CN111737451B - Expert recommendation method based on super network model - Google Patents
Expert recommendation method based on super network model Download PDFInfo
- Publication number
- CN111737451B CN111737451B CN202010406749.1A CN202010406749A CN111737451B CN 111737451 B CN111737451 B CN 111737451B CN 202010406749 A CN202010406749 A CN 202010406749A CN 111737451 B CN111737451 B CN 111737451B
- Authority
- CN
- China
- Prior art keywords
- technical
- knowledge
- expert
- network model
- super
- 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
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000012512 characterization method Methods 0.000 claims abstract description 4
- 238000012163 sequencing technique Methods 0.000 claims abstract description 4
- 238000003672 processing method Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 15
- 230000000694 effects Effects 0.000 description 6
- 238000011160 research Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000003012 network analysis Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/338—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/027—Frames
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an expert recommendation method based on a super network model, which comprises the following steps: preprocessing technical knowledge for constructing the super-network model to obtain technical knowledge for standardization characterization, calculating the association degree between technical experts according to the technical knowledge for standardization characterization, calculating the association degree between technical objects, the association degree between knowledge core contents, respectively constructing a private sub-network, an object sub-network and a knowledge sub-network according to the association degree, forming a super-edge according to the relation between technical knowledge basic elements in the super-network model, calculating the super-edge association degree between the object sub-network and the knowledge sub-network, forming the super-network model, inputting variables to be processed into the super-network model, calculating the association degree of the experts related to the problem according to a probability algorithm, and sequencing and outputting according to the association degree to obtain the rank of the expert for solving the problem.
Description
Technical Field
The invention relates to an expert recommendation method based on a technical knowledge super-network model, in particular to an expert recommendation method in the technical knowledge field of ship pilot navigation.
Background
At present, expert recommendation technology has been widely applied to enterprise organizations and online communities, including expert recommendation for knowledge review under a MediaWiki platform, a Q & a forum user recommendation system, an academic article reviewer query system, a specific disease doctor query system, and the like. According to different types of expert recommendation technologies, the expert recommendation technologies can be classified into an expert recommendation method based on knowledge content, an expert recommendation method based on social network analysis and a hybrid expert recommendation method. In early research, expert recommendation technology was based on a structured and normalized high-quality knowledge base in an enterprise organization, most students evaluated the technical capabilities of the expert in a specific field based on knowledge content, the professional capabilities of users were defined mainly by extracting features from expert-related documents through text mining technology, correlation methods (e.g., fuzzy logic and vector space models) were used to calculate the correlation of user requirements and expert technical capabilities, and the expert was ranked according to the correlation, and the best candidate expert was recommended to the target user. With the development of social network analysis technology, related research finds that social network analysis contributes to expert recommendation technology research, which extends from enterprise organizations to online communities. The three methods are long in application of enterprise organizations and online communities, expert recommendation research in the enterprise organizations is mainly based on knowledge document correlation and other aspects, and most of expert recommendation methods are applicable to organizations with high information quality and clear knowledge hierarchy; because the information quality of the online community is far lower than that of the organization, expert recommendation research of the online community is mainly based on knowledge topic correlation, social network structural characteristics and the like. Most expert recommendation techniques rely on knowledge correlation to assess the expertise level of an expert in a particular problem.
Before a new ship is sailed, many systems and devices are not debugged, and cannot be guaranteed to be in a normal working state, so that a large number of accident potential exist. In the pilot voyage process, once the problems with accident hidden trouble appear, relevant experts need to be found in time to solve the problems, so that the pilot voyage safety of the ship is ensured. Expert recommendations for ship pilot problems relate to different entities (e.g., technical experts, problem objects, technical problems, problem situations, etc.) and various relationships between entities (e.g., relationships between technical experts and problem objects, relationships between technical experts and technical problems, etc.), the relationships between entities being capable of reflecting expert expertise or social relationships of technical personnel. However, in the ship pilot problem, the existing expert recommendation methods are difficult to integrate different elements in the ship pilot problem and various relations among the elements into a unified frame, and cannot deeply describe the relations between each knowledge element and technical experts, so that the expert recommendation accuracy in the ship pilot problem is not high, and the high-precision requirements of searching by the expert in the ship pilot problem solving process cannot be met. Therefore, how to accurately recommend proper experts in time to solve specific problems in the pilot navigation process of the ship is a problem to be solved at present.
