CN106909680B - A kind of sci tech experts information aggregation method of knowledge based tissue semantic relation - Google Patents
A kind of sci tech experts information aggregation method of knowledge based tissue semantic relation Download PDFInfo
- Publication number
- CN106909680B CN106909680B CN201710123067.8A CN201710123067A CN106909680B CN 106909680 B CN106909680 B CN 106909680B CN 201710123067 A CN201710123067 A CN 201710123067A CN 106909680 B CN106909680 B CN 106909680B
- Authority
- CN
- China
- Prior art keywords
- expert
- relation
- information
- semantic
- knowledge
- 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.)
- Active
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
-
- 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
- G06F16/9558—Details of hyperlinks; Management of linked annotations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
- G06F16/9566—URL specific, e.g. using aliases, detecting broken or misspelled links
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
The invention discloses a kind of sci tech experts information aggregation method of knowledge based tissue semantic relation, it is related to information science and knowledge engineering technology field.This method, associated by the way that expert info is carried out into semantization with knowledge organization tool, under the semantic relation framework of knowledge organization tool, semantics fusion, automatic discovery and the dynamic for realizing expert info update, meet for expert's academic authority, professional correlation, research liveness, dynamically update and the selection requirement for avoidance of going together, so as to ensure that the expert chosen can be more objective and accurate.
Description
Technical field
The present invention relates to information science and knowledge engineering technology field, more particularly to a kind of knowledge based tissue semantic relation
Sci tech experts information aggregation method.
Background technology
Expert refers to there are the personnel for specializing in or being good at a certain technology to a certain door knowledge, is that China is the most valuable
Resources of human talents, very important effect is played in scientific research, project appraisal, achievements conversion, decision-making consulting etc..Scientific research
The particularly national major research item of project, generally have big, influence wide, the professional and strong innovation in face of subject span etc. important
Feature, generally require to rely on higher academic authority, professional correlation and the peer review expert for studying liveness, and lead to
Cross expert's update mechanism and escape mechanism realizes objective evaluation.
At present, the selection of sci tech experts typically uses the following two kinds mode：One kind is that expert voluntarily declares, forms expert
Storehouse, this mode are stronger to the autonomous control power and subjectivity for declaring information due to declarer, it is difficult to which expert info is carried out
Examine and upgrade in time one by one, influence the fairness of selection of specialists；Another kind be by being counted to the document that expert delivers,
According to the information such as its quantity of document auxiliary judgment, whether it can be used as expert, and this mode is mainly the angle from quantity of document
Chosen, but describing framework to expert info and knowledge connection need to be goed deep into, so as to more accurate from semantic angle
Select academic authority, professional correlation and the peer review expert for studying liveness.Meanwhile above two mode, in reality
Now expert's update mechanism and escape mechanism aspect also need to further perfect, so as to ensure that the expert chosen is more objective and accurate
Really.
The content of the invention
It is an object of the invention to provide a kind of sci tech experts information aggregation method of knowledge based tissue semantic relation, from
And solve foregoing problems present in prior art.
To achieve these goals, the technical solution adopted by the present invention is as follows：
A kind of sci tech experts information aggregation method of knowledge based tissue semantic relation, comprises the following steps：
S1, the candidate expert with compared with high-impact is filtered out in subdivision field according to scientific and technical literature data；
S2, keyword corresponding with the candidate expert is subjected to approximate correlation with knowledge organization tool concept term, it is real
The existing candidate expert associates with the knowledge organization tool, establishes pre-selection expert's relation map；
S3, according to expert info constraints, pre-selection expert's relation map is adjusted, forms final expert
Relation map；
S4, according to the incidence relation between expert info and knowledge organization tool and document resource, carry out expert info
Dynamic updates and safeguarded；
S5, the displaying of various dimensions semantic visualization and monitoring are carried out to expert's relation map.
Preferably, S1 comprises the following steps：
S101, expert info and standardization processing are extracted from document, including paper, patent, Science Report, is made with document
Person is core, is established respectively<Author, mechanism>、<Author, keyword>、<Chinese key, pair between English ＞ pairs of keyword
It should be related to, the mechanism, keyword in a manner of triple to expert are described, and form candidate expert, and expert's name is carried out
Disambiguation and merger processing；
S102, based on the category number in document, keyword and citation information, calculated by synonym, mean cited times,
Chain, discipline category information are quoted, weight and threshold value are set to the candidate expert, filtered out in subdivision field with compared with Gao Ying
Ring the candidate expert of power.
Preferably, S2 is specially：Keyword and knowledge organization are carried out by the way of synonym calculating and/or categorical map
The correspondence of instrument and association, the keyword with semantic dependency is mapped to Knowledge Organization System, and according to semantic relation pair
The academic relevance of expert info is judged, under the support that reference citation chain, author undertake project information, is determined by category
High-impact expert.
Preferably, in S3, the expert info constraints includes：Natural information, scientific research information and the education letter of expert
Breath, and mechanism information associated with it, achievement information and project information.
Preferably, in S3, pre-selection expert's relation map is adjusted, closed specifically, knowledge based tissue is semantic
System, carries out following adjustment：The word family and category of synonymy are merged, the expert with higher uniformity is formed and describes
Information；Technical term with hyponymy is extended, builds the small experts colony of thinner correlation；To with
The expert group of dependency relation, analyzed using social relation network SNA；Under the guiding of knowledge organization tool, to expert
Research direction and discipline category mapped, monitor the integral layout and evolution direction of scientific research, disclose individual expert's
Scientific research interest develops.
Preferably, S4 comprises the following steps：
S401, the multidate information of expert, including research interest and Academic Influence force information are quickly excavated from document, is passed through
Semantic relation, expert info is made inferences and judged with triple form；
S402, according to S401 mode, with triple form, the RDF that expert is established using Jena open source projects is formalized
Semantic model；
S403, according to the RDF Formal Semantics model, expert's RDF semantic queries are carried out using SparQL；
S404, semantic reasoning is carried out according to the information of RDF triples, the expert with semantic association is precisely polymerize
And recommendation.
Preferably, S5 comprises the following steps：
S501, expert group, cooperative relationship, research theme are carried out under same painting canvas to visualize presentation and analysis,
Obtain visualizing expert's relation map；
S502, dynamic monitoring is carried out to the visualization expert relation map with three time, theme and relation dimensions.
The beneficial effects of the invention are as follows：The sci tech experts letter of knowledge based tissue semantic relation provided in an embodiment of the present invention
Polymerization is ceased, is associated by the way that expert info is carried out into semantization with knowledge organization tool, is closed in the semanteme of knowledge organization tool
It is that semantics fusion, automatic discovery and the dynamic that expert info is realized under framework update, meets for expert's academic authority
Property, professional correlation, research liveness, dynamically update and the selection requirement for avoidance of going together, so as to ensure that the expert chosen can
It is more objective and accurate.
Brief description of the drawings
Fig. 1 is that the scientific research project evaluation expert of knowledge based tissue has found general technical route schematic diagram；
Fig. 2 is sci tech experts semantization information describing framework figure；
Fig. 3 is expert's cooperative relationship and research field the visual design point and line chart；
Fig. 4 is theme and time comparison figure；
Fig. 5 is that sci tech experts various dimensions visualize design sketch；
Fig. 6 is sci tech experts subject DYNAMIC DISTRIBUTION schematic diagram；
Fig. 7 is expert's polymerization model schematic diagram of knowledge based organization system；
Fig. 8 is by taking medical oncology field as an example, and the expert of knowledge based organization system polymerize schematic diagram.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, below in conjunction with accompanying drawing, the present invention is entered
Row is further described.It should be appreciated that embodiment described herein is not used to only to explain the present invention
Limit the present invention.
Expert info is the important content of knowledge organization research as a kind of specific knowledge with professional knowledge tight association
Due to knowledge organization tool both have semantization, ordering Knowledge Representation Model, suitable for being carried out to expert info
Efficient association and extension, but with magnanimity document tight association, can be realized on the basis of extensive true data in literature objective, dynamic
The expert info monitoring and checking of state, this for the accurate discovery of sci tech experts and quick renewal provide good theoretical foundation with
Technical support.
In face of enormous amount, professional complicated, dynamic change expert group, the concept and semantic relation of knowledge based tissue
Model, structure semantic association is close, shares convenient, renewal efficiently domain expert's academic relationship network, fast from magnanimity document
Speed, tissue and discovery are carried out to expert info exactly, and applied to the management and service of sci tech experts.
The present invention, using expert info as a kind of important knowledge base, studies open letter based on Knowledge Organization Theory
The semantization relation mechanism of expert info and conceptual relation network under environment is ceased, realizes the tight of expert info and knowledge organization tool
Close docking, two-way interaction, explore data in literature and domain expert's discovery of semantic relation double drive and polymerization.
Knowledge based organization tool semanteme advantage, the semantic association of expert's example and document is established, by document keyword,
Literature author and knowledge organization tool are subjected to generalities activation, association and extension, knowledge of the structure with multi-dimensional semantic association
Relational network, the knowledge organization traditionally based on document is extended into the representation of knowledge and discovery using expert's example as core,
Expand the adaptability and opening of knowledge organization tool, form the knowledge organization new paragon of application drive, realize expert it is quick,
Effectively polymerization, to support the practical applications such as science and technology item evaluation, scientific and technological decision-making.
