CN110197280A - A kind of knowledge mapping construction method, apparatus and system - Google Patents
A kind of knowledge mapping construction method, apparatus and system Download PDFInfo
- Publication number
- CN110197280A CN110197280A CN201910418358.9A CN201910418358A CN110197280A CN 110197280 A CN110197280 A CN 110197280A CN 201910418358 A CN201910418358 A CN 201910418358A CN 110197280 A CN110197280 A CN 110197280A
- Authority
- CN
- China
- Prior art keywords
- data
- enterprise
- knowledge
- semi
- 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.)
- Granted
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
- G06F16/36—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
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
Abstract
This specification embodiment discloses a kind of knowledge mapping construction method, apparatus and system, and the method includes the unstructured datas, semi-structured data and structural data according to industrial chain Relation acquisition target topic；Natural language processing carried out to the unstructured data, and to after natural language processing unstructured data and the semi-structured data handled using machine learning algorithm；Data conversion is carried out to the structural data and using machine learning algorithm treated unstructured data, semi-structured data, obtains pending data；Knowledge Extraction and knowledge fusion are carried out to the pending data, obtain the corresponding knowledge mapping of the target topic.Using each embodiment of this specification, the accuracy and efficiency of knowledge mapping building can be increased substantially.
Description
Technical field
The present invention relates to computer data processing technology fields, particularly, are related to a kind of knowledge mapping construction method, device
And system.
Background technique
The appearance of knowledge mapping concept and technology promotes data utilization efficiency for financial institution, breaks through current production and operation
Predicament provides important directions, and the reasoning of knowledge based map is commenced business for financial institution provides the decision branch of efficiently and accurately
It holds.The building of financial field knowledge mapping, can instruct financial structure carry out efficient risk prevention system, accurately marketing obtain visitor,
The accurately future trend of prediction existing customer promotes multiparty service development, realizes all-win.But traditional knowledge graph
It is referenced single with the calculating data source of acquisition to compose construction method, and preprocessing process is excessively complicated, to seriously affect
The accuracy and efficiency of knowledge mapping building.
Summary of the invention
This specification embodiment is designed to provide a kind of knowledge mapping construction method, apparatus and system, can be improved
The accuracy and efficiency of knowledge mapping building.
This specification provides a kind of knowledge mapping construction method, apparatus and system includes under type realization such as:
A kind of knowledge mapping construction method, comprising:
According to the unstructured data, semi-structured data and structural data of industrial chain Relation acquisition target topic；
To the unstructured data carry out natural language processing, and to after natural language processing unstructured data and
The semi-structured data is handled using machine learning algorithm；
To the structural data and utilize machine learning algorithm treated unstructured data, semi-structured data
Data conversion is carried out, pending data is obtained；
Knowledge Extraction and knowledge fusion are carried out to the pending data, obtain the corresponding knowledge graph of the target topic
Spectrum.
It is described to unstructured after natural language processing in another embodiment of the method that this specification provides
Data and semi-structured data are handled using machine learning algorithm, comprising:
To after natural language processing unstructured data and the semi-structured data carry out it is poly- based on correlation rule
Class processing.
In another embodiment of the method that this specification provides, the structural data includes the friendship between enterprise
Easy data, business capital flowing information and financial product handle data, and the unstructured data includes the row of honouring an agreement of enterprise
For data, the unstructured data includes the public information data of enterprise.
In another embodiment of the method that this specification provides, the acquisition business datum to be processed includes:
Unstructured data, semi-structured number based on preset business rule and industrial chain Relation acquisition target topic
Accordingly and structural data, the business rule include preconfigured according to the corresponding service application scene of the target topic
Business process rule.
It is described that knowledge pumping is carried out to the pending data in another embodiment of the method that this specification provides
It takes, comprising:
Knowledge Extraction is carried out to the pending data based on sorting algorithm and expert knowledge library.
In another embodiment of the method that this specification provides, the method also includes:
The attribute data that Target Enterprise is obtained according to the knowledge mapping is determined according to the attribute data of the Target Enterprise
First risk profile result of Target Enterprise；
Relationship type between Target Enterprise and other enterprises, relationship degree are determined according to the knowledge mapping, according to other
Relationship type, the relationship degree of the attribute data of enterprise and other enterprises and Target Enterprise determine the second risk of Target Enterprise
Prediction result；
According to the first risk profile result and the second risk profile as a result, determining that the risk of the Target Enterprise is pre-
Survey result.
On the other hand, this specification embodiment also provides a kind of knowledge mapping construction device, and described device includes:
Data acquisition module, for unstructured data, the semi-structured number according to industrial chain Relation acquisition target topic
Accordingly and structural data；
First data processing module, for carrying out natural language processing to the unstructured data, and to natural language
Treated unstructured data and the semi-structured data are handled using machine learning algorithm；
Second data processing module, for the structural data and utilizing machine learning algorithm treated non-knot
Structure data, semi-structured data carry out data conversion, obtain pending data；
Knowledge mapping constructs module, for carrying out Knowledge Extraction and knowledge fusion to the pending data, described in acquisition
The corresponding knowledge mapping of target topic.
In another embodiment for the described device that this specification provides, first data processing module includes:
First data processing unit, for the unstructured data and the semi-structured data after natural language processing
Carry out the clustering processing based on correlation rule.
In another embodiment for the described device that this specification provides, described device further include:
Business rule configuration module is used for the target master according to the target topic corresponding service application scene configuration
Inscribe corresponding business rule；
Correspondingly, the data acquisition module is also used to based on the business rule and industrial chain Relation acquisition target master
Unstructured data, semi-structured data and the structural data of topic.
In another embodiment for the described device that this specification provides, the knowledge mapping building module includes:
Knowledge Extraction unit, for carrying out knowledge pumping to the pending data based on sorting algorithm and expert knowledge library
It takes.
In another embodiment for the described device that this specification provides, described device further includes risk profile module,
In, the risk profile module includes:
First risk profile unit, for obtaining the attribute data of Target Enterprise according to the knowledge mapping, according to described
The attribute data of Target Enterprise determines the first risk profile result of Target Enterprise；
Second risk profile unit, for determining the relationship between Target Enterprise and other enterprises according to the knowledge mapping
Type, relationship degree, according to relationship type, the relationship degree of the attribute data of other enterprises and other enterprises and Target Enterprise, really
Set the goal the second risk profile result of enterprise；
Third risk profile unit is used for according to the first risk profile result and the second risk profile as a result, really
The risk profile result of the fixed Target Enterprise.
On the other hand, this specification embodiment also provides a kind of knowledge mapping building equipment, including processor and for depositing
Store up processor-executable instruction memory, when described instruction is executed by the processor realization the following steps are included:
According to the unstructured data, semi-structured data and structural data of industrial chain Relation acquisition target topic；
To the unstructured data carry out natural language processing, and to after natural language processing unstructured data and
The semi-structured data is handled using machine learning algorithm；
To the structural data and utilize machine learning algorithm treated unstructured data, semi-structured data
Data conversion is carried out, pending data is obtained；
Knowledge Extraction and knowledge fusion are carried out to the pending data, obtain the corresponding knowledge graph of the target topic
Spectrum.
On the other hand, this specification embodiment also provides a kind of knowledge mapping building system, the data processing system packet
It includes at least one processor and stores the memory of computer executable instructions, the processor is realized when executing described instruction
The step of any one above-mentioned embodiment the method.
Knowledge mapping construction method, the apparatus and system of this specification one or more embodiment offer, can be based on gold
It is most true comprehensive to obtain enterprise from most basic line production and operation data for the entire industries chain relation for melting business development
Data, guarantee knowledge mapping initial data accuracy and covering surface.And it is directed to different types of data source, provide difference
Property, distributed data processing method, so as to further increase the accuracy and high efficiency of data processing.Utilize this
The each embodiment of specification can increase substantially the accuracy and efficiency of knowledge mapping building.
Detailed description of the invention
In order to illustrate more clearly of this specification embodiment or technical solution in the prior art, below will to embodiment or
Attached drawing needed to be used in the description of the prior art is briefly described, it should be apparent that, the accompanying drawings in the following description is only
The some embodiments recorded in this specification, for those of ordinary skill in the art, in not making the creative labor property
Under the premise of, it is also possible to obtain other drawings based on these drawings.In the accompanying drawings:
Fig. 1 is a kind of flow diagram for knowledge mapping construction method embodiment that this specification provides；
Fig. 2 is that the knowledge mapping in one embodiment that this specification provides constructs flow chart schematic diagram；
Fig. 3 is the risk profile flow diagram in another embodiment that this specification provides；
Fig. 4 is the modular structure schematic diagram that a kind of knowledge mapping that this specification provides constructs system embodiment；
Fig. 5 is the modular structure schematic diagram that another knowledge mapping that this specification provides constructs system embodiment；
Fig. 6 is the schematic configuration diagram according to the server of an exemplary embodiment of this specification.
Specific embodiment
In order to make those skilled in the art more fully understand the technical solution in this specification, below in conjunction with this explanation
Attached drawing in book one or more embodiment carries out the technical solution in this specification one or more embodiment clear, complete
Site preparation description, it is clear that described embodiment is only specification a part of the embodiment, instead of all the embodiments.Based on saying
Bright book one or more embodiment, it is obtained by those of ordinary skill in the art without making creative efforts all
The range of this specification example scheme protection all should belong in other embodiments.
The appearance of knowledge mapping concept and technology promotes data utilization efficiency for financial institution, breaks through current production and operation
Predicament provides important directions, and the reasoning of knowledge based map is commenced business for financial institution provides the decision branch of efficiently and accurately
It holds.The building of financial field knowledge mapping, can instruct financial structure carry out efficient risk prevention system, accurately marketing obtain visitor,
The accurately future trend of prediction existing customer promotes multiparty service development, realizes all-win.But traditional knowledge graph
It is referenced single with the calculating data source of acquisition to compose construction method, and preprocessing process is excessively complicated, to seriously affect
The accuracy and efficiency of knowledge mapping building.
Correspondingly, this specification embodiment provides a kind of knowledge mapping construction method, can be carried out based on financial business
Entire industries chain relation obtain the most true comprehensive data of enterprise, guarantee from most basic line production and operation data
The accuracy of knowledge mapping initial data and covering surface.And be directed to different types of data source, provide otherness, it is distributed
Data processing method, so as to further increase the accuracy and high efficiency of data processing.It is each using this specification
Embodiment can increase substantially the accuracy and efficiency of knowledge mapping building.
Fig. 1 is a kind of knowledge mapping construction method embodiment flow diagram that this specification provides.Although this theory
Bright book provides as the following examples or method operating procedure shown in the drawings or apparatus structure, but based on conventional or without wound
Less operating procedure or module list after the labour for the property made may include more in the method or device or part merging
Member.In the step of there is no necessary causalities in logicality or structure, the execution sequence of these steps or the module of device
Structure is not limited to this specification embodiment or execution shown in the drawings sequence or modular structure.The method or modular structure
Device, server or end product in practice is in application, can be according to embodiment or method shown in the drawings or module
Structure carry out sequence execution or it is parallel execute (such as parallel processor or multiple threads environment, even include distribution
Formula processing, server cluster implementation environment).
Specific one embodiment as shown in Figure 1, the knowledge mapping construction method that this specification provides one embodiment
In, the method may include:
S102: according to the unstructured data, semi-structured data and structuring of industrial chain Relation acquisition target topic
Data.
The target topic may include application field corresponding to knowledge mapping, application scenarios etc., such as Target Enterprise wind
Dangerous prevention and control, Target Enterprise behavior prediction etc..The industry chain relation can be the industrial chain carried out based on existing financial institution
Industry chain relation between each enterprise that financial business determines.
Core enterprise in financial institution and industrial chain remains close cooperative relationship, is looked forward to the core of financial industry chain
Centered on industry, the finance data for other enterprises that the acquisition that financial institution can be convenient is cooperated with core enterprise, thus accurately handle
The information such as smb message stream, cash flow and logistics are controlled, and then the corresponding basis of knowledge mapping building can be greatly improved
The accuracy of data acquisition.
The corresponding multi-source heterogeneous data of the target topic can be extracted, are used for based on determining industry chain relation
The building of knowledge mapping.In some embodiments, the multi-source heterogeneous data may include unstructured data, semi-structured number
Accordingly and structural data.
In some embodiments of this specification, the structural data may include transaction data between enterprise, enterprise
Capital Flow information and financial product handle data；The unstructured data may include the behavioral data of honouring an agreement of enterprise；
The unstructured data may include the public information data of enterprise.
Transaction data, business capital flowing information and the finance between enterprise can be obtained according to business chain data
Product handles the structural datas such as data.Such as available contract, selling inventory, buying order, accounts receivable, should pay a bill at order
Money, invoice, product stream and enterprise's silver ticket honour discount, quotient's ticket honours discount, mobility loan, capital turnover details etc.
The data such as fund stream information.It is also based on the government part of existing cooperation simultaneously, public service obtains honouring an agreement for enterprise
The semi-structured data such as behavioral data, such as tax information, public utilities payment information, enterprises registration financial report, the row of enterprise are ground
Data.It further, can be with unstructured datas such as the public information datas of enterprise, such as internet public feelings, internal report, prison
The data such as pipe file.
The scheme of this specification above-described embodiment, by accurately extracting the transaction data of enterprise based on industrial chain, enterprise provides
Golden flowing information and financial product handle the basic creation data such as data, it is then possible to utilize above-mentioned basic creation data pair
The scale of enterprise, the fund flow of enterprise, investment orientation of enterprise etc. are analyzed, and then can be improved to enterprise's total evaluation
Accurate control.Meanwhile the relationship enterprise is analyzed using the Transaction Information between enterprise, it can be improved and closed between enterprise
The accurate determination for degree of being.
Further, by obtaining the basic creation data in industrial chain, honour an agreement behavioral data and public information data
Equal multi-sources head data, can also further increase the comprehensive of data acquisition.And combine honour an agreement behavioral data and the public affairs of enterprise
Co-information data are assisted the determination between relationship degree enterprise's total evaluation and enterprise, can be further improved and obtained using building
The accuracy that the knowledge mapping obtained analyzes enterprise.
S104: natural language processing is carried out to the unstructured data, and to unstructured after natural language processing
Data and the semi-structured data are handled using machine learning algorithm.
For unstructured data, text conversion device can be first passed through, in unstructured data audio, video,
The information for including in picture is converted to text information, then carries out natural language processing (NLP processing) to text information, such as participle,
Introduce stop words etc..Then, the information by NLP processing carries out characteristic processing, as vectorization and Hash Trick are handled.So
Afterwards, then by the data obtained after above-mentioned processing it is input in machine learning algorithm, carries out data pick-up using machine learning model.
To the semi-structured data, data pick-up directly can be carried out using the machine learning model constructed in advance, really
Core information data included in semi-structured data are made, while realizing the unification of data format and mode.
By the above-mentioned means, can quickly and effectively extract included in unstructured data and semi-structured data
Core information data, as subsequent knowledge mapping building basic data.Data format and mode can also be realized simultaneously
It is unified, it is handled convenient for follow-up data.
In one embodiment of this specification, the machine learning algorithm can be the clustering algorithm based on correlation rule.
Correlation rule can be preset according to actual needs, and then according to the correlation rule of setting, to NLP, that treated is unstructured
Data and semi-structured data carry out clustering processing, extract core in unstructured data and semi-structured data
Information.By setting correlation rule previously according to actual needs, the correlation rule for being then based on setting carries out cluster point to data
Analysis more can extract core data relevant to knowledge mapping to be built in mass data by precise and high efficiency, further
Improve the accuracy of used data when subsequent processing.
S106: to the structural data and machine learning algorithm treated unstructured data, half structure is utilized
Change data and carry out data conversion, obtains pending data.
Can be by structural data and treated through the above way semi-structured data, unstructured data carry out
Data conversion.In one or more embodiment of this specification, the data conversion may include that data cleansing and data turn
Change two steps.Wherein, the cleaning of data may include the value for filling in missing, smooth noise data, identification or delete outlier
And solve the manner of cleaning up such as inconsistency.It is then possible to which the data after cleaning are carried out data conversion, the data turn
Changing may include the modes such as smooth aggregation, Data generalization, standardization, in the form of converting the data into and be suitable for data mining.
Finally, unstructured data, semi-structured data and the structural data after conversion can be loaded into accordingly
Database in, using the basic data constructed as knowledge mapping.
It different process is based respectively on to the data of three types through the above way carries out the integration of data and handle, it can be with
It is highly efficient accurately will it is related with enterprise dispersion, messy, the skimble-scamble source Data Integration of standard to together, obtain wait locate
Manage data.And entire process flow can effectively be configured to distributed data processing form, so as to increase substantially
The efficiency of data processing.
In another embodiment of this specification, it is also based on preset business rule and industrial chain Relation acquisition mesh
Unstructured data, semi-structured data and the structural data of theme are marked, the business rule may include according to
The corresponding preconfigured business process rule of service application scene of target topic.
It can be pre-configured with business rule according to actual service application scene, which can be pre-set
And exist in the database, it is also possible to carry out sets itself according to the business scenario.It is then possible to the business rule into
The acquisition of row data and the integration processing of data, to further increase the specific aim and follow-up data of the knowledge mapping of building
The accuracy of analysis.
For example, can determine its corresponding business rule according to risk prevention system if application scenarios are risk prevention system.Accordingly
Business rule such as may include enterprise and the type of business to be analyzed, acquisition data requirement, different to the multi-source of acquisition
The requirement when processing of structure Data Data (such as to the requirement of correlation rule).It is then possible to obtain multi-source based on the business rule
Isomeric data and integration processing carried out to multi-source heterogeneous data, obtain constructed for the knowledge mapping of risk prevention system it is to be processed
Data.
S108: carrying out Knowledge Extraction and knowledge fusion to the pending data, obtains that the target topic is corresponding to be known
Know map.
It is described to the pending data carry out Knowledge Extraction may include to the attribute of target object, target object and
Relationship between target object is extracted, to obtain entity and entity relationship data for knowledge mapping building.It is described to know
Knowing fusion may include carrying out fusion treatment to the knowledge mapping of two or more separate sources of same target object,
More fully accurately to obtain the information of target object.The target object can be analysis pair corresponding to target topic
As such as target topic is enterprise's air control analysis, then various enterprises, unit and related with enterprise can be had by analyzing object
The entities such as people.
For example, in some embodiments of this specification, it, can be to the number in data warehouse after the completion of cleaning conversion load
According to progress Knowledge Extraction.Enterprise can be such as extracted, the relationship between attributes and enterprise such as scale, business standing of enterprise: as looked forward to
Industry A is the sub- enterprise of subordinate of enterprise B, and enterprise C is the client etc. of enterprise A.
After the extraction step for completing entity and entity relationship, knowledge fusion can be carried out, multiple data will be come from
The description information fusion about the same entity in source is got up.The specific steps of knowledge fusion may include that the grammer of data is regular
Change and data normalization, attributes similarity calculate and entity similarity calculation, piecemeal, load balancing etc..Ontology such as can be used
Matched mode carries out knowledge fusion, and the information fusion of identical entity is got up, multi-solution is eliminated, accurately described in building acquisition
The corresponding knowledge mapping of target topic.
It, can be based on sorting algorithm and expert knowledge library to the pending data in one embodiment of this specification
Carry out Knowledge Extraction.Financial application scene is complicated and changeable, by the method using expert knowledge library and based on the side of machine learning
Method is combined, and can be further improved the comprehensive and accuracy of entity and entity relation extraction.
The expert knowledge library can refer to that building knows system based on expert advice and empirical analysis, be known using expert
Entity and entity relationship in pending data can accurately be excavated by knowing library.Pass through the sorting algorithm pre-established
Relevant entity and entity relationship can be excavated from above-mentioned pending data automatically.The sorting algorithm may include determining
Plan tree classification method, simple Bayesian Classification Arithmetic, classification based on support vector machines etc..
In one or more embodiment of this specification, expert knowledge library and base can be controlled by being pre-configured with weight
The specific gravity of the final result shared by machine learning algorithm, to guarantee the accuracy of knowledge being finally drawn into and comprehensive.Using
Two ways combines and increases the mode of weight, can not only be detached from the human factor of traditional expert knowledge library, but also suspicious elimination
The uncontrollable characteristic of pure machine learning algorithm agency, and then improve the knot that the final knowledge mapping using building carries out analysis acquisition
The accuracy and applicability of fruit.
The scheme that the above-mentioned each embodiment of this specification provides, is closed by the complete industrial chain carried out based on financial business
System obtains the most true data of enterprise, accurate enterprise's production and operation data from most basic line production and operation data
It ensure that the original accuracy of knowledge mapping.And the synchronous acquisition tax data of enterprise, public utilities payment data, financial report row are ground
The non-institutional data such as the semi-structured data such as data and internet public feelings, supervision file, carry out knowledge mapping structure with auxiliary
It builds.So as to further increase for the covering surface of the data source of knowledge mapping building and accuracy and utilize building
Knowledge mapping carry out applied analysis accuracy.
And also directed to different types of data source, otherness, distributed data processing method are provided, is further mentioned
The high accuracy and high efficiency of data processing.And corresponding business rule can be further configured according to business scenario,
Business rule based on configuration carries out the acquisition and processing of data, so that finally obtain knowledge mapping more for specific aim, into
And the accuracy that concrete application analysis is carried out using the knowledge mapping of building can be improved.
Fig. 2 indicates the knowledge mapping building flow chart in the application scenarios that this specification provides.It is answered with risk prevention system
The knowledge mapping building in this specification embodiment is illustrated with for scene.As shown in Fig. 2, can be first anti-according to risk
The business rule that the application scenarios of control determine.Then, it is obtained according to financial industry chain relation and predetermined business rule
Structural data, semi-structured data and unstructured data.
It is then possible to based on distributed way respectively to structural data, semi-structured data and unstructured data
It is pre-processed respectively.NLP processing first can be carried out to unstructured data machine；It is then possible to according to determining business rule
It determines correlation rule, then NLP treated unstructured data and semi-structured data gathered based on correlation rule
Class processing；Structural data can be extracted directly, without processing.
It is then possible to by after structural data, clustering processing unstructured data and semi-structured data count
According to conversion, so that data are more suitable for data mining.The multi-source heterogeneous data after conversion process are finally loaded into database
In, using the basic data constructed as knowledge mapping.
It is then possible to by experts database combined with sorting algorithm in the way of to above-mentioned basic data carry out entity-relation
Extraction, and entity to extraction and entity relationship data carry out knowledge fusion, and building obtains knowledge mapping.
It is then possible to carry out the risk profile of enterprise using the knowledge mapping of building.Mesh can be obtained according to knowledge mapping
Mark the attribute datas such as the behavioral data of honouring an agreement of enterprise itself, the circulation of fund.Target is looked forward to using the attribute data of Target Enterprise
Industry carries out risk profile, obtains the first risk profile result of Target Enterprise.Meanwhile it can analyze the pass of Target Enterprise and enterprise
System, the second risk of Target Enterprise is determined using the relationship degree of the attribute data of other enterprises and other enterprises and Target Enterprise
Prediction result.In conjunction with the first risk profile result and the second risk profile as a result, determining the risk profile of Target Enterprise
As a result.
It, can be first according to knowledge mapping when determining influence degree of other enterprises to Target Enterprise in some embodiments
Determine the relationship type between Liang Ge enterprise, it, can be according between Liang Ge enterprise if between enterprise being business transaction relationship
The Transaction Informations such as trading volume, transaction amount, transaction categories calculate the relationship degree between Liang Ge enterprise.If the relationship between Liang Ge enterprise
For subordinate relation, i.e. the subsidiary that an enterprise is another enterprise, then can according between the two enterprises the assets amount of money, point
The data such as red accounting determine relationship degree between the two.
For example, A enterprise and B enterprise are business transaction relationship, B enterprise and C enterprise are subordinate relation, and B enterprise is C enterprise
Subsidiary.The first relationship degree between A and B can be then determined according to the Transaction Information between A and B, according to the money between B and C
The data such as pan volume, dividend accounting determine the second relationship degree between B and C.It is then possible to according to the first relationship degree and second
Relationship degree determines the third relationship degree between A and C.Further, can also according to relationship type, to the first relationship degree and
Second relationship degree determines the third relationship degree between A and C respectively multiplied by certain weight.
To can effectively establish the relationship between industrial chain Zhong Ge enterprise and pass using the knowledge mapping constructed in advance
Join tightness degree, to determine influence of other enterprises to Target Enterprise.It is then possible to using other enterprises credit data and
The relationship degree of other enterprises and Target Enterprise determines the second risk profile result of Target Enterprise.
Correspondingly, based on the scheme that above-mentioned scene embodiment provides, as shown in figure 3, in one embodiment of this specification,
The method can also include:
S110: determining the attribute data of Target Enterprise according to the knowledge mapping, according to the attribute data pair of Target Enterprise
Target Enterprise carries out risk profile, obtains the first risk profile result of Target Enterprise；
S112: determining relationship type between Target Enterprise and other enterprises, relationship degree according to the knowledge mapping, according to
Relationship type, the relationship degree of the attribute data of other enterprises and other enterprises and Target Enterprise, determine the second of Target Enterprise
Risk profile result；
S114: according to the first risk profile result and the second risk profile as a result, determining the Target Enterprise
Risk profile result.
Certainly, if predetermined application scenarios are precisely to obtain visitor or Customer behavior prediction etc., phase can also be based on
The application scenarios answered configure corresponding business rule, and guidance carries out the building of knowledge mapping.By matching previously according to business scenario
Corresponding business rule is set, the knowledge mapping that building can be made to obtain is more for specific aim, to improve business reasoning application
Precision of analysis.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Specifically it is referred to
The description of aforementioned relevant treatment related embodiment, does not do repeat one by one herein.
It is above-mentioned that this specification specific embodiment is described.Other embodiments are in the scope of the appended claims
It is interior.In some cases, the movement recorded in detail in the claims or step can be come according to the sequence being different from embodiment
It executes and desired result still may be implemented.In addition, process depicted in the drawing not necessarily require show it is specific suitable
Sequence or consecutive order are just able to achieve desired result.In some embodiments, multitasking and parallel processing be also can
With or may be advantageous.
The knowledge mapping construction method that this specification one or more embodiment provides can be carried out based on financial business
Entire industries chain relation obtains the most true comprehensive data of enterprise, guarantees to know from most basic line production and operation data
Know accuracy and the covering surface of map initial data.And be directed to different types of data source, provide otherness, it is distributed
Data processing method, so as to further increase the accuracy and high efficiency of data processing.Utilize each reality of this specification
Example is applied, the accuracy and efficiency of knowledge mapping building can be increased substantially.
Based on knowledge mapping construction method described above, this specification one or more embodiment also provides a kind of knowledge
Map construction device.The device may include the system for having used this specification embodiment the method, software (application),
Module, component, server etc. simultaneously combine the necessary device for implementing hardware.Based on same innovation thinking, this specification embodiment
Device in one or more embodiments of offer is as described in the following examples.The implementation solved the problems, such as due to device with
Method is similar, therefore the implementation of the specific device of this specification embodiment may refer to the implementation of preceding method, repeats place not
It repeats again.Used below, the group of the software and/or hardware of predetermined function may be implemented in term " unit " or " module "
It closes.Although device described in following embodiment is preferably realized with software, the combination of hardware or software and hardware
Realization be also that may and be contemplated.Specifically, Fig. 4 indicates a kind of knowledge mapping construction device embodiment that specification provides
Modular structure schematic diagram, as shown in figure 4, the apparatus may include:
Data acquisition module 202 can be used for the unstructured data according to industrial chain Relation acquisition target topic, half hitch
Structure data and structural data；
First data processing module 204 can be used for carrying out the unstructured data natural language processing, and to certainly
Unstructured data and the semi-structured data after right Language Processing are handled using machine learning algorithm；
Second data processing module 206 can be used for handling to the structural data and using machine learning algorithm
Unstructured data, semi-structured data afterwards carries out data conversion, obtains pending data；
Knowledge mapping constructs module 208, can be used for carrying out Knowledge Extraction and knowledge fusion to the pending data, obtain
Obtain the corresponding knowledge mapping of the target topic.
In another embodiment of this specification, first data processing module 204 may include:
First data processing unit can be used for unstructured data after natural language processing and described semi-structured
Data carry out the clustering processing based on correlation rule.
Fig. 5 indicates a kind of modular structure schematic diagram for knowledge mapping construction device embodiment that specification provides, such as Fig. 5 institute
Show, in another embodiment of this specification, described device can also include:
Business rule configuration module 201 can be used for according to the corresponding service application scene configuration institute of the target topic
State the corresponding business rule of target topic；
Correspondingly, the data acquisition module 202 can be also used for obtaining based on the business rule and industry chain relation
Take the unstructured data, semi-structured data and structural data of target topic.
In another embodiment of this specification, the knowledge mapping building module 208 may include:
Knowledge Extraction unit can be used for knowing the pending data based on sorting algorithm and expert knowledge library
Know and extracts.
As shown in figure 5, described device can also include risk profile module 210 in another embodiment of this specification,
Wherein, the risk profile module 201 may include:
First risk profile unit can be used for obtaining the attribute data of Target Enterprise according to the knowledge mapping, according to
The attribute data of the Target Enterprise determines the first risk profile result of Target Enterprise；
Second risk profile unit can be used for being determined between Target Enterprise and other enterprises according to the knowledge mapping
Relationship type, relationship degree, according to relationship type, the relationship of the attribute data of other enterprises and other enterprises and Target Enterprise
Degree, determines the second risk profile result of Target Enterprise；
Third risk profile unit can be used for according to the first risk profile result and the second risk profile knot
Fruit determines the risk profile result of the Target Enterprise.
It should be noted that device described above can also include other embodiment party according to the description of embodiment of the method
Formula.Concrete implementation mode is referred to the description of related method embodiment, does not repeat one by one herein.
The knowledge mapping construction device that this specification one or more embodiment provides can be carried out based on financial business
Entire industries chain relation obtains the most true comprehensive data of enterprise, guarantees to know from most basic line production and operation data
Know accuracy and the covering surface of map initial data.And be directed to different types of data source, provide otherness, it is distributed
Data processing method, so as to further increase the accuracy and high efficiency of data processing.Utilize each reality of this specification
Example is applied, the accuracy and efficiency of knowledge mapping building can be increased substantially.
Method or apparatus described in above-described embodiment that this specification provides can realize that business is patrolled by computer program
It collects and records on a storage medium, the storage medium can be read and be executed with computer, realize this specification embodiment institute
The effect of description scheme.Therefore, this specification also provides a kind of knowledge mapping building equipment, including processor and storage processor
The memory of executable instruction, when described instruction is executed by the processor realize the following steps are included:
According to the unstructured data, semi-structured data and structural data of industrial chain Relation acquisition target topic；
To the unstructured data carry out natural language processing, and to after natural language processing unstructured data and
The semi-structured data is handled using machine learning algorithm；
To the structural data and utilize machine learning algorithm treated unstructured data, semi-structured data
Data conversion is carried out, pending data is obtained；
Knowledge Extraction and knowledge fusion are carried out to the pending data, obtain the corresponding knowledge graph of the target topic
Spectrum.
The storage medium may include the physical unit for storing information, usually by after information digitalization again with benefit
The media of the modes such as electricity consumption, magnetic or optics are stored.It may include: that letter is stored in the way of electric energy that the storage medium, which has,
The device of breath such as, various memory, such as RAM, ROM；The device of information is stored in the way of magnetic energy such as, hard disk, floppy disk, magnetic
Band, core memory, magnetic bubble memory, USB flash disk；Using optical mode storage information device such as, CD or DVD.Certainly, there are also it
Readable storage medium storing program for executing of his mode, such as quantum memory, graphene memory etc..
It should be noted that equipment described above can also include other embodiment party according to the description of embodiment of the method
Formula.Concrete implementation mode is referred to the description of related method embodiment, does not repeat one by one herein.
Embodiment of the method provided by this specification embodiment can mobile terminal, terminal, server or
It is executed in similar arithmetic unit.For running on the server, Fig. 6 is the knowledge mapping structure using this specification embodiment
The hardware block diagram for the server built.As shown in fig. 6, server 10 may include one or more (only showing one in figure)
(processor 20 can include but is not limited to the processing dress of Micro-processor MCV or programmable logic device FPGA etc. to processor 20
Set), memory 30 for storing data and the transmission module 40 for communication function.This neighborhood those of ordinary skill can
To understand, structure shown in fig. 6 is only to illustrate, and does not cause to limit to the structure of above-mentioned electronic device.For example, server 10
May also include the more or less component than shown in Fig. 6, such as can also include other processing hardware, such as database or
Multi-level buffer, GPU, or with the configuration different from shown in Fig. 6.
Memory 30 can be used for storing the software program and module of application software, such as the searcher in the embodiment of the present invention
Corresponding program instruction/the module of method, the software program and module that processor 20 is stored in memory 30 by operation, thus
Perform various functions application and data processing.Memory 30 may include high speed random access memory, may also include non-volatile deposit
Reservoir, such as one or more magnetic storage device, flash memory or other non-volatile solid state memories.In some instances,
Memory 30 can further comprise the memory remotely located relative to processor 20, these remote memories can pass through network
It is connected to terminal.The example of above-mentioned network includes but is not limited to internet, intranet, local area network, mobile communication
Net and combinations thereof.
Transmission module 40 is used to that data to be received or sent via a network.Above-mentioned network specific example may include meter
The wireless network that the communication providers of calculation machine terminal provide.In an example, transmission module 40 includes a network adapter
(Network Interface Controller, NIC), can be connected by base station with other network equipments so as to interconnection
Net is communicated.In an example, transmission module 40 can be radio frequency (Radio Frequency, RF) module, be used to lead to
Wireless mode is crossed to be communicated with internet.
Knowledge mapping described in above-described embodiment constructs equipment, and the complete industrial chain that can be carried out based on financial business is closed
System obtains the most true comprehensive data of enterprise, guarantees knowledge mapping original number from most basic line production and operation data
According to accuracy and covering surface.And it is directed to different types of data source, provide otherness, distributed data processing side
Formula, so as to further increase the accuracy and high efficiency of data processing.Utilize each embodiment of this specification, Ke Yi great
Amplitude improves the accuracy and efficiency of knowledge mapping building.
This specification also provides a kind of knowledge mapping building system, and the system can be individual knowledge mapping building system
System, can also apply in a variety of computer data processing systems.The system can be individual server, also can wrap
Include the server cluster, system of the one or more the methods for having used this specification or one or more embodiment devices
(including distributed system), software (application), practical operation device, logic gates device, quantum computer etc. and combine must
The terminal installation for the implementation hardware wanted.The knowledge mapping building system may include that at least one processor and storage calculate
The memory of machine executable instruction, the processor are realized when executing described instruction in above-mentioned any one or multiple embodiments
The step of the method.
It should be noted that system described above can also include others according to the description of method or Installation practice
Embodiment, concrete implementation mode are referred to the description of related method embodiment, do not repeat one by one herein.
Knowledge mapping described in above-described embodiment constructs system, and the complete industrial chain that can be carried out based on financial business is closed
System obtains the most true comprehensive data of enterprise, guarantees knowledge mapping original number from most basic line production and operation data
According to accuracy and covering surface.And it is directed to different types of data source, provide otherness, distributed data processing side
Formula, so as to further increase the accuracy and high efficiency of data processing.Utilize each embodiment of this specification, Ke Yi great
Amplitude improves the accuracy and efficiency of knowledge mapping building.
It should be noted that this specification device or system described above according to the description of related method embodiment also
It may include other embodiments, concrete implementation mode is referred to the description of embodiment of the method, does not go to live in the household of one's in-laws on getting married one by one herein
It states.All the embodiments in this specification are described in a progressive manner, and same and similar part is mutual between each embodiment
Mutually referring to each embodiment focuses on the differences from other embodiments.Especially for hardware+program
For class, storage medium+program embodiment, since it is substantially similar to the method embodiment, so be described relatively simple, it is related
Place illustrates referring to the part of embodiment of the method.
Although data conversion, load for mentioning in this specification embodiment content etc. obtain, definition, interaction, calculate, judgement
Deng operation and data description, still, this specification embodiment is not limited to comply with standard data model/template or sheet
Situation described in specification embodiment.Certain professional standards or the practice processes described using customized mode or embodiment
On embodiment modified slightly also may be implemented above-described embodiment it is identical, it is equivalent or it is close or deformation after it is anticipated that reality
Apply effect.Using the embodiment of the acquisitions such as these modifications or deformed data acquisition, storage, judgement, processing mode, still may be used
To belong within the scope of the optional embodiment of this specification.
It is above-mentioned that this specification specific embodiment is described.Other embodiments are in the scope of the appended claims
It is interior.In some cases, the movement recorded in detail in the claims or step can be come according to the sequence being different from embodiment
It executes and desired result still may be implemented.In addition, process depicted in the drawing not necessarily require show it is specific suitable
Sequence or consecutive order are just able to achieve desired result.In some embodiments, multitasking and parallel processing be also can
With or may be advantageous.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,
Or it is realized by the product with certain function.It is a kind of typically to realize that equipment is computer.Specifically, computer for example may be used
Think personal computer, laptop computer, vehicle-mounted human-computer interaction device, cellular phone, camera phone, smart phone, individual
Digital assistants, media player, navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or
The combination of any equipment in these equipment of person.
For convenience of description, it is divided into various modules when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each module can be realized in the same or multiple software and or hardware when specification one or more, it can also be with
The module for realizing same function is realized by the combination of multiple submodule or subelement etc..Installation practice described above is only
It is only illustrative, for example, in addition the division of the unit, only a kind of logical function partition can have in actual implementation
Division mode, such as multiple units or components can be combined or can be integrated into another system or some features can be with
Ignore, or does not execute.Another point, shown or discussed mutual coupling, direct-coupling or communication connection can be logical
Some interfaces are crossed, the indirect coupling or communication connection of device or unit can be electrical property, mechanical or other forms.
It is also known in the art that other than realizing controller in a manner of pure computer readable program code, it is complete
Entirely can by by method and step carry out programming in logic come so that controller with logic gate, switch, specific integrated circuit, programmable
Logic controller realizes identical function with the form for being embedded in microcontroller etc..Therefore this controller is considered one kind
Hardware component, and the structure that the device for realizing various functions that its inside includes can also be considered as in hardware component.Or
Person even, can will be considered as realizing the device of various functions either the software module of implementation method can be hardware again
Structure in component.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want
There is also other identical elements in the process, method or equipment of element.
It will be understood by those skilled in the art that this specification one or more embodiment can provide as method, system or calculating
Machine program product.Therefore, this specification one or more embodiment can be used complete hardware embodiment, complete software embodiment or
The form of embodiment combining software and hardware aspects.Moreover, this specification one or more embodiment can be used at one or
It is multiple wherein include computer usable program code computer-usable storage medium (including but not limited to magnetic disk storage,
CD-ROM, optical memory etc.) on the form of computer program product implemented.
This specification one or more embodiment can computer executable instructions it is general on
It hereinafter describes, such as program module.Generally, program module includes executing particular task or realization particular abstract data type
Routine, programs, objects, component, data structure etc..This this specification one can also be practiced in a distributed computing environment
Or multiple embodiments, in these distributed computing environments, by being held by the connected remote processing devices of communication network
Row task.In a distributed computing environment, program module can be located at the local and remote computer including storage equipment
In storage medium.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality
For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method
Part explanation.In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ",
The description of " specific example " or " some examples " etc. means specific features described in conjunction with this embodiment or example, structure, material
Or feature is contained at least one embodiment or example of this specification.In the present specification, to the signal of above-mentioned term
Property statement must not necessarily be directed to identical embodiment or example.Moreover, specific features, structure, material or the spy of description
Point may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other,
Those skilled in the art can be by different embodiments or examples described in this specification and different embodiments or examples
Feature is combined.
The foregoing is merely the embodiments of this specification, are not limited to this specification.For art technology
For personnel, this specification can have various modifications and variations.It is all made any within the spirit and principle of this specification
Modification, equivalent replacement, improvement etc., should be included within the scope of the claims of this specification.
Claims (13)
1. a kind of knowledge mapping construction method characterized by comprising
According to the unstructured data, semi-structured data and structural data of industrial chain Relation acquisition target topic；
Natural language processing carried out to the unstructured data, and to unstructured data after natural language processing and described
Semi-structured data is handled using machine learning algorithm；
It is carried out to the structural data and using machine learning algorithm treated unstructured data, semi-structured data
Data conversion obtains pending data；
Knowledge Extraction and knowledge fusion are carried out to the pending data, obtain the corresponding knowledge mapping of the target topic.
2. the method according to claim 1, wherein the unstructured data to after natural language processing and
Semi-structured data is handled using machine learning algorithm, comprising:
To after natural language processing unstructured data and the semi-structured data carry out at the cluster based on correlation rule
Reason.
3. the method according to claim 1, wherein the structural data includes the number of deals between enterprise
Data are handled according to, business capital flowing information and financial product, the unstructured data includes the behavior number of honouring an agreement of enterprise
According to the unstructured data includes the public information data of enterprise.
4. method according to claim 1-3, which is characterized in that the acquisition business datum to be processed includes:
Unstructured data, semi-structured data based on preset business rule and industrial chain Relation acquisition target topic with
And structural data, the business rule include according to the corresponding preconfigured business of service application scene of the target topic
Processing rule.
5. the method according to claim 1, wherein described carry out Knowledge Extraction, packet to the pending data
It includes:
Knowledge Extraction is carried out to the pending data based on sorting algorithm and expert knowledge library.
6. the method according to claim 1, wherein the method also includes:
The attribute data that Target Enterprise is obtained according to the knowledge mapping, determines target according to the attribute data of the Target Enterprise
First risk profile result of enterprise；
Relationship type between Target Enterprise and other enterprises, relationship degree are determined according to the knowledge mapping, according to other enterprises
Attribute data and other enterprises and Target Enterprise relationship type, relationship degree, determine the second risk profile of Target Enterprise
As a result；
According to the first risk profile result and the second risk profile as a result, determining the risk profile knot of the Target Enterprise
Fruit.
7. a kind of knowledge mapping construction device, which is characterized in that described device includes:
Data acquisition module, for according to the unstructured data of industrial chain Relation acquisition target topic, semi-structured data with
And structural data；
First data processing module, for carrying out natural language processing to the unstructured data, and to natural language processing
Unstructured data and the semi-structured data afterwards is handled using machine learning algorithm；
Second data processing module, for the structural data and that treated is unstructured using machine learning algorithm
Data, semi-structured data carry out data conversion, obtain pending data；
Knowledge mapping constructs module, for carrying out Knowledge Extraction and knowledge fusion to the pending data, obtains the target
The corresponding knowledge mapping of theme.
8. device according to claim 7, which is characterized in that first data processing module includes:
First data processing unit, for after natural language processing unstructured data and the semi-structured data carry out
Clustering processing based on correlation rule.
9. device according to claim 7 or 8, which is characterized in that described device further include:
Business rule configuration module is used for the target topic pair according to the target topic corresponding service application scene configuration
The business rule answered；
Correspondingly, the data acquisition module is also used to based on the business rule and industrial chain Relation acquisition target topic
Unstructured data, semi-structured data and structural data.
10. device according to claim 7, which is characterized in that the knowledge mapping constructs module and includes:
Knowledge Extraction unit, for carrying out Knowledge Extraction to the pending data based on sorting algorithm and expert knowledge library.
11. device according to claim 7, which is characterized in that described device further includes risk profile module, wherein institute
Stating risk profile module includes:
First risk profile unit, for obtaining the attribute data of Target Enterprise according to the knowledge mapping, according to the target
The attribute data of enterprise determines the first risk profile result of Target Enterprise；
Second risk profile unit, for determining the relation object between Target Enterprise and other enterprises according to the knowledge mapping
Type, relationship degree are determined according to relationship type, the relationship degree of the attribute data of other enterprises and other enterprises and Target Enterprise
Second risk profile result of Target Enterprise；
Third risk profile unit is used for according to the first risk profile result and the second risk profile as a result, determining institute
State the risk profile result of Target Enterprise.
12. a kind of knowledge mapping constructs equipment, which is characterized in that including processor and for storage processor executable instruction
Memory, when described instruction is executed by the processor realize the following steps are included:
According to the unstructured data, semi-structured data and structural data of industrial chain Relation acquisition target topic；
Natural language processing carried out to the unstructured data, and to unstructured data after natural language processing and described
Semi-structured data is handled using machine learning algorithm；
It is carried out to the structural data and using machine learning algorithm treated unstructured data, semi-structured data
Data conversion obtains pending data；
Knowledge Extraction and knowledge fusion are carried out to the pending data, obtain the corresponding knowledge mapping of the target topic.
13. a kind of knowledge mapping constructs system, which is characterized in that the data processing system include at least one processor and
The memory of computer executable instructions is stored, the processor realizes that the claim 1-6 is any when executing described instruction
The step of item the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910418358.9A CN110197280B (en) | 2019-05-20 | 2019-05-20 | Knowledge graph construction method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910418358.9A CN110197280B (en) | 2019-05-20 | 2019-05-20 | Knowledge graph construction method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110197280A true CN110197280A (en) | 2019-09-03 |
| CN110197280B CN110197280B (en) | 2021-08-06 |
Family
ID=67752873
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910418358.9A Active CN110197280B (en) | 2019-05-20 | 2019-05-20 | Knowledge graph construction method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110197280B (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110750588A (en) * | 2019-10-29 | 2020-02-04 | 珠海格力电器股份有限公司 | Multi-source heterogeneous data fusion method, system, device and storage medium |
| CN110971674A (en) * | 2019-11-15 | 2020-04-07 | 北京明略软件系统有限公司 | Method, device, computer storage medium and terminal for realizing information processing |
| CN111027832A (en) * | 2019-11-28 | 2020-04-17 | 卓尔智联(武汉)研究院有限公司 | Tax risk determination method, apparatus and storage medium |
| CN111143448A (en) * | 2019-12-03 | 2020-05-12 | 北京博瑞彤芸科技股份有限公司 | Knowledge base construction method |
| CN111223004A (en) * | 2019-11-14 | 2020-06-02 | 国网湖北省电力有限公司电力科学研究院 | Relay protection knowledge modeling method and platform for business application |
| CN111241213A (en) * | 2020-01-23 | 2020-06-05 | 北京明略软件系统有限公司 | Method and device for constructing knowledge graph, computer storage medium and terminal |
| CN111242774A (en) * | 2020-01-23 | 2020-06-05 | 中国建设银行股份有限公司 | Bank customer asset map construction method and device |
| CN111428053A (en) * | 2020-03-30 | 2020-07-17 | 西安交通大学 | Tax field knowledge graph construction method |
| CN111428090A (en) * | 2020-03-10 | 2020-07-17 | 北京明略软件系统有限公司 | Method and device for realizing data processing, computer storage medium and terminal |
| CN111488741A (en) * | 2020-04-14 | 2020-08-04 | 税友软件集团股份有限公司 | Tax knowledge data semantic annotation method and related device |
| CN111488465A (en) * | 2020-04-14 | 2020-08-04 | 税友软件集团股份有限公司 | Knowledge graph construction method and related device |
| CN111552820A (en) * | 2020-04-30 | 2020-08-18 | 江河瑞通（北京）技术有限公司 | Water engineering scheduling data processing method and device |
| CN111951079A (en) * | 2020-08-14 | 2020-11-17 | 国网电子商务有限公司 | Credit rating method and device based on knowledge graph and electronic equipment |
| CN112579782A (en) * | 2020-12-28 | 2021-03-30 | 上海明略人工智能(集团)有限公司 | Data processing method, knowledge management system, electronic device, and readable storage medium |
| CN112685572A (en) * | 2020-12-31 | 2021-04-20 | 天云融创数据科技（北京）有限公司 | Heterogeneous data fusion method and device based on federal calculation |
| CN112784057A (en) * | 2021-01-11 | 2021-05-11 | 武汉大学 | Three-network industrial map construction method based on regional industrial enterprises |
| CN112818131A (en) * | 2021-02-01 | 2021-05-18 | 亚信科技（成都）有限公司 | Method, system and storage medium for constructing graph of threat information |
| CN113051365A (en) * | 2020-12-10 | 2021-06-29 | 深圳证券信息有限公司 | Industrial chain map construction method and related equipment |
| CN113297395A (en) * | 2021-07-08 | 2021-08-24 | 中国人民解放军国防科技大学 | Spatio-temporal multi-modal mixed data processing method, correlation method and indexing method |
| CN113392229A (en) * | 2021-08-13 | 2021-09-14 | 四川新龟科技有限公司 | Supply chain relation construction and prediction method, device, equipment and storage medium |
| CN113590835A (en) * | 2021-07-28 | 2021-11-02 | 上海致景信息科技有限公司 | Method and device for establishing knowledge graph of textile industry data and processor |
| CN114417012A (en) * | 2022-01-20 | 2022-04-29 | 上海弘玑信息技术有限公司 | Method for generating knowledge graph and electronic equipment |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182454A (en) * | 2014-07-04 | 2014-12-03 | 重庆科技学院 | Multi-source heterogeneous data semantic integration model constructed based on domain ontology and method |
| CN106815307A (en) * | 2016-12-16 | 2017-06-09 | 中国科学院自动化研究所 | Public Culture knowledge mapping platform and its use method |
| CN107945024A (en) * | 2017-12-12 | 2018-04-20 | 厦门市美亚柏科信息股份有限公司 | Identify that internet finance borrowing enterprise manages abnormal method, terminal device and storage medium |
| CN108073673A (en) * | 2017-05-15 | 2018-05-25 | 北京华宇元典信息服务有限公司 | A kind of legal knowledge map construction method, apparatus, system and medium based on machine learning |
| CN108182245A (en) * | 2017-12-28 | 2018-06-19 | 北京锐安科技有限公司 | The construction method and device of people's object properties classificating knowledge collection of illustrative plates |
| CN108345647A (en) * | 2018-01-18 | 2018-07-31 | 北京邮电大学 | Domain knowledge map construction system and method based on Web |
| CN108596439A (en) * | 2018-03-29 | 2018-09-28 | 北京中兴通网络科技股份有限公司 | A kind of the business risk prediction technique and system of knowledge based collection of illustrative plates |
| CN108875051A (en) * | 2018-06-28 | 2018-11-23 | 中译语通科技股份有限公司 | Knowledge mapping method for auto constructing and system towards magnanimity non-structured text |
| CN108874878A (en) * | 2018-05-03 | 2018-11-23 | 众安信息技术服务有限公司 | A kind of building system and method for knowledge mapping |
| CN108932340A (en) * | 2018-07-13 | 2018-12-04 | 华融融通（北京）科技有限公司 | The construction method of financial knowledge mapping under a kind of non-performing asset operation field |
| CN109064313A (en) * | 2018-07-20 | 2018-12-21 | 重庆富民银行股份有限公司 | Warning monitoring system after the loan of knowledge based graphical spectrum technology |
| CN109064318A (en) * | 2018-08-24 | 2018-12-21 | 苏宁消费金融有限公司 | A kind of internet financial risks monitoring system of knowledge based map |
| CN109189943A (en) * | 2018-09-19 | 2019-01-11 | 中国电子科技集团公司信息科学研究院 | A kind of capability knowledge extracts and the method for capability knowledge map construction |
| CN109255034A (en) * | 2018-08-08 | 2019-01-22 | 数据地平线（广州）科技有限公司 | A kind of domain knowledge map construction method based on industrial chain |
| CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
| CN109446387A (en) * | 2018-10-09 | 2019-03-08 | 众蚁(上海)信息技术有限公司 | A kind of Owners Committee's intelligent Answer System based on artificial intelligence |
| CN109597855A (en) * | 2018-11-29 | 2019-04-09 | 北京邮电大学 | Domain knowledge map construction method and system based on big data driving |
-
2019
- 2019-05-20 CN CN201910418358.9A patent/CN110197280B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182454A (en) * | 2014-07-04 | 2014-12-03 | 重庆科技学院 | Multi-source heterogeneous data semantic integration model constructed based on domain ontology and method |
| CN106815307A (en) * | 2016-12-16 | 2017-06-09 | 中国科学院自动化研究所 | Public Culture knowledge mapping platform and its use method |
| CN108073673A (en) * | 2017-05-15 | 2018-05-25 | 北京华宇元典信息服务有限公司 | A kind of legal knowledge map construction method, apparatus, system and medium based on machine learning |
| CN107945024A (en) * | 2017-12-12 | 2018-04-20 | 厦门市美亚柏科信息股份有限公司 | Identify that internet finance borrowing enterprise manages abnormal method, terminal device and storage medium |
| CN108182245A (en) * | 2017-12-28 | 2018-06-19 | 北京锐安科技有限公司 | The construction method and device of people's object properties classificating knowledge collection of illustrative plates |
| CN108345647A (en) * | 2018-01-18 | 2018-07-31 | 北京邮电大学 | Domain knowledge map construction system and method based on Web |
| CN108596439A (en) * | 2018-03-29 | 2018-09-28 | 北京中兴通网络科技股份有限公司 | A kind of the business risk prediction technique and system of knowledge based collection of illustrative plates |
| CN108874878A (en) * | 2018-05-03 | 2018-11-23 | 众安信息技术服务有限公司 | A kind of building system and method for knowledge mapping |
| CN108875051A (en) * | 2018-06-28 | 2018-11-23 | 中译语通科技股份有限公司 | Knowledge mapping method for auto constructing and system towards magnanimity non-structured text |
| CN108932340A (en) * | 2018-07-13 | 2018-12-04 | 华融融通（北京）科技有限公司 | The construction method of financial knowledge mapping under a kind of non-performing asset operation field |
| CN109064313A (en) * | 2018-07-20 | 2018-12-21 | 重庆富民银行股份有限公司 | Warning monitoring system after the loan of knowledge based graphical spectrum technology |
| CN109255034A (en) * | 2018-08-08 | 2019-01-22 | 数据地平线（广州）科技有限公司 | A kind of domain knowledge map construction method based on industrial chain |
| CN109064318A (en) * | 2018-08-24 | 2018-12-21 | 苏宁消费金融有限公司 | A kind of internet financial risks monitoring system of knowledge based map |
| CN109189943A (en) * | 2018-09-19 | 2019-01-11 | 中国电子科技集团公司信息科学研究院 | A kind of capability knowledge extracts and the method for capability knowledge map construction |
| CN109446387A (en) * | 2018-10-09 | 2019-03-08 | 众蚁(上海)信息技术有限公司 | A kind of Owners Committee's intelligent Answer System based on artificial intelligence |
| CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
| CN109597855A (en) * | 2018-11-29 | 2019-04-09 | 北京邮电大学 | Domain knowledge map construction method and system based on big data driving |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110750588A (en) * | 2019-10-29 | 2020-02-04 | 珠海格力电器股份有限公司 | Multi-source heterogeneous data fusion method, system, device and storage medium |
| CN111223004A (en) * | 2019-11-14 | 2020-06-02 | 国网湖北省电力有限公司电力科学研究院 | Relay protection knowledge modeling method and platform for business application |
| CN110971674A (en) * | 2019-11-15 | 2020-04-07 | 北京明略软件系统有限公司 | Method, device, computer storage medium and terminal for realizing information processing |
| CN111027832A (en) * | 2019-11-28 | 2020-04-17 | 卓尔智联(武汉)研究院有限公司 | Tax risk determination method, apparatus and storage medium |
| CN111143448B (en) * | 2019-12-03 | 2023-05-12 | 北京博瑞彤芸科技股份有限公司 | Knowledge base construction method |
| CN111143448A (en) * | 2019-12-03 | 2020-05-12 | 北京博瑞彤芸科技股份有限公司 | Knowledge base construction method |
| CN111241213A (en) * | 2020-01-23 | 2020-06-05 | 北京明略软件系统有限公司 | Method and device for constructing knowledge graph, computer storage medium and terminal |
| CN111242774A (en) * | 2020-01-23 | 2020-06-05 | 中国建设银行股份有限公司 | Bank customer asset map construction method and device |
| CN111428090A (en) * | 2020-03-10 | 2020-07-17 | 北京明略软件系统有限公司 | Method and device for realizing data processing, computer storage medium and terminal |
| CN111428053A (en) * | 2020-03-30 | 2020-07-17 | 西安交通大学 | Tax field knowledge graph construction method |
| CN111428053B (en) * | 2020-03-30 | 2023-10-20 | 西安交通大学 | Construction method of tax field-oriented knowledge graph |
| CN111488741A (en) * | 2020-04-14 | 2020-08-04 | 税友软件集团股份有限公司 | Tax knowledge data semantic annotation method and related device |
| CN111488465A (en) * | 2020-04-14 | 2020-08-04 | 税友软件集团股份有限公司 | Knowledge graph construction method and related device |
| CN111552820A (en) * | 2020-04-30 | 2020-08-18 | 江河瑞通（北京）技术有限公司 | Water engineering scheduling data processing method and device |
| CN111951079A (en) * | 2020-08-14 | 2020-11-17 | 国网电子商务有限公司 | Credit rating method and device based on knowledge graph and electronic equipment |
| CN111951079B (en) * | 2020-08-14 | 2024-04-02 | 国网数字科技控股有限公司 | Credit rating method and device based on knowledge graph and electronic equipment |
| CN113051365A (en) * | 2020-12-10 | 2021-06-29 | 深圳证券信息有限公司 | Industrial chain map construction method and related equipment |
| CN112579782A (en) * | 2020-12-28 | 2021-03-30 | 上海明略人工智能(集团)有限公司 | Data processing method, knowledge management system, electronic device, and readable storage medium |
| CN112685572A (en) * | 2020-12-31 | 2021-04-20 | 天云融创数据科技（北京）有限公司 | Heterogeneous data fusion method and device based on federal calculation |
| CN112685572B (en) * | 2020-12-31 | 2021-12-17 | 天云融创数据科技（北京）有限公司 | Heterogeneous data fusion method and device |
| CN112784057B (en) * | 2021-01-11 | 2022-05-13 | 武汉大学 | Three-network industrial map construction method based on regional industrial enterprises |
| CN112784057A (en) * | 2021-01-11 | 2021-05-11 | 武汉大学 | Three-network industrial map construction method based on regional industrial enterprises |
| CN112818131B (en) * | 2021-02-01 | 2023-10-03 | 亚信科技（成都）有限公司 | Map construction method, system and storage medium for threat information |
| CN112818131A (en) * | 2021-02-01 | 2021-05-18 | 亚信科技（成都）有限公司 | Method, system and storage medium for constructing graph of threat information |
| CN113297395A (en) * | 2021-07-08 | 2021-08-24 | 中国人民解放军国防科技大学 | Spatio-temporal multi-modal mixed data processing method, correlation method and indexing method |
| CN113590835A (en) * | 2021-07-28 | 2021-11-02 | 上海致景信息科技有限公司 | Method and device for establishing knowledge graph of textile industry data and processor |
| CN113392229A (en) * | 2021-08-13 | 2021-09-14 | 四川新龟科技有限公司 | Supply chain relation construction and prediction method, device, equipment and storage medium |
| CN114417012A (en) * | 2022-01-20 | 2022-04-29 | 上海弘玑信息技术有限公司 | Method for generating knowledge graph and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110197280B (en) | 2021-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110197280A (en) | A kind of knowledge mapping construction method, apparatus and system | |
| Zhang et al. | Deeplob: Deep convolutional neural networks for limit order books | |
| Yang et al. | Social media data analytics for business decision making system to competitive analysis | |
| Hofmann et al. | Big data analytics and demand forecasting in supply chains: a conceptual analysis | |
| Visconti et al. | Big data-driven value chains and digital platforms: From value co-creation to monetization | |
| TWI650653B (en) | Big data processing method and platform | |
| CN103870455A (en) | Multi-data-source data integrated processing method and device | |
| Kshirsagar et al. | A scalable platform to collect, store, visualize and analyze big data in real-time | |
| CN109285071A (en) | A kind of data processing platform (DPP) and data processing method based on block chain | |
| CN110188210A (en) | One kind is based on figure regularization and the independent cross-module state data retrieval method of mode and system | |
| CN108989581A (en) | A kind of consumer's risk recognition methods, apparatus and system | |
| CN104346698A (en) | Catering member big data analysis and checking system based on cloud computing and data mining | |
| CN116245670B (en) | Method, device, medium and equipment for processing financial tax data based on double-label model | |
| CN109308616A (en) | A kind of risk determination method and device of transaction record | |
| CN109993544A (en) | Data processing method, system, computer system and computer readable storage medium | |
| CN110288465A (en) | Object determines method and device, storage medium, electronic device | |
| CN111667307A (en) | Method and device for predicting financial product sales volume | |
| Liu et al. | Brand marketing decision support system based on computer vision and parallel computing | |
| CN110020118A (en) | A kind of method and device calculating similarity between user | |
| CN112836742A (en) | System resource adjusting method, device and equipment | |
| CN110300961A (en) | Unified intelligent connector | |
| Kuizinienė et al. | Cryptocurrencies short-term forecast: application of ARIMA, GARCH and SVR models | |
| CN110851655A (en) | Method and system for simplifying complex network | |
| Echeberria | The Impact of AI on Business, Economics and Innovation | |
| CN113283925B (en) | Network experiment distribution and node relation prediction method, device and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |