CN116304110A - Working method for constructing knowledge graph by using English vocabulary data - Google Patents
Working method for constructing knowledge graph by using English vocabulary data Download PDFInfo
- Publication number
- CN116304110A CN116304110A CN202310336495.4A CN202310336495A CN116304110A CN 116304110 A CN116304110 A CN 116304110A CN 202310336495 A CN202310336495 A CN 202310336495A CN 116304110 A CN116304110 A CN 116304110A
- Authority
- CN
- China
- Prior art keywords
- english
- keyword
- keywords
- literature
- similarity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000008569 process Effects 0.000 claims abstract description 18
- 238000004364 calculation method Methods 0.000 claims abstract description 7
- 238000013507 mapping Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 15
- 238000013135 deep learning Methods 0.000 claims description 14
- 238000010801 machine learning Methods 0.000 claims description 4
- 230000007935 neutral effect Effects 0.000 claims description 4
- 230000009977 dual effect Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 description 14
- 238000010276 construction Methods 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 238000000611 regression analysis Methods 0.000 description 2
- 230000002787 reinforcement Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000013526 transfer learning Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
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
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/268—Morphological analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a working method for constructing a knowledge graph by using English vocabulary data, which comprises the following steps: s1, executing a collection process of English documents according to query keywords, extracting a plurality of English vocabulary keywords, performing data convergence to form a keyword English document data set, and performing similarity judgment; s2, performing a grouping process on the data set after similarity judgment, performing derivative classification operation on English documents containing keywords with different attributes, and performing relation mapping according to derivative classification content; and S3, carrying out threshold judgment calculation on the derived and segmented keyword English literature, and thus constructing attribute information corresponding to the corresponding keyword English literature.
Description
Technical Field
The invention relates to the field of big data analysis, in particular to a working method for constructing a knowledge graph by using English vocabulary data.
Background
In the technological research and development process, a large amount of English documents in related fields are required to be acquired, the construction process of knowledge content is performed, the English articles are acquired, indexes can be collected for corresponding English key words or core words, and index summarized English word contact patterns are provided, the prior art uses BPE word segmentation processing, only English documents in the corresponding technological fields are subjected to simple attribute description, the deep knowledge pattern construction process cannot be performed, the knowledge structure drawing work of the fine mass English data cannot be completed, and therefore the technical problem of the corresponding technical problem is needed to be solved by a person in the art.
Disclosure of Invention
The invention aims at least solving the technical problems in the prior art, and particularly creatively provides a working method for constructing a knowledge graph by using English vocabulary data.
In order to achieve the above object of the present invention, the present invention provides a working method for constructing a knowledge graph using english vocabulary data, comprising the steps of:
s1, executing a collection process of English documents according to query keywords, extracting a plurality of English vocabulary keywords, performing data convergence to form a keyword English document data set, and performing similarity judgment;
s2, performing a grouping process on the data set after similarity judgment, performing derivative classification operation on English documents containing keywords with different attributes, and performing relation mapping according to derivative classification content;
and S3, carrying out threshold judgment calculation on the derived and segmented keyword English literature, and thus constructing attribute information corresponding to the corresponding keyword English literature.
Preferably, in the above technical solution, the S1 includes:
s1-1, setting corresponding query keywords according to user use requirements, establishing a query keyword log, acquiring English documents of the keywords, and initializing English documents generated by the query keywords;
s1-2, constructing a collection model R of the keyword English literature,
where m keywords are set, where the number of keyword english literature data sets r is j, x is english literature category, y is english literature attribute, μ is weight trained in the m-th keyword, and S is a keyword english literature data value having dual characteristics of category and attribute.
Preferably, in the above technical solution, the S1 further includes:
s1-3, after the collection of the data set is completed, carrying out similarity pairwise comparison on the keyword English documents, and comparing the collected keyword English documents with preset reference documents;
for keyword english literature similarity calculation, by gradually converging to Y trained keywords during training of the collection model R, a similarity influence weight λ needs to be defined first, where z (s, d) is the number of occurrences of a keyword s in the keyword english literature in the english literature d:
preferably, in the above technical solution, the S1 further includes:
X s keyword probability for preset reference X, Y s Calculating corresponding similarity influence weights for keyword probabilities of the keyword English documents, wherein i is the number sequence number of all keywords in the keyword English documents;
the similarity T between the keyword english literature and the preset reference is calculated as follows:
wherein D is a similarity factor, N is the most used number of keywords in English literature, the minimum value of the number is 1, and the maximum value of the number of the keywords in English literature; m(s) i ) The method comprises the steps of defining corresponding Machine learning and Deep learning as English documents with similarity, wherein the similarity is the similarity of keywords used in English documents and preset references; opera, operata, draga
s' is the total number of keywords in the preset reference.
Preferably, in the above technical solution, the S2 includes:
s2-1, classifying the attributes of the keyword English documents according to the similarity T, forming a complete sample vector by calculating the associated information of the keyword English documents with different attributes, carrying out set classification by adopting a weak classifier, and carrying out attribute classification after optimization according to the classifier weight in the keyword English documents;
s2-2, said attribute is classified as
η t In order to refer to the association coefficient of the sequence keyword English literature according to the time t, H is an attribute characteristic value, when H is 0, the negative keyword is represented, when H is 1, the positive keyword is represented, when H is other values are commonality or neutral keywords, L is a keyword English literature data value with attribute characteristics, W is a keyword English literature data value with attribute characteristics k For the total number of the English documents of the keywords with the category and the attribute of the similarity in the classifier, the subscript k is the data value sequence number of the English document of the keyword with the attribute characteristic.
Preferably, in the above technical solution, the S3 includes:
the keyword English literature after attribute classification is subjected to threshold judgment, so that attribute mapping operation is performed on the keyword English literature after similarity judgment,
wherein beta is k A threshold value of a keyword English literature data value k which is an attribute characteristic;the average value of the thresholds of the English literature of the keywords of all attribute characteristics in the training data; epsilon, (0 < epsilon < 1) represents the attribute correlation judgment coefficient。
In summary, due to the adoption of the technical scheme, the beneficial effects of the invention are as follows:
according to the invention, a BPE word segmentation method is abandoned, an efficient similarity judgment model is used for training the original English literature, sample errors in the training process are removed, a screened English literature training set is formed, topic classification is carried out according to the attribute of the part of speech of English literature semantics, the topic attribute of the corresponding English literature is judged, classification operation is carried out according to the topic attribute, threshold judgment is carried out on the original English literature and the topic classified English literature, and the process forms the knowledge graph construction of the English literature.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:
FIG. 1 is a general schematic of the present invention;
FIG. 2 is a schematic diagram of an embodiment of the present invention;
fig. 3 is a schematic diagram of another embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention.
As shown in fig. 1 to 3, the invention discloses a working method for constructing a knowledge graph by using english vocabulary data, comprising the following steps:
s1, executing a collection process of English documents according to query keywords, extracting a plurality of English vocabulary keywords, performing data convergence to form a keyword English document data set, and performing similarity judgment;
s2, performing a grouping process on the data set after similarity judgment, performing derivative classification operation on English documents containing keywords with different attributes, and performing relation mapping according to derivative classification content;
and S3, carrying out threshold judgment calculation on the derived and segmented keyword English literature, and thus constructing attribute information corresponding to the corresponding keyword English literature.
Preferably, in the above technical solution, the S1 includes:
s1-1, setting corresponding query keywords according to user use requirements, establishing a query keyword log, acquiring English documents of the keywords, and initializing English documents generated by the query keywords;
s1-2, constructing a collection model R of the keyword English literature,
wherein, by setting m keywords, the number of the keyword English literature data sets r is j, x is English literature category, y is English literature attribute, mu is weight trained when the m-th keyword, S is keyword English literature data value with dual characteristics of category and attribute,
training 20 rounds of training are performed by initializing training to be set to 0.1, matching a keyword English literature set of 5%, and training English literature is performed by using a similarity optimizer; according to english vocabulary keywords, for example: word processing using AI intelligence according to the software domain, wherein Machine learning, deep learning, neural networks, artificial intelligence (artificial intelligence), natural language processing (natural language processing), computer vision, reinforcement learning (reinforcement learning), supervised learning (supervised learning), unsupervised learning (unsupervised learning), convolutional Neural networks (convolutional Neural network), recurrent Neural networks (recurrent Neural network), transfer learning (transfer learning), generative adversarial networks (generation countermeasure network), bayesian networks (bayesian network), support vector machines (support vector Machine) Decision trees, clustering, regression analysis (regression analysis), data mining, big Data;
extracting the English literature of the keywords, training and classifying the English literature into a keyword English literature data set, and analyzing the English literature similarity according to the keyword similarity;
s1-3, after the collection of the data set is completed, carrying out similarity pairwise comparison on the keyword English documents, and comparing the collected keyword English documents with preset reference documents;
for keyword english literature similarity calculation, by gradually converging to Y trained keywords during training of the collection model R, a similarity influence weight λ needs to be defined first, where z (s, d) is the number of occurrences of a keyword s in the keyword english literature in the english literature d:
wherein X is s Keyword probability for preset reference X, Y s Calculating corresponding similarity influence weights for keyword probabilities of the keyword English documents, wherein i is the number sequence number of all keywords in the keyword English documents;
the similarity T between the keyword english literature and the preset reference is calculated as follows:
wherein D is a similarity factor, N is the most used number of keywords in English literature, the minimum value of the number is 1, and the maximum value of the number of the keywords in English literature; m(s) i ) The method comprises the steps of defining corresponding Machine learning and Deep learning as English documents with similarity, wherein the similarity is the similarity of keywords used in English documents and preset references; opera(opera), operatta (small opera), drama (opera)
s' is the number of all keywords in the preset reference;
the categories are as follows: liternature Literature, structure architecture, software, electronics, etc.;
attributes: positive, negative, neutral, similarity commonality.
