CN109087223A - A kind of educational resource model building method based on ontology - Google Patents
A kind of educational resource model building method based on ontology Download PDFInfo
- Publication number
- CN109087223A CN109087223A CN201810877818.XA CN201810877818A CN109087223A CN 109087223 A CN109087223 A CN 109087223A CN 201810877818 A CN201810877818 A CN 201810877818A CN 109087223 A CN109087223 A CN 109087223A
- Authority
- CN
- China
- Prior art keywords
- ontology
- concept
- educational resource
- model building
- resource model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
Abstract
The present invention discloses a kind of educational resource model building method based on ontology, comprising: (1) extracts educational resource term and concept, file each in corpus is carried out analysis using statistical method and extracts notional word；(2) it determines the hierarchical relationship between concept, calculates the similarity between notional word using hierarchical clustering algorithm, be allowed to be polymerized to one kind, form the cluster with hierarchical relationship；(3) attribute and relation on attributes for determining concept establish the semantic tagger and semantic relation of the educational resource dispersed on network；(4) educational resource example is created, ontology is filled using example, establishes logic knowledge base.The present invention is filtered the uncertainty of concept using comentropy and is determined hierarchical relationship between concept using hierarchical clustering algorithm, clearly indicate the main concept term of education sector, attribute and correlation, to the description that attribute rule is formalized possessed by education sector activity, the level of learning of user, the update of knowledge, development of technology etc. are improved.
Description
Technical field
The present invention relates to educational resource field more particularly to a kind of educational resource model building methods based on ontology.
Background technique
For online education by extensive concern, the basis of online education and core are exactly to establish the education money of profession in recent years
Source ontology library, but the various educational resources in current Web lack consistent standard, it can not be general and shared；Meanwhile resource and money
Lack the association between semanteme between source, the service such as intelligent retrieval between resource can not be carried out.This is but also learner faces
It is difficult to the problems such as selecting appropriate resources, resource content not to meet oneself requirement.Ontology (Ontology) is in message area in recent years
Cause everybody attention.Knowledge hierarchy and semantic conceptual model are effectively indicated as a kind of, and ontology has been widely used in
Among the fields such as Library processing, information management, web search, data integration, Semantic Web Services.But as ontology is ground
That studies carefully gos deep into, and the growth rate of ontology corpus scale is getting faster, and traditional method by artificial constructed ontology can not fit
The building of Large Scale Corpus is answered, therefore, the algorithm of semantic concept and Relation extraction based on computer technology constantly gushes
It is existing, to which the automation of ontological construction is done step-by-step.It can be said that the automation building of ontology is always the mesh that researcher pursues
Mark.
As the researcher of every subjects generates interest to ontology, ontology is gradually introduced into medicine, military science, geography
Multiple subjects such as section, agronomy, form multiple fields ontology.Up to the present, very with the method for ontological construction knowledge base
It is more, such as N-garm algorithm, correlation rule, similarity based on mathematical statistics etc., for another example it is based on philological Rule Extraction
Algorithm.But existing scheme do not use comentropy (Entropy) filter extract educational resource term and concept uncertainty, with
And information flow frame model concept and existing standard criterion are utilized, to analyze, determine the hierarchical relationship between concept.Due in
The complexity of literary knowledge all more or less requires manual intervention at present in the links of building ontology, to improve ontology
Accuracy it is also difficult to achieve by the full automation of machine processing completely.Although many researchers have proposed relevant calculating
The construction method that machine participates in, but due to the particularity of Chinese syntax, these methods be there is also some problems, be mentioned there are also very big
Between lift-off.
Summary of the invention
The present invention aiming at the problems existing in the prior art, provides a kind of educational resource model construction side based on ontology
Method determines hierarchical relationship between concept using the uncertainty of comentropy filtering concept and using hierarchical clustering algorithm, clearly
Indicate the main concept term of education sector, attribute and correlation, to attribute rule possessed by education sector activity into
The description of row formalization, improves the level of learning of user, the update of knowledge, development of technology etc..
