CN109086316A - Knowledge mapping towards industrial Internet of Things resource independently constructs system - Google Patents
Knowledge mapping towards industrial Internet of Things resource independently constructs system Download PDFInfo
- Publication number
- CN109086316A CN109086316A CN201810682986.3A CN201810682986A CN109086316A CN 109086316 A CN109086316 A CN 109086316A CN 201810682986 A CN201810682986 A CN 201810682986A CN 109086316 A CN109086316 A CN 109086316A
- Authority
- CN
- China
- Prior art keywords
- entity
- knowledge mapping
- resource
- candidate entity
- synonymous
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A kind of knowledge mapping towards industrial Internet of Things resource independently constructs system, comprising: acquiring unit, suitable for obtaining the resource request information of user；Resolution unit obtains the information of corresponding resource entity suitable for parsing to acquired resource request information；Alignment unit carrying out synonymous mapping between obtained resource entity and preset candidate entity suitable for will parse, obtaining synonymous candidate entity corresponding with the resource entity that parsing obtains；Incidence relation construction unit, suitable for the synonymous candidate entity obtained based on mapping, incidence relation of the resource entity that building parsing obtains in knowledge mapping.The efficiency and accuracy of industrial Internet of Things resource provision can be improved by constructing the incidence relation between industrial Internet of Things resource in above-mentioned scheme.
Description
Technical field
The present invention relates to internet of things field, certainly more particularly to a kind of knowledge mapping towards industrial Internet of Things resource
Main building system.
Background technique
With the fast development of global industry Internet of Things, the user in industrial Internet of Things is for industrial Internet of Things Resource Dependence
More loom large.Since resource category is more and more in industrial Internet of Things, the resource scale of construction is increasing, and it is quickly right how to realize
The demand of resource more effectively responds, and is that this industrial the internet of things era must be faced and be solved the problems, such as.
For isolated resources various in industrial Internet of Things, relevance between resource is weak, collaboration supply capacity is poor, if will
Knowledge mapping is introduced into the resource of industrial Internet of Things, realizes the relevance strengthened between various resources, then for efficiently responding
Resource request will have great impetus.
But the existing autonomous building how realized about that in industrial Internet of Things about the knowledge mapping of resource, into
And the relevance between resource is promoted, realize the effective supply of resource, everything is just particularly important.
Summary of the invention
Present invention solves the technical problem that being the incidence relation how constructed between industrial Internet of Things resource, to improve industry
The efficiency and accuracy of Internet of Things resource provision.
In order to solve the above technical problems, the embodiment of the invention provides a kind of knowledge mappings towards industrial Internet of Things resource
Autonomous building system, comprising:
Acquiring unit, suitable for obtaining the resource request information of user；
Resolution unit obtains the information of corresponding resource entity suitable for parsing to acquired resource request information；
Alignment unit carrying out synonymous mapping between obtained resource entity and preset candidate entity suitable for will parse, obtaining
To synonymous candidate entity corresponding with the obtained resource entity of parsing；
Incidence relation construction unit, suitable for the synonymous candidate entity obtained based on mapping, the resource that building parsing obtains is real
Incidence relation of the body in knowledge mapping.
Optionally, the acquiring unit, suitable for obtaining the resource request information of user according to preset message transmission rate.
Optionally, the alignment unit, suitable for calculating the phase between the resource entity and the candidate entity that parsing obtains
Like degree；When the similarity between the resource entity that determining parsing obtains and at least two candidate entities is all larger than preset phase
When like degree threshold value, the resource for determining that parsing is obtained from the candidate entity that similarity is greater than the similarity threshold using SVM is real
The synonymous resource entity of body.
