CN111061884B - Method for constructing K12 education knowledge graph based on deep technology - Google Patents
Method for constructing K12 education knowledge graph based on deep technology Download PDFInfo
- Publication number
- CN111061884B CN111061884B CN201911113450.0A CN201911113450A CN111061884B CN 111061884 B CN111061884 B CN 111061884B CN 201911113450 A CN201911113450 A CN 201911113450A CN 111061884 B CN111061884 B CN 111061884B
- Authority
- CN
- China
- Prior art keywords
- knowledge
- knowledge points
- data
- correlation
- deep
- 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
- 238000005516 engineering process Methods 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 5
- 238000013135 deep learning Methods 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 12
- 239000000284 extract Substances 0.000 claims description 8
- 230000009193 crawling Effects 0.000 claims description 5
- 238000005065 mining Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 230000002688 persistence Effects 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 239000008186 active pharmaceutical agent Substances 0.000 description 2
- 239000000969 carrier Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012800 visualization 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F16/951—Indexing; Web crawling techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method for constructing a K12 education knowledge graph based on deep love technology, which comprises the following steps of S1, inputting articles into a deep love deep learning frame; s2, excavating knowledge points, and storing the knowledge points obtained by deep decomposition into a csv file; s3, extracting the relation and the characteristics, and extracting the characteristics and the relation from the csv file; s4, calculating knowledge correlation, and then calculating correlation among knowledge points by using a method for calculating the correlation of knowledge points of different levels and the correlation of knowledge points of the same level; s5, drawing a knowledge graph, inputting the correlation between knowledge points into a NEO4J tool, and constructing the knowledge graph; the invention can improve the efficiency of obtaining the structured data by using the deep love technology; the quantized data are used for calculating the relation between knowledge points, so that the accuracy of the knowledge graph can be improved; and extracting knowledge points in the articles by comparing the existing knowledge points in the database.
Description
Technical Field
The invention relates to the technical field of computer science, in particular to a method for constructing a K12 education knowledge graph based on deep technology.
Background
Along with the development of computers, people are more and more used in computers, research on the computers is more and more advanced, the computers are applied to screening of knowledge points, namely, knowledge maps are drawn through the computers, the knowledge maps are called knowledge domain visualization or knowledge domain mapping maps in book information, a series of different graphs showing the knowledge development process and structural relationship are used for describing knowledge resources and carriers thereof, and knowledge and interrelationships among the knowledge resources, the carriers are mined, analyzed, constructed, drawn and displayed. Deep is a technique for extracting relationships between textual knowledge.
The prior art is also using built-in models and has its own APIs that have completed product recommendations, work lists and searches of personal details and work in the educational domain. More research efforts are underway in the educational field, but they do not provide good accuracy. Therefore, we propose to use deep technique to extract the relationship between knowledge points, and calculate the correlation between them through a large amount of article data to improve the accuracy.
Disclosure of Invention
The invention aims to provide a method for constructing a K12 education knowledge graph based on a deep technology, which has the advantages that the deep technology improves the efficiency of acquiring structured data; calculating the relation between knowledge points by using the quantized data, and improving the accuracy of the knowledge graph; the knowledge points are extracted by comparing the existing knowledge points in the database with the knowledge points in the articles, and the like, so that the problems in the background technology are solved.
In order to achieve the above purpose, the present invention provides the following technical solutions: a method for constructing a K12 education knowledge graph based on deep technology comprises the following steps:
s1, inputting articles, namely firstly capturing the articles from a website by utilizing a scrapy crawler technology, then extracting data from HTML and XML files through beaufullsource, and inputting the articles into a deep learning framework;
s2, mining knowledge points, splitting an input article into sentences by deep love through executing an NLP function, then performing word segmentation, part-of-speech tagging and grammar dependence, comparing the knowledge points with the existing knowledge points in a database, outputting the same knowledge points, and storing the knowledge points obtained by decomposition into a csv file;
s3, extracting the relation and the characteristics, extracting the characteristics and the relation from the csv file, and finally obtaining knowledge points meeting the requirements through a series of screening and integrating operations;
s4, calculating knowledge correlation, and then calculating the correlation among the obtained knowledge points by calculating the correlation of the knowledge points of different levels and the correlation of the knowledge points of the same level;
and S5, drawing a knowledge graph, and finally inputting the correlation between the knowledge points into a NEO4J tool to construct the knowledge graph.
