CN110019841A - Construct data analysing method, the apparatus and system of debtor's knowledge mapping - Google Patents
Construct data analysing method, the apparatus and system of debtor's knowledge mapping Download PDFInfo
- Publication number
- CN110019841A CN110019841A CN201810815397.8A CN201810815397A CN110019841A CN 110019841 A CN110019841 A CN 110019841A CN 201810815397 A CN201810815397 A CN 201810815397A CN 110019841 A CN110019841 A CN 110019841A
- Authority
- CN
- China
- Prior art keywords
- information
- debtor
- entity
- entity set
- knowledge mapping
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Abstract
The invention discloses a kind of data analysing method, apparatus and systems for constructing debtor's knowledge mapping, which comprises the first information relevant to the debtor is obtained, wherein the first information includes debtor's essential information；Structuring processing is carried out to the first information, extracts entity information；It is associated with the entity information and constructs entity set；When the entity set and preset data structure match, the entity set is exported.Structuring processing is carried out by the relevant information to debtor, and construct entity set, so that a large amount of data or message structure, it being capable of more detailed understanding debtor's situation, and the comprehensive displaying knowledge mapping of the debtor's information for having loan repayment capacity and refund wish is analyzed, to improve the working efficiency in the interpellation course of work.
Description
Technical field
The present invention relates to debt management fields, and in particular to it is a kind of construct debtor's knowledge mapping data analysing method,
Apparatus and system.
Background technique
With the rapid development of social economy and information technology, people increasingly increase the demand of fund, common gold
Melt operational means to be borrowed or lent money or invested by bank or personalized lending market.
Ordinary loan is to provide a large number of fund by loaning bill tissue to give credit side's use, and credit side then becomes debtor, it is necessary to
It refunds on schedule (as monthly) and gives loaning bill tissue.Traditional simple loan system, sometimes because credit side economic problems or other
Factor and insolvency, so that the risk of bad debt occurs, such case is once can generate loss as debit if generation.
It is covered in the interpellation of the poor sources management after the loan of financial field, collection operation process at present a large amount of
Manual operation, especially to the inquiry of the information of debtor, search, the real information of debtor is veritified, often in order to find debt
The current effective connection mode of business people can consume staff's a large amount of time.At present there is no effective solution schemes.
Summary of the invention
To solve the above problems, the present invention provides a kind of data analysing method for constructing debtor's knowledge mapping, method packet
It includes: the first information relevant to the debtor is obtained, wherein the first information includes debtor's essential information；To described
One information carries out structuring processing, extracts entity information；It is associated with the entity information and constructs entity set；When the entity set with
When preset data structure matches, the entity set is exported.
In a possible embodiment, the acquisition first information relevant to the debtor includes passing through network
Collector and/or the first information is obtained by interaction end.
In a possible embodiment, structuring processing is carried out to the first information by preset relationship templates,
Extract entity information.
In a possible embodiment, realize that entity information extracts by natural language processing NLP technology.
In a possible embodiment, it when the entity set is mutually mismatched with preset data structure, does not obtain not
The first information with part.
In a possible embodiment, the entity set includes debtor's organization information entity set, debtor periphery letter
Cease entity set.
The invention also discloses a kind of data analysis set-ups for constructing debtor's knowledge mapping, comprising: data obtaining module,
For obtaining the first information relevant to the debtor, wherein the first information includes debtor's essential information；Structuring
Processing module extracts entity information for carrying out structuring processing to the first information；Relating module, it is described for being associated with
Entity information simultaneously constructs entity set；Matching module, for exporting institute when the entity set matches with preset data structure
State entity set.
In a possible embodiment, the acquisition module, for being obtained by network collector and/or by interaction end
Take the first information.
In a possible embodiment, the structuring processing module, for passing through preset relationship templates to described
The first information carries out structuring processing, extracts entity information.
In a possible embodiment, realize that entity information extracts by natural language processing NLP technology.
In a possible embodiment, the matching module is also used to, when the entity set and preset data structure
When mutually mismatching, the first information of non-compatible portion is obtained.