Optionally, the incidence relation construction unit is suitable for judging between obtained synonymous candidate entity existing
With the presence or absence of association in knowledge mapping；The association includes at least one of direct correlation and indirect association；Obtained by determination
Synonymous candidate entity between when there is association in existing knowledge mapping, judge between obtained synonymous candidate's entity
With the presence or absence of direct correlation in existing knowledge mapping；When determining between obtained synonymous candidate entity in existing knowledge graph
When there is direct correlation in spectrum, according to the number that obtained synonymous candidate entity occurs simultaneously in resource request, to institute
Direct correlation relationship of the obtained synonymous candidate entity in the knowledge mapping is stated to be updated.
Optionally, the incidence relation construction unit, suitable for using following formula to the obtained synonymous candidate
Direct correlation relationship of the entity in the knowledge mapping is updated:
RELI, j'=| | RELI, j+d||2；
Wherein, RELI, j' indicate direct correlation degree of the updated synonymous candidate entity in the knowledge mapping, RELI, j
Indicate direct correlation degree of the synonymous candidate entity in the knowledge mapping before updating, d is preset constant.
Optionally, the incidence relation construction unit is further adapted for working as between determining obtained synonymous candidate entity
There is no when association in some knowledge mappings, direct correlation degree between the two will be appointed to be arranged in obtained synonymous candidate entity
For initial association angle value, to be closed in the direct correlation constructed in the knowledge mapping between the obtained synonymous candidate entity
System.
Optionally, the incidence relation creating unit is further adapted for determining between obtained synonymous candidate entity existing
Knowledge mapping in not exist when being directly linked, using one in obtained synonymous candidate entity and other between the two
Direct correlation relationship, be derived by it is described other both direct correlation relationships in the knowledge mapping.
Optionally, the incidence relation construction unit exists suitable for obtaining other described the two using the following derivation of equation
Direct correlation relationship in the knowledge mapping:
RELK, j=| | RELI, j*(mati-matj)+RELI, k*(mati-matk)||2；
Wherein, RELK, jIndicate the direct correlation degree of synonymous candidate entity j, k for being derived by the knowledge mapping,
RELI, jIndicate the direct correlation degree of synonymous candidate entity i, j in the knowledge mapping, RELI, kIndicate synonymous candidate entity i, k
Direct correlation degree in the knowledge mapping, mati、matj、matkSynonymous candidate entity i, j, k are respectively indicated in k dimension space
Vector.
Compared with prior art, the technical solution of the embodiment of the present invention has the advantages that
Above-mentioned scheme obtains the letter of corresponding resource entity by parsing to acquired resource request information
Breath, the resource entity that parsing is obtained and preset candidate entity carry out synonymous mapping, and the synonymous candidate obtained based on mapping
Entity, incidence relation of the resource entity that building parsing obtains in knowledge mapping, therefore the confession of industry internet resource can be improved
The efficiency and accuracy given.
Further, when determine there is association in existing knowledge mapping between obtained synonymous candidate entity when,
According to the number that obtained synonymous candidate entity occurs simultaneously in resource request, to the obtained synonymous candidate entity
Incidence relation in the knowledge mapping is updated, and can be strengthened to the incidence relation between resource entity, therefore can
To further increase the efficiency and accuracy of industry internet resource provision.
Further, by obtaining the resource request information of user according to preset message transmission rate, it can control money
The admission velocity of source solicited message prevents the spilling of data, can be improved and builds the reliable of industrial Internet of Things money knowledge mapping building
Property.
Detailed description of the invention
Fig. 1 is the flow diagram of the industrial Internet of Things resources and knowledge map construction method of one of embodiment of the present invention；
Fig. 2 is the process signal of the industrial Internet of Things resources and knowledge map construction method of another kind in the embodiment of the present invention
Figure；
Fig. 3 is the structure that a kind of knowledge mapping towards industrial Internet of Things resource independently constructs system in the embodiment of the present invention
Schematic diagram.
Specific embodiment
Technical solution in the embodiment of the present invention is obtained corresponding by parsing to acquired resource request information
The information of resource entity, the resource entity that parsing is obtained and preset candidate entity carry out synonymous mapping, and are based on mapping
The synonymous candidate entity arrived, incidence relation of the resource entity that building parsing obtains in knowledge mapping, therefore industry can be improved
The efficiency and accuracy of Internet resources supply.