Disclosure of Invention
The technical problem to be solved by the invention is to provide an expert recommending method based on a technical knowledge super-network model in order to solve the problems in the ship pilot navigation process in the prior art, but the problems that related experts cannot be found in time to solve or the expert recommending accuracy is not high.
The invention solves the technical problems by the following technical scheme:
an expert recommendation method based on a super network model, the method comprising:
preprocessing the technical knowledge for constructing the super network model to obtain the technical knowledge of normalized representation;
calculating the association degree between technical experts, the association degree between technical objects and the association degree between knowledge core contents according to the technical knowledge of the standardized characterization, and constructing a private subnet, an object subnet and a knowledge subnet according to the association degree;
forming a superside according to the relation between the technical knowledge basic elements in the supernetwork model, calculating the superside association degree between the object sub-network and the knowledge sub-network, and forming the supernetwork model;
inputting variables to be processed into the super network model;
calculating the relevance of the expert related to the problem according to a probability algorithm and sequencing and outputting according to the relevance;
a ranking of the expert solving the problem is obtained.
Preferably, the technical knowledge basic elements in the super network model comprise technical expert elements, technical object elements, technical problem elements, problem situation elements, solution elements and the like.
Preferably, the variables include technical object variables to be processed in ship pilot navigation, traversing the technical object variables and the technical object set in the super network model, and judging whether to add the technical object variables and the technical object set into the alternative set.
More preferably, the variables further comprise technical problem variables and problem situation variables which need to be processed in ship trial navigation, the relevance between the technical problem variables and the problem situation variables and each knowledge application situation in the super-network model is calculated, and whether a knowledge core set is added is judged.
Preferably, the method for preprocessing the technical knowledge comprises a word frequency-reverse file frequency processing method, wherein the word frequency-reverse file frequency processing method can filter a large amount of irrelevant information and retain key concepts in the technical knowledge.
Preferably, the word frequency-reverse file frequency processing method is used for constructing the technical knowledge basic elements in the super network model.
Preferably, the word frequency-reverse file frequency processing method is also used for processing the variables in ship pilot navigation.
Preferably, the probability algorithm is a bayesian probability algorithm.
Preferably, the ranking output comprises a descending ranking, outputting a plurality of top ranked technical experts.
On the basis of conforming to the common knowledge in the field, the above preferred conditions can be arbitrarily combined to obtain the preferred examples of the invention.
The invention has the positive progress effects that: in the ship pilot, different elements with problems and various relations among the elements are integrated into a super-network model, and are output according to the degree of correlation of the experts related to the problems in a sequencing mode according to a probability algorithm, so that a large amount of irrelevant information in the expert recommendation process is effectively avoided, expert recommendation accuracy of the ship pilot problem is improved, and difficulty of expert searching when the ship pilot problem occurs is effectively reduced.
Drawings
FIG. 1 is a schematic block diagram of a method for recommending experts based on a super network model according to an embodiment of the present invention.
FIG. 2 is a flowchart illustrating an expert recommendation method based on a super network model according to an embodiment of the present invention.
Fig. 3 is a technical effect diagram of an expert recommendation method based on a super network model according to an embodiment of the present invention.
Detailed Description
The invention is further illustrated by way of example below, which may be embodied in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "connected" to another element, it can be directly connected to and integrated with the other element or intervening elements may also be present. The terms "mounted," "one end," "the other end," and the like are used herein for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Referring to fig. 1, a schematic flow chart of a module in an embodiment of an expert recommendation method based on a super network model according to the present invention is shown, wherein a variable input 100 module includes the technical object variable 101, the technical problem variable 102 and the problem situation variable 103, and the technical object variable 101, the technical problem variable 102 and the problem situation variable 103 form detailed information of a ship pilot problem.