In literature, tragedy is negative, comady Comedy is positive, in software
In the learning of the neural network,
active keywords:
efficiency (Efficiency): algorithms for deep learning and neural networks can efficiently handle large-scale data sets and complex tasks such as image recognition and natural language processing.
Adaptive (adaptation): deep learning and neural networks can gradually adapt to new data and tasks through training and have very strong generalization capability.
Precision (Accuracy): deep learning and neural networks have exceeded human performance in many tasks and with the continued development of technology, their accuracy will continue to improve.
Automation (Automation): deep learning and neural networks can automatically learn features and extract useful information, thereby reducing the need for human intervention.
Interpretive (interpretive): in recent years, more and more research has been devoted to explaining the decision-making process of deep learning and neural networks to improve their interpretability.
Negative keywords:
data requirements (Data Requirements): deep learning and neural network algorithms typically require large amounts of data to train, which may limit their application in certain fields.
Complexity (Complexity): the algorithms of deep learning and neural networks are themselves complex and it is difficult to explain the mechanisms by which they operate internally.
Vulnerability (vulnerabilities): algorithms for deep learning and neural networks may be subject to resistance attacks, resulting in erroneous prediction results.
Misinterpretation and misinterpretation (Misunderstandings and Misinterpretations): due to the complexity of deep learning and neural network algorithms, one often misunderstands and misinterprets their decision process.
Bias (Bias): deep learning and neural network algorithms may be affected by bias in the dataset, producing erroneous decision results.
Preferably, in the above technical solution, the S2 includes:
s2-1, classifying the attributes of the keyword English documents according to the similarity T, forming a complete sample vector by calculating the associated information of the keyword English documents with different attributes, carrying out set classification by adopting a weak classifier, and carrying out attribute classification after optimization according to the classifier weight in the keyword English documents;
s2-2, said attribute is classified as
η t In order to refer to the association coefficient of the sequence keyword English literature according to the time t, H is an attribute characteristic value, when H is 0, the negative keyword is represented, when H is 1, the positive keyword is represented, when H is other values are commonality or neutral keywords, L is a keyword English literature data value with attribute characteristics, W is a keyword English literature data value with attribute characteristics k For the total number of the English documents of the keywords with the category and the attribute of the similarity in the classifier, the subscript k is the data value sequence number of the English document of the keyword with the attribute characteristic.
In order to improve the accuracy of the result, considering that the keyword English literature classifier with the same category and attribute has errors, performing error convergence by using threshold judgment.
Preferably, in the above technical solution, the S3 includes:
the keyword English literature after attribute classification is subjected to threshold judgment, so that attribute mapping operation is performed on the keyword English literature after similarity judgment,
wherein beta is k A threshold value of a keyword English literature data value k which is an attribute characteristic;the average value of the thresholds of the English literature of the keywords of all attribute characteristics in the training data; epsilon, (0 < epsilon < 1) represents the attribute correlation judgment coefficient.
The documents with the corresponding English keywords are required to be classified in the searching process, if the existing word segmentation method is adopted, the classification process is too slow, the corresponding contents can be classified by judging through the threshold value after the attribute classification, which is equivalent to the drawing process of the knowledge graph for the English documents, and the documents can be more visual and clear for reading and using personnel, so that the subsequent consulting work is convenient.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
Claims (6)
1. A working method for constructing a knowledge graph by using english vocabulary data, comprising:
s1, executing a collection process of English documents according to query keywords, extracting a plurality of English vocabulary keywords, performing data convergence to form a keyword English document data set, and performing similarity judgment;
s2, performing a grouping process on the data set after similarity judgment, performing derivative classification operation on English documents containing keywords with different attributes, and performing relation mapping according to derivative classification content;
and S3, carrying out threshold judgment calculation on the derived and segmented keyword English literature, and thus constructing attribute information corresponding to the corresponding keyword English literature.
2. The working method for constructing a knowledge graph using english vocabulary data according to claim 1, wherein S1 comprises:
s1-1, setting corresponding query keywords according to user use requirements, establishing a query keyword log, acquiring English documents of the keywords, and initializing English documents generated by the query keywords;
s1-2, constructing a collection model R of the keyword English literature,where m keywords are set, where the number of keyword english literature data sets r is j, x is english literature category, y is english literature attribute, μ is weight trained in the m-th keyword, and S is a keyword english literature data value having dual characteristics of category and attribute.
3. The working method for constructing a knowledge graph using english vocabulary data according to claim 1, wherein S1 further comprises:
s1-3, after the collection of the data set is completed, carrying out similarity pairwise comparison on the keyword English documents, and comparing the collected keyword English documents with preset reference documents;
for keyword english literature similarity calculation, by gradually converging to Y trained keywords during training of the collection model R, a similarity influence weight λ needs to be defined first, where z (s, d) is the number of occurrences of a keyword s in the keyword english literature in the english literature d:
4. the working method for constructing a knowledge graph using english vocabulary data according to claim 1, wherein S1 further comprises:
X s keyword probability for preset reference X, Y s Calculating corresponding similarity influence weights for keyword probabilities of the keyword English documents, wherein i is the number sequence number of all keywords in the keyword English documents;
the similarity T between the keyword english literature and the preset reference is calculated as follows:
wherein D is a similarity factor, N is the most used number of keywords in English literature, the minimum value of the number is 1, and the maximum value of the number of the keywords in English literature; m(s) i ) The method comprises the steps of defining corresponding Machine learning and Deep learning as English documents with similarity, wherein the similarity is the similarity of keywords used in English documents and preset references; opera, operata, draga
s' is the total number of keywords in the preset reference.
5. The working method for constructing a knowledge graph using english vocabulary data according to claim 1, wherein S2 comprises:
s2-1, classifying the attributes of the keyword English documents according to the similarity T, forming a complete sample vector by calculating the associated information of the keyword English documents with different attributes, carrying out set classification by adopting a weak classifier, and carrying out attribute classification after optimization according to the classifier weight in the keyword English documents;
s2-2, said attribute is classified as
η t In order to refer to the association coefficient of the sequence keyword English literature according to the time t, H is an attribute characteristic value, when H is 0, the negative keyword is represented, when H is 1, the positive keyword is represented, when H is other values are commonality or neutral keywords, L is a keyword English literature data value with attribute characteristics, W is a keyword English literature data value with attribute characteristics k For the total number of the English documents of the keywords with the category and the attribute of the similarity in the classifier, the subscript k is the data value sequence number of the English document of the keyword with the attribute characteristic.
6. The working method for constructing a knowledge graph using english vocabulary data according to claim 1, wherein S3 comprises:
the keyword English literature after attribute classification is subjected to threshold judgment, so that attribute mapping operation is performed on the keyword English literature after similarity judgment,
wherein beta is k A threshold value of a keyword English literature data value k which is an attribute characteristic;the average value of the thresholds of the English literature of the keywords of all attribute characteristics in the training data; epsilon, (0 < epsilon < 1) represents the attribute correlation judgment coefficient.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310336495.4A CN116304110B (en) | 2023-03-30 | 2023-03-30 | Working method for constructing knowledge graph by using English vocabulary data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310336495.4A CN116304110B (en) | 2023-03-30 | 2023-03-30 | Working method for constructing knowledge graph by using English vocabulary data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116304110A true CN116304110A (en) | 2023-06-23 |
CN116304110B CN116304110B (en) | 2023-09-08 |
Family
ID=86795849
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310336495.4A Active CN116304110B (en) | 2023-03-30 | 2023-03-30 | Working method for constructing knowledge graph by using English vocabulary data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116304110B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001337981A (en) * | 2000-05-30 | 2001-12-07 | Patolis Corp | Retrieval expression converting method for converting first language retrieval expression to second language retrieval expression |
KR20090119383A (en) * | 2008-05-16 | 2009-11-19 | 한국과학기술정보연구원 | System and method for providing terminology resource |
CN106294639A (en) * | 2016-08-01 | 2017-01-04 | 金陵科技学院 | Method is analyzed across the newly property the created anticipation of language patent based on semantic |
CN109947952A (en) * | 2019-03-20 | 2019-06-28 | 武汉市软迅科技有限公司 | Search method, device, equipment and storage medium based on english knowledge map |
CN110807101A (en) * | 2019-10-15 | 2020-02-18 | 中国科学技术信息研究所 | Scientific and technical literature big data classification method |
CN112269885A (en) * | 2020-11-16 | 2021-01-26 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for processing data |
CN112364141A (en) * | 2020-11-05 | 2021-02-12 | 天津大学 | Scientific literature key content potential association mining method based on graph neural network |
CN114511027A (en) * | 2022-01-29 | 2022-05-17 | 重庆工业职业技术学院 | Method for extracting English remote data through big data network |
-
2023
- 2023-03-30 CN CN202310336495.4A patent/CN116304110B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001337981A (en) * | 2000-05-30 | 2001-12-07 | Patolis Corp | Retrieval expression converting method for converting first language retrieval expression to second language retrieval expression |
KR20090119383A (en) * | 2008-05-16 | 2009-11-19 | 한국과학기술정보연구원 | System and method for providing terminology resource |
CN106294639A (en) * | 2016-08-01 | 2017-01-04 | 金陵科技学院 | Method is analyzed across the newly property the created anticipation of language patent based on semantic |
CN109947952A (en) * | 2019-03-20 | 2019-06-28 | 武汉市软迅科技有限公司 | Search method, device, equipment and storage medium based on english knowledge map |
CN110807101A (en) * | 2019-10-15 | 2020-02-18 | 中国科学技术信息研究所 | Scientific and technical literature big data classification method |
CN112364141A (en) * | 2020-11-05 | 2021-02-12 | 天津大学 | Scientific literature key content potential association mining method based on graph neural network |
CN112269885A (en) * | 2020-11-16 | 2021-01-26 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for processing data |
CN114511027A (en) * | 2022-01-29 | 2022-05-17 | 重庆工业职业技术学院 | Method for extracting English remote data through big data network |
Non-Patent Citations (2)
Title |
---|
CHUNHUI YUAN.ET.AL.: "Research on Data Link Ontology Mapping Algorithm Based on Bayesian Network Model", 《 IEEE ACCESS》, vol. 7 * |
贺金龙;付立军;姚郑;吕鹏飞;黄徐胜;: "基于网格LSTM混合算法的地质领域用户意图识别", 计算机系统应用, no. 10 * |
Also Published As
Publication number | Publication date |
---|---|
CN116304110B (en) | 2023-09-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110298032B (en) | Text classification corpus labeling training system | |
CN113806547B (en) | Deep learning multi-label text classification method based on graph model | |
CN115098690B (en) | Multi-data document classification method and system based on cluster analysis | |
Estevez-Velarde et al. | AutoML strategy based on grammatical evolution: A case study about knowledge discovery from text | |
CN110765285A (en) | Multimedia information content control method and system based on visual characteristics | |
MidhunChakkaravarthy | Evolutionary and incremental text document classifier using deep learning | |
Villa-Blanco et al. | Feature subset selection for data and feature streams: a review | |
Panda et al. | Multi-label software bug categorisation based on fuzzy similarity | |
CN110765781A (en) | Man-machine collaborative construction method for domain term semantic knowledge base | |
Mansour et al. | Text vectorization method based on concept mining using clustering techniques | |
Zobeidi et al. | Effective text classification using multi-level fuzzy neural network | |
CN116304110B (en) | Working method for constructing knowledge graph by using English vocabulary data | |
CN116578708A (en) | Paper data name disambiguation algorithm based on graph neural network | |
CN116340936A (en) | ICS intrusion detection system and method integrating reinforcement learning and feature selection optimization | |
Zheng | Improved K-means clustering algorithm based on dynamic clustering | |
CN110399544A (en) | Electronic health record digital object classifier generation method and final classification device system | |
CN113434668B (en) | Deep learning text classification method and system based on model fusion | |
CN111984762B (en) | Text classification method sensitive to attack resistance | |
Selvi et al. | Topic categorization of Tamil news articles | |
CN114491066A (en) | Entity relationship extraction method and system for knowledge graph construction | |
Ahmed et al. | A Comprehensive Review on Machine Learning Models for Medical Data Classification | |
CN113688229B (en) | Text recommendation method, system, storage medium and equipment | |
CN112579667B (en) | Data-driven engine multidisciplinary knowledge machine learning method and device | |
CN117891929B (en) | Knowledge graph intelligent question-answer information identification method of improved deep learning algorithm | |
CN113806739B (en) | Business access data detection method based on deep learning |
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 |