It is understandable to enable above-mentioned purpose of the invention, feature and beneficial effect to become apparent, with reference to the accompanying drawing to this
The specific embodiment of invention is described in detail.
Fig. 1 is the flow diagram of the industrial Internet of Things resources and knowledge map construction method of one of embodiment of the present invention.
Referring to Fig. 1, one of embodiment of the present invention industry Internet of Things resources and knowledge map construction method be can specifically include following
Step:
Step S101: the resource request information of user is obtained.
In specific implementation, the user can be the equipment in industrial Internet of Things or individual.
Step S102: parsing acquired resource request information, obtains the information of corresponding resource entity.
Step S103: the resource entity and preset candidate entity that parsing is obtained carry out synonymous mapping, obtain and parse
The corresponding synonymous candidate entity of obtained resource entity.
In specific implementation, the candidate entity is standardized resource entity provided by resource provision side.
Step S104: the synonymous candidate entity obtained based on mapping, the resource entity that building parsing obtains is in knowledge mapping
In incidence relation.
Above-mentioned scheme obtains the letter of corresponding resource entity by parsing to acquired resource request information
Breath, the resource entity that parsing is obtained and preset candidate entity carry out synonymous mapping, and the synonymous candidate obtained based on mapping
Entity, incidence relation of the resource entity that building parsing obtains in knowledge mapping, therefore the confession of industry internet resource can be improved
The efficiency and accuracy given.
The industrial Internet of Things resources and knowledge map construction method in the embodiment of the present invention is carried out below in conjunction with Fig. 2 detailed
Introduction.
Fig. 2 is the process signal of the industrial Internet of Things resources and knowledge map construction method of another kind in the embodiment of the present invention
Figure.Referring to fig. 2, the industrial Internet of Things resources and knowledge map construction method of one of embodiment of the present invention is suitable for constructing industrial object
The knowledge mapping of networked resources can specifically include following step:
Step S201: the resource request information of user is obtained.
In specific implementation, in order to improve functional reliability, it can obtain user's according to preset message transmission rate
Resource request information, to avoid data spilling.
Step S202: parsing acquired resource request information, obtains the information of corresponding resource entity.
In specific implementation, the information that corresponding resource entity is carried in acquired resource request information, by right
Acquired resource request information is parsed, the information of available user's requested resource entity.
Step S203: the resource entity and preset candidate entity that parsing is obtained carry out synonymous mapping, obtain and parse
The corresponding synonymous candidate entity of obtained resource entity.
In specific implementation, resource entity entrained in the resource request of user and standard provided by resource provision side
There may be certain othernesses between the candidate entity of change, therefore corresponding resource entity is extracted in the resource request from user
When, same benefit film showing can will be carried out between standardized candidate entity provided by the obtained resource entity of parsing and resource provision side
It penetrates, with the corresponding synonymous candidate entity of the resource entity for obtaining with parsing.
In an embodiment of the present invention, obtained resource entity and the synonymous mapping of preset candidate entity progress will parsed
When, the similarity between the resource entity and the candidate entity that parsing obtains can be calculated first, and is obtained determining to parse
Resource entity and at least two candidate entities between similarity when being all larger than preset similarity threshold, using support
Vector machine (SVM) determines the synonymous of the resource entity that parsing obtains from the candidate entity that similarity is greater than the similarity threshold
Resource entity.Wherein, the similarity calculation mode between resource entity and the candidate entity parsed can be according to reality
The needs on border are configured, herein with no restrictions.
Step S204: judge to whether there is association in existing knowledge mapping between obtained synonymous candidate entity；
When the judgment result is no, step S205 can be executed；Conversely, can then execute step S206.
In specific implementation, described to judge whether deposit in existing knowledge mapping between obtained synonymous candidate entity
It is being associated with, that is, is judging to appoint in obtained synonymous candidate entity and be closed between the two with the presence or absence of direct correlation relationship and indirect association
At least one of system.