In a possible embodiment, the invention also discloses a kind of data for constructing debtor's knowledge mapping to analyze system
System, aforementioned data analytical equipment and interaction end.Compared with prior art, technical solution of the present invention has the advantage that
Using the above scheme, the knowledge mapping of debtor and collection person are sketched out by data mining and artificial intelligence, are solved
Certainly personal finance non-performing asset management organization face not high a large amount of original client qualities of data, structuring and standardization it is insufficient,
It is dispersed in " predicament " that can not directly utilize in " isolated island ".Low price Value Data is automatically converted into as height by carrying out data improvement
The data of quality improve collection working efficiency to realize the Proper Match of collection person and debtor.
Detailed description of the invention
Fig. 1 is a kind of debt management network architecture schematic diagram in the embodiment of the present invention；
Fig. 2 is the data analysing method flow chart that debtor's knowledge mapping is constructed in the embodiment of the present invention；
Fig. 3 is debtor's entity set relational graph in the embodiment of the present invention；
Fig. 4 is the data analysis set-up block diagram that debtor's knowledge mapping is constructed in the embodiment of the present invention.
Specific embodiment
Such as Fig. 1, a kind of debt management network architecture is disclosed, which can pass through data mining analysis debtor's information
With the knowledge mapping information of collection person, it is embodied as different debtors and matches most suitable collection person.The system comprises cloud clothes
Business device 10, terminal 20, and the network node 30 for connecting Cloud Server 10 and terminal 20.Wherein, cloud
Server 10 can be used for realizing the storage, calculating and transmission of data；Terminal 20 can be used for providing a user graphical user
Interface inputs the data information of the various needs such as debtor, collection person convenient for user, and terminal 20 can be mobile electricity
Words, portable device, computer etc..
Such as Fig. 2, it is based on the aforementioned debt management network architecture, the embodiment of the invention discloses a kind of building debtor's knowledge graphs
The data analysing method of spectrum is applicable to Cloud Server 10, this method comprises:
S100 obtains the first information relevant to debtor, wherein the first information includes debtor's essential information, example
Such as name, address, phone, native place can also be the public information etc. of debtor work unit；
S102 carries out structuring processing to the first information, extracts entity information, wherein entity information refers to related to debt
Information.Such as administrative unit's contact method etc. of affiliated native place can be obtained by native place information.
S104 is associated with the entity information and constructs entity set；
S106 exports the entity set when the entity set meets preset data structure.Debt is preset in systems
The data structure of people's relevant information matches the entity set of construction complete with preset data structure, if successful match
Then export the entity set.
Structuring processing is carried out by the relevant information to debtor, and constructs entity set, so that a large amount of data
Or message structure, can more detailed understanding debtor's situation, and to the debtor for having loan repayment capacity and refund wish
The comprehensive displaying knowledge mapping analysis of information, to improve the working efficiency in the interpellation course of work.
In one embodiment, obtaining the first information relevant to debtor can be obtained by network collector, can also be led to
Terminal acquisition is crossed, such as relevant information is manually entered.
If it is network collector is used, goes to obtain relevant information on network according to the existing information of user, be deposited after acquisition
The entity for having correlation is stored by natural language processing NLP, forms entity set, completion debtor's information by storage.
For example, being stored with the partial information of debtor in Cloud Server 10, such as ID card information etc. can be according to the information
The information such as state administration region, open call, corporate facility are disclosed using distributed network collector crawl internet, other nothings
The information of method crawl is by manual entry and stores in the database.Network collector passes through list page, the details to targeted website
The crawl to internet public information is completed in the crawl and parsing of page, dynamic data interface and alternative document.
If it is use terminal 20, user can by debtor's information of interactive interface batch import format,
Debtor's information may include: business number, debtor's title, certificate number, unit one belongs to, household register address, phone number.
In one embodiment, structuring processing can be carried out to the first information by preset relationship templates, extracts entity
Information.For example, the information grabbed from network is carried out key message structuring processing one by one, extract entity information, as phone,
Location, mechanism etc..
In one embodiment, structuring pretreatment is carried out to some key messages, it can be by using the side of machine learning
Method constructs deep neural network, is trained to the sample comprising the aiming field marked within a context, passes through training
Good relationship templates carry out derivation extraction to the information that other are not marked.
For example, realizing that entity information extracts by natural language processing NLP technology.User inputs or collector obtains
Information, can not can not form related information with other information, need to collected information using NLP technology extract entity,
Proper noun.For example collected address information is the Nanjing Gulou District lane Luo Lang 251, system needs to extract drum tower
Area's common telephone number information.It is extracted firstly the need of by Gulou District with NLP, state administration coding is then converted into, with this
Public telephone information corresponding with coding administrative in database compares.
It needs to analyze the information of extraction again after extraction, forms entity set, storage is in the database.Such as entity set packet
Include organization information entity set and peripheral information entity set.Organization information entity set include mechanism responsible person, data, industrial and commercial information,
Legal person, phone, address；Peripheral information entity set includes committee, village, occupies the public organizations such as committee, Wei Jiwei, property, pharmacy, restaurant, silver
The life service informations such as row, convenience store.Referring to Fig. 3.
In one embodiment, the data structure of debtor is preset, such as debtor's data structure includes 7 big elements: surname
Name, phone, identity card, household register way address, residence address, unit information, contact information.Wherein, identity card address, household register
Way address can extract affiliated province, city and region, while can extract place villagers' committee, person neighbourhood committee, neighbourhood committee, government, send
The information of the public resources such as institute, health-center.In step s 106, by the entity set of formation and the progress of preset data structure
Match, stores corresponding informance if matching；If cannot exactly match, unmatched part can continue manually add or
Network crawl.Similarly, it cannot exactly match, can be manually added in the systems such as legal person, business address, contact method in unit information
Or network crawl.
In one embodiment, if still not grabbing relevant information by the preset time, then it is assumed that do not have
Related content stops grabbing information from network.
By preceding method, the information of debtor is searched for and excavated in all directions, first by ID card information
Data mining, imply bulk information real information in identity card, such as: birthplace, age, constellation, symbolic animal of the birth year, gender, family
Nationality, native place, regional GDP, etc. related data informations, while the residence and unit address of debtor analyzed, can be divided
A large amount of information is precipitated, such as: inhabitation room rate, income level, consuming capacity, loan repayment capacity, degree of accepting the education, periphery consumption
Environment, transportation cost take in stability, company's negative information, unit contact method etc..To understand debtor individual's letter in detail
The peripheral information of breath and debtor, in order to find defence line at heart, focus and the weakness of debtor, during reaching interpellation
Effective close advise legal communication.
Corresponding to the above method, a kind of data analysis for constructing debtor's knowledge mapping is also disclosed in the embodiment of the present invention
Device 40, as shown in figure 4, include data obtaining module 400, for obtaining the first information relevant to the debtor, wherein
The first information includes debtor's essential information；Structuring processing module 402, for carrying out structuring to the first information
Entity information is extracted in processing；Relating module 404, for being associated with the entity information and constructing entity set；Matching module 406 is used
In when the entity set matches with preset data structure, the entity set is exported.It is real that the device corresponds to preceding method
Example is applied, specific descriptions above-mentioned are also applied for the device, therefore repeat no more.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium may include: ROM, RAM, disk or CD etc..
Although present disclosure is as above, present invention is not limited to this.Anyone skilled in the art are not departing from this
It in the spirit and scope of invention, can make various changes or modifications, therefore protection scope of the present invention should be with claim institute
Subject to the range of restriction.
In addition, the terms "and/or", only a kind of incidence relation for describing affiliated partner, indicates may exist
Three kinds of relationships, for example, A and/or B, can indicate: individualism A exists simultaneously A and B, these three situations of individualism B.Separately
Outside, character "/" herein typicallys represent the relationship that forward-backward correlation object is a kind of "or".
It is apparent to those skilled in the art that for convenience of description and succinctly, foregoing description is
The specific work process of system, device and unit, can refer to corresponding processes in the foregoing method embodiment, details are not described herein.
In several embodiments provided herein, it should be understood that disclosed systems, devices and methods, it can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the division of unit,
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be with
In conjunction with or be desirably integrated into another system, or some features can be ignored or not executed.
Unit may or may not be physically separated as illustrated by the separation member, shown as a unit
Component may or may not be physical unit, it can and it is in one place, or may be distributed over multiple networks
On unit.It can select some or all of unit therein according to the actual needs to realize the mesh of the embodiment of the present invention
's.
Claims (12)
1. a kind of data analysing method for constructing debtor's knowledge mapping, which is characterized in that the described method includes:
The first information relevant to the debtor is obtained, wherein the first information includes debtor's essential information；
Structuring processing is carried out to the first information, extracts entity information；
It is associated with the entity information and constructs entity set；
When the entity set and preset data structure match, the entity set is exported.
2. the method as described in claim 1, which is characterized in that described to obtain first information packet relevant to the debtor
It includes, obtains the first information by network collector and/or by interaction end.
3. the method as described in claim 1, which is characterized in that tied by preset relationship templates to the first information
Structureization processing, extracts entity information.
4. method as claimed in claim 1 or 3, which is characterized in that realize entity information by natural language processing NLP technology
It extracts.
5. the method as described in claim 1, which is characterized in that further include, when the entity set and preset data structure phase
When mismatch, the first information of non-compatible portion is obtained.
6. the method as described in any one of claim 1,3,5, which is characterized in that the entity set includes debt robot mechanism letter
Cease entity set, debtor's peripheral information entity set.
7. a kind of data analysis set-up for constructing debtor's knowledge mapping characterized by comprising
Data obtaining module, for obtaining the first information relevant to the debtor, wherein the first information includes debt
People's essential information；
Structuring processing module extracts entity information for carrying out structuring processing to the first information；
Relating module, for being associated with the entity information and constructing entity set；
Matching module, for exporting the entity set when the entity set matches with preset data structure.
8. data analysis set-up as claimed in claim 7, which is characterized in that the acquisition module, for being acquired by network
Device and/or the first information is obtained by interaction end.
9. data analysis set-up as claimed in claim 7, which is characterized in that the structuring processing module, for by pre-
The relationship templates set carry out structuring processing to the first information, extract entity information.
10. the data analysis set-up as described in claim 7 or 9, which is characterized in that real by natural language processing NLP technology
Real body information extraction.
11. data analysis set-up as claimed in claim 7, which is characterized in that the matching module is also used to, when the entity
When collection is mutually mismatched with preset data structure, the first information of non-compatible portion is obtained.
12. a kind of data analysis system for constructing debtor's knowledge mapping, which is characterized in that including any in claim 7-11
Data analysis set-up and interaction end described in.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810815397.8A CN110019841A (en) | 2018-07-24 | 2018-07-24 | Construct data analysing method, the apparatus and system of debtor's knowledge mapping |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810815397.8A CN110019841A (en) | 2018-07-24 | 2018-07-24 | Construct data analysing method, the apparatus and system of debtor's knowledge mapping |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110019841A true CN110019841A (en) | 2019-07-16 |
Family
ID=67188332
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810815397.8A Pending CN110019841A (en) | 2018-07-24 | 2018-07-24 | Construct data analysing method, the apparatus and system of debtor's knowledge mapping |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110019841A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110399932A (en) * | 2019-07-31 | 2019-11-01 | 中国工商银行股份有限公司 | Soft Clause in Letter of Credit recognition methods and device |
| CN111178615A (en) * | 2019-12-24 | 2020-05-19 | 成都数联铭品科技有限公司 | Construction method and system of enterprise risk identification model |
| CN111553789A (en) * | 2020-04-28 | 2020-08-18 | 中国银行股份有限公司 | Method and device for distributing joint credit and debit amount of multi-entity company |
| CN113486124A (en) * | 2021-05-24 | 2021-10-08 | 山东佳联电子商务有限公司 | Bank bad asset management and management system, method, equipment and storage medium based on PCA and knowledge graph technology |
| CN113779136A (en) * | 2021-09-08 | 2021-12-10 | 平安银行股份有限公司 | Debt clearing object determining method and device based on knowledge graph and electronic equipment |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108182295A (en) * | 2018-02-09 | 2018-06-19 | 重庆誉存大数据科技有限公司 | A kind of Company Knowledge collection of illustrative plates attribute extraction method and system |
-
2018
- 2018-07-24 CN CN201810815397.8A patent/CN110019841A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108182295A (en) * | 2018-02-09 | 2018-06-19 | 重庆誉存大数据科技有限公司 | A kind of Company Knowledge collection of illustrative plates attribute extraction method and system |
Non-Patent Citations (1)
| Title |
|---|
| 李文哲: "知识图谱在互联网金融中的应用", 《HTTPS://WWW.INFOQ.CN/ARTICLE/APPLICATION-OF-KNOWLEDGE-GRAPH/》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110399932A (en) * | 2019-07-31 | 2019-11-01 | 中国工商银行股份有限公司 | Soft Clause in Letter of Credit recognition methods and device |
| CN111178615A (en) * | 2019-12-24 | 2020-05-19 | 成都数联铭品科技有限公司 | Construction method and system of enterprise risk identification model |
| CN111178615B (en) * | 2019-12-24 | 2023-10-27 | 成都数联铭品科技有限公司 | Method and system for constructing enterprise risk identification model |
| CN111553789A (en) * | 2020-04-28 | 2020-08-18 | 中国银行股份有限公司 | Method and device for distributing joint credit and debit amount of multi-entity company |
| CN113486124A (en) * | 2021-05-24 | 2021-10-08 | 山东佳联电子商务有限公司 | Bank bad asset management and management system, method, equipment and storage medium based on PCA and knowledge graph technology |
| CN113779136A (en) * | 2021-09-08 | 2021-12-10 | 平安银行股份有限公司 | Debt clearing object determining method and device based on knowledge graph and electronic equipment |
| CN113779136B (en) * | 2021-09-08 | 2024-04-19 | 平安银行股份有限公司 | Knowledge-graph-based debt collection object determining method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110019841A (en) | Construct data analysing method, the apparatus and system of debtor's knowledge mapping | |
| CN110489561A (en) | Knowledge mapping construction method, device, computer equipment and storage medium | |
| WO2022126963A1 (en) | Customer profiling method based on customer response corpora, and device related thereto | |
| CN111598143B (en) | Credit evaluation-based defense method for federal learning poisoning attack | |
| EP3485435A1 (en) | System and method for automatic learning of functions | |
| CN110751286A (en) | Training method and training system of neural network model | |
| CN110929039A (en) | Data processing method, device, equipment and storage medium | |
| CN110399533A (en) | Funds flow querying method and device | |
| Lohokare et al. | Automated data collection for credit score calculation based on financial transactions and social media | |
| CN106294676B (en) | A kind of data retrieval method of ecommerce government system | |
| CN107193974A (en) | Localized information based on artificial intelligence determines method and apparatus | |
| CN107679977A (en) | A kind of tax administration platform and implementation method based on semantic analysis | |
| CN111198969A (en) | Economic information consultation system and method based on network big data | |
| CN106779803A (en) | A kind of method that financial institution's flowing water is matched with carrier data | |
| CN116108934B (en) | Federal learning system, federal learning method and federal learning device | |
| CN110751287A (en) | Training method and system and prediction method and system of neural network model | |
| CN113822542A (en) | Enterprise credit investigation platform construction method based on government affair big data | |
| CN110197426A (en) | A kind of method for building up of credit scoring model, device and readable storage medium storing program for executing | |
| CN107563588A (en) | A kind of acquisition methods of personal credit and acquisition system | |
| WO2021093320A1 (en) | Method and apparatus for outputting information | |
| CN112417060A (en) | Method, device, equipment and computer readable medium for identifying enterprise relationship | |
| CN116071150A (en) | Data processing method, bank product popularization, wind control system, server and medium | |
| CN106779873A (en) | It is a kind of based on telecom operators' data acquisition, the method for collecting, concluding the business | |
| CN114417974B (en) | Model training method, information processing device, electronic equipment and medium | |
| CN113407734B (en) | Method for constructing knowledge graph system based on real-time big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190716 |