CN115115227A - Method for constructing product quality knowledge graph in papermaking field - Google Patents
Method for constructing product quality knowledge graph in papermaking field Download PDFInfo
- Publication number
- CN115115227A CN115115227A CN202210753820.2A CN202210753820A CN115115227A CN 115115227 A CN115115227 A CN 115115227A CN 202210753820 A CN202210753820 A CN 202210753820A CN 115115227 A CN115115227 A CN 115115227A
- Authority
- CN
- China
- Prior art keywords
- product quality
- papermaking
- data
- fault
- knowledge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000011218 segmentation Effects 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 6
- 238000012216 screening Methods 0.000 claims abstract description 4
- 238000001514 detection method Methods 0.000 claims description 25
- 238000003745 diagnosis Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 11
- 230000014509 gene expression Effects 0.000 claims description 8
- 238000002372 labelling Methods 0.000 claims description 7
- 230000009471 action Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
Images
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—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
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Animal Behavior & Ethology (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses a method for constructing a product quality knowledge graph in the papermaking field, which is characterized in that related data of the product quality is generated based on the existing structured data and internet data in the papermaking field, and the acquired data forms basic data of the product quality in the papermaking field through collection, screening, analysis and summarization; performing word segmentation processing according to the acquired data information to form a product quality corpus of the papermaking field; selecting partial data from a corpus as a training set, and marking the partial data as training data in a manual mode; iteratively training the named entity recognition model by using the labeled training data to realize the extraction of knowledge; according to the method, relevant books, webpages, forums and other information are acquired, product quality relevant data information in the comprehensive papermaking field is obtained, a product quality knowledge classification system based on the papermaking field is established, and the product quality knowledge classification system is stored in the form of a graph database; the technical scheme provided by the invention can also be generalized from the papermaking industry to other industries.
Description
Technical Field
The invention relates to the technical field of knowledge graph construction, in particular to a method for constructing a product quality knowledge graph in the field of papermaking.
Background
The knowledge graph takes concepts and entities as centers and expresses the relationship between the concepts and the relationships between the entities. The knowledge graph can express knowledge with complex relations, and the incidence relation of influencing factors, the propagation path of variable links and the hierarchy of data can be clearly seen from the knowledge graph. Meanwhile, fault delay can be found through the change of the state of the knowledge graph. These properties of the knowledge-graph are just as useful in solving the problem of difficult expression of complex industrial process (e.g., paper making) relationships.
The defects and shortcomings of the prior art are as follows: at present, the application of the knowledge graph in the paper making industry is still blank. The scale of the paper making production process is huge, the structure is complex, and the coupling between production units is extremely strong, so that the difficulty of fault diagnosis in the paper making production process is increasingly high. Since an accurate mathematical model cannot be established in the paper industry process, the method of diagnosis using the mathematical model is not applicable; in the paper-making production process, various equipment variables have complicated incidence relations, and the data-based method cannot well express the incidence relations, so that the diagnosis capability is insufficient. The knowledge base capable of expressing complex association relations is needed for the fault diagnosis of the quality problems of the papermaking products and the fault diagnosis of the papermaking production process so as to help relevant personnel to carry out fault diagnosis. In view of this, there is a need for one or more methods for extracting knowledge and creating a knowledge map for complex industrial processes such as papermaking.
Disclosure of Invention
The invention provides a method for constructing a product quality knowledge graph in the papermaking field, aiming at solving the technical problem.
The purpose of the invention is realized by the following technical scheme:
a knowledge extraction and knowledge graph construction method for the papermaking field comprises the following steps:
step (1), collecting data:
generating relevant data of the papermaking industry based on the existing structured data of the papermaking industry, the Internet data and the book data, wherein the data comprises the structured data of existing relevant equipment and processes and relevant document information of the quality problems of the papermaking products acquired by a crawler at relevant websites of the papermaking enterprises, websites of the papermaking faults and relevant websites of the quality problems of the papermaking products; the paper-making product quality related document information comprises paper-making product quality standard document information, policy standard, patent, report and encyclopedia; the acquired data forms basic data of the product quality in the papermaking field after collection, screening, analysis and summarization;
step (2), data word segmentation:
performing word segmentation processing by using a word segmentation model according to the data information acquired in the step (1), and finally forming a product quality corpus in the papermaking field;
step (3), data annotation:
according to the corpus in the step (2), selecting partial data, manually labeling each character of Chinese as a recognition unit, and then taking the labeled data as a training set;
in the manual labeling process, the labeled classification comprises a fault type, a fault name, a fault equipment name, fault description (phenomenon), a fault reason and a fault solution.