Step S205: the degree of association between the two will be appointed to be set as initial association degree in obtained synonymous candidate entity
Value, to construct the incidence relation between the obtained synonymous candidate entity in the knowledge mapping.
In specific implementation, it had both been not present in existing knowledge mapping between obtained synonymous candidate entity when determining
Direct correlation relationship can be by will appoint the two in obtained synonymous candidate entity when indirect association relationship is also not present
Between the degree of association be set as the mode of initial association angle value, constructed in the knowledge mapping described obtained synonymous candidate real
Direct correlation relationship between body.Wherein, the initial association angle value can be arranged according to the actual needs, not limit herein
System.
Step S206: judge to appoint in obtained synonymous candidate entity whether equal in existing knowledge mapping between the two
There are direct correlation；When the judgment result is yes, step S207 can be executed；Conversely, can then execute step S208.
Step S207: the number occurred simultaneously in resource request according to obtained synonymous candidate entity, to the institute
Incidence relation of the obtained synonymous candidate entity in the knowledge mapping is updated.
In specific implementation, when determine between obtained synonymous candidate entity exist in existing knowledge mapping it is direct
When association, according to the number that obtained synonymous candidate entity occurs simultaneously in resource request, to described obtained synonymous
Incidence relation of the candidate entity in the knowledge mapping is updated.
In an embodiment of the present invention, when obtained synonymous candidate entity occurs simultaneously in resource request every time,
For being carried out more using following formula to incidence relation of the obtained synonymous candidate entity in the knowledge mapping
It is new:
RELI, j'=| | RELI, j+d||2；
Wherein, RELI, jIndicate the degree of association of the updated synonymous candidate entity in the knowledge mapping, RELI, jIt indicates
The degree of association of the synonymous candidate entity in the knowledge mapping before update, d is preset constant.
Pass through above-mentioned formula, it can be seen that the number that synonymous candidate's entity occurs simultaneously in resource request is more, together
When occur go out direct correlation relationship of the synonymous candidate entity in the knowledge mapping will be bigger, can highlight while occur
Synonymous candidate entity between High relevancy, weaken resource isolation problem, effectively so as to improve the accurate of resource provision
Property.
Step S208: using one in obtained synonymous candidate entity and other direct correlation relationships between the two,
It is derived by other the described incidence relations of the two in the knowledge mapping.
In specific implementation, not exist in existing knowledge mapping between obtained synonymous candidate entity direct
Association refers to that at least there is no direct correlation relationships between the two between obtained synonymous candidate entity.At this point it is possible to
Determine that direct correlation relationship is all had between two synonymous candidate entities without the relationship of direct correlation one is synonymous first
Candidate entity, then the synonymous candidate entity determined by do not have two synonymous candidates of direct correlation relationship with this respectively
Direct correlation relationship between entity, reasoning obtain this two without direct correlation relationship synonymous candidate entities in knowledge graph
Direct correlation relationship in spectrum.
In an embodiment of the present invention, both another association in the knowledge mapping is obtained using the following derivation of equation
Relationship:
RELK, j=| | RELI, j*(mati-matj)+RELI, k*(mati-matk)||2；
Wherein, RELK, jIndicate the degree of association of synonymous candidate entity j, k for being derived by the knowledge mapping, RELI, j
Indicate the degree of association of synonymous candidate entity i, j in the knowledge mapping, RELI, kIndicate that synonymous candidate entity i, k know described
Know the degree of association in map, mati、matj、matkSynonymous candidate entity i, j, k is respectively indicated in the vector of k dimension space.
The above-mentioned method in the embodiment of the present invention is described in detail, below will be to the above-mentioned corresponding device of method
It is introduced.