The beaufullsource in the step S1 is a Python library for extracting data from HTML and XML files, and can acquire a single URL and cut specified data; scrapy is a free open-source Web crawling framework written in Python.
Deep love in step S2 extracts valuable data from dark data in the text document; deep love creates structured data SQL tables from unstructured information and integrates these data with existing structured databases, extracting useful knowledge points.
In the step S2, knowledge points are extracted by using deep technology and used as input, all unnecessary data are deleted according to the separation result, the data are converted into the form of key value pairs, and then the key value pairs are converted into the required specification, namely, different keys contain the same value, so that the keys containing the same value are combined together, and a single character and a special symbol are deleted from the obtained result.
All words and characters of the keyword, i.e. any word except the plural form in the selected keyword is the same as the last character at the end, the word will be moved to a new list, the new list is compared with the markup file (sentence), and if a single word of the new list is located in the markup file (sentence), the sentence is considered; repeating until all sentences are completed, combining all sentences into a list, and calculating the occurrence times of each word in the sentence list; the new list is again compared to the sentence list and the words common in the new list and the sentence list are separated by creating a new list.
And in the newly obtained list, a word2vec technology is adopted to search the correlation among words, and a neo4j technology is adopted to display a knowledge graph.
The knowledge data is converted into a knowledge matrix, and the data key values are integrated into a relation matrix between the knowledge.
The step S4 is that the correlation calculation of knowledge points at different levels is carried out: assuming that the four knowledge points a, b, c and d are all under the same knowledge point N, the number of occurrences of the knowledge point N is the number of articles containing abcd four knowledge points, and the relationship between a and N is the number of occurrences of a/the number of occurrences of N; co-level knowledge point correlation calculation: the calculation formula of the two knowledge points a and b is log2 (p (ab)/(p (a)) and p (b)), wherein p (ab) is the number of simultaneous occurrence of ab, p (a) is the number of occurrence of a, and p (b) is the number of occurrence of b.
Neo4j in step S5 is a high-performance, NOSQL graph database capable of storing structured data on the network instead of in tables; being an embedded, disk-based Java persistence engine with complete transactional properties, neo4j can also be viewed as a high performance graph engine.
Compared with the prior art, the invention has the beneficial effects that:
the invention uses deep love to convert unstructured data into a basic frame of structured data, extracts valuable data from dark data, extracts knowledge points from deep love technology, separates results, deletes all unnecessary data, converts data into a key value pair form, combines keys with the same value, deletes single characters and special symbols in the results, and further enables the deep love technology to improve the efficiency of obtaining structured data; the quantized data is used for calculating the relation between knowledge points, namely, the correlation calculation of knowledge points of different levels and the correlation calculation method of knowledge points of the same level can improve the accuracy of the knowledge graph; and extracting the knowledge points in a mode of comparing the existing knowledge points in the database with the knowledge points in the articles.
Drawings
Fig. 1 is a schematic block diagram of a method flow of the present invention.
Detailed Description
The technical solutions in the examples of the present invention will be clearly and completely described below with reference to the accompanying drawings in the examples of the present invention. The described examples are only some, but not all, examples of the invention. All other examples, based on the examples in this invention, which are obtained by others skilled in the art without making inventive changes, are within the scope of the invention.