The invention provides a kind of sci tech experts semantization polymerization, with expert info and the semanteme of knowledge organization tool
Change is associated as research object, under the semantic relation framework of knowledge organization tool, realizes expert info and knowledge organization tool
Fusion, and then realize that semantic association, automatic discovery and the dynamic of expert info update.The invention is to expert's research interest, science
Influence power, cooperative relationship network etc. carry out Dynamic Discovery, in real time monitoring and automatic recommendation, are built for expert info storehouse, scientific research item
Mesh management, technology monitoring etc. establish good basis, have higher precision and dynamic feature, support state research project to comment
Examine, manage and innovate.
To gather as shown in figure 1, the embodiments of the invention provide a kind of sci tech experts information of knowledge based tissue semantic relation
Conjunction method, comprises the following steps：
S1, the candidate expert with compared with high-impact is filtered out in subdivision field according to scientific and technical literature data；
S2, keyword corresponding with the candidate expert is subjected to approximate correlation with knowledge organization tool concept term, it is real
The existing candidate expert associates with the knowledge organization tool, establishes pre-selection expert's relation map；
S3, according to expert info constraints, pre-selection expert's relation map is adjusted, forms final expert
Relation map；
S4, according to the incidence relation between expert info and knowledge organization tool and document resource, carry out expert info
Dynamic updates and safeguarded；
S5, the displaying of various dimensions semantic visualization and monitoring are carried out to expert's relation map.
Wherein, S1 may include steps of：
S101, expert info and standardization processing are extracted from document, including paper, patent, Science Report, is made with document
Person is core, is established respectively<Author, mechanism>、<Author, keyword>、<Chinese key, pair between English ＞ pairs of keyword
It should be related to, the mechanism, keyword in a manner of triple to expert are described, and form candidate expert, and expert's name is carried out
Disambiguation and merger processing；
S102, based on the category number in document, keyword and citation information, calculated by synonym, mean cited times,
Chain, discipline category information are quoted, weight and threshold value are set to the candidate expert, filtered out in subdivision field with compared with Gao Ying
Ring the candidate expert of power.
Because scientific research personnel generally has certain science research output achievement, such as document, patent, Science Report, generally with
Crucial word form is described, and has reacted research interest and the direction of scientific research personnel.Therefore, in the present embodiment, with document
It based on category number, keyword and citation information, can be calculated by synonym, mean cited times, quote chain, the letter such as discipline category
Breath, weight and threshold value are set to candidate expert, the candidate expert with compared with high-impact is filtered out in subdivision field.
In a preferred embodiment of the present invention, S2 is specifically as follows：Using synonym calculating and/or the side of categorical map
Formula carries out keyword and the corresponding and association of knowledge organization tool, and the keyword with semantic dependency is mapped into knowledge organization
System, and the academic relevance of expert info is judged according to semantic relation, undertake project letter in reference citation chain, author
Under the support of breath, high-impact expert is determined by category.
After candidate expert is completed in screening, consider the frequency of keyword, keyword typically reflect expert research interest and
Speciality, the keyword with certain frequency and Knowledge Organization System are subjected to synonymy calculating, realize keyword and knowledge group
Weaver has the approximate correlation of concept term, and then can be by the pass related to conceptual system foundation of the expert info corresponding to keyword
System, so as to the conceptual system of activated knowledge organization tool, realize that expert info semanteme transmits, and then formation knowledge organization tool,
Close interaction between keyword, author.
In the present embodiment, in S3, the expert info constraints includes：Natural information, scientific research information and the religion of expert
Educate information, and mechanism information associated with it, achievement information and project information.
Wherein, the natural information of expert, such as age, name, sex, nationality, can be by inheriting existing describing framework
Realize, there is higher versatility, the standardization of metadata level is carried out with existing national standard, be existing all kinds of experts databases
Interconnect and provide basis with Semantic Interoperation.
The scientific research information of sci tech experts, mainly expert's classification and research direction are entered by classification information and specification term
Row normalization, is solved due to error caused by term ambiguity；Taxonomic hierarchies can use CDC and subject
Classification, it is consistent with existing taxonomic hierarchies.
The educational information of expert, the education experience and specialty background of main prominent expert, as Expert opinion it is basic according to
According to.
Using these information as point of penetration, then be associated and link with a variety of data resources, for example, document databse, achievement storehouse,
Project library etc., forms the expert info association system of data-driven, and renewal and checking for expert info provide secure support.
Relation between above-mentioned expert info constraints, as shown in Figure 2.
