CN109670837A - Recognition methods, device, computer equipment and the storage medium of bond default risk - Google Patents
Recognition methods, device, computer equipment and the storage medium of bond default risk Download PDFInfo
- Publication number
- CN109670837A CN109670837A CN201811454178.8A CN201811454178A CN109670837A CN 109670837 A CN109670837 A CN 109670837A CN 201811454178 A CN201811454178 A CN 201811454178A CN 109670837 A CN109670837 A CN 109670837A
- Authority
- CN
- China
- Prior art keywords
- event
- bond
- default
- risk
- corpus data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000005540 biological transmission Effects 0.000 claims abstract description 11
- 239000013598 vector Substances 0.000 claims description 44
- 230000008451 emotion Effects 0.000 claims description 29
- 238000004590 computer program Methods 0.000 claims description 27
- 239000011159 matrix material Substances 0.000 claims description 14
- 239000000284 extract Substances 0.000 claims description 7
- 238000012545 processing Methods 0.000 abstract description 7
- 238000011156 evaluation Methods 0.000 abstract description 6
- 238000012549 training Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Technology Law (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application involves recognition methods, device, computer equipment and the storage mediums of a kind of bond default risk.This method comprises: obtaining the related information of bond to be identified when receiving the inquiry request of terminal transmission, target industry type and the target distribution enterprise of bond to be identified are determined;First news corpus data relevant to bond to be identified are obtained from database;Event keyword is extracted from the first news corpus data, event keyword is matched with the event tag in preset event of default tag library, obtains matching result;The default risk grade of bond to be identified is determined according to matching result;Matching result and default risk grade are sent to terminal, so that terminal display matching result and default risk grade.This method is based on big data processing technique, realizes the tracking control that comprehensive risk identification and risk point are carried out to bond to be identified, provides comprehensive, intuitive bond default risk evaluation of bond default risk point for investor.
Description
Technical field
This application involves technical field of data processing, more particularly to a kind of recognition methods of bond default risk, device,
Computer equipment and storage medium.
Background technique
Bond promise breaking refers to that bond issue main body cannot be according to the behavior of its obligation of the bond transaction performance reached in advance, closely
High-incidence bond promise breaking phenomenon has beaten alarm bell to personal and institutional investor over year, therefore is directed to and is likely to result in bond promise breaking
Risk identification seem particularly important.Traditional intelligent analysis of bond tool can only often provide the financial data browsing of bond
With simple credit rating function, the information content is single, and investor can not be from provided financial data and credit rating
The visual evaluation of bond is obtained, and is difficult to realize comprehensive tracking control to bond default risk point.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide the recognition methods of bond default risk a kind of, device,
Computer equipment and storage medium.
A kind of recognition methods of bond default risk, which comprises
When receiving the inquiry request for being used to obtain bond default risk to be identified of terminal transmission, debt to be identified is obtained
The related information of certificate, and determine that the target industry type of the bond to be identified and target are issued from the related information
Enterprise;
First news corpus data relevant to the bond to be identified are obtained from database, wherein first news
Corpus data includes the news corpus data of the bond to be identified, the news corpus data of target industry type and the mesh
The news corpus data of mark distribution enterprise;
Event keyword is extracted from the first news corpus data, by the event keyword and preset promise breaking thing
Event tag in part tag library is matched, and matching result is obtained;It include different event class in the event of default tag library
The risk class value of the event tag of type and the event tag includes the object event mark being matched in the matching result
The risk class value of label, the event type of the object event label and the object event label;
Determine the default risk grade of the bond to be identified according to the matching result, and according to the matching result with
And the default risk grade generates default risk information;
The default risk information is sent to the terminal, the default risk information is used to indicate the terminal display
The matching result and the default risk grade.
The event by the event keyword and preset event of default tag library in one of the embodiments,
Before the step of label is matched, further includes:
History default bond is obtained, and determines default time, industry type and the distribution enterprise of the history default bond
Industry;
The second news corpus data in the default time are crawled, the second news corpus data include the history
The news corpus number of the news corpus data of default bond, the news corpus data of the distribution enterprise and the industry type
According to;
Different event tags is extracted from each second news corpus data, and not to each event tag setting
Same risk class value;
The event type for determining the second news corpus data, according to the event type, the event tag and
The risk class value of the event tag generates event of default tag library.
It is described in one of the embodiments, to extract different event tags from each second news corpus data
Step, comprising:
Pretreatment is carried out to the second news corpus data and obtains the word of the second news corpus, and obtains each list
The term vector of word;
Text emotion analysis is carried out to the second news corpus data using the term vector, obtains the news corpus
The text emotion of data;
The targeted news corpus data that text emotion is negative emotion is filtered out, and from the targeted news corpus data
Extract negative keyword;
Using the negative keyword as the event tag of event type corresponding with the targeted news corpus data.
Described the step of each event tag being arranged different risk class values in one of the embodiments, packet
It includes:
The number that the event tag of each history default bond occurs is counted, event tag matrix is generated;
The probability value that each event tag occurs is calculated according to event tag matrix;
The risk class value of each event tag is determined according to the probability value of each event tag.
It is described in one of the embodiments, to extract event keyword from the first news corpus data, it will be described
The step of event keyword is matched with the event tag in the event of default tag library, obtains matching result, comprising:
The term vector of event keyword is obtained using default term vector model;
All term vectors are input in preparatory trained SVM model, the term vector and each event are calculated
The confidence level of label;
The highest event tag of confidence level is determined as and the matched object event label of the event keyword.
The default risk etc. that the bond to be identified is determined according to the matching result in one of the embodiments,
The step of grade, comprising:
The risk class value of the object event label and the object event label is read from the matching result;
The risk class value of the object event label is added to obtain the risk total value of the bond to be identified;
When the risk total value is less than or equal to the first preset threshold, the default risk grade of the bond to be identified is determined
For security level;
When the risk total value is greater than first preset threshold and less than the second preset threshold, the bond to be identified
Default risk grade is determined as low risk level;
When the risk total value is greater than second preset threshold, the default risk grade of the bond to be identified is determined as
High-risk grade.