The super network model 200 module includes: the expert subnetwork 201, the object subnetwork 202, the knowledge subnetwork 203.
In one example, the technical object variable 101, the technical problem variable 102 and the problem situation variable 103 are processed by the word frequency-reverse file frequency method, and a great amount of irrelevant information is filtered through normalized features, so that the key concept of the input variable can still be maintained.
In one example, the technical knowledge in the super network model 200 is preprocessed by the word frequency-reverse file frequency method, a large amount of irrelevant information is filtered, the technical knowledge of the normalized representation is obtained, and a technical expert is calculated based on the technical knowledge of the normalized representationDegree of association between technical objects->Degree of association between knowledge core content +.>And the association degree between the two is used for constructing the expert sub-network 201, the object sub-network 202 and the knowledge sub-network 203.
In an alternative example, the degree of association between experts is calculated by the following formula:
the expert subnetwork is composed of technical experts in the problem solving process, and the association relation among the technical experts reflects the cooperation relation among the technical experts.Representing the cooperative relationship between the experts, if the expert +.>Expert->When two technical knowledge are written cooperatively, there is an association relationship between them, namely +.>P m Representing expert->Expert->Expert node set of the mth associated path of (a).
In an alternative example, the degree of association between objects is calculated by the following formula:
in the object subnetRepresentation object->And object->And the relation coefficient product of the kth association path. FN (Fn)um(O 1 ,O n ) The calculation method comprises the following steps: let O be 1 ,O 2 ,O 3 ,…,O n Is an object in the pilot navigation process, R 1 ,R 2 ,R 3 ,…,R m Is the association relationship between objects. If slave object O 1 To object O n There is a path to object O 1 With object O n Association, expressed asTaking this path as the object association path, denoted ORP (0 1 ,O n )。ORP(O 1 ,O n ) Association relation set or= { R 1 ,…,R m Corresponding association coefficient set ρs= { ρ } 1 ,…ρ m ' its semantic relation coefficient product
In an alternative example, the degree of association between knowledge is calculated by the following formula:
KAC in the knowledge subnetwork is a context applied to describe a technical solution in the technical knowledge of the super network model, including technical problems (TP, technology Problem) and problem contexts (PC, problem Circumstances) of the technical knowledge. KACSim represents the similarity of knowledge application scenarios, TSSim represents the similarity of TS attributes between two pieces of technical knowledge, and α represents the weight of the knowledge application scenario relevance.
The technical knowledge basic elements in the super network model comprise: TE (Technology Expert, technical expert), TO (Technology Object, technical object), TP (Technology Problem, technical problem), PC (Problem Circumstances, problem scenario), TS (Technology Solution, solution), the basic elements of technical knowledge in the super network model co-act TO form a super-edge HE 1 ......HE n Construction of a private subnetwork 101And calculating the association relation between the object subnetwork 102 and the knowledge subnetwork 103, and calculating the super-edge association degree between the subnetworks to form a super-network model 200, wherein TP, PC and TS are core Content (MC) of the technical knowledge.
In an alternative example, the degree of superside association between the mth expert in the expert subnet and the nth object in the object subnet is formulatedAnd (3) representing.
In an alternative example, the degree of superside association between the mth object in the object subnet and the kth knowledge in the knowledge subnet is formulatedAnd (3) representing.
In one example, according to the technical object variable 101, the problem variable 102, the problem situation variable 103 and the expert subnet 201 in the super network model 200 in the variable input 100, the object subnet 202, the knowledge subnet 203 performs judgment and association operation, and then inputs the expert ranks related to the problems to the output module 300 according to a probability algorithm.