Referring to fig. 1, the present invention provides a technical solution: a method for constructing a K12 education knowledge graph based on deep technology comprises the following steps:
s1, inputting articles, namely firstly capturing the articles from a website by utilizing a scrapy crawler technology, then extracting data from HTML and XML files through beaufullsource, and inputting the articles into a deep learning framework;
s2, mining knowledge points, splitting an input article into sentences by deep love through executing an NLP function, then performing word segmentation, part-of-speech tagging and grammar dependence, comparing the knowledge points with the existing knowledge points in a database, outputting the same knowledge points, and storing the knowledge points obtained by decomposition into a csv file;
s3, extracting the relation and the characteristics, extracting the characteristics and the relation from the csv file, and finally obtaining knowledge points meeting the requirements through a series of screening and integrating operations;
s4, calculating knowledge correlation, and then calculating the correlation among the obtained knowledge points by calculating the correlation of the knowledge points of different levels and the correlation of the knowledge points of the same level;
and S5, drawing a knowledge graph, and finally inputting the correlation between the knowledge points into a NEO4J tool to construct the knowledge graph.
The beaufullsource in the step S1 is a Python library for extracting data from HTML and XML files, and can acquire a single URL and cut specified data; scrapy is a free-open-source Web crawling framework written in Python, where beaufulso can acquire individual URLs and cut specified data, and Scrapy is a free-open-source Web crawling framework written in Python. It was originally designed for Web crawling and could also be used to extract data using APIs or as a general purpose Web crawler that can quickly intercept passage of articles through BeautiffulSoup and Scrapy into deep love.
Deep love in step S2 extracts valuable data from dark data in the text document; deep love creates structured data SQL tables from unstructured information and integrates the data with existing structured databases to extract useful knowledge points where dark data is largely hidden in text, tables, graphics and images, lacking structure; the structured data is created by deep love to realize exposure to dark data, and knowledge points can be rapidly extracted and compared with the existing knowledge point database.
The knowledge points are extracted in the step S2 by using deep technique and used as input, all unnecessary data are deleted according to the separation result, the data are converted into the form of key value pairs, and then converted into the required specification, namely, different keys contain the same value, so that we combine the keys containing the same value together, delete single characters and special symbols from the obtained result, compare all words and characters of the selected keyword, and if any word except the plural form in the selected keyword is the same as the last character at the end, the word will be moved to the new list. The new list is compared to the markup document or sentence and if a single word of the new list is located in the markup document or sentence, the sentence is considered. This process is repeated until all sentences are completed, and we merge all sentences into a list and count the number of occurrences of each word in the list of sentences. We compare the new list with the sentence list again, separating the words common in the new list from the sentence list by creating a new list. In the newly obtained list, word2vec technology is adopted to search the relativity between words, and neo4j technology is adopted to display the knowledge graph.
The knowledge data are converted into a knowledge matrix, and the data key values are integrated into a relation matrix between knowledge, so that the knowledge matrix and the relation matrix can be established to effectively and rapidly extract the relevant points of the relation and the characteristics, and the knowledge map is quite convenient to construct.
The step S4 is that the correlation calculation of knowledge points at different levels is carried out: assuming that the four knowledge points a, b, c and d are all under the same knowledge point N, the number of occurrences of the knowledge point N is the number of articles containing abcd four knowledge points, and the relationship between a and N is the number of occurrences of a/the number of occurrences of N; co-level knowledge point correlation calculation: the calculation formulas of the two knowledge points a and b are log2 (p (ab)/(p (a)) and p (b)), wherein p (ab) is the number of times of ab occurrence, p (a) is the number of times of a occurrence, and p (b) is the number of times of b occurrence, the correlation calculation of the knowledge points at different levels can calculate the relation between the knowledge points at different levels, the correlation calculation of the knowledge points at the same level can calculate the relation between the knowledge points at the same level, and the drawing accuracy of the knowledge map is improved.
Neo4j in step S5 is a high-performance, NOSQL graph database capable of storing structured data on the network instead of in tables; the system is an embedded Java persistence engine based on a disk and having complete transaction characteristics, neo4j can also be regarded as a high-performance graph engine, the extracted knowledge points are rapidly mapped through Neo4j, and the Neo4j has powerful functions and high operation speed and can effectively and accurately map the knowledge points.
