱购云链信息科技有限公司 | Supply chain financial risk assessment method, equipment and medium |
| WO2023029758A1 (en) * | 2021-09-01 | 2023-03-09 | 深圳云天励飞技术股份有限公司 | Enterprise economic crime investigation method, system and device |
| CN117649188A (en) * | 2023-11-08 | 2024-03-05 | 广州易云信息技术有限公司 | Digital industry financial platform based on big data |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8180713B1 (en) * | 2007-04-13 | 2012-05-15 | Standard & Poor's Financial Services Llc | System and method for searching and identifying potential financial risks disclosed within a document |
| US20140172751A1 (en) * | 2012-12-15 | 2014-06-19 | Greenwood Research, Llc | Method, system and software for social-financial investment risk avoidance, opportunity identification, and data visualization |
| CN107169632A (en) * | 2017-04-19 | 2017-09-15 | 广东数相智能科技有限公司 | Global media community image analysis method, device and system |
| CN108985583A (en) * | 2018-06-27 | 2018-12-11 | 中国银行股份有限公司 | Finance data risk control method and device based on artificial intelligence |
| CN109492945A (en) * | 2018-12-14 | 2019-03-19 | 深圳壹账通智能科技有限公司 | Business risk identifies monitoring method, device, equipment and storage medium |
| CN109800976A (en) * | 2019-01-07 | 2019-05-24 | 平安科技（深圳）有限公司 | Investment decision methods, device, computer equipment and storage medium |
| CN109829776A (en) * | 2018-12-14 | 2019-05-31 | 平安科技（深圳）有限公司 | Trade company's methods of risk assessment, device, computer equipment and storage medium |
-
2019
- 2019-08-26 CN CN201910792029.0A patent/CN110689438A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8180713B1 (en) * | 2007-04-13 | 2012-05-15 | Standard & Poor's Financial Services Llc | System and method for searching and identifying potential financial risks disclosed within a document |
| US20140172751A1 (en) * | 2012-12-15 | 2014-06-19 | Greenwood Research, Llc | Method, system and software for social-financial investment risk avoidance, opportunity identification, and data visualization |
| CN107169632A (en) * | 2017-04-19 | 2017-09-15 | 广东数相智能科技有限公司 | Global media community image analysis method, device and system |
| CN108985583A (en) * | 2018-06-27 | 2018-12-11 | 中国银行股份有限公司 | Finance data risk control method and device based on artificial intelligence |
| CN109492945A (en) * | 2018-12-14 | 2019-03-19 | 深圳壹账通智能科技有限公司 | Business risk identifies monitoring method, device, equipment and storage medium |
| CN109829776A (en) * | 2018-12-14 | 2019-05-31 | 平安科技（深圳）有限公司 | Trade company's methods of risk assessment, device, computer equipment and storage medium |
| CN109800976A (en) * | 2019-01-07 | 2019-05-24 | 平安科技（深圳）有限公司 | Investment decision methods, device, computer equipment and storage medium |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111402054A (en) * | 2020-03-16 | 2020-07-10 | 中科天玑数据科技股份有限公司 | Risk judgment method and system for equity financing platform |
| CN111383101B (en) * | 2020-03-25 | 2024-03-15 | 深圳前海微众银行股份有限公司 | Post-credit risk monitoring method, post-credit risk monitoring device, post-credit risk monitoring equipment and computer readable storage medium |
| CN111383101A (en) * | 2020-03-25 | 2020-07-07 | 深圳前海微众银行股份有限公司 | Post-loan risk monitoring method, device, equipment and computer-readable storage medium |
| CN111652501B (en) * | 2020-05-29 | 2023-05-05 | 泰康保险集团股份有限公司 | Financial product evaluation device and method, electronic equipment and storage medium |
| CN111652501A (en) * | 2020-05-29 | 2020-09-11 | 泰康保险集团股份有限公司 | Financial product evaluation device and method, electronic device, and storage medium |
| CN111798246A (en) * | 2020-07-16 | 2020-10-20 | 中国工商银行股份有限公司 | Financial risk grade assessment method and device |
| CN112750029A (en) * | 2020-12-30 | 2021-05-04 | 北京知因智慧科技有限公司 | Credit risk prediction method, device, electronic equipment and storage medium |
| CN112907101A (en) * | 2021-03-09 | 2021-06-04 | 山大地纬软件股份有限公司 | Enterprise illegal funding behavior risk early warning method and system |
| CN113177700A (en) * | 2021-04-15 | 2021-07-27 | 国任财产保险股份有限公司 | Risk assessment method, system, electronic equipment and storage medium |
| CN113129120A (en) * | 2021-04-16 | 2021-07-16 | 建信金融科技有限责任公司 | Financial institution data supervision method and device |
| CN113222414B (en) * | 2021-05-14 | 2023-09-29 | 北京百度网讯科技有限公司 | Model stability evaluation method and device, electronic equipment and storage medium |
| CN113222414A (en) * | 2021-05-14 | 2021-08-06 | 北京百度网讯科技有限公司 | Model stability evaluation method and device, electronic equipment and storage medium |