Fig. 2 is a flowchart of a procedure in an embodiment of the expert recommendation method based on the super network model according to the present invention, wherein the technical object variables, the technical problem variables, the problem situation variables and the ship technical knowledge super network model generated after the procedure is started are used as inputs of the procedure.
In one example, object subnet set V in the vessel technical knowledge super network model is traversed 0 For each technical object in the set of object subnets V, for whether the technical object variable exists in the set of object subnets V 0 And (3) judging.
In an alternative example, if the technical object variable exists in the object subnet set V 0 Then adding the neighbor node of the technical object variable to the alternative set Ω 0 Is a kind of medium.
In an alternative example, if the technical object variable is not present in the object subnet set V 0 Then calculate the technical object variable and the object subnet set V 0 The association degree of other objects in the ship technical knowledge super-network model, adding the technical object variable into an object sub-network in the ship technical knowledge super-network model, and associating nodes of the technical variableIs added to the alternative set Ω 0 Is a kind of medium.
In one example, the knowledge subnetwork V in the marine technology knowledge super network model is traversed K Calculating the technical problem variable, the problem situation variable and the knowledge sub-network V according to each knowledge application situation in the system K The knowledge applies a context association KACSim.
In one example, if the association degree KACSim is greater than or equal to a threshold value beta, the knowledge nodeAdd into the knowledge core content set->Is a kind of medium.
In one example, traversing the set of expert subnetworks V in the marine technology knowledge super network model S Each technical expert in (1) calculates the correlation of each expert
In one example, for the set of expert subnetworks V in the marine technology knowledge super network model S And judging whether the traversal is complete.
In an alternative example, the technological experts are ranked in descending order of final score, and the j-turn S with the highest rank is output 1 ,S 2 ......S j 。
As shown in fig. 3, which is a technical effect diagram of an embodiment of the expert recommendation method based on the super network model, the case analysis data of the present invention is from a large shipbuilding enterprise in the sea, and two groups of experiments are performed by performing expert recommendation algorithm in Python language under the computer configuration environment of Core i7CPU (3.6 GHz), 8G memory and Windows10 operating system in order to ensure the recommendation effect and the validity of the verification method of the method. And comparing and analyzing the effect of an expert recommendation method (Supernetwork-based) based on the super network model and an expert recommendation method (Content-based) which only considers the text Content relevance, a knowledge relevance and expert authority fusion expert recommendation method (REAU-based) so as to evaluate the method effectiveness.
Experiments show that the expert recommendation method based on the super network model has higher recommendation accuracy than other methods. In addition, the problem of trial run Q7, Q9, Q10 is found in the experimental process that it is very difficult to find the relevant expert accurately by using the expert recommendation method considering only the text Content relevance, but the accuracy of the search expert by the read-based method is low, the reason for this phenomenon is that the problem of trial run Q7, Q9, Q10 does not occur or rarely occurs in the past trial run process, it is very difficult to match the relevant technical knowledge documents or topics in the technical knowledge base, and the association relationship between the technical expert and the specific problem cannot be built, so that the expert recommendation method (Content-based) based on the text Content relevance and the expert recommendation method (read-based) based on the fusion of the knowledge relevance and the expert authority are very difficult to find a sufficient number of relevant experts in this kind of trial run problem, and the expert recommendation method (super network-based) based on the super network model can still calculate the relevance according to the technical object attribute in this kind of trial run problem, so that the accuracy of the expert recommendation method is higher than that of other methods. Therefore, as can be seen from fig. 3, the expert recommendation method based on the super network model has better recommendation effect in the expert recommendation for the ship pilot problem.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the principles and spirit of the invention, but such changes and modifications fall within the scope of the invention.
Claims (9)
1. An expert recommendation method based on a super network model is characterized by comprising the following steps:
preprocessing the technical knowledge for constructing the super network model to obtain the technical knowledge of normalized representation;
calculating the association degree between technical experts, the association degree between technical objects and the association degree between knowledge core contents according to the technical knowledge of the standardized characterization, and respectively constructing a private subnet, an object subnet and a knowledge subnet according to the association degree;
the degree of association between the technical specialists is calculated by the following formula:
wherein,representing the cooperative relationship between experts, P m Representing expert->Expert->Expert node sets of the mth associated path of (a);
the degree of association between the technical objects is calculated by the following formula:
wherein,representation object->And object->The product of the relation coefficients of the kth association path;
the degree of association between the knowledge core contents is calculated by the following formula:
wherein KACSim represents similarity of knowledge application situation, TSSim represents similarity of solution property between two pieces of technical knowledge, and alpha represents weight of knowledge application situation association degree;
forming a superside according to the relation between the technical knowledge basic elements in the supernetwork model, calculating the superside association degree between the object sub-network and the knowledge sub-network, and forming the supernetwork model;
inputting variables to be processed into the super network model;
calculating the relevance of the expert related to the problem according to a probability algorithm and sequencing and outputting according to the relevance;
a ranking of the expert solving the problem is obtained.
2. The expert recommendation method of claim 1, wherein the technical knowledge base elements in the super network model include a technical expert element, a technical object element, a technical problem element, a problem context element, and a solution element.
3. The expert recommendation method of claim 1 wherein the variables comprise technical object variables that need to be processed during a ship trial run, traversing the technical object variables with a set of technical objects in the super network model and determining whether to add to an alternative set.
4. The expert recommendation method of claim 1, wherein the variables further comprise technical problem variables and problem context variables to be processed in a ship trial voyage, calculating a degree of association of the technical problem variables and the problem context variables with each knowledge application context in the super-network model, and determining whether to add a knowledge core set.
5. The expert recommendation method of claim 1, wherein the method of preprocessing the technical knowledge comprises a word frequency-reverse document frequency processing method that filters out a large amount of irrelevant information, preserving key concepts in the technical knowledge.
6. The expert recommendation method of claim 5, wherein the word frequency-reverse document frequency processing method is used for construction of the technical knowledge base element in the super network model.
7. The expert recommendation method of claim 5 wherein said term frequency-reverse document frequency processing method is further used for processing said variables in ship pilot.
8. The expert recommendation method of claim 1, wherein the probability algorithm comprises a bayesian probability algorithm.
9. The expert recommendation method of claim 1, wherein the ranking output comprises a descending ranking, outputting top ranked ones of the technical experts.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010406749.1A CN111737451B (en) | 2020-05-14 | 2020-05-14 | Expert recommendation method based on super network model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010406749.1A CN111737451B (en) | 2020-05-14 | 2020-05-14 | Expert recommendation method based on super network model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111737451A CN111737451A (en) | 2020-10-02 |
CN111737451B true CN111737451B (en) | 2024-03-19 |
Family
ID=72647243