In a preferred embodiment of the present invention, in S3, pre-selection expert's relation map is adjusted, specifically,
Knowledge based tissue semantic relation, carries out following adjustment：The word family and category of synonymy are merged, being formed has more
Expert's description information of high uniformity；Technical term with hyponymy is extended, builds the small of thinner correlation
Experts colony；To the expert group with dependency relation, analyzed using social relation network SNA；In knowledge organization
Under the guiding of instrument, the research direction and discipline category of expert are mapped, monitor integral layout and the evolution of scientific research
Direction, the scientific research interest for disclosing individual expert develop.
In the embodiment of the present invention, S4 may include steps of：
S401, the multidate information of expert, including research interest and Academic Influence force information are quickly excavated from document, is passed through
Semantic relation, expert info is made inferences and judged with triple form；
S402, according to S401 mode, with triple form, the RDF that expert is established using Jena open source projects is formalized
Semantic model；
S403, according to the RDF Formal Semantics model, expert's RDF semantic queries are carried out using SparQL；
S404, semantic reasoning is carried out according to the information of RDF triples, the expert with semantic association is precisely polymerize
And recommendation.
In the above method, first, sci tech experts semantic reasoning mechanism is established.By semantic relation, the speciality of expert is entered
Row reasoning and judgement, such as the static semantic relation of regularity,；Can also be by dynamic calculation, the dynamical min from document
The multidate information of expert, such as calculated by co-occurrence, the cooperative relationship excavated between expert.And then by semantic classes, realize
The reasoning of expert；
Then, RDF resource description frameworks are established.In frame system, each expert can be regarded as a resource,
Each resource has the URI (Uniform Resource Locator, URL) of oneself, can using this URI
To get some expert, and then get the attribute and property value that this expert is described in detail；
Wherein, expert's RDF semantic frame models are built using Jena, as shown in Figure 3.Jena is one of Apache and increased income
Project, for building Semantic Web program, it provides one group of instrument and Java storehouses to help to develop semantic web, builds RDF moulds
Type, RDF files are read, generate RDF files, link data application etc.；
After constructing expert's rdf model, RDF semantic queries can be carried out.RDF can be entered after successfully constructing using SparQL
Row inquiry, as shown in figure 4, any one element information in SparQL inquiries in triple can be replaced initial is's
Variable, such as：A variable phone information is introduced, can so be defined：vcard:telephoneTelephone, where
Sentence redundancy is avoided to use prefix in sentence；
It is then possible to carry out RDF reasoning from logics and application.Semantic reasoning, such as A are carried out according to the information of RDF triples
In B working units, C expert can release A and B belongs to Peer Relationships in B working units expert：<Zhang San, isStaffof, A are mono-
Position>-<Li Si, sStaffof, A units>-<x,isStaffof,y>,<z,isStaffof,y>-><x,is
colleague,z>=》<Zhang San, is colleague, Li Si>.
In the embodiment of the present invention, S5 may include steps of：
S501, expert group, cooperative relationship, research theme are carried out under same painting canvas to visualize presentation and analysis,
Obtain visualizing expert's relation map；
S502, dynamic monitoring is carried out to the visualization expert relation map with three time, theme and relation dimensions.
In the above method, in expert's relation map is visualized, the semantic visualization analysis of sci tech experts can be carried out.Specially
The cooperative relationship of family can show the association between expert well by point and line chart, i.e. figure interior joint represents expert, section
Line between point represents the cooperative relationship of expert or other incidence relations.The research field feature of expert is substantially a kind of
Category attribute, and color, position and shape can the other attributes of fine geographic classification in visualized elements.Expert's association area is ground
Study carefully situation.Represented in the present invention with the Quantity of Papers under related subject, Quantity of Papers is numeric type data, can be big by area
The visualized elements such as small and transparency are presented.Animation can dynamically represent the change of data in time, can be very
The situation that expert's research field or research interest change over time is presented well.