The working steps are as follows:
firstly, inputting articles, namely firstly grabbing the articles from a website by utilizing a scrapy crawler technology, then extracting data from HTML and XML files through beatifullsource, and inputting the articles into a deep learning framework;
secondly, mining knowledge points, namely splitting an input article into sentences by executing an NLP function, then performing word segmentation, part-of-speech tagging and grammar dependence, creating a structured data SQL table by the deep love, integrating the unstructured information with the existing structured database, extracting useful knowledge points, comparing the knowledge points with the existing knowledge points in the database, outputting the same knowledge points, and storing the knowledge points obtained by decomposition into a csv file;
thirdly, extracting the characteristics and the relations from the csv file, converting knowledge data into a knowledge matrix, and integrating data key values into a relation matrix between knowledge, wherein the establishment of the knowledge matrix and the relation matrix can effectively and rapidly extract the relevant points of the relation and the characteristics, so that the establishment of a knowledge graph is quite convenient, and finally knowledge points meeting the requirements are obtained;
step four, calculating knowledge correlation, and then calculating the correlation among the obtained knowledge points by calculating the correlation of the knowledge points of different levels and the correlation of the knowledge points of the same level;
fifthly, drawing a knowledge graph, and finally inputting the correlation between the knowledge points into a NEO4J tool to construct the knowledge graph.
Although examples of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the spirit and scope of the invention as defined by the appended claims and their equivalents.
Claims (5)
1. A method for constructing a K12 education knowledge graph based on deep technology is characterized by comprising the following steps: the method comprises the following steps:
s1, inputting articles, namely firstly capturing the articles from a website by utilizing a scrapy crawler technology, then extracting data from HTML and XML files through beaufullsource, and inputting the articles into a deep learning framework;
s2, mining knowledge points, splitting an input article into sentences by deep love through executing an NLP function, then performing word segmentation, part-of-speech tagging and grammar dependence, comparing the knowledge points with the existing knowledge points in a database, outputting the same knowledge points, and storing the knowledge points obtained by decomposition into a csv file;
s3, extracting the relation and the characteristics, extracting the characteristics and the relation from the csv file, and finally obtaining knowledge points meeting the requirements through screening and integrating operation;
s4, calculating knowledge correlation, and then calculating the correlation among the obtained knowledge points by calculating the correlation of the knowledge points of different levels and the correlation of the knowledge points of the same level;
s5, drawing a knowledge graph, and finally inputting the correlation between knowledge points into a NEO4J tool to construct the knowledge graph;
the beaufullsource in the step S1 is a Python library for extracting data from HTML and XML files, and can acquire a single URL and cut specified data; scrapy is a free open-source Web crawling framework written in Python;
deep love in step S2 extracts valuable data from dark data in the text document; deep love creates structured data SQL tables with unstructured information, integrates the data with the existing structured database, and extracts useful knowledge points;
in the step S2, knowledge points are extracted by using deep technology and used as input, all unnecessary data are deleted according to the separation result, the data are converted into a form of key value pairs, then the key value pairs are converted into required specifications, i.e. different keys contain the same value, the keys containing the same value are combined together, and a single character and a special symbol are deleted from the obtained result;
all words and characters of the knowledge point, namely any word except the complex form in the selected keyword is the same as the last character at the end, the word is moved to a new list, the new list is compared with the markup file, and if a single word of the new list is positioned in the markup file, the sentence is considered; repeating until all sentences are completed, combining all sentences into a list, and calculating the occurrence times of each word in the sentence list; the new list is again compared to the sentence list and the words common in the new list and the sentence list are separated by creating a new list.
2. The method for constructing the K12 education knowledge graph based on deep technology according to claim 1, wherein the method comprises the following steps: and in the newly obtained list, a word2vec technology is adopted to search the correlation among words, and a NEO4J technology is used to display a knowledge graph.