Step (4), knowledge extraction
And (4) establishing a named entity recognition model according to the training set in the step (3), carrying out model training, and extracting knowledge of all documents by using the trained model.
Step (5), constructing a product quality knowledge map classification system
And constructing a concept and relationship classification system based on the product quality knowledge graph in the papermaking field by a top-down mode and a manual construction mode.
Constructing a concept and relationship classification system based on a product quality knowledge graph in the papermaking field, comprising the following steps of:
5.1, defining a knowledge classification system of the quality problem of the papermaking product, and designing 6 fault concepts which are respectively the product quality problem, the generation reason, the phenomenon, the solution, the position and the detection;
5.2, according to the fault concepts of the 6 types of defined papermaking product quality in the step 5.1, further subdividing the generalized concept co-occurrence relationship into concept relationships of 7 major classes and 14 minor classes according to semantic types;
7 the broad category of conceptual relationships includes: fault diagnosis, fault expression, action part, quality detection, fault part, detection result and diagnosis basis; the 14 subclasses of conceptual relationships include: the relation types between the product quality problem and the phenomenon, between the phenomenon and the generation reason, between the fault decision and the phenomenon are defined as fault expression; the relation type between the product quality problem and the occurrence part and between the part and the phenomenon is defined as a fault part; the type of the relationship between the product quality problem and the detection and the phenomenon is defined as the quality detection; the types of relationships between "product quality problems" and "cause of occurrence", "cause of occurrence" and "solution", "solution" and "product quality problems" are defined as "failure diagnosis"; the type of relationship between "detection" and "site", "site" and "solution" is defined as "site of action"; the type of the relationship between "detection" and "phenomenon" is defined as "detection result"; the type of relationship between "phenomenon" and "product quality problem" is defined as "diagnostic basis".
Step (6), knowledge storage
And correspondingly storing the extracted knowledge classification in a Neo4j database according to the constructed product quality concept and the relation classification system in the papermaking field.
The knowledge graph is used for describing various entities or concepts existing in the real world and relations of the entities or concepts, nodes represent the entities or concepts, and edges are formed by attributes or relations. An entity refers to something that is distinguishable and exists independently. A concept is a collection of entities with the same properties, such as product quality, equipment, process, etc. The concept relationship is used for describing the semantic relationship between two concepts and is an important constituent element of the structured knowledge.
Compared with the prior art, the technical scheme of the invention has the following beneficial effects:
by adopting the technical scheme of the invention, basic data of the product quality in the papermaking field is obtained by acquiring information of related websites, books and the like, a concept and relationship classification system based on the product quality knowledge graph in the papermaking field is constructed, and the extracted knowledge classification is correspondingly stored in a Neo4j graph database to form the product quality knowledge graph based on the papermaking field; the technical scheme provided by the invention can also be generalized from the paper making industry to other complex process industries.
Drawings
FIG. 1 is an overall operational schematic of the present invention;
FIG. 2 is a diagram of a product quality failure knowledge graph concept and classification architecture of the present invention;
FIG. 3 is a schematic flow chart of an embodiment of the present invention;
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1 and fig. 3, the present invention provides a specific example of a method for constructing a product quality knowledge graph in the papermaking field, which comprises the following steps:
step (1), collecting data:
generating relevant data of the papermaking industry based on the existing structured data of the papermaking industry, the Internet data and the book data, wherein the data comprises the structured data of existing relevant equipment and processes and relevant document information of the quality problems of the papermaking products acquired by a crawler at relevant websites of the papermaking enterprises, websites of the papermaking faults and relevant websites of the quality problems of the papermaking products; the paper-making product quality related document information comprises paper-making product quality standard document information, policy standard, patent, report and encyclopedia; the acquired data forms basic data of the product quality in the papermaking field after collection, screening, analysis and summarization;
step (2), data word segmentation:
performing word segmentation processing by using a word segmentation model according to the data information acquired in the step (1), and finally forming a product quality corpus in the papermaking field;
the description is given by taking a Thulac word segmentation model as an example, and the specific steps of the Thulac word segmentation model are as follows: firstly, introducing a Thulac toolkit; then reading the collected basic data of the quality of the products in the papermaking field; then calling a sulac module in a sulac toolkit to perform word segmentation processing on the collected basic data of the product quality in the papermaking field; then storing the data after word segmentation processing; finally, the stored data is subjected to punctuation removal and illegal character operation and is stored again in a text form;
step (3), data annotation:
according to the corpus in the step (2), selecting partial data, manually labeling each character of Chinese as a recognition unit, and then taking the labeled data as a training set;
in the manual labeling process, the labeled classification comprises a fault type, a fault name, a fault equipment name, fault description (phenomenon), a fault reason and a fault solution.
Related words such as fault type, fault name, fault equipment name, fault description (phenomenon), fault reason and fault solution appearing in the material library are respectively marked as a fault type entity, a fault name entity, a fault equipment name entity, a fault description (phenomenon) entity, a fault reason entity and a fault solution entity. The manual labeling by the BMES four-bit sequence labeling method is taken as an example for explanation: b represents the beginning of a word, M represents a word, E is marked with the end of a word, and S represents a single word.
Step (4), knowledge extraction
And (4) establishing a named entity recognition model according to the training set in the step (3), carrying out model training, and extracting knowledge of all documents by using the trained model.
The method is described by taking an example of training a named entity recognition model based on a bidirectional long-and-short time memory network and a conditional random field model (Bi-LSTM + CRF model for short) to realize extraction of knowledge: firstly, mapping the marked Chinese characters into word vectors as input of a model; then inputting the word vectors into a BilSTM layer, and outputting the score probability of each word corresponding to each label; then, obtaining a final prediction result by learning sequence dependence information among labels in a CRF layer, and outputting a predicted sequence label of each word; and finally, inputting the document data into a trained Bi-LSTM + CRF model for knowledge extraction.
Step (5), constructing a product quality knowledge map classification system
And constructing a concept and relationship classification system based on the product quality knowledge graph in the papermaking field by a top-down mode and a manual construction mode.
Constructing a concept and relationship classification system based on a product quality knowledge graph in the papermaking field, comprising the following steps of:
5.1, defining a knowledge classification system of the quality problem of the papermaking product, and designing 6 fault concepts which are respectively the product quality problem, the generation reason, the phenomenon, the solution, the position and the detection;
5.2, according to the fault concepts of the 6 types of defined papermaking product quality in the step 5.1, further subdividing the generalized concept co-occurrence relationship into concept relationships of 7 major classes and 14 minor classes according to semantic types;
5.1, defining a knowledge classification system of the quality problem of the papermaking product, and designing 6 fault concepts which are respectively the product quality problem, the generation reason, the phenomenon, the solution, the position and the detection;
5.2, according to the fault concepts of the 6 types of defined papermaking product quality in the step 5.1, further subdividing the generalized concept co-occurrence relationship into concept relationships of 7 major classes and 14 minor classes according to semantic types; as shown in fig. 2, the 7 broad-class conceptual relationships include: fault diagnosis, fault expression, action part, quality detection, fault part, detection result and diagnosis basis; as shown in fig. 2, the conceptual relationship of 14 subclasses includes: the relation types between the product quality problem and the phenomenon, between the phenomenon and the generation reason, between the fault decision and the phenomenon are defined as fault expression; the relation type between the product quality problem and the occurrence part and between the part and the phenomenon is defined as a fault part; the type of the relationship between the product quality problem and the detection and the phenomenon is defined as the quality detection; the types of relationships between "product quality problems" and "cause of occurrence", "cause of occurrence" and "solution", "solution" and "product quality problems" are defined as "failure diagnosis"; the type of relationship between "detection" and "site", "site" and "solution" is defined as "site of action"; the type of the relationship between "detection" and "phenomenon" is defined as "detection result"; the type of relationship between the "phenomenon" and the "product quality problem" is defined as "diagnostic basis".
Step (6), knowledge storage
And correspondingly storing the extracted knowledge classification in a Neo4j database according to the constructed product quality concept and the relation classification system in the papermaking field.
By adopting the technical scheme disclosed by the invention, the following beneficial effects are obtained: by adopting the technical scheme of the invention, basic data of the product quality in the papermaking field is obtained by acquiring information of related websites, books and the like, a concept and relationship classification system based on the product quality knowledge graph in the papermaking field is constructed, and the extracted knowledge classification is correspondingly stored in a Neo4j graph database to form the product quality knowledge graph based on the papermaking field; the technical scheme provided by the invention can also be generalized from the paper making industry to other complex process industries.
The principle and embodiments of the present invention have been described herein by way of specific examples, which are provided only to help understand the method and the core idea of the present invention, and the above is only a preferred embodiment of the present invention, and it should be noted that there are objectively infinite specific structures due to the limited character expressions, and it will be apparent to those skilled in the art that a plurality of modifications, decorations or changes can be made without departing from the principle of the present invention, and the above technical features can also be combined in a suitable manner; such modifications, variations, combinations, or adaptations of the invention in other instances, which may or may not be practiced, are intended to be within the scope of the present invention.
Claims (4)
1. A method for constructing a product quality knowledge graph in the papermaking field is characterized by comprising the following steps:
step (1), collecting data:
generating a papermaking industry based on the existing papermaking industry structured data, the internet data and the book data; the acquired data forms basic data of the product quality in the papermaking field after collection, screening, analysis and summarization;
step (2), data word segmentation:
performing word segmentation processing by using a word segmentation model according to the data information acquired in the step (1), and finally forming a product quality corpus in the papermaking field;
step (3), data annotation:
according to the corpus in the step (2), selecting partial data, manually labeling each character of Chinese as a recognition unit, and then taking the labeled data as a training set;
in the manual marking process, the marked classification comprises a fault type, a fault name, a fault equipment name, a fault description, a fault reason and a fault solution;
step (4), knowledge extraction
Establishing a named entity recognition model according to the training set in the step (3), carrying out model training, and extracting knowledge from all documents by using the trained model;
step (5) constructing a product quality knowledge graph classification system
Constructing a classification system of product quality concepts and relationships in the papermaking field by a top-down mode and a manual construction mode;
step (6), knowledge storage
And correspondingly storing the extracted knowledge classification in a Neo4j database according to the constructed product quality concept and the relation classification system in the papermaking field.
2. The method for constructing the product quality knowledge graph in the papermaking field according to claim 1, wherein the related data in the step (1) comprises structured data of existing related equipment and processes, and papermaking product quality problem related document information collected by a crawler at a related papermaking enterprise website, a papermaking failure website and a papermaking product quality problem related website; the paper-making product quality related document information comprises paper-making product quality standard document information, policy standard, patent, report and encyclopedia.
3. A method for constructing a product quality knowledge-graph for use in the papermaking art according to claim 1, characterized in that step (5) comprises the following sub-steps:
5.1, defining a knowledge classification system of the quality problem of the papermaking product, and designing 6 types of concepts of papermaking faults, namely product quality problem, generation reason, phenomenon, solution, position and detection;
and 5.2, further subdividing the generalized concept co-occurrence relationship into concept relationships of 7 major classes and concept relationships of 14 minor classes according to semantic types according to the 6 defined concepts of the faults of the paper making process in the step 5.1.
4. A method of building a product quality knowledge graph for use in the papermaking arts as claimed in claim 3 wherein 7 broad categories of conceptual relationships comprise: fault diagnosis, fault expression, action part, quality detection, fault part, detection result and diagnosis basis;
the 14 subclasses of conceptual relationships include: the relation types between the product quality problem and the phenomenon, between the phenomenon and the generation reason, between the fault decision and the phenomenon are defined as fault expression; the relation type between the product quality problem and the occurrence part and between the part and the phenomenon is defined as a fault part; the type of the relationship between the product quality problem and the detection and the phenomenon is defined as the quality detection; the types of relationships between "product quality problems" and "cause of occurrence", "cause of occurrence" and "solution", "solution" and "product quality problems" are defined as "failure diagnosis"; the type of relationship between "detection" and "site", "site" and "solution" is defined as "site of action"; the type of the relationship between "detection" and "phenomenon" is defined as "detection result"; the type of relationship between "phenomenon" and "product quality problem" is defined as "diagnostic basis".
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210753820.2A CN115115227A (en) | 2022-06-28 | 2022-06-28 | Method for constructing product quality knowledge graph in papermaking field |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210753820.2A CN115115227A (en) | 2022-06-28 | 2022-06-28 | Method for constructing product quality knowledge graph in papermaking field |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115115227A true CN115115227A (en) | 2022-09-27 |
Family
ID=83330016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210753820.2A Pending CN115115227A (en) | 2022-06-28 | 2022-06-28 | Method for constructing product quality knowledge graph in papermaking field |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115115227A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111897914A (en) * | 2020-07-20 | 2020-11-06 | 杭州叙简科技股份有限公司 | Entity information extraction and knowledge graph construction method for field of comprehensive pipe gallery |
| CN112231460A (en) * | 2020-10-27 | 2021-01-15 | 中国科学院合肥物质科学研究院 | Construction method of question-answering system based on agricultural encyclopedia knowledge graph |
| CN113360679A (en) * | 2021-07-08 | 2021-09-07 | 北京国信会视科技有限公司 | Fault diagnosis method based on knowledge graph technology |
| CN113569055A (en) * | 2021-07-26 | 2021-10-29 | 东北大学 | Strip mine knowledge map construction method based on genetic algorithm optimization neural network |
-
2022
- 2022-06-28 CN CN202210753820.2A patent/CN115115227A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111897914A (en) * | 2020-07-20 | 2020-11-06 | 杭州叙简科技股份有限公司 | Entity information extraction and knowledge graph construction method for field of comprehensive pipe gallery |
| CN112231460A (en) * | 2020-10-27 | 2021-01-15 | 中国科学院合肥物质科学研究院 | Construction method of question-answering system based on agricultural encyclopedia knowledge graph |
| CN113360679A (en) * | 2021-07-08 | 2021-09-07 | 北京国信会视科技有限公司 | Fault diagnosis method based on knowledge graph technology |
| CN113569055A (en) * | 2021-07-26 | 2021-10-29 | 东北大学 | Strip mine knowledge map construction method based on genetic algorithm optimization neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107862343B (en) | Commodity comment attribute level emotion classification method based on rules and neural network | |
| US10776583B2 (en) | Error correction for tables in document conversion | |
| US20170076225A1 (en) | Model-based classification of content items | |
| CN110609983B (en) | Structured decomposition method for policy file | |
| CN111783394A (en) | Training method of event extraction model, event extraction method, system and equipment | |
| US20170075978A1 (en) | Model-based identification of relevant content | |
| CN106778878B (en) | Character relation classification method and device | |
| Rashid et al. | Feature level opinion mining of educational student feedback data using sequential pattern mining and association rule mining | |
| CN111767725A (en) | Data processing method and device based on emotion polarity analysis model | |
| CN112183056A (en) | Context-dependent multi-classification emotion analysis method and system based on CNN-BilSTM framework | |
| CN111339260A (en) | BERT and QA thought-based fine-grained emotion analysis method | |
| CN109992653A (en) | Information processing method and processing system | |
| Abdoun et al. | Automatic text classification of pdf documents using nlp techniques | |
| Zuhanda et al. | Supply chain strategy during the COVID-19 terms: sentiment analysis and knowledge discovery through text mining | |
| CN111538893A (en) | Method for extracting network security new words from unstructured data | |
| Hossain et al. | Comparative sentiment analysis using difference types of machine learning algorithm | |
| CN115115227A (en) | Method for constructing product quality knowledge graph in papermaking field | |
| Khandokar et al. | Event detection and knowledge mining from unlabelled bengali news articles | |
| Umidjon | UNLOCKING THE POWER OF NATURAL LANGUAGE PROCESSING (NLP) FOR TEXT ANALYSIS | |
| Banshal et al. | MONOVAB: An Annotated Corpus for Bangla Multi-label Emotion Detection | |
| Malkadi et al. | Improving code extraction from coding screencasts using a code-aware encoder-decoder model | |
| Fritzner | Automated information extraction in natural language | |
| Shahade et al. | Deep learning approach-based hybrid fine-tuned Smith algorithm with Adam optimiser for multilingual opinion mining | |
| Detection et al. | 17 Emails Classification | |
| DURGA et al. | ``Sentiment analysis on bangla youtube comments using machine learning techniques,'' |
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 |