Fig. 3 shows one of embodiment of the present invention and independently constructs system towards the knowledge mapping of industrial Internet of Things resource
Structure.Referring to Fig. 3, a kind of knowledge mapping towards industrial Internet of Things resource independently constructs system 30, may include: obtain it is single
Member 301, resolution unit 302, alignment unit 303 and incidence relation construction unit 304, in which:
The acquiring unit 301, suitable for obtaining the resource request information of user.In an embodiment of the present invention, described to obtain
Unit 301 is taken, suitable for obtaining the resource request information of user according to preset message transmission rate.
The resolution unit 302 obtains corresponding resource entity suitable for parsing to acquired resource request information
Information.
The alignment unit 303, it is synonymous suitable for that will be carried out between the obtained resource entity of parsing and preset candidate entity
Mapping obtains synonymous candidate entity corresponding with the resource entity that parsing obtains.In an embodiment of the present invention, the alignment is single
Member 303, suitable for calculating the similarity between the resource entity and the candidate entity that parsing obtains；When the money for determining that parsing obtains
When similarity between source entity and at least two candidate entities is all larger than preset similarity threshold, using SVM from phase
It is greater than the synonymous resource entity for the resource entity for determining that parsing obtains in the candidate entity of the similarity threshold like degree.
The incidence relation construction unit 304, suitable for the synonymous candidate entity obtained based on mapping, building parsing is obtained
Incidence relation of the resource entity in knowledge mapping.
In specific implementation, the incidence relation construction unit 304 is suitable for judging between obtained synonymous candidate entity
With the presence or absence of association in existing knowledge mapping；The association includes at least one of direct correlation and indirect association；When true
When there is association in existing knowledge mapping between fixed obtained synonymous candidate entity, judge obtained synonymous candidate real
With the presence or absence of direct correlation in existing knowledge mapping between body；Having when determining between obtained synonymous candidate entity
Knowledge mapping in there is time when being directly linked, occurred simultaneously in resource request according to obtained synonymous candidate entity
Number is updated direct correlation relationship of the obtained synonymous candidate entity in the knowledge mapping.
Optionally, the incidence relation construction unit, suitable for using following formula to the obtained synonymous candidate
Direct correlation relationship of the entity in the knowledge mapping is updated:
RELI, j'=| | RELI, j+d||2；
Wherein, RELI, j' indicate the degree of association of the updated synonymous candidate entity in the knowledge mapping, RELI, jIt indicates
The degree of association of the synonymous candidate entity in the knowledge mapping before update, d is preset constant.
In specific implementation, the incidence relation construction unit 304 is further adapted for when determining obtained synonymous candidate entity
Between in existing knowledge mapping there is no when association, direct pass between the two will be appointed in obtained synonymous candidate entity
Connection degree is set as initial association angle value, with constructed in the knowledge mapping it is straight between the obtained synonymous candidate entity
Connect incidence relation.
In specific implementation, the incidence relation construction unit 304, be further adapted for determining obtained synonymous candidate entity it
Between not exist when being directly linked in existing knowledge mapping, using one in obtained synonymous candidate entity and other
Direct correlation relationship between the two is derived by other the described direct correlation relationships of the two in the knowledge mapping.
In specific implementation, the incidence relation construction unit 304, suitable for using the following derivation of equation obtain it is described its
Direct correlation relationship of both he in the knowledge mapping:
RELK, j=| | RELI, j*(mati-matj)+RELI, k*(mati-matk)||2；
Wherein, RELK, jIndicate the direct correlation degree of synonymous candidate entity j, k for being derived by the knowledge mapping,
RELI, jIndicate the direct correlation degree of synonymous candidate entity i, j in the knowledge mapping, RELI, kIndicate synonymous candidate entity i, k
Direct correlation degree in the knowledge mapping, mati、matj、matkSynonymous candidate entity i, j, k are respectively indicated in k dimension space
Vector.
The embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer instruction, described
The step of industrial Internet of Things resources and knowledge map construction method is executed when computer instruction is run.Wherein, the work
Industry Internet of Things resources and knowledge map construction method refers to being discussed in detail for preceding sections, repeats no more.