To achieve the above object, technical solution provided by the invention is as follows:
A kind of educational resource model building method based on ontology characterized by comprising
Step A extracts educational resource term and concept, and file each in corpus is carried out analysis using statistical method and is mentioned
Take notional word；
Step B determines the hierarchical relationship between concept, calculates the similarity between notional word using hierarchical clustering algorithm, is allowed to
It is polymerized to one kind, forms the cluster with hierarchical relationship；
Step C determines the attribute and relation on attributes of concept, establishes the semantic tagger and language of the educational resource dispersed on network
Adopted relationship；
Step D is created educational resource example, is filled using example to ontology, establishes logic knowledge base.
Further, the step A is specifically included:
Step A1 obtains Miscellaneous Documents from network and in types of databases and establishes corpus；
Step A2, the extraction document out of corpus that established in above-mentioned steps A1 use statistical method extraction document
Concept keyword；
The concept keyword extracted in file is integrated into a set and saved by step A3.
Further, the statistical method in the step A2 includes:
Statistical string frequency method: the frequency occurred hereof by calculating each word, by frequency height to the low sequence of frequency
Statistics, establishes resource term；
TF.IDF (the anti-document frequency statistical method of keyword): to assess a words for a file set or one
The significance level of a copy of it file in corpus；
Comentropy statistical method: to the uncertainty of description information, the concept extracted in above-mentioned steps A is filtered
Keyword does not know high words.
Further, statistical string frequency method cooperation morphology filter is using can make statistics more perfect.
Further, the TF.IDF (the anti-document frequency statistical method of keyword) meets:
Further, the comentropy statistical method meets:
Further, the hierarchical clustering algorithm in the step B specifically includes:
Each the concept keyword extracted in above-mentioned steps A is individually arranged into a class by step B1；
Step B2 calculates the similarity between the word two-by-two that above-mentioned steps B1 is individually listed；
The big merging fusion of similarity calculated in above-mentioned steps B2 is polymerized to one kind by step B3；
Step B4 repeats step B3, until the similarity of all concept keywords is fused into two-by-two in file belonging to completing
It is a kind of；
Step B5 continues to execute step B1-B4 to the part of speech for having completed to merge two-by-two, until forming circulation, forms one
A cluster with hierarchical relationship.
Further, the method that similarity is calculated in the step B2 is calculated using Dice coefficient and cosine formula.
Further, the method for the cluster is that all words in two clusters are all carried out to the calculating of similarity, then
Its average value is calculated, the average value of the similarity is the distance of two clustering clusters.
Further, the step C is specifically included:
Step C1 analyzes each daughter element data item, extracts data attribute, provides the education dispersed on network
There is a unified semantic tagger in source；
Step C2 carries out abstract analysis to relation between knowledge points and obtains the object properties between knowledge point.
Further, the step D is specifically included:
Step D1 is filled ontology with example；
Step D2, definitions example establish logic knowledge base.
Compared with prior art, the present invention using comentropy filtering concept uncertainty and using hierarchical clustering algorithm come
It determines hierarchical relationship between concept, clearly indicates the main concept term of education sector, attribute and correlation, education is led
The description that is formalized of attribute rule possessed by the activity of domain improves the level of learning of user, the update of knowledge, technology
Development etc..
Detailed description of the invention
Fig. 1: for the overall main flow chart of steps of construction method of the present invention；
Fig. 2: for construction method step A specific flow chart of the present invention；
Fig. 3: for construction method step B specific flow chart of the present invention；
Fig. 4: for construction method step C specific flow chart of the present invention；
Fig. 5: for construction method step D specific flow chart of the present invention；
Fig. 6: to construct level illustraton of model in construction method step B of the present invention.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Implement below
Example is not intended to limit the scope of the invention for illustrating the present invention.
As shown in Figure 1, for the present invention is based on a kind of embodiment of the educational resource model building method of ontology, this method packets
It includes:
Step A extracts educational resource term and concept, and file each in corpus is carried out analysis using statistical method and is mentioned
Take notional word；
Step B determines the hierarchical relationship between concept, calculates the similarity between notional word using hierarchical clustering algorithm, is allowed to
It is polymerized to one kind, forms the cluster with hierarchical relationship；
Step C determines the attribute and relation on attributes of concept, establishes the semantic tagger and language of the educational resource dispersed on network
Adopted relationship；
Step D is created educational resource example, is filled using example to ontology, establishes logic knowledge base.