3. The method for constructing the K12 education knowledge graph based on deep technology according to claim 1, wherein the method comprises the following steps: the knowledge data is converted into a knowledge matrix, and the data key values are integrated into a relation matrix between the knowledge.
4. The method for constructing the K12 education knowledge graph based on deep technology according to claim 1, wherein the method comprises the following steps: the step S4 is that the correlation calculation of knowledge points at different levels is carried out: when the four knowledge points a, b, c and d are all under the same knowledge point N, the number of occurrences of the knowledge point N is the number of articles containing abcd four knowledge points, and the relation between a and N is the number of occurrences of a/the number of occurrences of N; co-level knowledge point correlation calculation: the calculation formula of the two knowledge points a and b is log2 (p (ab)/(p (a)) and p (b)), wherein p (ab) is the number of simultaneous occurrence of ab, p (a) is the number of occurrence of a, and p (b) is the number of occurrence of b.
5. The method for constructing the K12 education knowledge graph based on deep technology according to claim 1, wherein the method comprises the following steps: the NEO4J in step S5 is a high-performance, NOSQL graph database capable of storing structured data on the network instead of in tables; is an embedded, disk-based Java persistence engine with complete transactional properties.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911113450.0A CN111061884B (en) | 2019-11-14 | 2019-11-14 | Method for constructing K12 education knowledge graph based on deep technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911113450.0A CN111061884B (en) | 2019-11-14 | 2019-11-14 | Method for constructing K12 education knowledge graph based on deep technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111061884A CN111061884A (en) | 2020-04-24 |
| CN111061884B true CN111061884B (en) | 2023-11-21 |
Family
ID=70298606
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911113450.0A Active CN111061884B (en) | 2019-11-14 | 2019-11-14 | Method for constructing K12 education knowledge graph based on deep technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111061884B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111984799A (en) * | 2020-09-27 | 2020-11-24 | 上海松鼠课堂人工智能科技有限公司 | Method and system for generating knowledge graph of classical Chinese |
| CN114428909A (en) * | 2022-01-27 | 2022-05-03 | 英大传媒投资集团有限公司 | Searching method, device, equipment and storage medium based on industry knowledge graph |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103729402A (en) * | 2013-11-22 | 2014-04-16 | 浙江大学 | Method for establishing mapping knowledge domain based on book catalogue |
| CN106355627A (en) * | 2015-07-16 | 2017-01-25 | 中国石油化工股份有限公司 | Method and system used for generating knowledge graphs |
| CN107633005A (en) * | 2017-08-09 | 2018-01-26 | 广州思涵信息科技有限公司 | A kind of knowledge mapping structure, comparison system and method based on class teaching content |
| CN107862075A (en) * | 2017-11-29 | 2018-03-30 | 浪潮软件股份有限公司 | A kind of knowledge mapping construction method and device based on health care big data |
| CN109902187A (en) * | 2019-03-21 | 2019-06-18 | 广东小天才科技有限公司 | Method and device for constructing characteristic knowledge graph and terminal equipment |
| CN110110096A (en) * | 2019-05-13 | 2019-08-09 | 上海乂学教育科技有限公司 | Artificial intelligence K12 knowledge mapping makes management system and implementation method |
| CN110321549A (en) * | 2019-04-09 | 2019-10-11 | 广州数说故事信息科技有限公司 | Based on the new concept method for digging for serializing study, relation excavation, Time-Series analysis |
| CN110442730A (en) * | 2019-07-18 | 2019-11-12 | 北京市天元网络技术股份有限公司 | A kind of knowledge mapping construction method based on deepdive |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101876981B (en) * | 2009-04-29 | 2015-09-23 | 阿里巴巴集团控股有限公司 | A kind of method and device building knowledge base |
-
2019