| CN113298373B (en) * | 2021-05-20 | 2024-09-06 | 中国建设银行股份有限公司 | Financial risk assessment method, device, storage medium and equipment |
| CN113298373A (en) * | 2021-05-20 | 2021-08-24 | 中国建设银行股份有限公司 | Financial risk assessment method, device, storage medium and equipment |
| CN113344695A (en) * | 2021-06-21 | 2021-09-03 | 支付宝(杭州)信息技术有限公司 | Elastic wind control method, device, equipment and readable medium |
| CN113313615A (en) * | 2021-06-23 | 2021-08-27 | 北京鼎泰智源科技有限公司 | Method and device for quantitatively grading and grading enterprise judicial risks |
| CN113705909A (en) * | 2021-08-31 | 2021-11-26 | 平安银行股份有限公司 | Risk level prediction method and device based on prediction model and storage medium |
| WO2023029758A1 (en) * | 2021-09-01 | 2023-03-09 | 深圳云天励飞技术股份有限公司 | Enterprise economic crime investigation method, system and device |
| CN113986843A (en) * | 2021-11-02 | 2022-01-28 | 青岛海尔工业智能研究院有限公司 | Data risk early warning processing method and device and electronic equipment |
| CN114219277A (en) * | 2021-12-14 | 2022-03-22 | 中国建设银行股份有限公司 | Credit report generation method and system based on crawler and model scoring |
| CN115205044B (en) * | 2022-07-29 | 2024-02-13 | 山东浪潮爱购云链信息科技有限公司 | Method, equipment and medium for evaluating financial risk of supply chain |
| CN115205044A (en) * | 2022-07-29 | 2022-10-18 | 山东浪潮爱购云链信息科技有限公司 | Supply chain financial risk assessment method, equipment and medium |
| CN117649188A (en) * | 2023-11-08 | 2024-03-05 | 广州易云信息技术有限公司 | Digital industry financial platform based on big data |
| CN117649188B (en) * | 2023-11-08 | 2024-06-11 | 广州易云信息技术有限公司 | Digital industry financial platform based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110689438A (en) | Enterprise financial risk scoring method and device, computer equipment and storage medium | |
| CN107945024B (en) | Method for identifying internet financial loan enterprise operation abnormity, terminal equipment and storage medium | |
| US10783457B2 (en) | Method for determining risk preference of user, information recommendation method, and apparatus | |
| US10614073B2 (en) | System and method for using data incident based modeling and prediction | |
| CN109711955B (en) | Poor evaluation early warning method and system based on current order and blacklist base establishment method | |
| CN112668859A (en) | Big data based customer risk rating method, device, equipment and storage medium | |
| CN113989019A (en) | Method, device, equipment and storage medium for identifying risks | |
| CN111708883A (en) | Credit credit limit determination method and device based on machine learning and equipment fingerprint | |
| CN112200402B (en) | Risk quantification method, device and equipment based on risk portrait | |
| CN111754241A (en) | User behavior perception method, device, equipment and medium | |
| CN111179051A (en) | Financial target customer determination method and device and electronic equipment | |
| CN117714722A (en) | Data analysis method and system for live shopping of electronic commerce | |
| CN109636627B (en) | Insurance product management method, device, medium and electronic equipment based on block chain | |
| CN117575595A (en) | Payment risk identification method, device, computer equipment and storage medium | |
| CN116664306A (en) | Intelligent recommendation method and device for wind control rules, electronic equipment and medium | |
| CN115550077A (en) | Real-time online detection danger source data and trigger automatic defense method | |
| CN115809930A (en) | Anti-fraud analysis method, device, equipment and medium based on data fusion matching | |
| CN115965464A (en) | Empty shell enterprise identification method and device, storage medium and electronic device | |
| CN109816234A (en) | Service access method, service access device, electronic equipment and storage medium | |
| CN115408672A (en) | Deep early warning method, device, equipment and storage medium for blacklist | |
| CN115659351A (en) | Information security analysis method, system and equipment based on big data office | |
| CN115564591A (en) | Financing product determination method and related equipment | |
| Pavía et al. | Is the cardholder an efficient alarm system to detect credit card incidents? | |
| Knuth | Fraud prevention in the B2C e-Commerce mail order business: a framework for an economic perspective on data mining | |
| CN112712270A (en) | Information processing method, device, 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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200114 |