As shown in Fig. 2, the step A is specifically included:
Step A1 obtains Miscellaneous Documents from network and in types of databases and establishes corpus；
Step A2, the extraction document out of corpus that established in above-mentioned steps A1 use statistical method extraction document
Concept keyword；
The concept keyword extracted in file is integrated into a set and saved by step A3.
With continued reference to Fig. 2:, this patent Statistics-Based Method extracts educational resource term and concept, based on statistics
Method refers to first analyzing a large amount of input files through row to obtain statistical data abundant enough, meets statistics in extraction
A kind of method of the character string sequence of the certain conditions of data.It is considered as simplest statistical parameter that frequency, which is also known as gone here and there frequently,.It is candidate
Term can be formed from the parameter value of the character string of a certain range.It may be related to these statistics ginsengs during selecting word
Number, it is also possible to reference to the context of candidate terms, it is also possible to being selected as candidate terms to reference
Character string, to avoid repeating.This method mainly includes following technical essential:
(1) string frequency (Frequency): being referred to as a kind of common statistical method, is the frequency occurred by word and statistics
To extract term, implement direct, simple.Especially those fixed phrases are extracted by the frequency of occurrences, and effect is very
It is good.Meanwhile if cooperating some morphology filters, effect can be more preferable.
(2)TF.IDF(Term Frequency Inverted Document Frequency):
TF is the abbreviation of Term Frequency, and the frequency for being exactly the appearance of some keyword is exactly specifically dictionary
In the frequency that occurs in current article of some word.Wherein molecule is the frequency of occurrence of the word hereof, and denominator is then
The sum of the frequency of occurrence of all words hereof.IDF, full name in English: Inverse Document Frequency is that is, " anti-
Document frequency ".TF.IDF is to assess a words for the weight of a copy of it file in a file set or a corpus
Want degree.The importance of words, but simultaneously can be as it be in corpus with the directly proportional increase of number that it occurs hereof
The frequency of middle appearance is inversely proportional decline.Wherein n is the total number of files in corpus, dfi be the number of files comprising word (i.e.
Number of files) if the word is not in corpus, will lead to denominator is zero, therefore under normal circumstances used as denominator.
(3) comentropy (Entropy):
In the case where practical, the probability that every kind of possible situation occurs not is identical, so comentropy is used to describe
The uncertainty of information, if uncertain higher, comentropy is bigger, otherwise then lower.Pi indicates that vocabulary i occurs general
Rate.Determining situation, uncertain smaller, information content is fewer, i.e., calculated entropy is with regard to smaller.
As shown in figure 3, the step B is specifically included:
Each the concept keyword extracted in above-mentioned steps A is individually arranged into a class by step B1；
Step B2 calculates the similarity between the word two-by-two that above-mentioned steps B1 is individually listed；
The big merging fusion of similarity calculated in above-mentioned steps B2 is polymerized to one kind by step B3；
Step B4 repeats step B3, until the similarity of all concept keywords is fused into two-by-two in file belonging to completing
It is a kind of；
Step B5 continues to execute step B1-B4 to the part of speech for having completed to merge two-by-two, until forming circulation, forms one
A cluster with hierarchical relationship.
Referring to Fig. 6, this patent is taken based on the grade extracting method of text to determine the hierarchical relationship between concept, utilizes layer
Secondary clustering algorithm generates hierarchical relationship.Each word is individually arranged into a class first by this method, then calculate two-by-two word it
Between similarity, similarity it is big be polymerized to one kind, to push away in this, form a circulation, ultimately form one with hierarchical relationship
Dendrogram.There are two aspect is important in the algorithm, first is algorithmic issue about similarity, second be about
The method problem of cluster.For the algorithm of similarity, calculated using Dice coefficient, cosine formula etc..About the method for cluster,
We seek similarity of the average value of the distance between two words in two clustering clusters as two clustering clusters.Will two cluster in
All words all carry out the calculating of similarity, then calculate its average value, the average value of the similarity is two clustering clusters
Distance.