A kind of identification device of bond default risk, described device include:
Bond to be identified obtains module, for when receive terminal transmission for obtaining bond default risk to be identified
When inquiry request, the related information of bond to be identified is obtained, and determines the bond to be identified from the related information
Target industry type and target issue enterprise;
Public feelings information obtains module, for obtaining first news corpus relevant to the bond to be identified from database
Data, wherein the first news corpus data include the news corpus data of the bond to be identified, target industry type
News corpus data and the news corpus data of target distribution enterprise;
Matching result generation module, for extracting event keyword from the first news corpus data, by the thing
Part keyword is matched with the event tag in preset event of default tag library, obtains matching result;The event of default
The risk class value of event tag and the event tag in tag library including different event type, in the matching result
Risk including the event type of object event label, the object event label and the object event label that are matched to
Grade point;
Risk class obtains module, for determining the default risk etc. of the bond to be identified according to the matching result
Grade, and default risk information is generated according to the matching result and the default risk grade;
Risk information sending module, for the default risk information to be sent to the terminal, the default risk letter
Breath is used to indicate matching result described in the terminal display and the default risk grade.
The tag library obtains module and is used in one of the embodiments:
History default bond is obtained, and determines default time, industry type and the distribution enterprise of the history default bond
Industry;
The second news corpus data in the default time are crawled, the second news corpus data include the history
The news corpus number of the news corpus data of default bond, the news corpus data of the distribution enterprise and the industry type
According to;
Different event tags is extracted from each second news corpus data, and not to each event tag setting
Same risk class value;
The event type for determining the second news corpus data, according to the event type, the event tag and
The risk class value of the event tag generates event of default tag library.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
When receiving the inquiry request for being used to obtain bond default risk to be identified of terminal transmission, debt to be identified is obtained
The related information of certificate, and determine that the target industry type of the bond to be identified and target are issued from the related information
Enterprise;
First news corpus data relevant to the bond to be identified are obtained from database, wherein first news
Corpus data includes the news corpus data of the bond to be identified, the news corpus data of target industry type and the mesh
The news corpus data of mark distribution enterprise;
Event keyword is extracted from the first news corpus data, by the event keyword and preset promise breaking thing
Event tag in part tag library is matched, and matching result is obtained;It include different event class in the event of default tag library
The risk class value of the event tag of type and the event tag includes the object event mark being matched in the matching result
The risk class value of label, the event type of the object event label and the object event label;
Determine the default risk grade of the bond to be identified according to the matching result, and according to the matching result with
And the default risk grade generates default risk information;
The default risk information is sent to the terminal, the default risk information is used to indicate the terminal display
The matching result and the default risk grade.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
When receiving the inquiry request for being used to obtain bond default risk to be identified of terminal transmission, debt to be identified is obtained
The related information of certificate, and determine that the target industry type of the bond to be identified and target are issued from the related information
Enterprise;
First news corpus data relevant to the bond to be identified are obtained from database, wherein first news
Corpus data includes the news corpus data of the bond to be identified, the news corpus data of target industry type and the mesh
The news corpus data of mark distribution enterprise;
Event keyword is extracted from the first news corpus data, by the event keyword and preset promise breaking thing
Event tag in part tag library is matched, and matching result is obtained;It include different event class in the event of default tag library
The risk class value of the event tag of type and the event tag includes the object event mark being matched in the matching result
The risk class value of label, the event type of the object event label and the object event label;
Determine the default risk grade of the bond to be identified according to the matching result, and according to the matching result with
And the default risk grade generates default risk information;
The default risk information is sent to the terminal, the default risk information is used to indicate the terminal display
The matching result and the default risk grade.
Recognition methods, device, computer equipment and the storage medium of above-mentioned bond default risk, by obtain with it is to be identified
The relevant news corpus data of bond, by news corpus data event keyword and event of default library in event tag into
Row matching generates matching result, and the promise breaking of bond to be identified is determined according to the risk class value of the event tag with Keywords matching
Risk class is provided by the way that the matching result of bond to be identified and default risk grade are sent terminal display for investor
The visual evaluation of bond default risk, wherein news corpus data relevant to bond to be identified include the new of bond to be identified
INDUSTRY OVERVIEW corpus belonging to news corpus data, the news corpus data of issue of bonds enterprise to be identified and bond to be identified
Data are realized and carry out comprehensive risk identification to bond to be identified, no longer only carry out from the financial data of bond and credit rating
Risk identification realizes comprehensive tracking control to bond default risk point to be identified.
Detailed description of the invention
Fig. 1 is the application scenario diagram of the recognition methods of bond default risk in one embodiment;
Fig. 2 is the flow diagram of the recognition methods of bond default risk in one embodiment;
Fig. 3 is the displaying picture drawing that matching result and default risk grade are shown in one embodiment;
Fig. 4 is the structural block diagram of the identification device of bond default risk in one embodiment;
Fig. 5 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
The recognition methods of bond default risk provided by the present application, can be applied in application environment as shown in Figure 1.Its
In, user terminal 102 is communicated with server 104 by network by network.Investment user can pass through user terminal 102
The default risk inquiry request of bond to be identified is sent in server 104, server 104 receives default risk inquiry and asks
Bond to be identified is determined after asking, and then obtains the enterprise of industry type belonging to bond to be identified and distribution bond to be identified,
By crawl from network the news corpus data of bond to be identified, the news corpus data of issue of bonds enterprise to be identified and
INDUSTRY OVERVIEW corpus data belonging to bond to be identified, by these news corpus data event keyword and event of default library
In event tag matched, obtain with the event tag of Keywords matching, and it is true according to the risk class value of event tag
The default risk grade of fixed bond to be identified realizes comprehensive tracking to bond default risk point to be identified, while server 104
The default risk grade of event tag that bond house to be identified is matched to, with default risk and bond to be identified is sent
Into user terminal 102, these event tags and default risk grade are shown by the display screen of user terminal 102, are informed
The default risk of investment user bond to be identified provides the visual evaluation of bond for investment user.Wherein, user terminal 102 can
With but be not limited to various personal computers, laptop, smart phone, tablet computer and portable wearable device, take
Business device 104 can be realized with the server cluster of the either multiple server compositions of independent server.
In one embodiment, it as shown in Fig. 2, providing a kind of recognition methods of bond default risk, answers in this way
For being illustrated for the server in Fig. 1, comprising the following steps:
Step S210: it when receiving the inquiry request for being used to obtain bond default risk to be identified of terminal transmission, obtains
The related information of bond to be identified is taken, and determines the target industry type and target hair of bond to be identified from related information
Row enterprise.