Designed for sci tech experts semantic visualization, can be as shown in Fig. 3, Fig. 4, Fig. 5, a large amount of different characteristics reflection to one
In individual painting canvas, there are enough visualized elements that these features can be presented, the visual design is carried out according to different demands, suitably
Ground integrates visualized elements and provides the user method for visualizing auxiliary expert recommendation, ensures the readable and lively of visualized graphs
Property；
Using visualization technique, expert info polymerization result can more intuitively be disclosed, such as Fig. 3, Fig. 4, Fig. 5 institute
Show.In figure 3, with node on behalf difference expert, line represents the cooperative relationship between expert, node size and expert in node
It is directly proportional in the dispatch quantity of the professional domain, select node being capable of highlighted node and which expert by interactive mode
With cooperative relationship, this has certain effect for the escape mechanism that expert recommends；Size of node shows expert in correlation
The achievement in research in field, it is more in the achievement in research of association area for the bigger explanation of node, is thus easy to selection to have height
Influence power expert；Node color illustrates the difference of expert's research direction, and user can intuitively distinguish grinding for expert by color
Study carefully direction, and find out the small experts to match with project research direction.User can conveniently and efficiently contrast different experts
The feature such as cooperative relationship, ambit and achievement in research, not only can individually observe single features, moreover it is possible to Comprehensive Correlation point
Analyse multiple angle characters of different experts.When user puts mouse on the curved section into Fig. 3, curve can highlight automatically (to be become
For blueness), the specifying information that the curved section represents can be shown beside figure, for example, so-and-so is cooperative relationship with so-and-so.Fig. 4,5
The shown the visual design longitudinal axis represents different experts, transverse axis represents the research theme of all experts.Each node of ordinate
The expert in the field is represented, each node of abscissa represents some research directions under the field.Size represents the expert
In the research intensity of the direction, calculated with scientific achievement quantity；Different colors represents citation times of the author in the direction,
Color is deeper, illustrates that times cited is more, influence power is bigger.The research theme and research interest of expert can with discipline development with
And study hotspot constantly changes, therefore the effect of animation is added in the visual design shown in Fig. 4, Fig. 5, existed by mouse
Movement on lower left time label, the situation of change of Dynamic Announce different year expert achievement in research under different themes, such as
The contrast of 2010 and expert achievement in research and influence power under different themes in 2014 is shown in Fig. 4, Fig. 5 respectively, from figure
In it can be seen that expert's research interest there occurs bigger change.By in the visual design shown in Fig. 3, Fig. 4, Fig. 5, energy
Quickly, precisely find in recent years to sci tech experts of the research theme achievement in research compared with horn of plenty.Fig. 6 is mounted with scientific and technical literature
Afterwards, the distribution situation of expert is shown with discipline classification.
Method provided by the invention, as a result of knowledge organization tool, expert polymerize accuracy and greatly improved, so as to solve
Determine and limited to caused by traditionally relying on keyword merely.Its implementation model can be found in Fig. 7, wherein, knowledge organization layer represents to know
Semantic relation between knowledge, can be using the thesaurus in field, domain body etc.；" expert's polymerization " layer refers in the field
Expert's co-occurrence and incidence relation, calculated by synonym and be associated keyword and the concept in " knowledge organization layer ", entered
And find experts；" document resource layer " is related ends and statistics of the candidate expert in the field, for pushing away for candidate expert
Recommend and finally determine that providing quantization supports, and dynamically updated with the change of data resource.Pass through key between three aspects
Word and knowledge organization tool are associated, and realize the polymerization and optimization of small experts.For example, the medical expert of tumor area can
To be extended by knowledge organization tool, " small colleague " expert with more high correlation is found, and pass through the hair in document
Literary quantity, drawn the frequency, year distribution angularly, selecting has higher authoritative domain expert, and its implementation process can join
As shown in Figure 8.
Specific embodiment：The embodiments of the invention provide " oncology " field technology of knowledge based tissue semantic relation is special
Family's information aggregation method, comprises the following steps：
S1, from document databse, with《CDC》In the document metadata of " oncology " classification taken out
Take, document type includes journal article, meeting paper, academic dissertation, Science Report, patent etc.；Metadata fields include document
Title, author, mechanism, keyword, classification number, quotation, h indexes, source etc..Statistics<Author, keyword word frequency>, by key
Expert of the word word frequency more than 10 is as candidate expert；Statistics<Keyword, quote number>, pass of the number more than 10 will be quoted
Candidate expert corresponding to keyword is as candidate expert, generation<Candidate expert, keyword>Tables of data.Meanwhile made by document
Person's co-occurrence calculates, and obtains the related partner of candidate expert, is formed<Candidate expert, partner>、<Author, mechanism of holding a post>》Close
It is table, data basis is provided for expert's optimized relation.For example, " document resource layer " in the figure 7, by all core periodical papers
Keyword more than 10 times, the expert of citation times more than 10 times screened, as candidate expert.In order to solve expert
Synonym, typically with<Author, structure of holding a post>Author is accurately judged.
S2, will<Candidate expert, keyword>In keyword by synonym calculating instrument, be mapped to《Medical subject headings
Table》, the existing knowledge organization tool such as SUMO ontology knowledge bases, and pushed away by the semantic relation in knowledge organization tool
Reason.With《MeSH》In use, generation, category, point, ginseng etc. semantic type, be indicated and pushed away using RDF format
Reason, to judge whether candidate expert belongs to same subdivision professional domain.Such as in knowledge organization layer, " Li Saimei " and " Song Hui " two
The document of position scientific research personnel belongs to " liver tumour " field, therefore can be used as experts.
S3, expert's relation is adjusted.If two experts in S2 belong to same subdivision field, and in the absence of in S1
Cooccurrence relation, then recommended；If failing to find direct experts in S2, by knowledge organization semantic relation, upwards
The extension of position word field, obtain association area expert, expert group of the composition with complementary relationship.In addition, candidate's expert info will
Associated with project library etc., if two experts belong to same mechanism or same project, need to avoid, arranged from recommendation list
Remove.This step is the optimization to S2, forms expert's relation map of determination.For example, in S2, " Li Saimei " and " Song Hui " two
The quantity of document that scientific research personnel delivers is 60 and 40 core periodical papers respectively, and paper cooperative relationship is not present；With
Expert's mechanism information is matched, and Peer Relationships are also not present in the two, then preferential recommendation " Li Saimei " is used as core expert, can be with
Evaluate the relevant item and achievement of " Song Hui ".If conversely, failing to find associated specialist, carried out by the knowledge organization layer in S2
Extension, associated specialist is selected in bigger professional range.
S4 adjusts S1-S3, judges change and the liveness of expert's research field according to the dynamic change of document；Can also
According to the change of knowledge organization tool, compatible multiple different types of knowledge organization tools, interdisciplinary, cross-cutting expert is realized
Auto-polymerization.For example, regularly updating expert's performance data in document resource layer, and the change of expert's unit is monitored in time, to this
Recommendation results enter Mobile state renewal.
S5 expert's polymerization result visualizes.To S1-S4 Various types of data, using co-occurrence figure, discipline classification, expert power
The modes such as thermodynamic chart are shown, and in a manner of more directly perceived, dynamic, improve expert's polymerization effect.For example, to expert in S1
Cooccurrence relation counted, be shown with social relation network figure；According to dimensions such as time, theme, relations to expert's
Liveness, influence power carry out visualization judgement；Fig. 6 is then that the professional domain of expert is monitored on the whole, with satisfaction pair
Intersect professional domain and the demand of experts database renewal, realize the dynamic renewal of experts database.
By using above-mentioned technical proposal disclosed by the invention, following beneficial effect has been obtained：The embodiment of the present invention carries
The sci tech experts information aggregation method of the knowledge based tissue semantic relation of confession, by the way that expert info and knowledge organization tool are entered
Row semantization associates, and under the semantic relation framework of knowledge organization tool, realizes the semantics fusion of expert info, automatic discovery
Updated with dynamic, meet for expert's academic authority, professional correlation, research liveness, dynamically update and avoidance of going together
Selection requirement, so as to ensure choose expert can be more objective and accurate.
Each embodiment in this specification is described by the way of progressive, what each embodiment stressed be with
The difference of other embodiment, between each embodiment identical similar part mutually referring to.
Those skilled in the art should be understood that the sequential for the method and step that above-described embodiment provides can be entered according to actual conditions
Row accommodation, also can concurrently it be carried out according to actual conditions.
All or part of step in the method that above-described embodiment is related to can by program come instruct the hardware of correlation come
Complete, described program can be stored in the storage medium that computer equipment can be read, for performing the various embodiments described above side
All or part of step described in method.The computer equipment, such as：Personal computer, server, the network equipment, intelligent sliding
Dynamic terminal, intelligent home device, wearable intelligent equipment, vehicle intelligent equipment etc.；Described storage medium, such as：RAM、
ROM, magnetic disc, tape, CD, flash memory, USB flash disk, mobile hard disk, storage card, memory stick, webserver storage, network cloud storage
Deng.
Finally, it is to be noted that, herein, such as first and second or the like relational terms be used merely to by
One entity or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or operation
Between any this actual relation or order be present.Moreover, term " comprising ", "comprising" or its any other variant meaning
Covering including for nonexcludability, so that process, method, commodity or equipment including a series of elements not only include that
A little key elements, but also the other element including being not expressly set out, or also include for this process, method, commodity or
The intrinsic key element of equipment.In the absence of more restrictions, the key element limited by sentence "including a ...", is not arranged
Except other identical element in the process including the key element, method, commodity or equipment being also present.
Described above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications also should
Depending on protection scope of the present invention.
Claims (4)
1. a kind of sci tech experts information aggregation method of knowledge based tissue semantic relation, it is characterised in that comprise the following steps：
S1, the candidate expert with compared with high-impact is filtered out in subdivision field according to scientific and technical literature data；
S2, keyword corresponding with the candidate expert is subjected to approximate correlation with knowledge organization tool concept term, realizes institute
Associating for candidate expert and the knowledge organization tool is stated, establishes pre-selection expert's relation map；
S3, according to expert info constraints, pre-selection expert's relation map is adjusted, forms final expert's relation
Collection of illustrative plates；
S4, according to the incidence relation between expert info and knowledge organization tool and document resource, carry out the dynamic of expert info
Renewal and maintenance；
S5, the displaying of various dimensions semantic visualization and monitoring are carried out to expert's relation map；
In S3, the expert info constraints includes：Natural information, scientific research information and the educational information of expert, and and its
Mechanism information, achievement information and the project information of association；
In S3, pre-selection expert's relation map is adjusted, specifically, knowledge based tissue semantic relation, is carried out as follows
Adjustment：The word family and category of synonymy are merged, form expert's description information with higher uniformity；To with
The technical term of hyponymy is extended, and builds the small experts colony of thinner correlation；To with dependency relation
Expert group, analyzed using social relation network SNA；Under the guiding of knowledge organization tool, to the research direction of expert
Mapped with discipline category, monitor the integral layout and evolution direction of scientific research, the scientific research interest for disclosing individual expert is drilled
Become；
S4 comprises the following steps：
S401, the multidate information of expert, including research interest and Academic Influence force information are quickly excavated from document, passes through semanteme
Relation, expert info is made inferences and judged with triple form；
S402, according to S401 mode, with triple form, the RDF Formal Semantics of expert are established using Jena open source projects
Model；
S403, according to the RDF Formal Semantics model, expert's RDF semantic queries are carried out using SparQL；
S404, semantic reasoning is carried out according to the information of RDF triples, the expert with semantic association is precisely polymerize and pushed away
Recommend.
2. the sci tech experts information aggregation method of knowledge based tissue semantic relation according to claim 1, its feature exist
In S1 comprises the following steps：
S101, expert info and standardization processing are extracted from document, including paper, patent, Science Report, using literature author as
Core, establish respectively<Author, mechanism>、<Author, keyword>、<Chinese key, the corresponding pass between English ＞ pairs of keyword
System, mechanism, keyword in a manner of triple to expert are described, and form candidate expert, and carry out disambiguation to expert's name
Handled with merger；
S102, based on the category number in document, keyword and citation information, calculated by synonym, mean cited times, reference
Chain, discipline category information, weight and threshold value are set to the candidate expert, filtered out in subdivision field with compared with high-impact
Candidate expert.
3. the sci tech experts information aggregation method of knowledge based tissue semantic relation according to claim 1, its feature exist
In S2 is specially：Using synonym calculate and/or categorical map by the way of carry out keyword and the corresponding of knowledge organization tool and
Association, Knowledge Organization System is mapped to by the keyword with semantic dependency, and according to expert info of semantic relation
Art relevance is judged, under the support that reference citation chain, author undertake project information, determines that high-impact is special by category
Family.
4. the sci tech experts information aggregation method of knowledge based tissue semantic relation according to claim 1, its feature exist
In S5 comprises the following steps：
S501, expert group, cooperative relationship, research theme are carried out under same painting canvas to visualize presentation and analysis, obtained
Visualize expert's relation map；
S502, dynamic monitoring is carried out to the visualization expert relation map with three time, theme and relation dimensions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710123067.8A CN106909680B (en) | 2017-03-03 | 2017-03-03 | A kind of sci tech experts information aggregation method of knowledge based tissue semantic relation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710123067.8A CN106909680B (en) | 2017-03-03 | 2017-03-03 | A kind of sci tech experts information aggregation method of knowledge based tissue semantic relation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106909680A CN106909680A (en) | 2017-06-30 |
| CN106909680B true CN106909680B (en) | 2018-04-03 |
Family
ID=59186199
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710123067.8A Active CN106909680B (en) | 2017-03-03 | 2017-03-03 | A kind of sci tech experts information aggregation method of knowledge based tissue semantic relation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106909680B (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2018313902B2 (en) * | 2017-08-10 | 2023-10-19 | The Dun & Bradstreet Corporation | System and method for dynamic synthesis and transient clustering of semantic attributions for feedback and adjudication |
| CN110119812A (en) * | 2018-02-07 | 2019-08-13 | 刘劲彤 | A kind of knowledge base and its methods of exhibiting, querying method |
| CN109033362A (en) * | 2018-07-26 | 2018-12-18 | 北京仿真中心 | Graphical relation query method and system, computer equipment and readable storage medium storing program for executing |
| CN110941662A (en) * | 2019-06-24 | 2020-03-31 | 上海市研发公共服务平台管理中心 | Graphical method, system, storage medium and terminal for scientific research cooperative relationship |
| CN110909975B (en) * | 2019-10-11 | 2022-11-29 | 广东省科技基础条件平台中心 | Scientific research platform benefit evaluation method and device |
| CN112836060B (en) * | 2019-11-25 | 2023-11-24 | 中国科学技术信息研究所 | Atlas construction method and apparatus for technological innovation data |
| CN111008330A (en) * | 2019-11-27 | 2020-04-14 | 清华大学 | Expert recommendation method and system based on multiple data sources |
| CN111008215B (en) * | 2019-11-29 | 2021-04-06 | 中科院计算技术研究所大数据研究院 | Expert recommendation method combining label construction and community relation avoidance |
| CN111259041A (en) * | 2020-02-26 | 2020-06-09 | 山东理工大学 | Scientific and technological expert resource virtualization and semantic reasoning retrieval method |
| CN112966053B (en) * | 2020-09-18 | 2023-04-18 | 青岛海洋科学与技术国家实验室发展中心 | Knowledge graph-based marine field expert database construction method and device |
| CN112199518B (en) * | 2020-11-17 | 2023-08-15 | 西安交通大学 | Knowledge graph recommendation driving production technology route map configuration method in production technology |
| CN112463950B (en) * | 2020-12-10 | 2023-10-24 | 中国科学院深圳先进技术研究院 | Document searching method and device and electronic equipment |
| CN113255364A (en) * | 2021-05-28 | 2021-08-13 | 华斌 | Multi-expert opinion machine integration method for government affair informatization project based on knowledge fusion |
| CN113434693B (en) * | 2021-06-23 | 2023-02-21 | 重庆邮电大学工业互联网研究院 | Data integration method based on intelligent data platform |
| CN113780001B (en) * | 2021-08-12 | 2023-12-15 | 北京工业大学 | Visual analysis method for academic paper homonymy disambiguation |
| CN116595192B (en) * | 2023-05-18 | 2023-11-21 | 中国科学技术信息研究所 | Technological front information acquisition method and device, electronic equipment and readable storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1366261A (en) * | 2001-08-08 | 2002-08-28 | 钟音 | Computer index system for choosing and discriminating experts |
| US9141668B2 (en) * | 2009-12-29 | 2015-09-22 | International Business Machines Corporation | Expert locator based on user polling |
| US9582495B2 (en) * | 2014-06-17 | 2017-02-28 | Business Objects Software Ltd. | Domain knowledge driven semantic extraction system |
| CN104281714A (en) * | 2014-10-29 | 2015-01-14 | 南通大学 | Hospital portal website clinic specialist information extracting system |
-
2017
- 2017-03-03 CN CN201710123067.8A patent/CN106909680B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106909680A (en) | 2017-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106909680B (en) | A kind of sci tech experts information aggregation method of knowledge based tissue semantic relation | |
| CN103995858B (en) | The individualized knowledge active push method that task based access control is decomposed | |
| Devillers et al. | Towards spatial data quality information analysis tools for experts assessing the fitness for use of spatial data | |
| Heer et al. | Orion: A system for modeling, transformation and visualization of multidimensional heterogeneous networks | |
| Cho et al. | Link prediction for interdisciplinary collaboration via co-authorship network | |
| Cao et al. | Ontology-based customer preference modeling for concept generation | |
| Niu et al. | FACETS: A cognitive business intelligence system | |
| Velden et al. | Mapping the cognitive structure of astrophysics by infomap clustering of the citation network and topic affinity analysis | |
| CN105787068A (en) | Academic recommendation method and system based on citation network and user proficiency analysis | |
| Afzal et al. | Expertise Recommender System for Scientific Community. | |
| KR20150031087A (en) | Method and apparatus for providing search service based on knowladge service | |
| Schaible et al. | TermPicker: Enabling the reuse of vocabulary terms by exploiting data from the Linked Open Data cloud | |
| Melchiorsen | Bibliometric differences–a case study in bibliometric evaluation across SSH and STEM | |
| Spirin et al. | People search within an online social network: Large scale analysis of facebook graph search query logs | |
| Liao et al. | PORE: a personal ontology recommender system for digital libraries | |
| Vega-Gorgojo et al. | Visual query interfaces for semantic datasets: An evaluation study | |
| Hou et al. | Question answering system based on military knowledge graph | |
| Kuo et al. | An intellectual structure of activity-based costing: a co-citation analysis | |
| Wu et al. | Embedding funding consultation in library services: a co-occurrences network analysis of knowledge flow in scientific funding | |
| Ryjov | Personalization of social networks: adaptive semantic layer approach | |
| HG et al. | An investigative study on the quality aspects of linked open data | |
| Joshi et al. | Linkgen: Multipurpose linked data generator | |
| Ye et al. | An interpretable mechanism for personalized recommendation based on cross feature | |
| Kannan | Semantic-based Researcher Profile Management System: Case Study on VIVO | |
| Chudasama et al. | InterpretME: A tool for interpretations of machine learning models over knowledge graphs |
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 |