As shown in figure 4, the step C is specifically included:
Step C1 analyzes each daughter element data item, extracts data attribute, provides the education dispersed on network
There is a unified semantic tagger in source；
Step C2 carries out abstract analysis to relation between knowledge points and obtains the object properties between knowledge point.
With continued reference to Fig. 4, the attribute of ontology can be divided into data attribute (DataProperty) and object properties
(ObjectProperty) two parts.The domain of data attribute is the class of ontology, and codomain is data type, such as int type,
String type etc..Object properties are the attributes for indicating relationship between all individuals.
(1) data attribute.In order to make the educational resource dispersed on network have a unified semantic tagger, we are to each
A sub- element data item is analyzed, and data attribute is extracted.As shown in the table.
| Data attribute | Domain | Codomain | Explanation |
| Title | Resource | String | Title |
| Language | Resource | String | Language |
| Keywords | Resource | String | Keyword |
| Version | Resource | Float | Version |
| Contribute | Resource | String | Uploader |
| Date | Resource | Date | Uplink time |
| Size | Resource | Float | Size |
| Location | Resource | String | Resource URL |
| .... | .... | .... | .... |
(2) object properties.The main object attribute of the educational resource domain body constructed herein is the object of knowledge point class
Attribute.Due to having semantic relation abundant between course set point, so as to establish ontology category by these semantic relations
Property, and ontology inference and inquiry are carried out using these attributes, the basis of rope is received as educational resource semanteme.In order to determine knowledge point
The relation on attributes of class carries out abstract analysis to relation between knowledge points and obtains object properties shown in following table according to course features.
| Object properties | Domain | Codomain | Axiom |
| Contain | Concept | Concept | Include |
| Belong to | Concept | Concept | Belong to |
| Is neighbor of | Concept | Concept | It is adjacent |
| Is parallel of | Concept | Concept | In parallel |
| Isprecursor of | Concept | Concept | Premise |
| Isreference of | Concept | Concept | Reference |
| Has concept | Resource | Concept | Concept |
| Has resource | Concept | Resource | Resource |
| Hasdiscipline | Concept | Discipline | Description |
As shown in figure 5, the step D is specifically included:
Step D1 is filled ontology with example；
Step D2, definitions example establish logic knowledge base.
With continued reference to Fig. 5, example is the specific descriptions of class, and class is the abstract representation of example.Example has the institute of affiliated class
There is feature, creating example to be exactly is class creation characteristic item.After being established because of such and attribute, ontology is filled with example.
The class and attribute for defining ontology are equivalent to the process for establishing TBox in description logic knowledge base, and definitions example, which is equivalent to, establishes logic
The process of ABox in knowledge base.Example is established in protege.
The present invention provides a kind of educational resource model building method based on ontology, has the advantage that use of the present invention
Comentropy is filtered the uncertainty of concept and is determined hierarchical relationship between concept using hierarchical clustering algorithm, clearly indicates education
The main concept term in field, attribute and correlation, formalize attribute rule possessed by education sector activity
Description, improve the level of learning of user, the update of knowledge, development of technology etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to restrict the invention, it is all in spirit of the invention and
In principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (11)
1. a kind of educational resource model building method based on ontology characterized by comprising
Step A extracts educational resource term and concept, and file each in corpus is carried out analysis using statistical method and is extracted generally
Read word；
Step B determines the hierarchical relationship between concept, calculates the similarity between notional word using hierarchical clustering algorithm, is allowed to be polymerized to
One kind forms the cluster with hierarchical relationship；
Step C determines the attribute and relation on attributes of concept, and the semantic tagger and semanteme for establishing the educational resource dispersed on network close
System；
Step D is created educational resource example, is filled using example to ontology, establishes logic knowledge base.
2. the educational resource model building method according to claim 1 based on ontology, which is characterized in that the step A
It specifically includes:
Step A1 obtains Miscellaneous Documents from network and in types of databases and establishes corpus；
Step A2, the extraction document out of corpus that established in above-mentioned steps A1 use the concept of statistical method extraction document
Keyword；
The concept keyword extracted in file is integrated into a set and saved by step A3.
3. the educational resource model building method according to claim 2 based on ontology, which is characterized in that the step A2
In statistical method include:
Statistical string frequency method: the frequency occurred hereof by calculating each word, by frequency height to the low sequencing statistical of frequency,
Establish resource term；
TF.IDF (the anti-document frequency statistical method of keyword): to assess a words for a file set or a corpus
The significance level of a copy of it file in library；
Comentropy statistical method: to the uncertainty of description information, it is crucial to filter the concept extracted in above-mentioned steps A
Word does not know high words.
4. the educational resource model building method according to claim 3 based on ontology, which is characterized in that the string frequency is united
Meter method cooperate morphology filter using can make statistics it is more perfect.
5. the educational resource model building method according to claim 3 based on ontology, which is characterized in that the TF.IDF
(the anti-document frequency statistical method of keyword) meets:
6. the educational resource model building method according to claim 3 based on ontology, which is characterized in that the comentropy
Statistical method meets:
7. the educational resource model building method according to claim 1 based on ontology, which is characterized in that the step B
In hierarchical clustering algorithm specifically include:
Each the concept keyword extracted in above-mentioned steps A is individually arranged into a class by step B1；
Step B2 calculates the similarity between the word two-by-two that above-mentioned steps B1 is individually listed；
The big merging fusion of similarity calculated in above-mentioned steps B2 is polymerized to one kind by step B3；
Step B4 repeats step B3, until the similarity of all concept keywords is fused into one kind two-by-two in file belonging to completing；
Step B5 continues to execute step B1-B4 to the part of speech for having completed to merge two-by-two, until forming circulation, forms a tool
There is the cluster of hierarchical relationship.
8. the educational resource model building method according to claim 6 based on ontology, which is characterized in that the step B2
The middle method for calculating similarity is calculated using Dice coefficient and cosine formula.
9. the educational resource model building method according to claim 6 based on ontology, which is characterized in that the cluster
Method is that all words in two clusters are all carried out to the calculating of similarity, then calculates its average value, which is averaged
Value is the distance of two clustering clusters.
10. the educational resource model building method according to claim 1 based on ontology, which is characterized in that the step C
It specifically includes:
Step C1 analyzes each daughter element data item, extracts data attribute, there is the educational resource dispersed on network
One unified semantic tagger；
Step C2 carries out abstract analysis to relation between knowledge points and obtains the object properties between knowledge point.
11. the educational resource model building method according to claim 1 based on ontology, which is characterized in that the step D
It specifically includes:
Step D1 is filled ontology with example；
Step D2, definitions example establish logic knowledge base.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810877818.XA CN109087223A (en) | 2018-08-03 | 2018-08-03 | A kind of educational resource model building method based on ontology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810877818.XA CN109087223A (en) | 2018-08-03 | 2018-08-03 | A kind of educational resource model building method based on ontology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109087223A true CN109087223A (en) | 2018-12-25 |
Family
ID=64833522
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810877818.XA Pending CN109087223A (en) | 2018-08-03 | 2018-08-03 | A kind of educational resource model building method based on ontology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109087223A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109947953A (en) * | 2019-03-27 | 2019-06-28 | 武汉市软迅科技有限公司 | Building method, system and the equipment of English domain knowledge ontology |
| CN111104478A (en) * | 2019-09-05 | 2020-05-05 | 李轶 | Domain concept semantic drift exploration method |
| CN112860940A (en) * | 2021-02-05 | 2021-05-28 | 陕西师范大学 | Music resource retrieval method based on sequential concept space on description logic knowledge base |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103761264A (en) * | 2013-12-31 | 2014-04-30 | 浙江大学 | Concept hierarchy establishing method based on product review document set |