In this step, after the inquiry request that server receiving terminal is sent, bond to be identified is determined according to inquiry request, with
And target industry type belonging to bond to be identified and the target of distribution bond to be identified issue enterprise.Specifically, investment is used
The inquiry request for carrying the identification number of bond to be identified can be sent in server by family by user terminal, and server connects
After receiving inquiry request, industry class belonging to bond to be identified and bond to be identified is determined according to the identification number of inquiry request
The enterprise of type and distribution bond to be identified.
Step S220: obtaining first news corpus data relevant to bond to be identified from database, wherein first is new
Hearing corpus data includes the news corpus data of bond to be identified, the news corpus data of target industry type and target distribution
The news corpus data of enterprise.
In this step, database can be the local data base of server, and server is crawled from internet in advance and debt
The relevant news public feelings information of certificate information, and denoising is carried out to the news public feelings information crawled, by news public feelings information
In advertisement noise, dirty word noise etc. filter out one by one, obtain only include body content a news corpus data, and save extremely
The local data base of server;Database is also possible to the news platform or media platform that server is connected by connecting interface
Database includes a large amount of news public feelings information relevant to bond information in database.Specifically, server can will be to be identified
The name of the title of bond, the title of target industry type or target detection enterprise is referred to as search key, searches from database
Rope obtains news corpus data relevant to bond to be identified, news relevant with target industry type belonging to bond to be identified
Corpus data and news corpus data relevant to target distribution enterprise.
Step S230: extracting event keyword from the first news corpus data, by event keyword and preset promise breaking
Event tag in event tag library is matched, and matching result is obtained;It include different event type in event of default tag library
Event tag and event tag risk class value, include the object event label being matched to, target thing in matching result
The event type of part label and the risk class value of object event label.
It include several preset event types in event of default tag library, different event types includes different event mark
Label, each event tag are provided with risk class value;Specifically, predeterminable event type can specifically include financial event, law
Event, capital event and event is managed, by taking financial event type as an example, the corresponding event tag of financial event type be can wrap
Include the labels such as the Change of Capital Structure, poor fluidity and achievement loss.In this step, server can be in advance by known promise breaking
Bond as an example, analyzes the news public feelings information of the different event type of default bond, obtains different event type
Under event tag and to event tag be arranged risk class value, obtain event of default tag library.Server to acquisition first
News corpus data carry out keyword extraction, and the event tag in the event keyword of acquisition and event tag library is carried out
Match, when event keyword and event tag successful match, then will be determined as with the event tag of event keyword successful match
Default risk event, and the event tag and its event type, risk class value are written into matching result;Specifically, clothes
Business device can carry out word segmentation processing to the first news corpus data and stop words is gone to handle, and the participle word of acquisition is as first
The event keyword of news corpus data.
Step S240: determining the default risk grade of bond to be identified according to matching result, and according to matching result and
Default risk grade generates default risk information.
In this step, server is after obtaining matching result, according to the event tag and event recorded in matching result
The risk class value of label calculates the default risk value of bond to be identified, to determine the bond to be identified according to default risk value
Default risk grade.
Step S250: default risk information is sent to terminal, default risk information is used to indicate terminal display matching knot
Fruit and default risk grade.
In this step, the matching result of bond to be identified and default risk grade are sent to the user terminal by server,
The matching result and default risk grade are shown by the display device of user terminal, are provided for investment user comprehensive, intuitive
Bond default risk grade and default risk event.Specifically, Fig. 3 is to show matching result in one embodiment and disobey
The about displaying picture drawing of risk class includes showing what default risk grade was matched under different event type in Fig. 3
The default risk grade of event tag and bond.By the way that the matching result of bond to be identified and default risk grade are sent
Make to user terminal so that user terminal shows matching result and default risk grade comprising various risk case labels
Investment user learn in real time bond to be identified default risk point and intuitive default risk grade.
In the recognition methods of above-mentioned bond default risk, by obtaining news corpus data relevant to bond to be identified,
Keyword and the event tag in event of default library in news corpus data match and generates matching result, according to pass
The risk class value of the matched event tag of keyword determines the default risk grade of bond to be identified, by by bond to be identified
Matching result and default risk grade send terminal display, provide the visual evaluation of bond default risk for investor, wherein
News corpus data relevant to bond to be identified include the news corpus data of bond to be identified, issue of bonds to be identified enterprise
INDUSTRY OVERVIEW corpus data belonging to the news corpus data of industry and bond to be identified is realized and is carried out comprehensively to bond to be identified
Risk identification, no longer only carry out risk identification from the financial data of bond and credit rating, realize and break a contract to bond to be identified
Comprehensive tracking control of risk point provides comprehensive, intuitive bond default risk evaluation of bond default risk point for investor.
In one embodiment, event keyword is matched with the event tag in preset event of default tag library
The step of before, further includes: obtain history default bond, and determine the default time of history default bond, industry type and
Issue enterprise;The second news corpus data in default time are crawled, the second news corpus data include history default bond
The news corpus data of news corpus data, the news corpus data for issuing enterprise and industry type;From each second news language
Different event tags is extracted in material data, and each event tag is arranged different risk class values;Determine the second news language
The event type for expecting data generates event of default mark according to the risk class value of event type, event tag and event tag
Sign library.
The present embodiment is the step process for constructing event of default tag library, and server obtains relevant to history default bond
News corpus data, news corpus data relevant to target industry type belonging to history default bond and with history break a contract
The relevant news corpus data of issue of bonds enterprise;Specifically, server can use TF-IDF (term frequency-
Inverse document frequency) algorithm analyzes these news corpus data, from every news corpus data
In extract the event tag that can summarize the news corpus data, and the event tag of acquisition is arranged different risk class
Value;By determining the event type of news corpus data, the event mark event tag of acquisition being determined as under the event type
The risk class value of the event type finally obtained, event tag and event tag is generated event tag library by label.By right
The news corpus data of history default bond are analyzed, and the event tag and its risk class value of different event type are obtained,
History case foundation is provided for the default risk identification of bond to be identified, is known in the subsequent default risk for carrying out bond to be identified
When other, bond news corpus data to be identified are matched with the event tag of history default bond, is realized to debt to be identified
Comprehensive tracking control of certificate default risk point.
In one embodiment, the step of extracting different event tags from each second news corpus data, comprising: right
Second news corpus data carry out pretreatment and obtain the word of the second news corpus, and obtain the term vector of each word;Utilize word
Vector carries out text emotion analysis to the second news corpus data, obtains the text emotion of news corpus data;Filter out text
Emotion is the targeted news corpus data of negative emotion, and negative keyword is extracted from targeted news corpus data;It will be negative
Event tag of the keyword as event type corresponding with targeted news corpus data.
In the present embodiment, pretreatment includes word segmentation processing and stop words is gone to handle;Specifically, server passes through to second
News corpus data carry out word segmentation processing and go stop words to handle to obtain the word of the second news corpus data, and can benefit
The term vector of word is obtained with word2vec model;Text emotion analysis is carried out to news public feelings information using term vector, is obtained
The text emotion of news public feelings information;The text emotion for filtering out news public feelings information is the targeted news public sentiment letter of negative emotion
Breath extracts the keyword in targeted news public feelings information;Using the keyword as the corresponding event of targeted news public feelings information
The event tag of type.By the sentiment analysis to the second news corpus, the mesh of negative emotion is obtained from the second news corpus
News public feelings information is marked, keyword is extracted from the news corpus data of negative emotion as event tag, is realized from history
Event tag relevant to bond generation violations is obtained in the numerous news corpus data of default bond, is bond to be identified
Default risk identification provide history case foundation.
In one embodiment, the step of different risk class values being arranged to each event tag, comprising: count each history
The number that the event tag of default bond occurs generates event tag matrix;Each event tag is calculated according to event tag matrix
The probability value of appearance;The risk class value of each event tag is determined according to the probability value of each event tag.
In the present embodiment, server obtains after obtaining event tag in the news corpus data of each history default bond
The corresponding event tag of all history default bonds is taken, duplicate event tag is removed, obtains event tag table;Statistics is each gone through
In the corresponding event tag of history default bond, the number of event tag appearance is corresponded to, in event tag table to generate event mark
Sign matrix;Server is calculated in the case where bond is default bond, each event tag occurs after obtaining event tag matrix
Probability value, the probability value of acquisition is quantified as the corresponding risk class value of each event tag.For example, event tag " flowing
Property it is poor " occur probability value be 80% to 89%, then the corresponding risk class value of event tag " poor fluidity " is set as 8.It is logical
The number that the event tag of statistical history default bond occurs is crossed, bond event of default is calculated according to the number that event tag occurs
In the case where generation, the probability that event tag occurs, and then determine the risk class value of each event tag, it realizes according to event mark
Event tag risk class value is arranged with the correlation degree of default bond in label, improves the accuracy of risk class value, it is subsequent into
During the default risk identification of row bond to be identified, the accuracy for calculating bond default risk grade to be identified is improved.
In one embodiment, event keyword is extracted from the first news corpus data, by event keyword and promise breaking
The step of event tag in event tag library is matched, obtains matching result, comprising: obtained using default term vector model
The term vector of event keyword;All term vectors are input in preparatory trained SVM model, term vector and each thing are calculated
The confidence level of part label;The highest event tag of confidence level is determined as and the matched object event label of event keyword.
In the present embodiment, default term vector model can be word2vec model;Server can use word2vec mould
Type obtains the term vector of each event keyword, and the term vector of acquisition is input to preparatory trained SVM (Support
Vector Machine, support vector machines) in model, SVM model is calculated according to the term vector of event keyword in event key
The maximum event tag of confidence level is determined as closing with event by the confidence level that word and each different event label match, server
The matched object event label of keyword, by by object event label, the corresponding event type of object event label and risk
Grade point is recorded in matching result, generates final matching result.Pass through the determination of SVM model and the matched thing of event keyword
Part keyword effectively improves the accuracy for obtaining object event label.
Further, SVM model can use the second news corpus data of history default bond as training data into
Row training;Specifically, after extracting different event tags in each second news corpus data, to the second news corpus data
It carries out word segmentation processing and goes stop words to handle to obtain the event word of every second news corpus data, and can use
The term vector of word2vec model acquisition event word;Using the term vector of the event word of every second news corpus data as
One training sample data, and corresponding event tag in the second news corpus data is added to the mark of training sample data
Label;According to each training sample data and its label, Training is carried out to the SVM model of initialization.
It in one embodiment, include the object event label being matched to, the event of object event label in matching result
The risk class value of type and object event label;The bond default risk grade of bond to be identified is generated according to matching result
The step of, comprising: the risk class value of object event label and object event label is read from matching result;By target thing
The risk class value of part label is added to obtain the risk total value of bond to be identified;When risk total value is less than or equal to the first default threshold
Value, the default risk grade of bond to be identified are determined as security level;When risk total value is greater than the first preset threshold and less than the
The default risk grade of two preset thresholds, bond to be identified is determined as low risk level;When risk total value is greater than the second default threshold
Value, the default risk grade of bond to be identified are determined as high-risk grade.
In the present embodiment, the risk class value of the event tag recorded in matching result is added by server, is obtained wait know
The risk total value of other bond compares the risk total value of bond to be identified with the first preset threshold and the second preset threshold
Compared with determining the promise breaking wind of bond to be identified according to the comparison result of risk total value and the first preset threshold and the second preset threshold
Dangerous grade is determined as high-risk grade.
It should be understood that although each step in the flow chart of Fig. 2 is successively shown according to the instruction of arrow, this
A little steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly state otherwise herein, these steps
It executes there is no the limitation of stringent sequence, these steps can execute in other order.Moreover, at least part in Fig. 2
Step may include that perhaps these sub-steps of multiple stages or stage are executed in synchronization to multiple sub-steps
It completes, but can execute at different times, the execution sequence in these sub-steps or stage, which is also not necessarily, successively to be carried out,
But it can be executed in turn or alternately at least part of the sub-step or stage of other steps or other steps.
In one embodiment, as shown in figure 4, providing a kind of identification device of bond default risk, comprising: to be identified
Bond obtains module 410, corpus data obtains module 420, matching result generation module 430, risk class obtain 440 and of module
Risk information sending module 450, in which:
Bond to be identified obtains module 410, for when receive terminal transmission for obtaining bond promise breaking wind to be identified
When the inquiry request of danger, the related information of bond to be identified is obtained, and the debt to be identified is determined from the related information
The target industry type and target of certificate issue enterprise;
Corpus data obtains module 420, for obtaining first news corpus relevant to bond to be identified from database
Data, wherein the first news corpus data include the news corpus of the news corpus data of bond to be identified, target industry type
Data and the news corpus data of target distribution enterprise;
Matching result generation module 430, for extracting event keyword from the first news corpus data, by event key
Word is matched with the event tag in preset event of default tag library, obtains matching result;It is wrapped in event of default tag library
The event tag of different event type and the risk class value of event tag are included, includes the target thing being matched in matching result
The risk class value of part label, the event type of object event label and object event label;
Risk class obtains module 440, for determining the default risk grade of bond to be identified, and root according to matching result
Default risk information is generated according to matching result and default risk grade;
Risk information sending module 450, for default risk information to be sent to terminal, default risk information is used to indicate
Terminal display matching result and default risk grade.