The embodiment of the invention also provides a kind of terminal, including memory and processor, energy is stored on the memory
Enough computer instructions run on the processor, the processor execute the industry when running the computer instruction
The step of Internet of Things resources and knowledge map construction method.Wherein, the industrial Internet of Things resources and knowledge map construction method is asked
Referring to being discussed in detail for preceding sections, repeat no more.
It is obtained using the above scheme in the embodiment of the present invention by being parsed to acquired resource request information
The information of corresponding resource entity, the resource entity that parsing is obtained and preset candidate entity carry out synonymous mapping, and are based on
Obtained synonymous candidate entity, incidence relation of the resource entity that building parsing obtains in knowledge mapping are mapped, therefore can be mentioned
The efficiency and accuracy of high industry Internet resources supply.
Further, when determine there is association in existing knowledge mapping between obtained synonymous candidate entity when,
According to the number that obtained synonymous candidate entity occurs simultaneously in resource request, to the obtained synonymous candidate entity
Incidence relation in the knowledge mapping is updated, and can be strengthened to the incidence relation between resource entity, therefore can
To further increase the efficiency and accuracy of industry internet resource provision.
Further, by obtaining the resource request information of user according to preset message transmission rate, it can control money
The admission velocity of source solicited message prevents the spilling of data, can be improved and builds the reliable of industrial Internet of Things money knowledge mapping building
Property.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can store in computer readable storage medium, and storage is situated between
Matter may include: ROM, RAM, disk or CD etc..
Although present disclosure is as above, present invention is not limited to this.Anyone skilled in the art are not departing from this
It in the spirit and scope of invention, can make various changes or modifications, therefore protection scope of the present invention should be with claim institute
Subject to the range of restriction.
Claims (8)
1. a kind of knowledge mapping towards industrial Internet of Things resource independently constructs system characterized by comprising acquiring unit,
Suitable for obtaining the resource request information of user；
Resolution unit obtains the information of corresponding resource entity suitable for parsing to acquired resource request information；
Alignment unit, suitable for synonymous mapping will be carried out between the obtained resource entity of parsing and preset candidate entity, obtain with
Parse the corresponding synonymous candidate entity of obtained resource entity；
Incidence relation construction unit, suitable for the synonymous candidate entity obtained based on mapping, the resource entity that building parsing obtains exists
Incidence relation in knowledge mapping.
2. the knowledge mapping according to claim 1 towards industrial Internet of Things resource independently constructs system, which is characterized in that
The acquiring unit, suitable for obtaining the resource request information of user according to preset message transmission rate.
3. the knowledge mapping of industry Internet of Things resource according to claim 1 constructs system, which is characterized in that the alignment
Unit, suitable for calculating the similarity between the resource entity and the candidate entity that parsing obtains；When the money for determining that parsing obtains
When similarity between source entity and at least two candidate entities is all larger than preset similarity threshold, using SVM from phase
It is greater than the synonymous resource entity for the resource entity for determining that parsing obtains in the candidate entity of the similarity threshold like degree.
4. the knowledge mapping according to claim 1 towards industrial Internet of Things resource independently constructs system, which is characterized in that
The incidence relation construction unit, suitable for judging whether deposit in existing knowledge mapping between obtained synonymous candidate entity
It is being associated with；The association includes at least one of direct correlation and indirect association；When determine obtained synonymous candidate entity it
Between in existing knowledge mapping exist association when, judge it is obtained it is synonymous candidate entity between in existing knowledge mapping
With the presence or absence of direct correlation；It is directly closed when determining to exist in existing knowledge mapping between obtained synonymous candidate entity
When connection, according to the number that obtained synonymous candidate entity occurs simultaneously in resource request, to the obtained synonymous time
Direct correlation relationship of the entity in the knowledge mapping is selected to be updated.