| CN104484328A (en) * | 2014-10-23 | 2015-04-01 | 安徽教育网络出版有限公司 | Educational resource semantic annotation method |
| CN106095753A (en) * | 2016-06-07 | 2016-11-09 | 大连理工大学 | A kind of financial field based on comentropy and term credibility term recognition methods |
| CN107818140A (en) * | 2017-10-07 | 2018-03-20 | 江苏睿泰数字产业园有限公司 | A kind of digital publication semantic tagger optimization method |
| CN108170840A (en) * | 2018-01-15 | 2018-06-15 | 浙江大学 | A kind of domain classification relationship Auto-learning Method of text-oriented |
-
2018
- 2018-08-03 CN CN201810877818.XA patent/CN109087223A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103761264A (en) * | 2013-12-31 | 2014-04-30 | 浙江大学 | Concept hierarchy establishing method based on product review document set |
| CN104484328A (en) * | 2014-10-23 | 2015-04-01 | 安徽教育网络出版有限公司 | Educational resource semantic annotation method |
| CN106095753A (en) * | 2016-06-07 | 2016-11-09 | 大连理工大学 | A kind of financial field based on comentropy and term credibility term recognition methods |
| CN107818140A (en) * | 2017-10-07 | 2018-03-20 | 江苏睿泰数字产业园有限公司 | A kind of digital publication semantic tagger optimization method |
| CN108170840A (en) * | 2018-01-15 | 2018-06-15 | 浙江大学 | A kind of domain classification relationship Auto-learning Method of text-oriented |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109947953A (en) * | 2019-03-27 | 2019-06-28 | 武汉市软迅科技有限公司 | Building method, system and the equipment of English domain knowledge ontology |
| CN109947953B (en) * | 2019-03-27 | 2022-05-17 | 武汉市软迅科技有限公司 | Construction method, system and equipment of knowledge ontology in English field |
| CN111104478A (en) * | 2019-09-05 | 2020-05-05 | 李轶 | Domain concept semantic drift exploration method |
| CN112860940A (en) * | 2021-02-05 | 2021-05-28 | 陕西师范大学 | Music resource retrieval method based on sequential concept space on description logic knowledge base |
| CN112860940B (en) * | 2021-02-05 | 2022-11-25 | 陕西师范大学 | Music resource retrieval method based on sequential concept space on description logic knowledge base |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108052593B (en) | Topic keyword extraction method based on topic word vector and network structure | |
| CN109189942B (en) | Construction method and device of patent data knowledge graph | |
| CN106919689B (en) | Professional domain knowledge mapping dynamic fixing method based on definitions blocks of knowledge | |
| CN106372061A (en) | Short text similarity calculation method based on semantics | |
| CN104951548A (en) | Method and system for calculating negative public opinion index | |
| Sarkhel et al. | Visual segmentation for information extraction from heterogeneous visually rich documents | |
| CN102117281A (en) | Method for constructing domain ontology | |
| CN109086355B (en) | Hot-spot association relation analysis method and system based on news subject term | |
| CN112925901B (en) | Evaluation resource recommendation method for assisting online questionnaire evaluation and application thereof | |
| CN109087223A (en) | A kind of educational resource model building method based on ontology | |
| CN109522396A (en) | A kind of method of knowledge processing and system towards science and techniques of defence field | |
| CN114997288A (en) | Design resource association method | |
| CN114168739A (en) | Hidden danger knowledge reasoning method for enhancing association rule | |
| CN107544958B (en) | Term extraction method and device | |
| CN101968797A (en) | Inter-lens context-based video concept labeling method | |
| CN115146062A (en) | Intelligent event analysis method and system fusing expert recommendation and text clustering | |
| Hu et al. | EGC: A novel event-oriented graph clustering framework for social media text | |
| CN113610626A (en) | Bank credit risk identification knowledge graph construction method and device, computer equipment and computer readable storage medium | |
| CN111339258B (en) | University computer basic exercise recommendation method based on knowledge graph | |
| CN109871429B (en) | Short text retrieval method integrating Wikipedia classification and explicit semantic features | |
| Qiu et al. | CLDA: An effective topic model for mining user interest preference under big data background | |
| Li et al. | The research on text clustering based on LDA joint model | |
| CN112463974A (en) | Method and device for establishing knowledge graph | |
| Riga et al. | Atmospheric environment and quality of life information extraction from twitter with the use of self-organizing maps | |
| Zhang et al. | AVT-NBL: An algorithm for learning compact and accurate naive bayes classifiers from attribute value taxonomies and data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181225 |