In one embodiment, the identification device of bond default risk further includes that tag library obtains module, and tag library obtains
Module is used for: being obtained history default bond, and is determined default time, industry type and the distribution enterprise of history default bond;
The second news corpus data in default time are crawled, the second news corpus data include the news corpus number of history default bond
According to, distribution enterprise news corpus data and industry type news corpus data;It is mentioned from each second news corpus data
Different event tags is taken, and each event tag is arranged different risk class values;Determine the thing of the second news corpus data
Part type generates event of default tag library according to the risk class value of event type, event tag and event tag.
In one embodiment, tag library obtains module and is used for: carrying out pretreatment to the second news corpus data and obtains the
The word of two news corpus, and obtain the term vector of each word;Text feelings are carried out to the second news corpus data using term vector
Sense analysis, obtains the text emotion of news corpus data;The targeted news corpus data that text emotion is negative emotion is filtered out,
And negative keyword is extracted from targeted news corpus data;Using negative keyword as corresponding with targeted news corpus data
The event tag of event type.
In one embodiment, tag library obtains module and is used to count time that the event tag of each history default bond occurs
Number generates event tag matrix;The probability value that each event tag occurs is calculated according to event tag matrix;According to each event tag
Probability value determine the risk class value of each event tag.
In one embodiment, matching result generation module 430 is used to obtain event using default term vector model crucial
The term vector of word;All term vectors are input in preparatory trained SVM model, term vector and each event tag are calculated
Confidence level;The highest event tag of confidence level is determined as and the matched object event label of event keyword.
In one embodiment, risk class obtain module 440, for from matching result read object event label with
And the risk class value of object event label;It is added the risk class value of object event label to obtain the risk of bond to be identified
Total value;When risk total value is less than or equal to the first preset threshold, the default risk grade of bond to be identified is determined as security level;
When risk total value is greater than the first preset threshold and less than the second preset threshold, the default risk grade of bond to be identified is determined as low
Risk class;When risk total value is greater than the second preset threshold, the default risk grade of bond to be identified is determined as high-risk grade.
The specific restriction of identification device about bond default risk may refer to above for bond default risk
The restriction of recognition methods, details are not described herein.Modules in the identification device of above-mentioned bond default risk can whole or portion
Divide and is realized by software, hardware and combinations thereof.Above-mentioned each module can be embedded in the form of hardware or independently of computer equipment
In processor in, can also be stored in a software form in the memory in computer equipment, in order to processor calling hold
The corresponding operation of the above modules of row.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 5.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing the data such as event of default tag library.The network interface of the computer equipment is used for and outside
Terminal passes through network connection communication.A kind of identification side of bond default risk is realized when the computer program is executed by processor
Method.
It will be understood by those skilled in the art that structure shown in Fig. 5, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, the processor perform the steps of when executing computer program
When receiving the inquiry request for being used to obtain bond default risk to be identified of terminal transmission, debt to be identified is obtained
The related information of certificate, and determine that the target industry type of bond to be identified and target issue enterprise from related information;
First news corpus data relevant to bond to be identified are obtained from database, wherein the first news corpus data
The news of news corpus data and target the distribution enterprise of news corpus data, target industry type including bond to be identified
Corpus data;
Event keyword is extracted from the first news corpus data, by event keyword and preset event of default tag library
In event tag matched, obtain matching result;It include the event tag of different event type in event of default tag library
And the risk class value of event tag, it include the object event label being matched to, the thing of object event label in matching result
The risk class value of part type and object event label;
The default risk grade of bond to be identified is determined according to matching result, and according to matching result and default risk etc.
Grade generates default risk information;
Default risk information is sent to terminal, default risk information is used to indicate terminal display matching result and promise breaking
Risk class.
In one embodiment, it is also performed the steps of when processor executes computer program and obtains history default bond,
And determine default time, industry type and the distribution enterprise of history default bond;Crawl the second news language in default time
Expect that data, the second news corpus data include the news corpus data of history default bond, the news corpus data for issuing enterprise
And the news corpus data of industry type;Different event tags is extracted from each second news corpus data, and to each thing
Different risk class values is arranged in part label;The event type for determining the second news corpus data, according to event type, event mark
The risk class value of label and event tag generates event of default tag library.
In one embodiment, processor executes computer program and realizes that extraction is different from each second news corpus data
Event tag step when, implement following steps: to the second news corpus data carry out pretreatment obtain the second news
The word of corpus, and obtain the term vector of each word;Text emotion analysis is carried out to the second news corpus data using term vector,
Obtain the text emotion of news corpus data;The targeted news corpus data that text emotion is negative emotion is filtered out, and from mesh
Negative keyword is extracted in mark news corpus data;Using negative keyword as event class corresponding with targeted news corpus data
The event tag of type.
In one embodiment, processor, which executes computer program and realizes, each event tag is arranged different risk class
When the step of value, following steps are implemented: counting the number that the event tag of each history default bond occurs, generate event mark
Sign matrix;The probability value that each event tag occurs is calculated according to event tag matrix;It is determined according to the probability value of each event tag
The risk class value of each event tag.
In one embodiment, processor executes computer program and realizes that extracting event from the first news corpus data closes
Keyword matches event keyword with the event tag in event of default tag library, when obtaining the step of matching result, tool
Body performs the steps of the term vector that event keyword is obtained using default term vector model;All term vectors are input to pre-
First in trained SVM model, the confidence level of term vector Yu each event tag is calculated;The highest event tag of confidence level is true
It is set to and the matched object event label of event keyword.
In one embodiment, processor executes computer program realization and determines disobeying for bond to be identified according to matching result
About the step of risk class when, implement following steps: reading object event label and object event from matching result
The risk class value of label;The risk class value of object event label is added to obtain the risk total value of bond to be identified;Work as wind
Dangerous total value is less than or equal to the first preset threshold, and the default risk grade of bond to be identified is determined as security level;When risk is total
Value is greater than the first preset threshold and less than the second preset threshold, and the default risk grade of bond to be identified is determined as low-risk etc.
Grade;When risk total value is greater than the second preset threshold, the default risk grade of bond to be identified is determined as high-risk grade.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
When receiving the inquiry request for being used to obtain bond default risk to be identified of terminal transmission, debt to be identified is obtained
The related information of certificate, and determine that the target industry type of bond to be identified and target issue enterprise from related information;
First news corpus data relevant to bond to be identified are obtained from database, wherein the first news corpus data
The news of news corpus data and target the distribution enterprise of news corpus data, target industry type including bond to be identified
Corpus data;
Event keyword is extracted from the first news corpus data, by event keyword and preset event of default tag library
In event tag matched, obtain matching result;It include the event tag of different event type in event of default tag library
And the risk class value of event tag, it include the object event label being matched to, the thing of object event label in matching result
The risk class value of part type and object event label;
The default risk grade of bond to be identified is determined according to matching result, and according to matching result and default risk etc.
Grade generates default risk information;
Default risk information is sent to terminal, default risk information is used to indicate terminal display matching result and promise breaking
Risk class.
In one embodiment, it is also performed the steps of when computer program is executed by processor and obtains history promise breaking debt
Certificate, and determine default time, industry type and the distribution enterprise of history default bond;Crawl the second news in default time
Corpus data, the second news corpus data include the news corpus data of history default bond, the news corpus number for issuing enterprise
Accordingly and the news corpus data of industry type;Different event tags is extracted from each second news corpus data, and to each
Different risk class values is arranged in event tag;The event type for determining the second news corpus data, according to event type, event
The risk class value of label and event tag generates event of default tag library.
In one embodiment, computer program is executed by processor realization and extracts not from each second news corpus data
When the step of same event tag, following steps are implemented: pretreatment being carried out to the second news corpus data and obtains second newly
The word of corpus is heard, and obtains the term vector of each word;Text emotion point is carried out to the second news corpus data using term vector
Analysis, obtains the text emotion of news corpus data;Text emotion is filtered out as the targeted news corpus data of negative emotion, and from
Negative keyword is extracted in targeted news corpus data;Using negative keyword as event corresponding with targeted news corpus data
The event tag of type.
In one embodiment, computer program be executed by processor realization each event tag is arranged different risks etc.
When the step of grade value, following steps are implemented: counting the number that the event tag of each history default bond occurs, generate event
Label matrix;The probability value that each event tag occurs is calculated according to event tag matrix;Probability value according to each event tag is true
The risk class value of fixed each event tag.
In one embodiment, computer program is executed by processor realization and extracts event from the first news corpus data
Keyword matches event keyword with the event tag in event of default tag library, when obtaining the step of matching result,
It implements following steps: obtaining the term vector of event keyword using default term vector model;All term vectors are input to
In preparatory trained SVM model, the confidence level of term vector Yu each event tag is calculated;By the highest event tag of confidence level
It is determined as and the matched object event label of event keyword.
In one embodiment, computer program is executed by processor realization and determines bond to be identified according to matching result
When the step of default risk grade, following steps are implemented: object event label and target thing are read from matching result
The risk class value of part label;The risk class value of object event label is added to obtain the risk total value of bond to be identified;When
Risk total value is less than or equal to the first preset threshold, and the default risk grade of bond to be identified is determined as security level;Work as risk
Total value is greater than the first preset threshold and less than the second preset threshold, and the default risk grade of bond to be identified is determined as low-risk etc.
Grade;When risk total value is greater than the second preset threshold, the default risk grade of bond to be identified is determined as high-risk grade.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of recognition methods of bond default risk, which comprises
When receiving the inquiry request for being used to obtain bond default risk to be identified of terminal transmission, bond to be identified is obtained
Related information, and determine that the target industry type of the bond to be identified and target distribution are looked forward to from the related information
Industry;
First news corpus data relevant to the bond to be identified are obtained from database, wherein first news corpus
Data include the news corpus data of the bond to be identified, the news corpus data of target industry type and target hair
The news corpus data of row enterprise;
Event keyword is extracted from the first news corpus data, by the event keyword and preset event of default mark
Event tag in label library is matched, and matching result is obtained;Including different event type in the event of default tag library
The risk class value of event tag and the event tag, include in the matching result object event label being matched to,
The risk class value of the event type of the object event label and the object event label;
The default risk grade of the bond to be identified is determined according to the matching result, and according to the matching result and institute
It states default risk grade and generates default risk information;
The default risk information is sent to the terminal, the default risk information is used to indicate described in the terminal display
Matching result and the default risk grade.
2. the method according to claim 1, wherein described by the event keyword and preset event of default
Before the step of event tag in tag library is matched, further includes:
History default bond is obtained, and determines default time, industry type and the distribution enterprise of the history default bond;
The second news corpus data in the default time are crawled, the second news corpus data include the history promise breaking
The news corpus data of the news corpus data of bond, the news corpus data of the distribution enterprise and the industry type;
Different event tags is extracted from each second news corpus data, and each event tag is arranged different
Risk class value;
The event type for determining the second news corpus data, according to the event type, the event tag and described
The risk class value of event tag generates event of default tag library.
3. according to the method described in claim 2, it is characterized in that, described extract not from each second news corpus data
With event tag the step of, comprising:
Pretreatment is carried out to the second news corpus data and obtains the word of the second news corpus, and obtains each word
Term vector;
Text emotion analysis is carried out to the second news corpus data using the term vector, obtains the news corpus data
Text emotion;
It filters out text emotion and is the targeted news corpus data of negative emotion, and extracted from the targeted news corpus data
Negative keyword;
Using the negative keyword as the event tag of event type corresponding with the targeted news corpus data.
4. according to the method described in claim 2, it is characterized in that, described each event tag is arranged different risks etc.
The step of grade value, comprising:
The number that the event tag of each history default bond occurs is counted, event tag matrix is generated;
The probability value that each event tag occurs is calculated according to event tag matrix;
The risk class value of each event tag is determined according to the probability value of each event tag.
5. the method according to claim 1, wherein described extract event from the first news corpus data
The event keyword is matched with the event tag in the event of default tag library, obtains matching result by keyword
The step of, comprising:
The term vector of event keyword is obtained using default term vector model;
All term vectors are input in preparatory trained SVM model, the term vector and each event tag are calculated
Confidence level;
The highest event tag of confidence level is determined as and the matched object event label of the event keyword.
6. the method according to claim 1, wherein described determine the debt to be identified according to the matching result
The step of default risk grade of certificate, comprising:
The risk class value of the object event label and the object event label is read from the matching result;
The risk class value of the object event label is added to obtain the risk total value of the bond to be identified;
When the risk total value is less than or equal to the first preset threshold, the default risk grade of the bond to be identified is determined as pacifying
Congruent grade;
When the risk total value is greater than first preset threshold and less than the second preset threshold, the promise breaking of the bond to be identified
Risk class is determined as low risk level;
When the risk total value is greater than second preset threshold, the default risk grade of the bond to be identified is determined as high wind
Dangerous grade.
7. a kind of identification device of bond default risk, which is characterized in that described device includes:
Bond to be identified obtains module, for when the inquiry for being used to obtain bond default risk to be identified for receiving terminal transmission
When request, the related information of bond to be identified is obtained, and determines the target of the bond to be identified from the related information
Industry type and target issue enterprise;
Corpus data obtains module, for obtaining first news corpus number relevant to the bond to be identified from database
According to, wherein the first news corpus data include the news corpus data of the bond to be identified, target industry type it is new
Hear the news corpus data of corpus data and target distribution enterprise;
Matching result generation module closes the event for extracting event keyword from the first news corpus data
Keyword is matched with the event tag in preset event of default tag library, obtains matching result;The event of default label
Include the event tag of different event type and the risk class value of the event tag in library, includes in the matching result
The event type of the object event label, the object event label that are matched to and the risk class of the object event label
Value;
Risk class obtains module, for determining the default risk grade of the bond to be identified according to the matching result, and
Default risk information is generated according to the matching result and the default risk grade;
Risk information sending module, for the default risk information to be sent to the terminal, the default risk information is used
Matching result and the default risk grade described in the instruction terminal display.
8. the identification device of bond default risk according to claim 7, which is characterized in that further include that tag library obtains mould
Block, the tag library obtain module and are used for:
History default bond is obtained, and determines default time, industry type and the distribution enterprise of the history default bond;
The second news corpus data in the default time are crawled, the second news corpus data include the history promise breaking
The news corpus data of the news corpus data of bond, the news corpus data of the distribution enterprise and the industry type;
Different event tags is extracted from each second news corpus data, and each event tag is arranged different
Risk class value;
The event type for determining the second news corpus data, according to the event type, the event tag and described
The risk class value of event tag generates event of default tag library.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 6 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 6 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811454178.8A CN109670837A (en) | 2018-11-30 | 2018-11-30 | Recognition methods, device, computer equipment and the storage medium of bond default risk |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811454178.8A CN109670837A (en) | 2018-11-30 | 2018-11-30 | Recognition methods, device, computer equipment and the storage medium of bond default risk |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109670837A true CN109670837A (en) | 2019-04-23 |
Family
ID=66145033
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811454178.8A Pending CN109670837A (en) | 2018-11-30 | 2018-11-30 | Recognition methods, device, computer equipment and the storage medium of bond default risk |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109670837A (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110377731A (en) * | 2019-06-18 | 2019-10-25 | 深圳壹账通智能科技有限公司 | Complain text handling method, device, computer equipment and storage medium |
CN110442713A (en) * | 2019-07-08 | 2019-11-12 | 深圳壹账通智能科技有限公司 | Abstract generation method, apparatus, computer equipment and storage medium |
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 |
CN110472025A (en) * | 2019-07-15 | 2019-11-19 | 平安科技(深圳)有限公司 | Processing method, device, computer equipment and the storage medium of session information |
CN110489631A (en) * | 2019-07-10 | 2019-11-22 | 平安科技(深圳)有限公司 | Stock market development method, apparatus, computer equipment and storage medium |
CN110688463A (en) * | 2019-10-11 | 2020-01-14 | 支付宝(杭州)信息技术有限公司 | Enterprise list processing method and device |
CN110782123A (en) * | 2019-09-18 | 2020-02-11 | 中国平安财产保险股份有限公司 | Matching method and device of decision scheme, computer equipment and storage medium |
CN111553818A (en) * | 2020-04-29 | 2020-08-18 | 搜信信用产业集团有限公司 | Intelligent monitoring contract performing dynamic tracking method, system, device and storage medium |
CN111583012A (en) * | 2020-03-23 | 2020-08-25 | 北京航空航天大学 | Method for evaluating default risk of credit, debt and debt main body by fusing text information |
CN111598691A (en) * | 2020-04-20 | 2020-08-28 | 北京航空航天大学 | Method, system and device for evaluating default risk of credit/debt main body |
CN112115710A (en) * | 2019-06-03 | 2020-12-22 | 腾讯科技(深圳)有限公司 | Industry information identification method and device |
CN112434163A (en) * | 2020-11-30 | 2021-03-02 | 北京沃东天骏信息技术有限公司 | Risk identification method, model construction method, risk identification device, electronic equipment and medium |
CN112750028A (en) * | 2020-12-30 | 2021-05-04 | 北京知因智慧科技有限公司 | Risk early warning method and device of event text based on entity extraction |
CN113505221A (en) * | 2020-03-24 | 2021-10-15 | 国家计算机网络与信息安全管理中心 | Enterprise false propaganda risk identification method, device and storage medium |
CN113822739A (en) * | 2021-08-11 | 2021-12-21 | 未鲲(上海)科技服务有限公司 | Product recommendation method and device, electronic equipment and storage medium |
CN115086086A (en) * | 2022-08-19 | 2022-09-20 | 湖南三湘银行股份有限公司 | Distributed monitoring method and device for data security |
WO2024040817A1 (en) * | 2022-08-25 | 2024-02-29 | 深圳市富途网络科技有限公司 | Bond risk information processing method based on big data and related device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050071217A1 (en) * | 2003-09-30 | 2005-03-31 | General Electric Company | Method, system and computer product for analyzing business risk using event information extracted from natural language sources |
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 |
CN107527288A (en) * | 2017-06-16 | 2017-12-29 | 兴业数字金融服务(上海)股份有限公司 | A kind of bond survival phase Warning System |
CN107909274A (en) * | 2017-11-17 | 2018-04-13 | 平安科技(深圳)有限公司 | Enterprise investment methods of risk assessment, device and storage medium |
-
2018
- 2018-11-30 CN CN201811454178.8A patent/CN109670837A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050071217A1 (en) * | 2003-09-30 | 2005-03-31 | General Electric Company | Method, system and computer product for analyzing business risk using event information extracted from natural language sources |
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 |
CN107527288A (en) * | 2017-06-16 | 2017-12-29 | 兴业数字金融服务(上海)股份有限公司 | A kind of bond survival phase Warning System |
CN107909274A (en) * | 2017-11-17 | 2018-04-13 | 平安科技(深圳)有限公司 | Enterprise investment methods of risk assessment, device and storage medium |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112115710A (en) * | 2019-06-03 | 2020-12-22 | 腾讯科技(深圳)有限公司 | Industry information identification method and device |
CN112115710B (en) * | 2019-06-03 | 2023-08-08 | 腾讯科技(深圳)有限公司 | Industry information identification method and device |
CN110377731A (en) * | 2019-06-18 | 2019-10-25 | 深圳壹账通智能科技有限公司 | Complain text handling method, device, computer equipment and storage medium |
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 |
CN110442713A (en) * | 2019-07-08 | 2019-11-12 | 深圳壹账通智能科技有限公司 | Abstract generation method, apparatus, computer equipment and storage medium |
CN110489631A (en) * | 2019-07-10 | 2019-11-22 | 平安科技(深圳)有限公司 | Stock market development method, apparatus, computer equipment and storage medium |
CN110472025A (en) * | 2019-07-15 | 2019-11-19 | 平安科技(深圳)有限公司 | Processing method, device, computer equipment and the storage medium of session information |
CN110472025B (en) * | 2019-07-15 | 2024-01-30 | 平安科技(深圳)有限公司 | Method, device, computer equipment and storage medium for processing session information |
CN110782123A (en) * | 2019-09-18 | 2020-02-11 | 中国平安财产保险股份有限公司 | Matching method and device of decision scheme, computer equipment and storage medium |
CN110688463A (en) * | 2019-10-11 | 2020-01-14 | 支付宝(杭州)信息技术有限公司 | Enterprise list processing method and device |
CN111583012B (en) * | 2020-03-23 | 2021-09-21 | 北京航空航天大学 | Method for evaluating default risk of credit, debt and debt main body by fusing text information |
CN111583012A (en) * | 2020-03-23 | 2020-08-25 | 北京航空航天大学 | Method for evaluating default risk of credit, debt and debt main body by fusing text information |
CN113505221A (en) * | 2020-03-24 | 2021-10-15 | 国家计算机网络与信息安全管理中心 | Enterprise false propaganda risk identification method, device and storage medium |
CN113505221B (en) * | 2020-03-24 | 2024-03-12 | 国家计算机网络与信息安全管理中心 | Enterprise false propaganda risk identification method, equipment and storage medium |
CN111598691A (en) * | 2020-04-20 | 2020-08-28 | 北京航空航天大学 | Method, system and device for evaluating default risk of credit/debt main body |
CN111553818A (en) * | 2020-04-29 | 2020-08-18 | 搜信信用产业集团有限公司 | Intelligent monitoring contract performing dynamic tracking method, system, device and storage medium |
CN112434163A (en) * | 2020-11-30 | 2021-03-02 | 北京沃东天骏信息技术有限公司 | Risk identification method, model construction method, risk identification device, electronic equipment and medium |
CN112750028A (en) * | 2020-12-30 | 2021-05-04 | 北京知因智慧科技有限公司 | Risk early warning method and device of event text based on entity extraction |
CN113822739A (en) * | 2021-08-11 | 2021-12-21 | 未鲲(上海)科技服务有限公司 | Product recommendation method and device, electronic equipment and storage medium |
CN115086086A (en) * | 2022-08-19 | 2022-09-20 | 湖南三湘银行股份有限公司 | Distributed monitoring method and device for data security |
CN115086086B (en) * | 2022-08-19 | 2022-11-11 | 湖南三湘银行股份有限公司 | Distributed monitoring method and device for data security |
WO2024040817A1 (en) * | 2022-08-25 | 2024-02-29 | 深圳市富途网络科技有限公司 | Bond risk information processing method based on big data and related device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109670837A (en) | Recognition methods, device, computer equipment and the storage medium of bond default risk | |
CN110489520B (en) | Knowledge graph-based event processing method, device, equipment and storage medium | |
CN111177569B (en) | Recommendation processing method, device and equipment based on artificial intelligence | |
CN109523153A (en) | Acquisition methods, device, computer equipment and the storage medium of illegal fund collection enterprise | |
CN109634698B (en) | Menu display method and device, computer equipment and storage medium | |
US11062413B1 (en) | Automated secondary linking for fraud detection systems | |
CN109767327A (en) | Customer information acquisition and its application method based on anti money washing | |
CN109710402A (en) | Method, apparatus, computer equipment and the storage medium of process resource acquisition request | |
CN108334625B (en) | User information processing method and device, computer equipment and storage medium | |
CN109299094A (en) | Tables of data processing method, device, computer equipment and storage medium | |
CN107644106B (en) | Method, terminal device and storage medium for automatically mining service middleman | |
CN109542956A (en) | Report form generation method, device, computer equipment and storage medium | |
WO2022116419A1 (en) | Automatic determination method and apparatus for domain name infringement, electronic device, and storage medium | |
CN109767326A (en) | Suspicious transaction reporting generation method, device, computer equipment and storage medium | |
CN113177700B (en) | Risk assessment method, system, electronic equipment and storage medium | |
CN111666346A (en) | Information merging method, transaction query method, device, computer and storage medium | |
CN109767226A (en) | Suspicious transaction statistical views generation method and device based on big data | |
CN112084342A (en) | Test question generation method and device, computer equipment and storage medium | |
CN109271624A (en) | A kind of target word determines method, apparatus and storage medium | |
CN113837836A (en) | Model recommendation method, device, equipment and storage medium | |
CN113887214A (en) | Artificial intelligence based wish presumption method and related equipment thereof | |
CN109582834B (en) | Data risk prediction method and device | |
CN116155597A (en) | Access request processing method and device and computer equipment | |
CN115544214A (en) | Event processing method and device and computer readable storage medium | |
CN110309312B (en) | Associated event acquisition method and device |
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 |