5. the knowledge mapping according to claim 4 towards industrial Internet of Things resource independently constructs system, which is characterized in that
The incidence relation construction unit, suitable for using following formula to the obtained synonymous candidate entity in the knowledge graph
Direct correlation relationship in spectrum is updated:
RELI, j'=| | RELI, j+d||2；
Wherein, RELI, j' indicate direct correlation degree of the updated synonymous candidate entity in the knowledge mapping, RELI, jIt indicates
Direct correlation degree of the synonymous candidate entity in the knowledge mapping before update, d is preset constant.
6. the knowledge mapping according to claim 5 towards industrial Internet of Things resource independently constructs system, which is characterized in that
The incidence relation construction unit is further adapted for working as between determining obtained synonymous candidate entity in existing knowledge mapping not
When in the presence of association, direct correlation degree between the two will be appointed to be set as initial association angle value in obtained synonymous candidate entity,
To construct the direct correlation relationship between the obtained synonymous candidate entity in the knowledge mapping.
7. the knowledge mapping according to claim 6 towards industrial Internet of Things resource independently constructs system, which is characterized in that
The incidence relation creating unit is further adapted for determining between obtained synonymous candidate entity in existing knowledge mapping not
Exist when being directly linked, using one in obtained synonymous candidate entity and other direct correlation relationships between the two,
It is derived by other the described direct correlation relationships of the two in the knowledge mapping.
8. the knowledge mapping according to claim 7 towards industrial Internet of Things resource independently constructs system, which is characterized in that
The incidence relation construction unit, suitable for obtaining other described the two in the knowledge mapping using the following derivation of equation
Direct correlation relationship:
RELK, j=| | RELI, j*(mati-matj)+RELI, k*(mati-matk)||2；
Wherein, RELK, jIndicate the direct correlation degree of synonymous candidate entity j, k for being derived by the knowledge mapping, RELI, j
Indicate the direct correlation degree of synonymous candidate entity i, j in the knowledge mapping, RELI, kIndicate synonymous candidate entity i, k in institute
State the direct correlation degree in knowledge mapping, matj、matj、matkRespectively indicate synonymous candidate entity i, j, k k dimension space to
Amount.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810682986.3A CN109086316B (en) | 2018-06-27 | 2018-06-27 | Knowledge graph autonomous construction system for industrial Internet of things resources |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810682986.3A CN109086316B (en) | 2018-06-27 | 2018-06-27 | Knowledge graph autonomous construction system for industrial Internet of things resources |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109086316A true CN109086316A (en) | 2018-12-25 |
| CN109086316B CN109086316B (en) | 2021-09-14 |
Family
ID=64839946
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810682986.3A Active CN109086316B (en) | 2018-06-27 | 2018-06-27 | Knowledge graph autonomous construction system for industrial Internet of things resources |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109086316B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110209834A (en) * | 2019-04-19 | 2019-09-06 | 广东省智能制造研究所 | A kind of hypergraph construction method for manufacturing industry process equipment Information Atlas |
| CN111198852A (en) * | 2019-12-30 | 2020-05-26 | 浪潮通用软件有限公司 | Knowledge graph driven metadata relation reasoning method under micro-service architecture |
| CN111984641A (en) * | 2020-08-14 | 2020-11-24 | 薛东 | Data processing method and big data platform based on industrial internet and intelligent manufacturing |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150317302A1 (en) * | 2014-04-30 | 2015-11-05 | Microsoft Corporation | Transferring information across language understanding model domains |
| CN105760439A (en) * | 2016-02-02 | 2016-07-13 | 西安交通大学 | Figure cooccurrence relation graph establishing method based on specific behavior cooccurrence network |
| 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 |
| CN106649878A (en) * | 2017-01-07 | 2017-05-10 | 陈翔宇 | Artificial intelligence-based internet-of-things entity search method and system |
| CN107368468A (en) * | 2017-06-06 | 2017-11-21 | 广东广业开元科技有限公司 | A kind of generation method and system of O＆M knowledge mapping |
| 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 |
-
2018
- 2018-06-27 CN CN201810682986.3A patent/CN109086316B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150317302A1 (en) * | 2014-04-30 | 2015-11-05 | Microsoft Corporation | Transferring information across language understanding model domains |
| 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 |
| CN105760439A (en) * | 2016-02-02 | 2016-07-13 | 西安交通大学 | Figure cooccurrence relation graph establishing method based on specific behavior cooccurrence network |
| 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 |
| CN106649878A (en) * | 2017-01-07 | 2017-05-10 | 陈翔宇 | Artificial intelligence-based internet-of-things entity search method and system |
| CN107368468A (en) * | 2017-06-06 | 2017-11-21 | 广东广业开元科技有限公司 | A kind of generation method and system of O＆M knowledge mapping |
Non-Patent Citations (2)
| Title |
|---|
| YUYAN ZHENG,CHUAN SHI,ET AL.: "A Meta Path based Method for Entity Set Expansion in Knowledge Graph", 《IEEE TRANSACTIONS ON BIG DATA》 * |
| 李涛，王次臣，李华康: "知识图谱的发展与构建", 《南京理工大学学报》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110209834A (en) * | 2019-04-19 | 2019-09-06 | 广东省智能制造研究所 | A kind of hypergraph construction method for manufacturing industry process equipment Information Atlas |
| CN110209834B (en) * | 2019-04-19 | 2021-06-25 | 广东省智能制造研究所 | Hypergraph construction method for information map of processing equipment in manufacturing industry |
| CN111198852A (en) * | 2019-12-30 | 2020-05-26 | 浪潮通用软件有限公司 | Knowledge graph driven metadata relation reasoning method under micro-service architecture |
| CN111984641A (en) * | 2020-08-14 | 2020-11-24 | 薛东 | Data processing method and big data platform based on industrial internet and intelligent manufacturing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109086316B (en) | 2021-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10157226B1 (en) | Predicting links in knowledge graphs using ontological knowledge | |
| US10929294B2 (en) | Using caching techniques to improve graph embedding performance | |
| JP6827912B2 (en) | Systems and methods for entrusting robot functions to the cloud with enhanced network edge | |
| WO2017080170A1 (en) | Group user profiling method and system | |
| WO2017118133A1 (en) | Anomaly detection method for internal virtual machine of cloud system | |
| US8370359B2 (en) | Method to perform mappings across multiple models or ontologies | |
| US8719211B2 (en) | Estimating relatedness in social network | |
| CN109086316A (en) | Knowledge mapping towards industrial Internet of Things resource independently constructs system | |
| CN109432777B (en) | Path generation method and device, electronic equipment and storage medium | |
| CN106027593B (en) | For dynamically maintaining the method and system of data structure | |
| US10164995B1 (en) | Determining malware infection risk | |
| WO2022213954A1 (en) | Federated learning method and apparatus, electronic device, and storage medium | |
| CN109165296A (en) | Industrial Internet of Things resources and knowledge map construction method, readable storage medium storing program for executing and terminal | |
| CN110502519B (en) | Data aggregation method, device, equipment and storage medium | |
| KR102009787B1 (en) | Information pushing method and apparatus | |
| JP2018537760A (en) | Method and apparatus for account mapping based on address information | |
| CN111678527B (en) | Path network graph generation method and device, electronic equipment and storage medium | |
| KR20190026853A (en) | Collecting user information from computer systems | |
| WO2021189925A1 (en) | Risk detection method and apparatus for protecting user privacy | |
| Eltarjaman et al. | Private retrieval of POI details in top-K queries | |
| US9767157B2 (en) | Predicting site quality | |
| CN109711555B (en) | Method and system for predicting single-round iteration time of deep learning model | |
| Kozma et al. | TMFoldWeb: a web server for predicting transmembrane protein fold class | |
| CN114817003A (en) | Test information processing method, device, equipment and storage medium | |
| US20150169628A1 (en) | Location detection from queries using evidence for location alternatives |
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 |