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010406749.1A Active CN111737451B (en) | 2020-05-14 | 2020-05-14 | Expert recommendation method based on super network model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111737451B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115905702B (en) * | 2022-12-06 | 2023-10-10 | 雨果跨境(厦门)科技有限公司 | Data recommendation method and system based on user demand analysis |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105335447A (en) * | 2014-08-14 | 2016-02-17 | 北京奇虎科技有限公司 | Computer network-based expert question-answering system and construction method thereof |
CN105740460A (en) * | 2016-02-24 | 2016-07-06 | 中国科学技术信息研究所 | Webpage collection recommendation method and device |
CN109872244A (en) * | 2019-01-29 | 2019-06-11 | 汕头大学 | A kind of task instructs type wisdom agricultural planting expert system |
CN110162638A (en) * | 2019-04-12 | 2019-08-23 | 淮阴工学院 | A kind of expert's combination proposed algorithm based on figure vector |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TW201126430A (en) * | 2010-01-26 | 2011-08-01 | Univ Nat Taiwan Science Tech | Expert list recommendation methods and systems |
-
2020
- 2020-05-14 CN CN202010406749.1A patent/CN111737451B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105335447A (en) * | 2014-08-14 | 2016-02-17 | 北京奇虎科技有限公司 | Computer network-based expert question-answering system and construction method thereof |
CN105740460A (en) * | 2016-02-24 | 2016-07-06 | 中国科学技术信息研究所 | Webpage collection recommendation method and device |
CN109872244A (en) * | 2019-01-29 | 2019-06-11 | 汕头大学 | A kind of task instructs type wisdom agricultural planting expert system |
CN110162638A (en) * | 2019-04-12 | 2019-08-23 | 淮阴工学院 | A kind of expert's combination proposed algorithm based on figure vector |
Non-Patent Citations (6)
Title |
---|
An inner-enterprise knowledge recommender system;Lu Zhen; George Q. Huang; Zuhua Jiang;;Expert Systems with Applications;第1703-1712页 * |
MediaWiki平台下工程经验知识审阅的专家推荐方法;黄颖;蒋祖华;黄咏文;;上海交通大学学报(12);第1833-1841页 * |
Wang Hong ; Sun Yanshen ; Yu Xiaomei;.Personalized recommendation based on link prediction in dynamic super-networks.2014 5th International Conference on Computing, Communication and Networking Technologies (ICCCNT).2014,第1-7页. * |
并行超网络的研究及其在电影评分预测等问题中的应用;田茂根;;中国优秀硕士学位论文全文数据库信息科技辑;第I138-6389页 * |
超网络研究分析综述;郭秋萍;华康民;;管理工程师(04);第51-55页 * |
面向中文工程论坛问答的知识应用情境获取及应用;李心雨;蒋祖华;宋博;王海丽;孙小明;;计算机集成制造***(05);第1187-1196页 * |
Also Published As
Publication number | Publication date |
---|---|
CN111737451A (en) | 2020-10-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Hayat et al. | Best concept selection in design process: An application of generalized intuitionistic fuzzy soft sets | |
US20120239650A1 (en) | Unsupervised message clustering | |
EP2045739A2 (en) | Modeling topics using statistical distributions | |
EP2045737A2 (en) | Selecting tags for a document by analysing paragraphs of the document | |
CN104298776B (en) | Search-engine results optimization system based on LDA models | |
JP2009093649A (en) | Recommendation for term specifying ontology space | |
US11416907B2 (en) | Unbiased search and user feedback analytics | |
US20160180732A1 (en) | Evaluating Expert Opinions in a Question and Answer System | |
CN108287875B (en) | Character co-occurrence relation determining method, expert recommending method, device and equipment | |
US20120310951A1 (en) | Custodian Suggestion for Efficient Legal E-Discovery | |
CN111797222A (en) | Course knowledge graph construction method, device, terminal and storage medium | |
Binkley et al. | Learning to rank improves IR in SE | |
CN111737451B (en) | Expert recommendation method based on super network model | |
Fan et al. | A two-layer Wang-Mendel fuzzy approach for predicting the residuary resistance of sailing yachts | |
Amato et al. | An application of semantic techniques for forensic analysis | |
CN110795640B (en) | Self-adaptive group recommendation method for compensating group member difference | |
CN116431895A (en) | Personalized recommendation method and system for safety production knowledge | |
US20090172573A1 (en) | Activity centric resource recommendations in a computing environment | |
Mandal et al. | Finding experts in community question answering services: a theme based query likelihood language approach | |
Naouar et al. | Collaborative information retrieval model based on fuzzy clustering | |
Li et al. | A service mode of expert finding in social network | |
CN112269877A (en) | Data labeling method and device | |
Mashina | Application of statistical methods to solve the problem of enriching ontologies of developing subject areas | |
Mehrpoor et al. | Using process ontologies to contextualize recommender systems in engineering projects for knowledge access improvement | |
Atzmueller et al. | Towards Mining Semantic Maturity in Social Bookmarking Systems. |
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 |