- 2019-11-14 CN CN201911113450.0A patent/CN111061884B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103729402A (en) * | 2013-11-22 | 2014-04-16 | 浙江大学 | Method for establishing mapping knowledge domain based on book catalogue |
| CN106355627A (en) * | 2015-07-16 | 2017-01-25 | 中国石油化工股份有限公司 | Method and system used for generating knowledge graphs |
| CN107633005A (en) * | 2017-08-09 | 2018-01-26 | 广州思涵信息科技有限公司 | A kind of knowledge mapping structure, comparison system and method based on class teaching content |
| CN107862075A (en) * | 2017-11-29 | 2018-03-30 | 浪潮软件股份有限公司 | A kind of knowledge mapping construction method and device based on health care big data |
| CN109902187A (en) * | 2019-03-21 | 2019-06-18 | 广东小天才科技有限公司 | Method and device for constructing characteristic knowledge graph and terminal equipment |
| CN110321549A (en) * | 2019-04-09 | 2019-10-11 | 广州数说故事信息科技有限公司 | Based on the new concept method for digging for serializing study, relation excavation, Time-Series analysis |
| CN110110096A (en) * | 2019-05-13 | 2019-08-09 | 上海乂学教育科技有限公司 | Artificial intelligence K12 knowledge mapping makes management system and implementation method |
| CN110442730A (en) * | 2019-07-18 | 2019-11-12 | 北京市天元网络技术股份有限公司 | A kind of knowledge mapping construction method based on deepdive |
Non-Patent Citations (1)
| Title |
|---|
| 薛昕惟等.专业课程群知识图谱可视化平台的设计与现实.《实验室研究与探索》.2018,第37卷(第7期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111061884A (en) | 2020-04-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107797991B (en) | Dependency syntax tree-based knowledge graph expansion method and system | |
| CN106649260B (en) | Product characteristic structure tree construction method based on comment text mining | |
| KR101465769B1 (en) | Dictionary word and phrase determination | |
| Pal et al. | An approach to automatic text summarization using WordNet | |
| US20150178273A1 (en) | Unsupervised Relation Detection Model Training | |
| CN112948547B (en) | Logging knowledge graph construction query method, device, equipment and storage medium | |
| KR101646754B1 (en) | Apparatus and Method of Mobile Semantic Search | |
| CN103092956B (en) | The method and system that in social network-i i-platform, topic keyword self-adaptation expands | |
| Al-Zoghby et al. | Arabic semantic web applications–a survey | |
| CN103106189B (en) | A kind of method and apparatus excavating synonym attribute word | |
| CN105426360A (en) | Keyword extracting method and device | |
| CN114328951B (en) | Knowledge graph construction method integrating information acquisition and triplet extraction | |
| CN108073576A (en) | Intelligent search method, searcher and search engine system | |
| CN110795932A (en) | Text information extraction method of geological report based on geological ontology | |
| CN111061884B (en) | Method for constructing K12 education knowledge graph based on deep technology | |
| Staar et al. | Corpus processing service: a knowledge graph platform to perform deep data exploration on corpora | |
| CN107784019A (en) | Word treatment method and system are searched in a kind of searching service | |
| CN111008285B (en) | Author disambiguation method based on thesis key attribute network | |
| CN105426490A (en) | Tree structure based indexing method | |
| CN103678355A (en) | Text mining method and text mining device | |
| CN106168947A (en) | A kind of related entities method for digging and system | |
| CN107622125B (en) | Information crawling method and device and electronic equipment | |
| CN108614821B (en) | Geological data interconnection and mutual-checking system | |
| CN103870472B (en) | Compound word mining method and device | |
| Thottempudi | A visual narrative of ramayana using extractive summarization topic modeling and named entity recognition |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: No.55, Volvo Road, economic and Technological Development Zone, Linyi City, Shandong Province Applicant after: LINYI INFOTOP NETWORK Co.,Ltd. Address before: 276000 No.66, Volvo Road, Jinan Economic and Technological Development Zone, Shandong Province Applicant before: LINYI INFOTOP NETWORK Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |