CN107909274A - Enterprise investment methods of risk assessment, device and storage medium - Google Patents
Enterprise investment methods of risk assessment, device and storage medium Download PDFInfo
- Publication number
- CN107909274A CN107909274A CN201711141730.3A CN201711141730A CN107909274A CN 107909274 A CN107909274 A CN 107909274A CN 201711141730 A CN201711141730 A CN 201711141730A CN 107909274 A CN107909274 A CN 107909274A
- Authority
- CN
- China
- Prior art keywords
- business entity
- risk
- feature vector
- entity
- enterprise
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—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
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention proposes a kind of enterprise investment methods of risk assessment, including：Crawl the relevant news corpus of investment objective business entity, extraction other entities associated with the business entity；Incidence relation between entitled node, the business entity and other entities builds relational network as side；The vector representation of the business entity is calculated, generates the first eigenvector of the business entity；According to the first preset rules, the internal information of the business entity is quantified, generation second feature vector；According to the second preset rules, the external information of the business entity is quantified, generation third feature vector；And the first eigenvector, second feature vector and third feature vector input business risk assessment models, output are obtained into the corresponding risk label of the business entity.The present invention also proposes a kind of electronic device and computer-readable recording medium.Using the present invention, the information revealed in news corpus is analyzed, the risk of investment objective enterprise can be assessed.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of enterprise investment methods of risk assessment, electronic device and
Computer-readable recording medium.
Background technology
At present, in observation investment target angle, related tool on the market is all relatively easy, largely rests on tradition
Financial analysis, statement analysis aspect, lack to the association measurement of upstream and downstream, affiliated party and market focus, policy clue
Consider.
With the popularization of network, each news website has thousands of bar news daily, and news can real-time update.Such as
Fruit can extract the big data that investment objective enterprise is associated, such as enterprises situation from the news corpus of magnanimity：Manage,
Finance, senior executive, recruitment, network upgrade frequency etc., enterprise external situation, such as affiliated company's situation such as upstream and downstream, client etc., are commented
These information are formed relational network, analysis, assessment by the information such as grading of the level mechanism to the enterprise, news media's relevant report
The risk factor of investment objective enterprise, so that can investor can consider receive the risk and decide whether to throw according to risk factor
Provide the enterprise.Therefore, the information that investment objective enterprise is associated how is extracted from news corpus, and utilizes the information into sector-style
Danger assessment is urgent problem.
The content of the invention
The present invention provides a kind of enterprise investment methods of risk assessment, electronic device and computer-readable recording medium, it is led
Syllabus is analyzed in the information revealed in by news corpus, the risk of assessment investment objective enterprise.
To achieve the above object, the present invention provides a kind of electronic device, which includes：Memory, processor, institute
Stating memory storage has the enterprise investment risk assessment procedures that can be run on the processor, which is held by the processor
Following steps are realized during row：
A1, the relevant news corpus of business entity for crawling risk to be assessed, pre-process news corpus, from process
Other entities associated with the business entity are extracted in pretreated news corpus；
A2, the incidence relation between entitled node, the business entity and other entities build the business entity as side
With the relational network between other entities；
A3, the vector representation for calculating according to relational network the business entity, generate the first eigenvector of the business entity；
A4, according to the first preset rules, the internal information of the business entity is quantified, generation second feature vector；
A5, the external information for extracting from news corpus the business entity, according to the second preset rules, to the business entity
External information quantified, generate the business entity third feature vector；And
A6, by the first eigenvector, second feature vector and third feature vector input predetermined enterprise's wind
Dangerous assessment models, output obtain the corresponding risk label of the business entity.
In addition, to achieve the above object, the present invention also provides a kind of enterprise investment methods of risk assessment, this method includes：
S1, the relevant news corpus of business entity for crawling risk to be assessed, pre-process news corpus, from process
Other entities associated with the business entity are extracted in pretreated news corpus；
S2, the incidence relation between entitled node, the business entity and other entities build the business entity as side
With the relational network between other entities；
S3, the vector representation for calculating according to relational network the business entity, generate the first eigenvector of the business entity；
S4, according to the first preset rules, the internal information of the business entity is quantified, generation second feature vector；
S5, the external information for extracting from news corpus the business entity, according to the second preset rules, to the business entity
External information quantified, generate the business entity third feature vector；And
S6, by the first eigenvector, second feature vector and third feature vector input predetermined enterprise's wind
Dangerous assessment models, output obtain the corresponding risk label of the business entity.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer-readable recording medium
Storage medium is stored with enterprise investment risk assessment procedures, which realizes enterprise investment as described above when being executed by processor
The arbitrary steps of methods of risk assessment.
Enterprise investment methods of risk assessment, electronic device and computer-readable recording medium proposed by the present invention, by from
Relation, the internal information of business entity and the external information that business entity is associated between entity are understood in news corpus, point
Do not obtain the first eigenvector, second feature vector and third feature vector of the business entity, using risk evaluation model and
The first eigenvector, second feature vector and third feature vector, carry out risk assessment to investing the business entity, are easy to
Investor catches market investment chance, look-ahead investment risk.
Brief description of the drawings
Fig. 1 is the application environment schematic diagram of enterprise investment methods of risk assessment preferred embodiment of the present invention；
Relational network figures of the Fig. 2 between business entity A and other associated entities；
Fig. 3 is the vector representation of business entity A；
Fig. 4 is the module diagram of enterprise investment risk assessment procedures in Fig. 1；
Fig. 5 is the flow chart of enterprise investment methods of risk assessment preferred embodiment of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The present invention provides a kind of enterprise investment methods of risk assessment, and this method is applied to a kind of electronic device 1.With reference to Fig. 1
It is shown, it is the application environment schematic diagram of enterprise investment methods of risk assessment preferred embodiment of the present invention.
In the present embodiment, the electronic device 1 can be PC (Personal Computer, PC), can also
It is the terminal devices such as smart mobile phone, tablet computer, E-book reader, pocket computer.
The electronic device 1 includes memory 11, processor 12, communication bus 13, and network interface 14.
Wherein, memory 11 includes at least a type of readable storage medium storing program for executing, the readable storage medium storing program for executing include flash memory,
Hard disk, multimedia card, card-type memory (for example, SD or DX memories etc.), magnetic storage, disk, CD etc..Memory 11
Can be the internal storage unit of the electronic device 1 in certain embodiments, such as the hard disk of the electronic device 1.Memory
11 can also be what is be equipped with the External memory equipment of the electronic device 1, such as the electronic device 1 in further embodiments
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, dodges
Deposit card (Flash Card) etc..Further, memory 11 can also both include the internal storage unit of the electronic device 1 or wrap
Include External memory equipment.Memory 11 can be not only used for the application software and Various types of data that storage is installed on the electronic device 1,
Such as enterprise investment risk assessment procedures 10 etc., it can be also used for temporarily storing the data that has exported or will export.
Processor 12 can be in certain embodiments a central processing unit (Central Processing Unit,
CPU), controller, microcontroller, microprocessor or other data processing chips, for the program stored in run memory 11
Code or processing data, such as enterprise investment risk assessment procedures 10 etc..
Communication bus 13 is used for realization the connection communication between these components.
Network interface 14 can optionally include standard wireline interface and wireless interface (such as WI-FI interfaces), be commonly used in
Communication connection is established between the device and other electronic equipments.
Fig. 1 illustrate only the electronic device 1 with component 11-14, it should be understood that being not required for implementing all show
The component gone out, what can be substituted implements more or less components.
Alternatively, which can also include user interface, user interface can include display (Display),
Input unit such as keyboard (Keyboard), optional user interface can also include standard wireline interface and wireless interface.
Alternatively, in certain embodiments, display can be that light-emitting diode display, liquid crystal display, touch control type LCD are shown
Device and OLED (Organic Light-Emitting Diode, Organic Light Emitting Diode) touch device etc..Wherein, display
Display screen or display unit are properly termed as, for showing the information that handles in the electronic apparatus 1 and visual for showing
User interface.
In the device embodiment shown in Fig. 1, enterprise investment risk assessment procedures 10 are stored with memory 11；Processor
Following steps are realized during the enterprise investment risk assessment procedures 10 stored in 12 execution memories 11：
A1, the relevant news corpus of business entity for crawling risk to be assessed, pre-process news corpus, from process
Other entities associated with the business entity are extracted in pretreated news corpus；
A2, the incidence relation between entitled node, the business entity and other entities build the business entity as side
With the relational network between other entities；
A3, the vector representation for calculating according to relational network the business entity, generate the first eigenvector of the business entity；
A4, according to the first preset rules, the internal information of the business entity is quantified, generation second feature vector；
A5, the external information for extracting from news corpus the business entity, according to the second preset rules, to the business entity
External information quantified, generate the business entity third feature vector；And
A6, by the first eigenvector, second feature vector and third feature vector input predetermined enterprise's wind
Dangerous assessment models, output obtain the corresponding risk label of the business entity.
Language material is related to multiple and different fields, and the present embodiment carries out the concrete scheme of the present invention by taking news corpus as an example
Illustrate, but be not limited only to News Field.As investor it should be understood that news at present, is associated with obtaining investment objective enterprise
Internal data and external data when, Internet news is crawled from internet using web crawlers, for example, being crawled newly by reptile
The Internet news of wave, Baidu, Tencent etc..It is understood that business circumstance of each enterprise within the different periods is not
Equally, therefore, in order to make investor more accurately understand the information of investment objective enterprise, the network on time dimension to crawling
News is filtered, and is set preset time section, the Internet news of the period is only crawled, for example, only crawling the net of nearly half a year
Network news.Since the source of news corpus has diversity, Format Type is relatively more in language material, for ease of to language material into
Row subsequent treatment, need to pre-process news corpus, obtain news corpus text data, form news corpus text set.
In other embodiments, the uniform format of news corpus can be text formatting by the pretreatment, from news language
Advertisement noise is removed in material and filters the one or more in dirty word and sensitive word.It is being text by the uniform format of news corpus
During form, the information filtering that current techniques be able to wouldn't can be converted to text formatting is fallen.
Next, using the method for above-mentioned participle, according to predetermined enterprise name storehouse, from by pretreated new
Hear in language material and extract all enterprise names, then according to the association of the business entity (i.e. investment objective enterprise) of risk to be assessed
Business data, filters out other entities associated with the business entity of risk to be assessed, and by business entity and other entities
It is built into relational network.Wherein, affiliated enterprise's data can be obtained by third party's data.It is understood that from new
It is possible many to hear other entities that extraction is associated with business entity in language material, to all structure is closing by all associated entities
It is that network is unreasonable, therefore, before relational network is built, other entities associated with business entity extracted was carried out
Screen selects, and specifically, is included by other entities associated with business entity retained after filtering screening step：The enterprise is real
The shareholder company of body, have other entities that money occurs and comes and goes, supplier, client, credit to comment structure etc. with business entity.
In the present embodiment, it is associated with business entity A to being extracted from news corpus by taking business entity A as an example
After other entities are screened, it is assumed that other entities of reservation are respectively B1, B2, B3, wherein, B1 is gives business entity A to carry out
The rating organization of credit rating, it is recognized that B1 to the credit rating of business entity A is BBB, B2 from history ratings data
To provide the supplier of raw material or kinds of goods to business entity A, business entity A is enterprise for 300,000, B3 to the amount owed of B2
The client of entity A, business entity A once broke a contract B3 2 times.Using business entity A, B1, B2, B3 as node, with B1, B2, B3 and A
Incidence relation is side, builds the relational network figure between business entity as shown in Figure 2 and other entities.
Then, according to above-mentioned relation network, the vector representation of business entity A is calculated, the present embodiment is using Skip-
Gram methods because in relational network the vector representation of business entity A entity B 1, B2, B3 associated there vector representation
Between there is administrative relationships.Training for business entity's title vector, Skip-Gram methods are gone using current enterprise entity
Predict surrounding entity, as shown in Figure 3.An1 in Fig. 3, An2, An3, An4 are that do not have sequential, are represented as business entity A's
Adjacent entities.It is similar with the method using Skip-Gram training term vectors, a fixed prediction length L is set, to predict enterprise
L adjacent entities around industry entity A, if truth adjacent entities, not as good as L, output is NULL.In this way, can
To obtain the vector representation embedding (E1) of business entity A, embedding (E2) ..., using the vector representation as enterprise
The first eigenvector of entity A.
It is understood that it is to be understood that the risk of investment enterprise's entity A, it is necessary to understand finance, operation of business entity A etc.
The information of aspect, therefore, it is necessary to the internal information in view of business entity A, wherein, internal information includes the warp of business entity A
The information such as battalion, finance, recruitment, network upgrade frequency, which part information is digital information, such as financial information is including in enterprise
One annual net profit, stock yield etc..According to rule by each reference factor in enterprises information be converted to numeral into
Row quantifies, for example, the numerical value in financial information can be converted into characteristic value, for example in the present embodiment, net profit is 300,000 yuan,
It is corresponding characteristic value to take 30, and network upgrade frequency, nearest 1 year the number of recruits are also numerical value, can also be by default conversion
Rule is corresponding numerical value.In other embodiments, other numerical value can also be converted to by 300,000 yuan by default conversion proportion.
After each reference factor in the internal information of business entity A is quantified, the second feature vector of business entity A is generated.
It should be noted that the level of managerial competence of business entity A, in addition to oneself factor, extraneous factor is also most important,
Therefore also need to consider the external information of business entity A, wherein, external information includes the upstream-downstream relationship of business entity A, such as
Whether supplier, client, the enterprise produced promise breaking, debt to other entities of upstream-downstream relationship, if any promise breaking number, owe
The money cycle is respectively how many.In addition, the external information of business entity A further includes grading (grading of the rating organization to business entity A
Rank 3A, 2A represent excellent, and A represents good, and BBB represents general etc.), news media are to the positive/negative report of business entity A
Road etc..Then, each reference factor in enterprises information is converted to numeral according to rule to be quantified, for example, at this
In embodiment, promise breaking number can be quantified as 3 numerical value, no promise breaking -0, slight promise breaking -1, severe promise breaking -2；Debt can be measured
2 numerical value are turned to, there is debt -1 in no debt -0；Grading can be quantified as multiple numerical value, rating level 3A-6, rating level 2A-
5, rating level A-4, rating level BBB-3, rating level BB-2, rating level B-1.According to the concrete condition of business entity A,
Its external information is quantified, number -1 of breaking a contract, debt -1, grading -3, according to the information generation business entity A's after quantifying
Third feature vector.
So far, the internal information and external information of other entities associated with business entity A, business entity A have been understood
Afterwards, next risk assessment can be carried out to investment enterprise's entity A.By the first of the title of business entity A and business entity A
Feature vector, second feature vector and third feature vector input in predetermined risk evaluation model and carry out risk assessment,
And export risk evaluation result.Wherein, the training step of the predetermined risk evaluation model includes：Utilize above-mentioned A1-
A5 steps, obtain the first eigenvector, second feature vector and third feature vector of a large amount of business entities, its specific embodiment party
Formula is consistent with above-mentioned steps, and which is not described herein again.Then risk label is marked for each business entity, to the enterprise of " devoid of risk "
Entity, mark risk label are 0, and to the business entity of " excessive risk ", mark risk label is 1, then by each business entity
First eigenvector, second feature vector, third feature is vectorial and corresponding risk label is as sample data.From sample number
The first eigenvector of the business entity for randomly selecting the first ratio (such as 60%) in, second feature vector, the 3rd spy
Sign vector and the corresponding risk label of business entity of first ratio (such as 60%) are as training set, from remaining sample set
In the business entity for randomly selecting the second ratio (such as 50%) first eigenvector, second feature vector, third feature
The corresponding risk label of the business entity of vector and second ratio (such as 50%) collects as verification, that is to say, that extracts sample
20% sample data of notebook data collects as verification；Support vector machines is trained using described 50% sample data,
Determine the model parameter of risk evaluation model, the associated entity, internal information, external information and investment for determining business entity should
Relation between the risk of business entity；The accuracy of the risk evaluation model is tested using 20% sample data
Card, if accuracy rate is more than or equal to default accuracy rate (such as 90%), training terminates, if alternatively, accuracy rate is less than default
Accuracy rate (such as 90%), then increase sample size and re-execute training step.
The first eigenvector of business entity A, second feature vector and third feature vector are inputted into the risk assessment
After model, if model output result is 0, then it represents that the basic devoid of risk of investment enterprise's entity A, if model output result is 1, table
Show that investment enterprise's entity A has greater risk.
The electronic device 1 that above-described embodiment proposes, by understanding relation, the enterprise that business entity is associated between entity
The internal information and external information of entity, respectively obtain first eigenvector, the second feature vector and the 3rd of the business entity
Feature vector, using the risk evaluation model and first eigenvector, second feature vector and third feature vector, to investment
The business entity carries out risk assessment, and market investment chance is caught easy to investor.
Alternatively, in other examples, enterprise investment risk assessment procedures 10 can also be divided into one or
Multiple modules, one or more module are stored in memory 11, and by one or more processors (the present embodiment for
Manage device 12) it is performed, to complete the present invention, the module alleged by the present invention is the series of computation machine for referring to complete specific function
Programmed instruction section.It is the module diagram of enterprise investment risk assessment procedures 10 in Fig. 1, in this reality for example, referring to shown in Fig. 4
Apply in example, which can be divided into extraction module 110, structure module 120, the first computing module 130, the second computing module
140th, the 3rd computing module 150 and evaluation module 160, the functions or operations step that the module 110-160 is realized with
It is similar above, no longer it is described in detail herein, exemplarily, such as wherein：
Extraction module 110, the relevant news corpus of business entity for crawling risk to be assessed, carries out news corpus
Pretreatment, from by extracting other entities associated with the business entity in pretreated news corpus；
Module 120 is built, for the incidence relation between entitled node, the business entity and other entities as side,
Build the relational network between the business entity and other entities；
First computing module 130, for calculating the vector representation of the business entity according to relational network, generates enterprise reality
The first eigenvector of body；
Second computing module 140, for according to the first preset rules, quantifying to the internal information of the business entity,
Generate second feature vector；
3rd computing module 150, it is default according to second for extracting the external information of the business entity from news corpus
Rule, quantifies the external information of the business entity, generates the third feature vector of the business entity；And
Evaluation module 160, for the first eigenvector, second feature vector and third feature vector input is advance
Definite business risk assessment models, output obtain the corresponding risk label of the business entity.
In addition, the present invention also provides a kind of enterprise investment methods of risk assessment.With reference to shown in Fig. 5, thrown for enterprise of the present invention
Provide the flow chart of methods of risk assessment preferred embodiment.This method can be performed by device, the device can by software and/
Or hardware realization.
In the present embodiment, enterprise investment methods of risk assessment includes：
S1, the relevant news corpus of business entity for crawling risk to be assessed, pre-process news corpus, from process
Other entities associated with the business entity are extracted in pretreated news corpus；
S2, the incidence relation between entitled node, the business entity and other entities build the business entity as side
With the relational network between other entities；
S3, the vector representation for calculating according to relational network the business entity, generate the first eigenvector of the business entity；
S4, according to the first preset rules, the internal information of the business entity is quantified, generation second feature vector；
S5, the external information for extracting from news corpus the business entity, according to the second preset rules, to the business entity
External information quantified, generate the business entity third feature vector；And
S6, by the first eigenvector, second feature vector and third feature vector input predetermined enterprise's wind
Dangerous assessment models, output obtain the corresponding risk label of the business entity.
Language material is related to multiple and different fields, and the present embodiment carries out the concrete scheme of the present invention by taking news corpus as an example
Illustrate, but be not limited only to News Field.As investor it should be understood that news at present, is associated with obtaining investment objective enterprise
Internal data and external data when, Internet news is crawled from internet using web crawlers, for example, being crawled newly by reptile
The Internet news of wave, Baidu, Tencent etc..It is understood that business circumstance of each enterprise within the different periods is not
Equally, therefore, in order to make investor more accurately understand the information of investment objective enterprise, the network on time dimension to crawling
News is filtered, and is set preset time section, the Internet news of the period is only crawled, for example, only crawling the net of nearly half a year
Network news.Since the source of news corpus has diversity, Format Type is relatively more in language material, for ease of to language material into
Row subsequent treatment, need to pre-process news corpus, obtain news corpus text data, form news corpus text set.
In other embodiments, the uniform format of news corpus can be text formatting by the pretreatment, from news language
Advertisement noise is removed in material and filters the one or more in dirty word and sensitive word.It is being text by the uniform format of news corpus
During form, the information filtering that current techniques be able to wouldn't can be converted to text formatting is fallen.
Next, using the method for above-mentioned participle, according to predetermined enterprise name storehouse, from by pretreated new
Hear in language material and extract all enterprise names, then according to the association of the business entity (i.e. investment objective enterprise) of risk to be assessed
Business data, filters out other entities associated with the business entity of risk to be assessed, and by business entity and other entities
It is built into relational network.Wherein, affiliated enterprise's data can be obtained by third party's data.It is understood that from new
It is possible many to hear other entities that extraction is associated with business entity in language material, to all structure is closing by all associated entities
It is that network is unreasonable, therefore, before relational network is built, other entities associated with business entity extracted was carried out
Screen selects, and specifically, is included by other entities associated with business entity retained after filtering screening step：The enterprise is real
The shareholder company of body, have other entities that money occurs and comes and goes, supplier, client, credit to comment structure etc. with business entity.
In the present embodiment, it is associated with business entity A to being extracted from news corpus by taking business entity A as an example
After other entities are screened, it is assumed that other entities of reservation are respectively B1, B2, B3, wherein, B1 is gives business entity A to carry out
The rating organization of credit rating, it is recognized that B1 to the credit rating of business entity A is BBB, B2 from history ratings data
To provide the supplier of raw material or kinds of goods to business entity A, business entity A is enterprise for 300,000, B3 to the amount owed of B2
The client of entity A, business entity A once broke a contract B3 2 times.Using business entity A, B1, B2, B3 as node, with B1, B2, B3 and A
Incidence relation is side, builds the relational network figure between business entity as shown in Figure 2 and other entities.
Then, according to above-mentioned relation network, the vector representation of business entity A is calculated, the present embodiment is using Skip-
Gram methods because in relational network the vector representation of business entity A entity B 1, B2, B3 associated there vector representation
Between there is administrative relationships.Training for business entity's title vector, Skip-Gram methods are gone using current enterprise entity
Predict surrounding entity, as shown in Figure 3.An1 in Fig. 3, An2, An3, An4 are that do not have sequential, are represented as business entity A's
Adjacent entities.It is similar with the method using Skip-Gram training term vectors, a fixed prediction length L is set, to predict enterprise
L adjacent entities around industry entity A, if truth adjacent entities, not as good as L, output is NULL.In this way, can
To obtain the vector representation embedding (E1) of business entity A, embedding (E2) ..., using the vector representation as enterprise
The first eigenvector of entity A.
It is understood that it is to be understood that the risk of investment enterprise's entity A, it is necessary to understand finance, operation of business entity A etc.
The information of aspect, therefore, it is necessary to the internal information in view of business entity A, wherein, internal information includes the warp of business entity A
The information such as battalion, finance, recruitment, network upgrade frequency, which part information is digital information, such as financial information is including in enterprise
One annual net profit, stock yield etc..According to rule by each reference factor in enterprises information be converted to numeral into
Row quantifies, for example, the numerical value in financial information can be converted into characteristic value, for example in the present embodiment, net profit is 300,000 yuan,
It is corresponding characteristic value to take 30, and network upgrade frequency, nearest 1 year the number of recruits are also numerical value, can also be by default conversion
Rule is corresponding numerical value.In other embodiments, other numerical value can also be converted to by 300,000 yuan by default conversion proportion.
After each reference factor in the internal information of business entity A is quantified, the second feature vector of business entity A is generated.
It should be noted that the level of managerial competence of business entity A, in addition to oneself factor, extraneous factor is also most important,
Therefore also need to consider the external information of business entity A, wherein, external information includes the upstream-downstream relationship of business entity A, such as
Whether supplier, client, the enterprise produced promise breaking, debt to other entities of upstream-downstream relationship, if any promise breaking number, owe
The money cycle is respectively how many.In addition, the external information of business entity A further includes grading (grading of the rating organization to business entity A
Rank 3A, 2A represent excellent, and A represents good, and BBB represents general etc.), news media are to the positive/negative report of business entity A
Road etc..Then, each reference factor in enterprises information is converted to numeral according to rule to be quantified, for example, at this
In embodiment, promise breaking number can be quantified as 3 numerical value, no promise breaking -0, slight promise breaking -1, severe promise breaking -2；Debt can be measured
2 numerical value are turned to, there is debt -1 in no debt -0；Grading can be quantified as multiple numerical value, rating level 3A-6, rating level 2A-
5, rating level A-4, rating level BBB-3, rating level BB-2, rating level B-1.According to the concrete condition of business entity A,
Its external information is quantified, number -1 of breaking a contract, debt -1, grading -3, according to the information generation business entity A's after quantifying
Third feature vector.
So far, the internal information and external information of other entities associated with business entity A, business entity A have been understood
Afterwards, next risk assessment can be carried out to investment enterprise's entity A.By the first of the title of business entity A and business entity A
Feature vector, second feature vector and third feature vector input in predetermined risk evaluation model and carry out risk assessment,
And export risk evaluation result.Wherein, the training step of the predetermined risk evaluation model includes：Utilize above-mentioned S1-
S5 steps, obtain the first eigenvector, second feature vector and third feature vector of a large amount of business entities, its specific embodiment party
Formula is consistent with above-mentioned steps, and which is not described herein again.Then risk label is marked for each business entity, to the enterprise of " devoid of risk "
Entity, mark risk label are 0, and to the business entity of " excessive risk ", mark risk label is 1, then by each business entity
First eigenvector, second feature vector, third feature is vectorial and corresponding risk label is as sample data.From sample number
The first eigenvector of the business entity for randomly selecting the first ratio (such as 60%) in, second feature vector, the 3rd spy
Sign vector and the corresponding risk label of business entity of first ratio (such as 60%) are as training set, from remaining sample set
In the business entity for randomly selecting the second ratio (such as 50%) first eigenvector, second feature vector, third feature
The corresponding risk label of the business entity of vector and second ratio (such as 50%) collects as verification, that is to say, that extracts sample
20% sample data of notebook data collects as verification；Support vector machines is trained using described 50% sample data,
Determine the model parameter of risk evaluation model, the associated entity, internal information, external information and investment for determining business entity should
Relation between the risk of business entity；The accuracy of the risk evaluation model is tested using 20% sample data
Card, if accuracy rate is more than or equal to default accuracy rate (such as 90%), training terminates, if alternatively, accuracy rate is less than default
Accuracy rate (such as 90%), then increase sample size and re-execute training step.
The first eigenvector of business entity A, second feature vector and third feature vector are inputted into the risk assessment
After model, if model output result is 0, then it represents that the basic devoid of risk of investment enterprise's entity A, if model output result is 1, table
Show that investment enterprise's entity A has greater risk.
The enterprise investment methods of risk assessment that above-described embodiment proposes, is associated between entity by understanding business entity
Relation, the internal information of business entity and external information, respectively obtain first eigenvector, the second feature of the business entity
Vector and third feature vector, utilize the risk evaluation model and first eigenvector, second feature vector and third feature
Vector, carries out risk assessment to investing the business entity, market investment chance is caught easy to investor.
In addition, the embodiment of the present invention also proposes a kind of computer-readable recording medium, the computer-readable recording medium
Enterprise investment risk assessment procedures are stored with, following behaviour is realized when the enterprise investment risk assessment procedures are executed by processor
Make：
A1, the relevant news corpus of business entity for crawling risk to be assessed, pre-process news corpus, from process
Other entities associated with the business entity are extracted in pretreated news corpus；
A2, the incidence relation between entitled node, the business entity and other entities build the business entity as side
With the relational network between other entities；
A3, the vector representation for calculating according to relational network the business entity, generate the first eigenvector of the business entity；
A4, according to the first preset rules, the internal information of the business entity is quantified, generation second feature vector；
A5, the external information for extracting from news corpus the business entity, according to the second preset rules, to the business entity
External information quantified, generate the business entity third feature vector；And
A6, by the first eigenvector, second feature vector and third feature vector input predetermined enterprise's wind
Dangerous assessment models, output obtain the corresponding risk label of the business entity.
Computer-readable recording medium embodiment of the present invention and above-mentioned enterprise investment methods of risk assessment and electronics
Each embodiment of device is essentially identical, does not make tired state herein.
It should be noted that the embodiments of the present invention are for illustration only, the quality of embodiment is not represented.And
Term " comprising " herein, "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that bag
To include process, device, article or the method for a series of elements not only include those key elements, but also including being not explicitly listed
Other element, or further include as this process, device, article or the intrinsic key element of method.Do not limiting more
In the case of, the key element that is limited by sentence "including a ...", it is not excluded that in the process including the key element, device, article
Or also there are other identical element in method.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme substantially in other words does the prior art
Going out the part of contribution can be embodied in the form of software product, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disc, CD), including some instructions use so that a station terminal equipment (can be mobile phone,
Computer, server, or network equipment etc.) perform method described in each embodiment of the present invention.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow shift that bright specification and accompanying drawing content are made, is directly or indirectly used in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
- A kind of 1. enterprise investment methods of risk assessment, applied to electronic device, it is characterised in that this method includes：S1, the relevant news corpus of business entity for crawling risk to be assessed, pre-process news corpus, from passing through in advance Other entities associated with the business entity are extracted in news corpus after reason；S2, the incidence relation between entitled node, the business entity and other entities build the business entity and its as side Relational network between his entity；S3, the vector representation for calculating according to relational network the business entity, generate the first eigenvector of the business entity；S4, according to the first preset rules, the internal information of the business entity is quantified, generation second feature vector；S5, the external information for extracting from news corpus the business entity, according to the second preset rules, to the outer of the business entity Portion's information is quantified, and generates the third feature vector of the business entity；AndS6, input predetermined business risk by the first eigenvector, second feature vector and third feature vector and comment Estimate model, output obtains the corresponding risk label of the business entity.
- 2. enterprise investment methods of risk assessment as claimed in claim 1, it is characterised in that first preset rules are：Will Each reference factor is converted to the rule of digital quantization in the internal information of the business entity.
- 3. enterprise investment methods of risk assessment as claimed in claim 1 or 2, it is characterised in that second preset rules are： Each reference factor in the external information of the business entity is converted to the rule of digital quantization.
- 4. enterprise investment methods of risk assessment as claimed in claim 3, it is characterised in that the predetermined business risk The training step of assessment models includes：The relevant news corpus of multiple business entities is crawled, other associated with the plurality of business entity are extracted from news corpus Entity, the incidence relation between entitled node, entity are built between the plurality of business entity and other entities respectively as side Relational network；Calculate the vector representation of the multiple business entity respectively according to relational network, generate the first of the multiple business entity Feature vector；According to the first preset rules, the internal information of the multiple business entity is quantified, generation second feature vector；The external information of the business entity is extracted from news corpus, according to the second preset rules, to the outside of the business entity Information is quantified, and generates the third feature vector of the business entity；Recorded according to historical risk assessments, risk label is marked to the multiple business entity respectively, by multiple business entities First eigenvector, second feature vector, third feature vector and risk label are as sample data；The sample data of the first ratio is extracted as training set, the sample data for extracting the second ratio collects as verification；Support vector machines is trained using the training set, obtains the risk evaluation model；AndVerified using the accuracy of risk evaluation model described in the verification set pair, preset if accuracy rate is more than or equal to Accuracy rate, then training terminate, if alternatively, accuracy rate is less than default accuracy rate, increase sample size simultaneously re-executes trained step Suddenly.
- 5. enterprise investment methods of risk assessment as claimed in claim 1, it is characterised in that bag is pre-processed in the step S1 Include：It is text formatting by the uniform format of news corpus, advertisement noise is removed from news corpus.
- 6. a kind of electronic device, it is characterised in that the device includes：Memory, processor, the memory storage has can be in institute The enterprise investment risk assessment procedures run on processor are stated, which realizes following steps when being performed by the processor：A1, the relevant news corpus of business entity for crawling risk to be assessed, pre-process news corpus, from passing through in advance Other entities associated with the business entity are extracted in news corpus after reason；A2, the incidence relation between entitled node, the business entity and other entities build the business entity and its as side Relational network between his entity；A3, the vector representation for calculating according to relational network the business entity, generate the first eigenvector of the business entity；A4, according to the first preset rules, the internal information of the business entity is quantified, generation second feature vector；A5, the external information for extracting from news corpus the business entity, according to the second preset rules, to the outer of the business entity Portion's information is quantified, and generates the third feature vector of the business entity；AndA6, input predetermined business risk by the first eigenvector, second feature vector and third feature vector and comment Estimate model, output obtains the corresponding risk label of the business entity.
- 7. enterprise investment risk assessment device according to claim 6, it is characterised in that first preset rules are： Each reference factor in the internal information of the business entity is converted to the rule of digital quantization.
- 8. the enterprise investment risk assessment device according to claim 6 or 7, it is characterised in that second preset rules For：Each reference factor in the external information of the business entity is converted to the rule of digital quantization.
- 9. enterprise investment risk assessment device according to claim 6, it is characterised in that bag is pre-processed in the step A1 Include：It is text formatting by the uniform format of news corpus, advertisement noise is removed from news corpus.
- 10. a kind of computer-readable recording medium, it is characterised in that enterprise's throwing is stored with the computer-readable recording medium Risk assessment procedures are provided, the enterprise investment wind as any one of claim 1 to 5 is realized when which is executed by processor The step of dangerous appraisal procedure.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711141730.3A CN107909274B (en) | 2017-11-17 | 2017-11-17 | Enterprise investment risk assessment method and device and storage medium |
| PCT/CN2018/076169 WO2019095572A1 (en) | 2017-11-17 | 2018-02-10 | Enterprise investment risk assessment method, device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711141730.3A CN107909274B (en) | 2017-11-17 | 2017-11-17 | Enterprise investment risk assessment method and device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107909274A true CN107909274A (en) | 2018-04-13 |
| CN107909274B CN107909274B (en) | 2023-02-28 |
Family
ID=61845968
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711141730.3A Active CN107909274B (en) | 2017-11-17 | 2017-11-17 | Enterprise investment risk assessment method and device and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107909274B (en) |
| WO (1) | WO2019095572A1 (en) |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108985638A (en) * | 2018-07-25 | 2018-12-11 | 腾讯科技（深圳）有限公司 | A kind of customer investment methods of risk assessment and device and storage medium |
| CN109087163A (en) * | 2018-07-06 | 2018-12-25 | 阿里巴巴集团控股有限公司 | The method and device of credit evaluation |
| CN109214904A (en) * | 2018-10-11 | 2019-01-15 | 平安科技（深圳）有限公司 | Acquisition methods, device, computer equipment and the storage medium of financial fraud clue |
| CN109299362A (en) * | 2018-09-21 | 2019-02-01 | 平安科技（深圳）有限公司 | Similar enterprise's recommended method, device, computer equipment and storage medium |
| CN109345089A (en) * | 2018-09-13 | 2019-02-15 | 杭州索骥数据科技有限公司 | Enterprise development state evaluating method and system based on big data |
| CN109359901A (en) * | 2018-12-13 | 2019-02-19 | 泰康保险集团股份有限公司 | Method and device, medium and electronic equipment are determined based on the business risk of block chain |
| CN109472485A (en) * | 2018-11-01 | 2019-03-15 | 成都数联铭品科技有限公司 | Enterprise breaks one's promise Risk of Communication inquiry system and method |
| CN109523117A (en) * | 2018-10-11 | 2019-03-26 | 平安科技（深圳）有限公司 | Risk Forecast Method, device, computer equipment and storage medium |
| CN109523153A (en) * | 2018-11-12 | 2019-03-26 | 平安科技（深圳）有限公司 | Acquisition methods, device, computer equipment and the storage medium of illegal fund collection enterprise |
| CN109543985A (en) * | 2018-11-15 | 2019-03-29 | 李志东 | Business risk appraisal procedure, system and medium |
| CN109558592A (en) * | 2018-11-29 | 2019-04-02 | 上海点融信息科技有限责任公司 | The method and apparatus of customer Credit Risk assessment information is obtained based on artificial intelligence |
| CN109597894A (en) * | 2018-09-30 | 2019-04-09 | 阿里巴巴集团控股有限公司 | A kind of correlation model generation method and device, a kind of data correlation method and device |
| CN109657917A (en) * | 2018-11-19 | 2019-04-19 | 平安科技（深圳）有限公司 | Assess method for prewarning risk, device, computer equipment and the storage medium of object |
| CN109670837A (en) * | 2018-11-30 | 2019-04-23 | 平安科技（深圳）有限公司 | Recognition methods, device, computer equipment and the storage medium of bond default risk |
| CN109740865A (en) * | 2018-12-13 | 2019-05-10 | 平安科技（深圳）有限公司 | Methods of risk assessment, system, 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 |
| CN109829640A (en) * | 2019-01-23 | 2019-05-31 | 平安科技（深圳）有限公司 | Recognition methods, device, computer equipment and the storage medium of enterprise's default risk |
| CN110009229A (en) * | 2019-04-04 | 2019-07-12 | 泰康保险集团股份有限公司 | Supply chain management method, device, storage medium and equipment based on block chain |
| CN110033120A (en) * | 2019-03-06 | 2019-07-19 | 阿里巴巴集团控股有限公司 | For providing the method and device that risk profile energizes service for trade company |
| CN110188980A (en) * | 2019-04-15 | 2019-08-30 | 深圳壹账通智能科技有限公司 | Business risk methods of marking, device, computer equipment and storage medium |
| CN110533528A (en) * | 2019-08-30 | 2019-12-03 | 北京市天元网络技术股份有限公司 | Assess the method and apparatus of business standing |
| CN111104442A (en) * | 2019-11-06 | 2020-05-05 | 杭州绿程网络科技有限公司 | Preprocessing method for enterprise comprehensive data |
| CN111291932A (en) * | 2020-02-12 | 2020-06-16 | 徐佳慧 | Investment and financing relation network link prediction method, device and equipment |
| CN111311105A (en) * | 2020-02-28 | 2020-06-19 | 深圳前海微众银行股份有限公司 | Combined product scoring method, device, equipment and readable storage medium |
| CN111340246A (en) * | 2020-02-26 | 2020-06-26 | 未来地图(深圳)智能科技有限公司 | Processing method and device for enterprise intelligent decision analysis and computer equipment |
| CN111353728A (en) * | 2020-05-06 | 2020-06-30 | 支付宝(杭州)信息技术有限公司 | Risk analysis method and system |
| CN111459961A (en) * | 2020-03-31 | 2020-07-28 | 深圳前海微众银行股份有限公司 | Method, device and equipment for updating service data and storage medium |
| CN111602157A (en) * | 2018-12-17 | 2020-08-28 | 持续可能发展所 | Supplier supply chain risk analysis method |
| CN111626887A (en) * | 2019-02-27 | 2020-09-04 | 北京奇虎科技有限公司 | Social relationship evaluation method and device |
| CN112016850A (en) * | 2020-09-14 | 2020-12-01 | 支付宝(杭州)信息技术有限公司 | Service evaluation method and device |
| CN112053021A (en) * | 2019-06-05 | 2020-12-08 | 国网信息通信产业集团有限公司 | Feature coding method and device for enterprise operation management risk identification |
| CN112598302A (en) * | 2020-12-25 | 2021-04-02 | 北京知因智慧科技有限公司 | Enterprise data evaluation method and device and server |
| CN112732804A (en) * | 2020-12-23 | 2021-04-30 | 北京金堤征信服务有限公司 | Cooperation data evaluation method and device, electronic equipment and readable storage medium |
| CN112884496A (en) * | 2021-05-06 | 2021-06-01 | 达而观数据(成都)有限公司 | Method, device and computer storage medium for calculating enterprise credit factor score |
| CN113592519A (en) * | 2020-04-30 | 2021-11-02 | 景德镇陶瓷大学 | Marketing data analysis and evaluation system beneficial to enterprise development |
| CN114168757A (en) * | 2022-02-11 | 2022-03-11 | 子长科技(北京)有限公司 | Company event risk prediction method, device, storage medium and electronic equipment |
Families Citing this family (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443459A (en) * | 2019-07-05 | 2019-11-12 | 深圳壹账通智能科技有限公司 | Warning information method for pushing, device, computer equipment and storage medium |
| CN110414806B (en) * | 2019-07-10 | 2024-05-14 | 平安科技（深圳）有限公司 | Employee risk early warning method and related device |
| CN110532357B (en) * | 2019-09-04 | 2024-03-12 | 深圳前海微众银行股份有限公司 | ESG scoring system generation method, device, equipment and readable storage medium |
| CN113643035A (en) * | 2020-05-11 | 2021-11-12 | 阿里巴巴集团控股有限公司 | Information processing method, information display method, device, equipment and storage medium |
| CN111951079B (en) * | 2020-08-14 | 2024-04-02 | 国网数字科技控股有限公司 | Credit rating method and device based on knowledge graph and electronic equipment |
| CN113743111B (en) * | 2020-08-25 | 2024-06-04 | 国家计算机网络与信息安全管理中心 | Financial risk prediction method and device based on text pre-training and multi-task learning |
| CN112418320B (en) * | 2020-11-24 | 2024-01-19 | 杭州未名信科科技有限公司 | Enterprise association relation identification method, device and storage medium |
| CN112365194A (en) * | 2020-12-01 | 2021-02-12 | 未鲲(上海)科技服务有限公司 | Enterprise data processing method, device, equipment and computer storage medium |
| CN113837517A (en) * | 2020-12-01 | 2021-12-24 | 北京沃东天骏信息技术有限公司 | Event triggering method and device, medium and electronic equipment |
| CN112598496B (en) * | 2020-12-15 | 2024-04-30 | 深圳前海微众银行股份有限公司 | Wind control blacklist setting method and device, terminal equipment and readable storage medium |
| CN112579773A (en) * | 2020-12-16 | 2021-03-30 | 中国建设银行股份有限公司 | Risk event grading method and device |
| CN112613762B (en) * | 2020-12-25 | 2024-04-16 | 北京知因智慧科技有限公司 | Group rating method and device based on knowledge graph and electronic equipment |
| CN113283806A (en) * | 2021-06-22 | 2021-08-20 | 中国平安财产保险股份有限公司 | Enterprise information evaluation method and device, computer equipment and storage medium |
| CN113506173A (en) * | 2021-08-06 | 2021-10-15 | 国网电子商务有限公司 | Credit risk assessment method and related equipment thereof |
| CN113673870B (en) * | 2021-08-23 | 2024-04-30 | 杭州安恒信息技术股份有限公司 | Enterprise data analysis method and related components |
| CN113689288B (en) * | 2021-08-25 | 2024-05-14 | 深圳前海微众银行股份有限公司 | Risk identification method, device, equipment and storage medium based on entity list |
| CN113962568A (en) * | 2021-10-26 | 2022-01-21 | 天元大数据信用管理有限公司 | Model label labeling method, device and medium based on support vector machine |
| CN114118816A (en) * | 2021-11-30 | 2022-03-01 | 建信金融科技有限责任公司 | Risk assessment method, device and equipment and computer storage medium |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040215551A1 (en) * | 2001-11-28 | 2004-10-28 | Eder Jeff S. | Value and risk management system for multi-enterprise organization |
| US20050027645A1 (en) * | 2002-01-31 | 2005-02-03 | Wai Shing Lui William | Business enterprise risk model and method |
| US20070208600A1 (en) * | 2006-03-01 | 2007-09-06 | Babus Steven A | Method and apparatus for pre-emptive operational risk management and risk discovery |
| JP2013080456A (en) * | 2011-09-21 | 2013-05-02 | Norihide Noda | System, method, and program for enterprise evaluation |
| CN103942718A (en) * | 2014-04-14 | 2014-07-23 | 中国人民银行征信中心 | Enterprise credit information collection and integration method |
| WO2014160296A1 (en) * | 2013-03-13 | 2014-10-02 | Guardian Analytics, Inc. | Fraud detection and analysis |
| US9087088B1 (en) * | 2012-11-13 | 2015-07-21 | American Express Travel Related Services Company, Inc. | Systems and methods for dynamic construction of entity graphs |
| CN105528465A (en) * | 2016-02-03 | 2016-04-27 | 天弘基金管理有限公司 | Credit status assessment method and device |
| CN105740335A (en) * | 2016-01-22 | 2016-07-06 | 山东合天智汇信息技术有限公司 | Titan-based enterprise information analysis platform and construction method thereof |
| CN105913195A (en) * | 2016-04-29 | 2016-08-31 | 浙江汇信科技有限公司 | All-industry data based enterprise's financial risk scoring method |
| CN105975491A (en) * | 2016-04-26 | 2016-09-28 | 重庆誉存企业信用管理有限公司 | Enterprise news analysis method and system |
| CN106126614A (en) * | 2016-06-21 | 2016-11-16 | 山东合天智汇信息技术有限公司 | A kind of method and system reviewing Liang Ge enterprise multi-layer associated path |
| CN106203808A (en) * | 2016-07-01 | 2016-12-07 | 中国民生银行股份有限公司 | Enterprise Credit Risk Evaluation method and apparatus |
| CN106445988A (en) * | 2016-06-01 | 2017-02-22 | 上海坤士合生信息科技有限公司 | Intelligent big data processing method and system |
| CN106447066A (en) * | 2016-06-01 | 2017-02-22 | 上海坤士合生信息科技有限公司 | Big data feature extraction method and device |
| CN106934712A (en) * | 2017-03-16 | 2017-07-07 | 深圳微众税银信息服务有限公司 | A kind of enterprise's representation data processing method and system |
| CN107133732A (en) * | 2017-04-27 | 2017-09-05 | 青岛格兰德信用管理咨询有限公司 | The relation loop method for digging analyzed based on big data and its application |
| CN107220237A (en) * | 2017-05-24 | 2017-09-29 | 南京大学 | A kind of method of business entity's Relation extraction based on convolutional neural networks |
| CN107239882A (en) * | 2017-05-10 | 2017-10-10 | 平安科技（深圳）有限公司 | Methods of risk assessment, device, computer equipment and storage medium |
| CN107301493A (en) * | 2017-05-19 | 2017-10-27 | 四川新网银行股份有限公司 | A kind of mutual golden business ratings model based on deep neural network |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| SG11201402420VA (en) * | 2013-05-02 | 2015-02-27 | Dun & Bradstreet Corp | A system and method using multi-dimensional rating to determine an entity's future commercial viability |
| CN107229756A (en) * | 2017-06-30 | 2017-10-03 | 山东合天智汇信息技术有限公司 | A kind of design method and system directly perceived for showing business connection collection of illustrative plates |
-
2017
- 2017-11-17 CN CN201711141730.3A patent/CN107909274B/en active Active
-
2018
- 2018-02-10 WO PCT/CN2018/076169 patent/WO2019095572A1/en active Application Filing
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040215551A1 (en) * | 2001-11-28 | 2004-10-28 | Eder Jeff S. | Value and risk management system for multi-enterprise organization |
| US20050027645A1 (en) * | 2002-01-31 | 2005-02-03 | Wai Shing Lui William | Business enterprise risk model and method |
| US20070208600A1 (en) * | 2006-03-01 | 2007-09-06 | Babus Steven A | Method and apparatus for pre-emptive operational risk management and risk discovery |
| JP2013080456A (en) * | 2011-09-21 | 2013-05-02 | Norihide Noda | System, method, and program for enterprise evaluation |
| US9087088B1 (en) * | 2012-11-13 | 2015-07-21 | American Express Travel Related Services Company, Inc. | Systems and methods for dynamic construction of entity graphs |
| WO2014160296A1 (en) * | 2013-03-13 | 2014-10-02 | Guardian Analytics, Inc. | Fraud detection and analysis |
| CN103942718A (en) * | 2014-04-14 | 2014-07-23 | 中国人民银行征信中心 | Enterprise credit information collection and integration method |
| CN105740335A (en) * | 2016-01-22 | 2016-07-06 | 山东合天智汇信息技术有限公司 | Titan-based enterprise information analysis platform and construction method thereof |
| CN105528465A (en) * | 2016-02-03 | 2016-04-27 | 天弘基金管理有限公司 | Credit status assessment method and device |
| CN105975491A (en) * | 2016-04-26 | 2016-09-28 | 重庆誉存企业信用管理有限公司 | Enterprise news analysis method and system |
| CN105913195A (en) * | 2016-04-29 | 2016-08-31 | 浙江汇信科技有限公司 | All-industry data based enterprise's financial risk scoring method |
| CN106445988A (en) * | 2016-06-01 | 2017-02-22 | 上海坤士合生信息科技有限公司 | Intelligent big data processing method and system |
| CN106447066A (en) * | 2016-06-01 | 2017-02-22 | 上海坤士合生信息科技有限公司 | Big data feature extraction method and device |
| CN106126614A (en) * | 2016-06-21 | 2016-11-16 | 山东合天智汇信息技术有限公司 | A kind of method and system reviewing Liang Ge enterprise multi-layer associated path |
| CN106203808A (en) * | 2016-07-01 | 2016-12-07 | 中国民生银行股份有限公司 | Enterprise Credit Risk Evaluation method and apparatus |
| CN106934712A (en) * | 2017-03-16 | 2017-07-07 | 深圳微众税银信息服务有限公司 | A kind of enterprise's representation data processing method and system |
| CN107133732A (en) * | 2017-04-27 | 2017-09-05 | 青岛格兰德信用管理咨询有限公司 | The relation loop method for digging analyzed based on big data and its application |
| CN107239882A (en) * | 2017-05-10 | 2017-10-10 | 平安科技（深圳）有限公司 | Methods of risk assessment, device, computer equipment and storage medium |
| CN107301493A (en) * | 2017-05-19 | 2017-10-27 | 四川新网银行股份有限公司 | A kind of mutual golden business ratings model based on deep neural network |
| CN107220237A (en) * | 2017-05-24 | 2017-09-29 | 南京大学 | A kind of method of business entity's Relation extraction based on convolutional neural networks |
Non-Patent Citations (3)
| Title |
|---|
| 余步雷: "基于灰色综合关联分析的企业集团信用风险研究", 《中国博士学位论文全文数据库经济与管理科学辑》 * |
| 刘堃 等: "中国信用风险预警模型及实证研究——基于企业关联关系和信贷行为的视角", 《财经研究》 * |
| 杨扬等: "基于文本大数据的企业信用风险评估", 《大数据》 * |
Cited By (46)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109087163A (en) * | 2018-07-06 | 2018-12-25 | 阿里巴巴集团控股有限公司 | The method and device of credit evaluation |
| CN109087163B (en) * | 2018-07-06 | 2021-07-09 | 创新先进技术有限公司 | Credit assessment method and device |
| CN108985638B (en) * | 2018-07-25 | 2020-07-24 | 腾讯科技（深圳）有限公司 | User investment risk assessment method and device and storage medium |
| CN108985638A (en) * | 2018-07-25 | 2018-12-11 | 腾讯科技（深圳）有限公司 | A kind of customer investment methods of risk assessment and device and storage medium |
| CN109345089A (en) * | 2018-09-13 | 2019-02-15 | 杭州索骥数据科技有限公司 | Enterprise development state evaluating method and system based on big data |
| CN109299362A (en) * | 2018-09-21 | 2019-02-01 | 平安科技（深圳）有限公司 | Similar enterprise's recommended method, device, computer equipment and storage medium |
| CN109299362B (en) * | 2018-09-21 | 2023-04-14 | 平安科技（深圳）有限公司 | Similar enterprise recommendation method and device, computer equipment and storage medium |
| CN109597894B (en) * | 2018-09-30 | 2023-10-03 | 创新先进技术有限公司 | Correlation model generation method and device, and data correlation method and device |
| CN109597894A (en) * | 2018-09-30 | 2019-04-09 | 阿里巴巴集团控股有限公司 | A kind of correlation model generation method and device, a kind of data correlation method and device |
| CN109214904A (en) * | 2018-10-11 | 2019-01-15 | 平安科技（深圳）有限公司 | Acquisition methods, device, computer equipment and the storage medium of financial fraud clue |
| CN109523117A (en) * | 2018-10-11 | 2019-03-26 | 平安科技（深圳）有限公司 | Risk Forecast Method, device, computer equipment and storage medium |
| CN109472485A (en) * | 2018-11-01 | 2019-03-15 | 成都数联铭品科技有限公司 | Enterprise breaks one's promise Risk of Communication inquiry system and method |
| CN109523153A (en) * | 2018-11-12 | 2019-03-26 | 平安科技（深圳）有限公司 | Acquisition methods, device, computer equipment and the storage medium of illegal fund collection enterprise |
| CN109543985A (en) * | 2018-11-15 | 2019-03-29 | 李志东 | Business risk appraisal procedure, system and medium |
| CN109657917B (en) * | 2018-11-19 | 2022-04-29 | 平安科技（深圳）有限公司 | Risk early warning method and device for evaluation object, computer equipment and storage medium |
| CN109657917A (en) * | 2018-11-19 | 2019-04-19 | 平安科技（深圳）有限公司 | Assess method for prewarning risk, device, computer equipment and the storage medium of object |
| CN109558592A (en) * | 2018-11-29 | 2019-04-02 | 上海点融信息科技有限责任公司 | The method and apparatus of customer Credit Risk assessment information is obtained based on artificial intelligence |
| CN109670837A (en) * | 2018-11-30 | 2019-04-23 | 平安科技（深圳）有限公司 | Recognition methods, device, computer equipment and the storage medium of bond default risk |
| CN109740865A (en) * | 2018-12-13 | 2019-05-10 | 平安科技（深圳）有限公司 | Methods of risk assessment, system, equipment and storage medium |
| CN109359901A (en) * | 2018-12-13 | 2019-02-19 | 泰康保险集团股份有限公司 | Method and device, medium and electronic equipment are determined based on the business risk of block chain |
| CN111602157B (en) * | 2018-12-17 | 2023-12-01 | 持续可能发展所 | Supplier Supply Chain Risk Analysis Method |
| CN111602157A (en) * | 2018-12-17 | 2020-08-28 | 持续可能发展所 | Supplier supply chain risk analysis method |
| 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 |
| CN109829640A (en) * | 2019-01-23 | 2019-05-31 | 平安科技（深圳）有限公司 | Recognition methods, device, computer equipment and the storage medium of enterprise's default risk |
| CN111626887A (en) * | 2019-02-27 | 2020-09-04 | 北京奇虎科技有限公司 | Social relationship evaluation method and device |
| CN110033120A (en) * | 2019-03-06 | 2019-07-19 | 阿里巴巴集团控股有限公司 | For providing the method and device that risk profile energizes service for trade company |
| CN110009229A (en) * | 2019-04-04 | 2019-07-12 | 泰康保险集团股份有限公司 | Supply chain management method, device, storage medium and equipment based on block chain |
| CN110188980A (en) * | 2019-04-15 | 2019-08-30 | 深圳壹账通智能科技有限公司 | Business risk methods of marking, device, computer equipment and storage medium |
| CN112053021A (en) * | 2019-06-05 | 2020-12-08 | 国网信息通信产业集团有限公司 | Feature coding method and device for enterprise operation management risk identification |
| CN110533528A (en) * | 2019-08-30 | 2019-12-03 | 北京市天元网络技术股份有限公司 | Assess the method and apparatus of business standing |
| CN111104442A (en) * | 2019-11-06 | 2020-05-05 | 杭州绿程网络科技有限公司 | Preprocessing method for enterprise comprehensive data |
| CN111291932A (en) * | 2020-02-12 | 2020-06-16 | 徐佳慧 | Investment and financing relation network link prediction method, device and equipment |
| CN111340246A (en) * | 2020-02-26 | 2020-06-26 | 未来地图(深圳)智能科技有限公司 | Processing method and device for enterprise intelligent decision analysis and computer equipment |
| CN111311105A (en) * | 2020-02-28 | 2020-06-19 | 深圳前海微众银行股份有限公司 | Combined product scoring method, device, equipment and readable storage medium |
| CN111459961A (en) * | 2020-03-31 | 2020-07-28 | 深圳前海微众银行股份有限公司 | Method, device and equipment for updating service data and storage medium |
| CN113592519A (en) * | 2020-04-30 | 2021-11-02 | 景德镇陶瓷大学 | Marketing data analysis and evaluation system beneficial to enterprise development |
| CN111353728A (en) * | 2020-05-06 | 2020-06-30 | 支付宝(杭州)信息技术有限公司 | Risk analysis method and system |
| CN112016850A (en) * | 2020-09-14 | 2020-12-01 | 支付宝(杭州)信息技术有限公司 | Service evaluation method and device |
| CN112732804A (en) * | 2020-12-23 | 2021-04-30 | 北京金堤征信服务有限公司 | Cooperation data evaluation method and device, electronic equipment and readable storage medium |
| CN112732804B (en) * | 2020-12-23 | 2024-04-26 | 北京金堤征信服务有限公司 | Cooperative data evaluation method and device, electronic equipment and readable storage medium |
| CN112598302A (en) * | 2020-12-25 | 2021-04-02 | 北京知因智慧科技有限公司 | Enterprise data evaluation method and device and server |
| CN112598302B (en) * | 2020-12-25 | 2024-03-26 | 北京知因智慧科技有限公司 | Enterprise data evaluation method, device and server |
| CN112884496B (en) * | 2021-05-06 | 2021-08-20 | 达而观数据(成都)有限公司 | Method, device and computer storage medium for calculating enterprise credit factor score |
| CN112884496A (en) * | 2021-05-06 | 2021-06-01 | 达而观数据(成都)有限公司 | Method, device and computer storage medium for calculating enterprise credit factor score |
| CN114168757A (en) * | 2022-02-11 | 2022-03-11 | 子长科技(北京)有限公司 | Company event risk prediction method, device, storage medium and electronic equipment |
| CN114168757B (en) * | 2022-02-11 | 2022-04-29 | 子长科技(北京)有限公司 | Company event risk prediction method, device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019095572A1 (en) | 2019-05-23 |
| CN107909274B (en) | 2023-02-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107909274A (en) | Enterprise investment methods of risk assessment, device and storage medium | |
| Choi et al. | Optimizing enterprise risk management: a literature review and critical analysis of the work of Wu and Olson | |
| Farrell et al. | Moderating influences on the ERM maturity-performance relationship | |
| WO2017117230A1 (en) | Method and apparatus for facilitating on-demand building of predictive models | |
| KR20110056502A (en) | Entity performance analysis engines | |
| CA2987838A1 (en) | Risk identification and risk register generation system and engine | |
| US20210117889A1 (en) | Co-operative resource pooling system | |
| US20110137848A1 (en) | General prediction market | |
| Izzo et al. | The role of digital transformation in enabling continuous accounting and the effects on intellectual capital: the case of Oracle | |
| US20180025428A1 (en) | Methods and systems for analyzing financial risk factors for companies within an industry | |
| Wu et al. | Political connection, ownership, and post-crisis industrial upgrading investment: evidence from China | |
| CN113723737A (en) | Enterprise portrait-based policy matching method, device, equipment and medium | |
| Zhao et al. | Revolutionizing finance with llms: An overview of applications and insights | |
| Javid et al. | Sectoral investment analysis for Saudi Arabia | |
| Glova et al. | Analysis of bonds with embedded options/Analyza dlhopisov s vlozenymi opciami | |
| Rahahleh et al. | The artificial intelligence in the audit on reliability of accounting information and earnings manipulation detection | |
| Barjaktarovic et al. | Possibilities of financial support to small and medium hotel companies in Serbie | |
| Kumar et al. | Natural Language Generation and Artificial Intelligence in Financial Reporting: Transforming Financial Data into Strategic Insights for Executive Leadership | |
| Shang et al. | The Impacts of the Infectious Disease Epidemic on the Permanent Volatility of Precious Metal and Crude Oil Futures Markets: A Long‐Term Perspective | |
| Jain et al. | Exploring the research landscape of implied volatility index: A bibliometric analysis | |
| Lipitakis et al. | On the e-valuation of certain e-business strategies on firm performance by adaptive algorithmic modeling: An alternative strategic managerial approach | |
| Sun | Accounting Information Systems outputs: XBRL, AI and in-memory technologies | |
| Karanovic et al. | Techniques for managing projects risk in capital budgeting process | |
| Kuzmenko et al. | Implementation of information technologies in the international accounting system of fuel and energy sector enterprises | |
| Hoyt et al. | Computing Value at Risk: a simulation assignment to illustrate the value of enterprise risk management |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |