CN110245241A - Plastics knowledge mapping construction device, method and computer readable storage medium - Google Patents
Plastics knowledge mapping construction device, method and computer readable storage medium Download PDFInfo
- Publication number
- CN110245241A CN110245241A CN201910528551.8A CN201910528551A CN110245241A CN 110245241 A CN110245241 A CN 110245241A CN 201910528551 A CN201910528551 A CN 201910528551A CN 110245241 A CN110245241 A CN 110245241A
- Authority
- CN
- China
- Prior art keywords
- plastics
- entity
- plastic industry
- plastic
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of plastics knowledge mapping construction method, it include: the plastic industry data for obtaining a target area, and multiple plastic industry entities are extracted from the plastic industry data, the plurality of plastic industry entity includes an at least plastic product entity and an at least Plastics Company entity；Entity is carried out to the plastic industry entity that extraction obtains to disambiguate and reference resolution processing；Establish the incidence relation between multiple plastic industry entities；According to the incidence relation between each plastic industry entity and each plastic industry entity, plastics knowledge mapping is established.The present invention also provides a kind of plastics knowledge mapping construction device and computer readable storage mediums.Above-mentioned plastics knowledge mapping construction device, method and computer readable storage medium are, it can be achieved that construct plastics knowledge mapping, the convenience that promotion plastic industry data management efficiency and data use for plastic industry field.
Description
Technical field
The present invention relates to technical field of data processing more particularly to a kind of plastics knowledge mapping construction devices, method and meter
Calculation machine readable storage medium storing program for executing.
Background technique
Knowledge mapping has powerful data descriptive power, provides technical foundation for intelligent information application, passes through
Implementation of inference conceptual retrieval, while structural knowledge can be presented to user in a manner of patterned.Knowledge mapping is in multiple necks
Domain has application, such as medical treatment, finance, education, investment etc. to have industry existing for relationship.But not yet there is mature modeling at present
Expect knowledge mapping building mode.
Summary of the invention
In view of this, it is necessary to provide a kind of plastics knowledge mapping construction device, method and computer readable storage medium,
It, which can be realized, constructs plastics knowledge mapping for plastic industry field, what promotion plastic industry data management efficiency and data used
Convenience.
An embodiment of the present invention provides a kind of plastics knowledge mapping construction method, which comprises obtains a target
The plastic industry data in region, and multiple plastic industry entities are extracted from the plastic industry data, wherein multiple modelings
Expect that industry entity includes an at least plastic product entity, at least a Plastics Company entity, an at least plastics class instance and at least
One process entities, described the step of extracting multiple plastic industry entities from the plastic industry data include: from the plastics
Plastic product information is extracted in industry data；And extracted from the plastic product information an at least plastics class instance and
An at least process entities；
Entity is carried out to the plastic industry entity that extraction obtains to disambiguate and reference resolution processing；
Establish the incidence relation between multiple plastic industry entities；
According to the incidence relation between each plastic industry entity and each plastic industry entity, modeling is established
Expect knowledge mapping；And
Quantification treatment is carried out to the confidence level of the knowledge in the plastics knowledge mapping, and gives up confidence level lower than preset value
Knowledge；
Wherein, the plastic industry entity that the plastic industry data source is obtained in Plastic enterprise database and web crawlers
Information.
Preferably, the step of incidence relation established between multiple plastic industry entities includes:
The production method relationship between the plastic product entity and the process entities is established, and establishes the plastics and produces
Belonging relation between product entity and the plastics class instance.
Preferably, the method also includes:
Rule is updated according to presupposed information and updates the information of the plastic product entity, the Plastics Company entity
Information, the information of the plastics class instance and the information of the process entities；And
Information, the information of the Plastics Company entity, the Plastic based on the updated plastic product entity
The information of other entity and the information of the process entities are updated the plastics knowledge mapping.
It is preferably, described after the step of extracting multiple plastic industry entities in the plastic industry data further include:
Each plastic industry entity attributes information is extracted from the plastic industry data；
The step of incidence relation established between multiple plastic industry entities includes:
The attribute information and the plastic industry entity are established into incidence relation.
Preferably, the plastic industry data include non-structured plastic industry data, semi-structured plastic industry
Data and the plastic industry data of structuring.
Preferably, the step of confidence level to the knowledge in the plastics knowledge mapping carries out quantification treatment include:
Credibility quantification is carried out to the knowledge in the plastics knowledge mapping using default method for sieving or logistic regression
Processing.
Preferably, the association according between each plastic industry entity and each plastic industry entity
Relationship, the step of establishing plastics knowledge mapping include:
Association between the name identification of each plastic industry entity and each plastic industry entity is closed
System is directed into preset pattern database, and carries out visualization and be converted to the plastics knowledge mapping.
An embodiment of the present invention provides a kind of plastics knowledge mapping construction device, the plastics knowledge mapping construction device
Including processor and memory, several computer programs are stored on the memory, the processor is for executing memory
The step of above-mentioned plastics knowledge mapping construction method is realized when the computer program of middle storage.
An embodiment of the present invention also provides a kind of computer readable storage medium, and the computer readable storage medium is deposited
A plurality of instruction is contained, a plurality of described instruction can be executed by one or more processor, to realize above-mentioned plastics knowledge mapping
The step of construction method.
Compared with prior art, above-mentioned plastics knowledge mapping construction device, method and computer readable storage medium, can be with
It realizes the plastics knowledge mapping in one specified region of building, promotes the convenience that plastic industry data management efficiency and data use,
Data analysis can be carried out with assisted plastic manufacturing enterprise, client is facilitated to carry out plastic product buying, for public science popularization plastics knowledge.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of the plastics knowledge mapping construction device of an embodiment of the present invention.
Fig. 2 is the functional block diagram of the plastics knowledge mapping building system of an embodiment of the present invention.
Fig. 3 is the building schematic diagram of the plastics knowledge mapping structure of an embodiment of the present invention.
Fig. 4 is the flow chart of the plastics knowledge mapping construction method of an embodiment of the present invention.
Main element symbol description
The present invention that the following detailed description will be further explained with reference to the above drawings.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.Based on the embodiments of the present invention, those of ordinary skill in the art are not before making creative work
Every other embodiment obtained is put, shall fall within the protection scope of the present invention.
Explanation is needed further exist for, herein, the terms "include", "comprise" or its any other variant are intended to contain
Lid non-exclusive inclusion, so that process, method, article or device including a series of elements are not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or device
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or device including the element.
Referring to Fig. 1, being the schematic diagram of plastics knowledge mapping construction device preferred embodiment of the present invention.
The plastics knowledge mapping construction device 100 is including memory 10, processor 20 and is stored in the memory
In 10 and the computer program 30 that can be run on the processor 20, such as plastics knowledge mapping construction procedures.The processing
Device 20 realizes the step in plastics knowledge mapping construction method embodiment when executing the computer program 30, such as shown in Fig. 4
Step S400~S408.Alternatively, the processor 20 realizes the building of plastics knowledge mapping when executing the computer program 30
The function of each module in system embodiment, such as the module 101~105 in Fig. 2.
The computer program 30 can be divided into one or more modules, and one or more of modules are stored
It is executed in the memory 10, and by the processor 20, to complete the present invention.One or more of modules can be energy
The series of computation machine program instruction section of specific function is enough completed, described instruction section is for describing the computer program 30 in institute
State the implementation procedure in plastics knowledge mapping construction device 100.For example, the computer program 30 can be divided into Fig. 2
Extraction module 101, processing module 102, first establish module 103, second establish module 104 and update module 105.Each module
Concrete function constructs the function of each module in system embodiment referring to plastics knowledge mapping.
The plastics knowledge mapping construction device 100 can be computer, server etc. and calculate equipment.Those skilled in the art
It is appreciated that the schematic diagram is only the example of plastics knowledge mapping construction device 100, do not constitute to plastics knowledge mapping structure
The restriction for building device 100 may include perhaps combining certain components or different portions than illustrating more or fewer components
Part, such as the plastics knowledge mapping construction device 100 can also include input-output equipment, network access equipment, bus etc..
Alleged processor 20 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor 20 is also possible to any conventional processing
Device etc., the processor 20 can use the various pieces of various interfaces and connection plastics knowledge mapping construction device 100.
The memory 10 can be used for storing the computer program 30 and/or module, and the processor 20 passes through operation
Or the computer program and/or module being stored in the memory 10 are executed, and call the number being stored in memory 10
According to realizing the various functions of the plastics knowledge mapping construction device 100.The memory 10 may include high random access
Memory can also include nonvolatile memory, such as hard disk, memory, plug-in type hard disk, intelligent memory card (Smart
Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card), at least one disk
Memory device, flush memory device or other volatile solid-state parts.
Fig. 2 is the functional block diagram that plastics knowledge mapping of the present invention constructs system preferred embodiment.
As shown in fig.2, plastics knowledge mapping building system 40 may include extraction module 101, processing module 102, the
One establishes module 103, second establishes module 104 and update module 105.In one embodiment, above-mentioned module can be storage
In the memory 10 and the programmable software instruction executed can be called by the processor 20.It is understood that
In other embodiments, above-mentioned module can also be to solidify program instruction or firmware (firmware) in the processor 20.
The extraction module 101 is used to obtain the plastic industry data of a target area, and from the plastic industry data
Middle to extract multiple plastic industry entities, the plurality of plastic industry entity includes an at least plastic product entity and at least one
Plastics Company entity.
In one embodiment, the target area can be set according to actual use demand, than if necessary
The plastics knowledge mapping in a specified city is established, then the plastic industry data of the target area can be the plastic industry in the specified city
If desired data establish the plastics knowledge mapping in a specified county, then it is specified to can be this for the plastic industry data of the target area
The plastic industry data in county.The plastic industry data can be the database of the Plastics Company in the target area and lead to
Cross the data of other modes acquisition.The other modes include but is not limited to web crawlers, purchase plastics commercial data base, inquiry modeling
Expect industry research report, using open plastic industry data set, the plastic industry knowledge searched for using search engine etc..
In one embodiment, the plastic industry data can be unstructured data, semi-structured data and structure
Change data, the unstructured data such as can be plastic product picture, audio, video, and the semi-structured data is such as
Can be include plastic industry data XML, JSON, include the encyclopaedia page of plastic industry data, the structuring number
According to can be with plastic industry relational database, original plastics knowledge mapping etc..
In one embodiment, the plastic industry data may include plastic product data, process data, Plastic enterprise
Data, industry related data etc..The plastic product data may include the name of an article, type, performance, combustion characteristic, purposes etc..Institute
Stating the name of an article may include polyvinyl chloride (PVC), polyethylene (PE), polypropylene (PP), polyamide (being commonly called as nylon, PA), poly- methyl
Methyl acrylate (being commonly called as organic glass, PMMA), styrene-dibutene-acrylonitrile copolymers (ABS), gather polyformaldehyde (POM)
Tetrafluoroethene (being commonly called as King, PTFE), chlorinated polyether (or polyether, CPS), polycarbonate (PC), gathers poly- alum (PSF)
Urethane plastics (PUR), phenoplasts (being commonly called as bakelite, PF), epoxy plastics (EP), silicone plasties, polyphenylene oxide (PPO), gather it is p-
Carboxyl benzoic ether, phenolic aldehyde, ureaformaldehyde, melamine, furans, alkyd resin, unsaturated polyester (UP), diallyl phthalate,
Epoxy, silicone resin, polyurethane, polytrifluorochloroethylene (PCTFE), cellulose acetate (CA), cellulose acetate-butyrate (CAB), second
Sour cellulose propionate (CAP), nitrocellulose (CN), ethyl cellulose (EC), polyvinyl acetate (PVAC), polyvinyl alcohol contracting
Fourth (PVB), phenolic resin (PF), phenolic resin (wood powder), acid aldehyde resin (Bu Ji), phenolic resin (paper base), urea formaldehyde resin
(UF), melamine resin, polyester resin, vinyl chloride vinyl acetate copolymer (VC/VAC) etc..
The type can refer to by general-purpose plastics, the engineering plastics, special plastic for using characteristic to divide, and may also mean that
Thermosetting plastics, the thermoplastic divided by physicochemical property.The performance may include resistance to abrasion, Quality Cost ratio, resist
Compressive Strength, cost volume ratio, dielectric constant, loss factor, carrying resistance to deformation, elasticity modulus, resistive, extension at break
Rate, bending modulus, bend yield strength noted, low-friction coefficient, hardness, impact strength, moisture-proof, the property of softening, ultimate tensile strength,
Tensile yield strength, thermal conductivity, the coefficient of expansion, transparency, quality, whiteness conservation degree, density, form and aspect, heat resisting temperature, molding
Property, shrinking percentage etc..The combustion characteristic may include burning difficulty, from after fire whether self-extinguishment, flame status, plastics variation shape
State, smell of burning etc..The purposes may include electronic communication, machine components, coating, adhesive, feeder, resistant material,
Foam damping material etc..
The process data may include technology type and technological parameter.Technology type may include injection moulding, squeeze out
Molding, calendering formation, blow molding, thermoforming, hand pasting forming, Transfer molding, cast molding, is wound in compression moulding
Type, injection molding, drawing molding, foaming etc..Technological parameter may include shape feature, finite size factor, minimum in
Diameter, undercutting, gradient, minimum thickness, maximum gauge, inserts, assembling chip, mold inner hole, set boss, set reinforcing rib, Mo Nei is set
Meter, design number overall dimensions tolerance, are surface-treated, set screw thread etc..
The Plastic enterprise data may include enterprise name, registered capital, legal representative, location, main business, production
Category type, product yield, financial data etc..The industry related data may include supervision department, industry organization, policy
Regulation, industry yield, industry market value etc..
The extraction module 101 can extract multiple plastic industry entities from the plastic industry data, multiple described
Plastic industry entity may include multiple plastic product entities and multiple Plastics Company entities, such as multiple plastic industry realities
Body includes 100 plastic product A1~A100 and 10 Plastics Company B1~B10.It is more in other embodiments of the invention
A plastic industry entity can also include multiple plastic product entities, multiple Plastics Company entities, multiple process entities and
Multiple plastics class instances.
In one embodiment, the extraction module 101 first can extract plastic product from the plastic industry data
Information is further extracted from the plastic product information and obtains multiple plastics class instances and multiple process entities.It is described
Plastic product information may include attribute, technique and the affiliated plastics classification of plastic product.
In one embodiment, the extraction module 101 includes real to the operation that the plastic industry data extract
Body extracts, relationship is extracted and attributes extraction.Entity extraction is that plastic industry entity is identified and extracted from plastic industry data,
Relationship is extracted as extracting the incidence relation between entity from plastic industry data, the webbed structure of knowledge of shape.Attribute mentions
It is taken as extracting entity attributes information from plastic industry data.
The processing module 102 is used to carry out at entity disambiguation and reference resolution the plastic industry entity that extraction obtains
Reason.
In one embodiment, the extraction module 101 extracts in obtained multiple plastic industry entities, it is understood that there may be certain
One or more entity has multiple meanings, needs to carry out entity disambiguation processing.The processing module 102 can be using cluster
Method carries out entity disambiguation processing to the plastic industry entity that extraction obtains, which may be implemented to refer to entity in a manner of cluster
Claim item to be disambiguated, the denotion item for being directed toward the entity of the same target is gathered under same category.Specifically, to each entity
It censures item and extracts its feature (word, entity, concept of context etc.) composition characteristic vector, calculate the similarity censured between item,
It is clustered using default clustering method to item is censured.Calculating can be using based on superficial feature when censuring the similarity between item
Entity censure item similarity calculation algorithm or using based on extension feature entity censure item similarity calculation algorithm.At this
In the other embodiments of invention, the processing module 102 can also be using chain of entities connection to the obtained plastic industry of extraction
Entity carries out entity disambiguation processing.
In one embodiment, the plastic industry entity that the extraction of extraction module 101 obtains is possible, and there are many different
Entity in expression way, such as some semantic relation may be to occur in the form of pronoun, in order to more acurrate and do not omit
Ground extracts entity information from text, need to carry out reference resolution processing to the reference phenomenon in data.The specified resolution can be with
Including dominant pronoun resolution, empty anaphora resolution, coreference resolution.
Described first establishes module 103 for establishing the incidence relation between multiple plastic industry entities.
In one embodiment, obtained plastic industry entity is extracted when 102 pairs of the processing module carries out entity disambiguation
After processing, described first, which establishes module 103, can construct incidence relation between multiple plastic industry entities.Described first establishes
Module 103 can establish the incidence relation between multiple plastic industry entities by preset incidence relation method for building up, described
Preset incidence relation method for building up can be the correlation rule pre-established, for example pre-establish multiple plastic product entities
With the incidence relation between multiple Plastics Company entities, multiple plastic products are then established according to the correlation rule pre-established
Incidence relation between entity and multiple Plastics Company entities.Described first establishes module 103 can also be according to previously being closed
The incidence relation that system extracts obtained result to establish between multiple plastic industry entities.
In one embodiment, the incidence relation for including needed for the plastics knowledge mapping can be according to actual use demand
It is determined.For example, the incidence relation may include the producer between the plastic product entity and the process entities
Belonging relation, the plastic product entity and institute between method relationship, the plastic product entity and the plastics class instance
State the incidence relation between manufacture relationship, the attribute information and each plastic industry entity between Plastics Company entity
Deng.
Described second establishes module 104 for real according to each plastic industry entity and each plastic industry
Incidence relation between body establishes plastics knowledge mapping.
In one embodiment, after the incidence relation between each plastic industry entity is established, described second
Establishing module 104 can be according to the incidence relation between each plastic industry entity and each plastic industry entity
Foundation obtains the plastics knowledge mapping.
It in one embodiment, include Plastics Company entity, plastic product entity, technique reality with the plastic industry entity
For body and plastics class instance, described second, which establishes module 104, can be accomplished by the following way the building plastics and know
Know map: described second, which establishes module 104, obtains the Plastics Company entity, the plastic product entity, the process entities
And the name identification of plastics class instance, and the Plastics Company entity based on acquisition, the plastic product entity, the work
The name identification of skill entity and plastics class instance constructs plastics knowledge mapping frame, then by the incidence relation between each entity
Filling obtains the plastics knowledge mapping to the plastics knowledge mapping frame.
In one embodiment, described second establish module 104 can also be by the title of each plastic industry entity
Incidence relation between mark and each plastic industry entity is directed into preset pattern database, and by described default
The visualization of graph data is converted to the plastics knowledge mapping.For example, the preset pattern database can be Noe4j figure
Graphic data library, described second establishes name identification and each plastics of the module 104 by each plastic industry entity
Incidence relation between industry entity is directed into Noe4j graphic data base and is visualized, and the plastics knowledge can be generated
Map.
For example, it is following context that the extraction module 101, which acquires a plastic industry data of the target area,
Content: " Chu Doutai modeling is polyvinyl chloride (PVC) manufacturer.PVC belongs to thermoplasticity modeling as polyethylene (PE)
Material, purposes includes electrical apparatus insulation casing, drainpipe etc. ", the extraction module 101 can extract from above-mentioned text and obtain reality
Body " Chu Doutai modeling ", " polyvinyl chloride ", " polyethylene ", " PVC ", " PE ", " thermoplastic ".The processing module 102 carries out
Entity is disambiguated to be handled with specified resolution.Entity disambiguation processing: it is " polychlorostyrene that " PVC ", which is disambiguated, in " PVC is a kind of thermoplastic "
Ethylene ", it is " polyethylene " that " PE " in polyethylene (PE), which is disambiguated,.Reference resolution processing: " its purposes include electrical apparatus insulation casing,
" its " replaces with " polyvinyl chloride " in drainpipe etc. ".Entity attribute information and the entity associated relationship of building are as follows: Chu Doutai
Modeling-production-polyvinyl chloride, the name of an article: polyvinyl chloride, classification: thermoplastic, purposes: electrical apparatus insulation casing, drainpipe；May be used also
Thermoplastic is classified as with obtain polyethylene.Described second establishes module 104 for entity " Chu Doutai modeling ", " polyvinyl chloride "
The name identification of " polyethylene " three entities and between incidence relation (including entity attribute information) be directed into default figure
Graphic data library (such as Node4j), and carry out visualization and be converted to a plastic industry knowledge mapping.
In one embodiment, in order to promote the quality of plastics knowledge mapping, described second, which establishes module 104, is also used to
After generating the plastics knowledge mapping, quantification treatment is carried out to the confidence level of the knowledge in the plastics knowledge mapping, and give up
Confidence level is lower than the knowledge of preset value, retains the knowledge that confidence level is higher than the preset value.Described second establishes module 104 can be with
Credibility quantification processing is carried out to the knowledge in the plastics knowledge mapping using default method for sieving or logistic regression.
It should be understood that when establish obtain plastics knowledge mapping after, the plastics knowledge mapping can assist intelligent search,
Realize data analysis, plastic industry knowledge base question and answer function etc..It can use knowledge reasoning and infer relationship between new entity,
Or the collision detection of logic is carried out to plastics knowledge mapping.Knowledge reasoning can be obtained according to the information that plastics knowledge mapping provides
To more implicit information, plastic data such as can be obtained from plastics knowledge mapping by ontology or rule-based reasoning technology and deposited
Tacit knowledge, predict the relationship implied between entity in map, social computing algorithm can also be used in plastics knowledge mapping
Community present on map is calculated and obtained on network, and associated path between profile information is provided.
The update module 105 is used to update Rule according to presupposed information and updates each plastic industry entity
Information, and the information based on the updated plastic industry entity is updated the plastics knowledge mapping.
In one embodiment, in order to ensure the accuracy of the plastics knowledge mapping, a presupposed information can be set more
New rule is updated the plastics knowledge mapping.The update module 105 can be updated according to the presupposed information advises
Then the plastics knowledge mapping is updated.The update mode can be incremental update or global update.The increment
Update, which can refer to, is added to the knowledge newly increased in plastics knowledge mapping by processing, and global update can be from zero
Start to rebuild new plastics knowledge mapping.
It include that plastic product entity, Plastics Company entity, plastics class instance and technique are real with the plastic industry entity
For body.The update module 105 updates Rule according to the presupposed information and updates the letter of the plastic product entity
Breath, the information of the Plastics Company entity, the information of the plastics class instance and the information of the process entities, and it is based on institute
State the information of the updated plastic product entity, the information of the Plastics Company entity, the plastics class instance letter
The information of breath and the process entities is updated the plastics knowledge mapping.
In one embodiment, the presupposed information updates rule and can be set according to actual use demand, such as
It may include the information for updating the plastic product entity weekly and the letter of the process entities that the presupposed information, which updates rule,
Breath, monthly updates the information of the Plastics Company entity and the information of the plastics class instance.
Please refer to Fig. 3, system 40 is constructed for plastics knowledge mapping in an embodiment of the present invention and constructs the plastics
The flow diagram of knowledge mapping.The building process can be divided into five parts: data acquisition, information extraction, knowledge are melted
It closes, knowledge is processed and the renewal of knowledge.The data acquisition, which can be, obtains non-structured plastic industry data, semi-structured
Plastic industry data and the plastic industry data of structuring.The information extraction can be from the plastic industry data acquired
The structured messages such as entity, relationship and entity attribute are extracted, the information extraction includes entity extraction, Relation extraction and attribute
It extracts.The knowledge fusion includes that entity link and knowledge merge.The entity link can be from the plastics knowledge base of extraction
Candidate entity is selected, and carries out entity and disambiguates and reference resolution processing.It includes merging external data base, merging that the knowledge, which merges,
Entity, the external data base may include existing plastic product structured database, plastic industry structured database, modeling
Expect pattern of enterprises database, third party's plastics knowledge mapping etc., the map knowledge after merging is possibly stored to RDF or default
In chart database (such as Node4j).
The knowledge processing may include ontological construction, knowledge reasoning and quality evaluation.The sheet of plastic industry knowledge mapping
Body can refer to the set of plastic industry related notion, and building ontology may include three phases: entity coordination similarity
It calculates, the extraction of entity hyponymy, Ontology learning.Knowledge reasoning includes but is not limited to the reasoning of logic-based, based on figure
The reasoning of spectrum and the reasoning based on deep learning etc..The quality evaluation is quantified to the confidence level of plastics knowledge mapping,
Give up the lower knowledge of confidence level, to guarantee the quality of knowledge in plastics knowledge mapping.The renewal of knowledge may include concept
Update and data update.Wherein, concept updating includes but is not limited to that the addition of plastic product new varieties, plastic industry are newly looked forward to
Addition, increase of new process of industry etc., data update update, the plastic product of including but not limited to plastic product and business connection
Update, update of enterprise attributes of attribute etc..
Fig. 4 is the flow chart of plastics knowledge mapping construction method in an embodiment of the present invention.Institute according to different requirements,
The sequence for stating step in flow chart can change, and certain steps can be omitted.
Step S400, obtains the plastic industry data of a target area, and extracts from the plastic industry data multiple
Plastic industry entity, wherein multiple plastic industry entities include an at least plastic product entity, at least Plastics Company reality
Body, at least a plastics class instance and an at least process entities.
Step S402 carries out entity to the plastic industry entity that extraction obtains and disambiguates and reference resolution processing.
Step S404 establishes the incidence relation between multiple plastic industry entities.
Step S406 is closed according to the association between each plastic industry entity and each plastic industry entity
System, establishes plastics knowledge mapping.
In some embodiments, in order to promote the quality of plastics knowledge mapping, the method can also include: to generate institute
After stating plastics knowledge mapping, quantification treatment is carried out to the confidence level of the knowledge in the plastics knowledge mapping, and give up confidence level
Lower than the knowledge of preset value, retain the knowledge that confidence level is higher than the preset value.It, can be using default screening in present embodiment
Method or logistic regression carry out credibility quantification processing to the knowledge in the plastics knowledge mapping.
Step S408 updates Rule according to presupposed information and updates the information of each plastic industry entity, and
Information based on updated plastic industry entity is updated the plastics knowledge mapping.
It is specified that building one may be implemented in above-mentioned plastics knowledge mapping construction device, method and computer readable storage medium
The plastics knowledge mapping in region promotes the convenience that plastic industry data management efficiency and data use, can be raw with assisted plastic
It produces enterprise and carries out data analysis, client is facilitated to carry out plastic product buying, for public science popularization plastics knowledge.
It will be apparent to those skilled in the art that the reality of production can be combined with scheme of the invention according to the present invention and inventive concept
Border needs to make other and is altered or modified accordingly, and these change and adjustment all should belong to range disclosed in this invention.
Claims (9)
1. a kind of plastics knowledge mapping construction method, which is characterized in that the described method includes:
The plastic industry data of a target area are obtained, and extract multiple plastic industry entities from the plastic industry data,
Wherein, multiple plastic industry entities include an at least plastic product entity, at least a Plastics Company entity, at least a plastics
Class instance and at least a process entities, the step of extracting multiple plastic industry entities from plastic industry data packet
It includes: extracting plastic product information from the plastic industry data；And described at least one is extracted from the plastic product information
Plastics class instance and an at least process entities；
Entity is carried out to the plastic industry entity that extraction obtains to disambiguate and reference resolution processing；
Establish the incidence relation between multiple plastic industry entities；
According to the incidence relation between each plastic industry entity and each plastic industry entity, establishes plastics and know
Know map；And
Quantification treatment is carried out to the confidence level of the knowledge in the plastics knowledge mapping, and gives up confidence level knowing lower than preset value
Know；
Wherein, the plastic industry entity letter that the plastic industry data source is obtained in Plastic enterprise database and web crawlers
Breath.
2. the method as described in claim 1, which is characterized in that the incidence relation established between multiple plastic industry entities
The step of include:
The production method relationship between the plastic product entity and the process entities is established, and establishes the plastic product reality
Belonging relation between body and the plastics class instance.
3. the method as described in claim 1, which is characterized in that the method also includes:
Rule is updated according to presupposed information and updates the letter of the information of the plastic product entity, the Plastics Company entity
The information of breath, the information of the plastics class instance and the process entities；And
Information, the plastics classification of information, the Plastics Company entity based on the updated plastic product entity are real
The information of body and the information of the process entities are updated the plastics knowledge mapping.
4. the method as described in claim 1, which is characterized in that described to extract multiple plastics rows from the plastic industry data
After the step of industry entity further include:
Each plastic industry entity attributes information is extracted from the plastic industry data；
The step of incidence relation established between multiple plastic industry entities includes:
The attribute information and the plastic industry entity are established into incidence relation.
5. the method as described in claim 1, which is characterized in that the plastic industry data include non-structured plastic industry
The plastic industry data of data, semi-structured plastic industry data and structuring.
6. the method as described in claim 1, which is characterized in that the confidence level to the knowledge in the plastics knowledge mapping
Carry out quantification treatment the step of include:
Credibility quantification processing is carried out to the knowledge in the plastics knowledge mapping using default method for sieving or logistic regression.
7. the method as described in claim 1, which is characterized in that described according to each plastic industry entity and each institute
The step of stating the incidence relation between plastic industry entity, establishing plastics knowledge mapping include:
Incidence relation between the name identification of each plastic industry entity and each plastic industry entity is led
Enter to preset pattern database, and carries out visualization and be converted to the plastics knowledge mapping.
8. a kind of plastics knowledge mapping construction device, described device includes processor and memory, is stored on the memory
Several computer programs, which is characterized in that realized such as when the processor is for executing the computer program stored in memory
The step of claim 1-7 described in any item plastics knowledge mapping construction methods.
9. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has a plurality of instruction,
A plurality of described instruction can be executed by one or more processor, to realize as the described in any item plastics of claim 1-7 are known
The step of knowing map construction method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910528551.8A CN110245241A (en) | 2019-06-18 | 2019-06-18 | Plastics knowledge mapping construction device, method and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910528551.8A CN110245241A (en) | 2019-06-18 | 2019-06-18 | Plastics knowledge mapping construction device, method and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110245241A true CN110245241A (en) | 2019-09-17 |
Family
ID=67888012
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910528551.8A Pending CN110245241A (en) | 2019-06-18 | 2019-06-18 | Plastics knowledge mapping construction device, method and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110245241A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110825889A (en) * | 2020-01-09 | 2020-02-21 | 广东博智林机器人有限公司 | Propaganda information interaction method and device, electronic equipment and storage medium |
| CN112016850A (en) * | 2020-09-14 | 2020-12-01 | 支付宝(杭州)信息技术有限公司 | Service evaluation method and device |
| CN113177095A (en) * | 2021-04-29 | 2021-07-27 | 北京明略软件系统有限公司 | Enterprise knowledge management method, system, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355627A (en) * | 2015-07-16 | 2017-01-25 | 中国石油化工股份有限公司 | Method and system used for generating knowledge graphs |
| US20180039696A1 (en) * | 2016-08-08 | 2018-02-08 | Baidu Usa Llc | Knowledge graph entity reconciler |
| CN107783973A (en) * | 2016-08-24 | 2018-03-09 | 慧科讯业有限公司 | The methods, devices and systems being monitored based on domain knowledge spectrum data storehouse to the Internet media event |
| CN108052576A (en) * | 2017-12-08 | 2018-05-18 | 国家计算机网络与信息安全管理中心 | A kind of reason knowledge mapping construction method and system |
| CN109378053A (en) * | 2018-11-30 | 2019-02-22 | 安徽影联云享医疗科技有限公司 | A kind of knowledge mapping construction method for medical image |
| CN109446341A (en) * | 2018-10-23 | 2019-03-08 | 国家电网公司 | The construction method and device of knowledge mapping |
| CN109508383A (en) * | 2018-10-30 | 2019-03-22 | 北京国双科技有限公司 | The construction method and device of knowledge mapping |
-
2019
- 2019-06-18 CN CN201910528551.8A patent/CN110245241A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355627A (en) * | 2015-07-16 | 2017-01-25 | 中国石油化工股份有限公司 | Method and system used for generating knowledge graphs |
| US20180039696A1 (en) * | 2016-08-08 | 2018-02-08 | Baidu Usa Llc | Knowledge graph entity reconciler |
| CN107783973A (en) * | 2016-08-24 | 2018-03-09 | 慧科讯业有限公司 | The methods, devices and systems being monitored based on domain knowledge spectrum data storehouse to the Internet media event |
| CN108052576A (en) * | 2017-12-08 | 2018-05-18 | 国家计算机网络与信息安全管理中心 | A kind of reason knowledge mapping construction method and system |
| CN109446341A (en) * | 2018-10-23 | 2019-03-08 | 国家电网公司 | The construction method and device of knowledge mapping |
| CN109508383A (en) * | 2018-10-30 | 2019-03-22 | 北京国双科技有限公司 | The construction method and device of knowledge mapping |
| CN109378053A (en) * | 2018-11-30 | 2019-02-22 | 安徽影联云享医疗科技有限公司 | A kind of knowledge mapping construction method for medical image |
Non-Patent Citations (1)
| Title |
|---|
| 贾丙静 等: "基于实体对齐的知识图谱构建研究", 《佳木斯大学学报(自然科学版)》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110825889A (en) * | 2020-01-09 | 2020-02-21 | 广东博智林机器人有限公司 | Propaganda information interaction method and device, electronic equipment and storage medium |
| CN112016850A (en) * | 2020-09-14 | 2020-12-01 | 支付宝(杭州)信息技术有限公司 | Service evaluation method and device |
| CN113177095A (en) * | 2021-04-29 | 2021-07-27 | 北京明略软件系统有限公司 | Enterprise knowledge management method, system, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110245241A (en) | Plastics knowledge mapping construction device, method and computer readable storage medium | |
| RU2657173C2 (en) | Sentiment analysis at the level of aspects using methods of machine learning | |
| CN103814351B (en) | Collaborative gesture-based input language | |
| CN103207914B (en) | The preference vector evaluated based on user feedback generates method and system | |
| US9542477B2 (en) | Method of automated discovery of topics relatedness | |
| CN101694668B (en) | Method and device for confirming web structure similarity | |
| CN106919689A (en) | Professional domain knowledge mapping dynamic fixing method based on definitions blocks of knowledge | |
| CN108182245A (en) | The construction method and device of people's object properties classificating knowledge collection of illustrative plates | |
| CN104199972A (en) | Named entity relation extraction and construction method based on deep learning | |
| CN108427723B (en) | Author recommendation method and system based on clustering algorithm and local perception reconstruction model | |
| CN111783443B (en) | Text disturbance detection method, disturbance recovery method, disturbance processing method and device | |
| CN108681557A (en) | Based on the short text motif discovery method and system indicated from expansion with similar two-way constraint | |
| CN108664574A (en) | Input method, terminal device and the medium of information | |
| CN105027040A (en) | Text input system and method | |
| CN103034726B (en) | Text filtering system and method | |
| US10303770B2 (en) | Determining confidence levels associated with attribute values of informational objects | |
| US8402042B2 (en) | Named entity database or mining rule database update apparatus and method using named entity database and mining rule merged ontology schema | |
| CN106897309A (en) | The polymerization and device of a kind of similar word | |
| CN109033069A (en) | A kind of microblogging Topics Crawling method based on Social Media user's dynamic behaviour | |
| Beniamine et al. | Inferring inflection classes with description length | |
| Zhu et al. | An efficient path computing model for measuring semantic similarity using edge and density | |
| CN110795573B (en) | Method and device for predicting geographic position of webpage content | |
| Clark et al. | Consistent unsupervised estimators for anchored PCFGs | |
| US20120076416A1 (en) | Determining correlations between slow stream and fast stream information | |
| CN114117134A (en) | Abnormal feature detection method, device, equipment and computer readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190917 |