CN114186075B - Semantic search method for knowledge graph in cultural domain - Google Patents
Semantic search method for knowledge graph in cultural domain Download PDFInfo
- Publication number
- CN114186075B CN114186075B CN202111525616.7A CN202111525616A CN114186075B CN 114186075 B CN114186075 B CN 114186075B CN 202111525616 A CN202111525616 A CN 202111525616A CN 114186075 B CN114186075 B CN 114186075B
- Authority
- CN
- China
- Prior art keywords
- search
- result
- knowledge graph
- concept
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000011218 segmentation Effects 0.000 claims description 26
- 230000004927 fusion Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000009412 basement excavation Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000004806 packaging method and process Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000003672 processing method 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The invention provides a semantic search method for a knowledge graph in the cultural domain, which comprises a knowledge graph ontology model in the cultural domain, wherein the ontology model is combined with search intention to configure the searched recommended associated vocabulary entry, recommended vocabulary entry weight and result ranking, and the knowledge graph ontology model is used together with a full-text search engine based on search configuration.
Description
Technical Field
The invention belongs to the technical field of semantic search, and particularly relates to a semantic search method for knowledge graphs in the cultural field.
Background
In knowledge content publishing sites in the cultural field, in-site searching is generally carried out by adopting a full text searching technology based on word segmentation, the principle of the searching is that after word segmentation processing is carried out on articles and search sentences, the word segmentation matching rate is calculated to obtain weight scores, then the weight scores are ranked according to the scores, the processing method cannot identify searching intention, if only full text fuzzy keyword matching searching is carried out, the content with association relation with the searched terms cannot be matched, the searching method has great limitation, and the traditional word segmentation full text searching cannot understand the searching intention; the content of the association relation with the searched entry cannot be matched; the weight cannot be set on the searched term according to the content of the association relation, so that the invention provides a semantic searching method for knowledge graphs in the cultural domain.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a semantic search method for a knowledge graph in the cultural field, which is reasonable in design, an ancient historical character model is added, character concept classification is set, character instance information and character relations are imported at the same time, character search is added to be configured into first three words which are relatives, middle three words are social relation words, then later three data are copyrighted words of a user, after the configuration is stored, a traditional search engine is used for searching, the method is used for carrying out search, the name is segmented by the results searched by the traditional search engine, a large number of words which contain segmentation but are not related to searched contents are matched, the search results of the method can accurately return to the father, son and copyrighted works of the search words to be ordered before, after the result is matched with key words which are not related, the search experience and the requirement can be effectively improved, and the search results are more accurate.
In order to achieve the above object, the present invention is realized by the following technical scheme: the semantic search method for the knowledge graph in the cultural field comprises a knowledge graph ontology model in the cultural field, wherein the ontology model is combined with search intention to configure related recommended vocabulary entries, recommended vocabulary entry weights and result ordering of search, and the knowledge graph ontology model is used together with a full-text search engine based on search configuration, and specifically comprises the following steps:
Building a knowledge graph body model; the related culture field metadata ontology model is based on a concept reference model (CIDOC-CRM) of the international literature working committee, the ontology model after being adjusted and modified by the invention is suitable for the construction of a knowledge graph database of a conventional related thematic knowledge base, and the model consists of two parts of ontology concept classification and concept relation dictionary; the related recommended vocabulary entry, the recommended vocabulary entry weight and the result ordering of the search are configured based on the ontology model and the search intention, and the specific steps are as follows:
the search query structure is configured for different concepts using a search configuration system, the configuration steps being as follows:
① Selecting a search intention concept: selecting concepts to be configured with search intents from the configuration page, wherein the concepts are the attributions of the preset search terms to the concepts of which the intention is to identify hits;
② : adding an associated concept; selecting concepts to be configured from the configuration page, wherein the concepts are attributed to the concepts of the identified hits of the preset search term;
③ : setting the number of the result strips; setting the number of the related concept query results;
④ : setting a result weight coefficient; the weight coefficient can participate in a formula to calculate a grading value of each result, the grading value affects the priority ranking of the associated concepts, the grading calculation formula is equivalent to the grading calculation of the full-text search engine, and the grading calculation formula is as follows:
score(q,d)=coord(q,d)×queryNorm(q)×∑t_in_q(tf(t_in_d)×idf(t)2×t.getBoost()×norm(t,d))
⑤ : defining and storing an intention scene; defining and storing the intended scene, and if various association results exist after the scene is stored, continuing to add association concepts to repeat the step;
The knowledge graph ontology model is used in combination with a full-text search engine based on search configuration, and the knowledge graph ontology model is specifically as follows:
Processing the search; the method comprises the following specific steps:
① : searching by a user; submitting a search request by a user;
② : word segmentation; the method comprises the steps of carrying out natural semantic word segmentation on search sentences requested by a user, and extracting part of speech of each word segmentation result at the same time, wherein in the method, jieba plug-in based on Python is adopted for word segmentation and part of speech extraction, and in actual application, the word segmentation plug-in is not limited to only one plug-in;
③ : named entity and intention recognition; combining word segmentation results, using a deep learning technology to identify named entities and search intentions for search sentences requested by a user by using a trained natural semantic identification model, obtaining concepts of the entities, modifying, expanding and training by using a lexical _analysis pre-training model based on PADDLEPADDLE frames, and carrying out Chinese lexical analysis and named entity identification on trained model results;
④ : acquiring a search configuration; acquiring configured concept search configuration according to the identified intention concept;
⑤ : searching a graph data path; obtaining an associated entity result by using a graph data path algorithm according to the obtained concept configuration;
⑥ : searching the full text; according to word segmentation results of the user request search statement, using a full-text search engine to perform full-text search of text resources;
⑦ : data fusion; the method comprises the following sub-steps of data merging and fusion of a path searching result of a graph database and a full text searching result of a search engine, and then sorting of the weight reverse sequence fusion result through a weight set by a configuration system, wherein the data merging process comprises the following sub-steps:
Sub-step 1: the path result a of the graph data prioritizes the result of the full text search b;
Sub-step 2: the result a is ranked in the reverse order from the big to the small after scoring is calculated item by item;
Sub-step 3: the result a and the result b are formatted into a unified array data format;
sub-step 4: combining the array a with the array b to obtain an array c (arrc [ ] = [ arra, arrb ]);
sub-step 5: performing duplicate removal cleaning on the array c;
⑧ : outputting a result; and outputting the fusion result packaging unified interface return format to the client.
In a preferred embodiment of the present invention, the named entity and the intention recognition method for fusing the knowledge graph ontology model and the full-text search engine based on the search configuration are not limited to only the one method.
As a preferred embodiment of the invention, the concept relation dictionary of the knowledge graph ontology model in the culture field is a basis for setting the relation between model concepts, for example, a character comprises the relations of father, mother, son, brother, sister, tert-nephew and the like, and a mechanism comprises the relations of collection, excavation, flow and the like.
The invention has the beneficial effects that:
the semantic search method for knowledge graphs in the cultural field adds an ancient historical character model, sets character concept classification, simultaneously imports character instance information and character relations, adds character search configuration into the first three characters which are related relation terms, the middle three characters are social relation terms, and the last three data are work terms of users, stores and configures the first three characters and the second three characters, and then searches the second three characters by using a traditional search engine.
Drawings
FIG. 1 is a conceptual diagram of an ontology model of a semantic search method for knowledge graph in cultural domain according to the present invention;
FIG. 2 is a schematic diagram of a search configuration flow of a semantic search method for knowledge graph in cultural domain according to the present invention;
FIG. 3 is a schematic diagram of a character concept disagreement diagram setting condition of a semantic search method for knowledge graph in cultural domain;
FIG. 4 is a schematic diagram of a scoring formula of search results of a semantic search method for knowledge graph in cultural domain according to the present invention;
fig. 5 is a schematic diagram of a search business flow of a semantic search method for knowledge graph in cultural domain according to the present invention.
Detailed Description
The invention is further described in connection with the following detailed description, in order to make the technical means, the creation characteristics, the achievement of the purpose and the effect of the invention easy to understand.
Referring to fig. 1 to 5, the present invention provides a technical solution: the semantic search method for the knowledge graph in the cultural field comprises a knowledge graph ontology model in the cultural field, wherein the ontology model is combined with search intention to configure related recommended vocabulary entries, recommended vocabulary entry weights and result ordering of search, and the knowledge graph ontology model is used together with a full-text search engine based on search configuration, and specifically comprises the following steps:
building a knowledge graph body model; the related culture field metadata ontology model is based on a concept reference model (CIDOC-CRM) of the international literature working committee, the ontology model after being adjusted and modified by the invention is suitable for the construction of a knowledge graph database of a conventional related thematic knowledge base, and the model consists of two parts of ontology concept classification and concept relation dictionary, as shown in figure 1;
The related recommended vocabulary entry, the recommended vocabulary entry weight and the result ordering of the search are configured based on the ontology model and the search intention, and the specific steps are as follows:
The search query structure is configured for different concepts using a search configuration system, as shown in FIG. 2, with the following configuration steps:
① Selecting a search intention concept: selecting concepts to be configured with search intents from the configuration page, wherein the concepts are the attributions of the preset search terms to the concepts of which the intention is to identify hits;
② : adding an associated concept; selecting concepts to be configured from the configuration page, wherein the concepts are attributed to the concepts of the identified hits of the preset search term, as shown in fig. 3;
③ : setting the number of the result strips; setting the number of the related concept query results;
④ : setting a result weight coefficient; the weight coefficient can participate in a formula to calculate a grading value of each result, the grading value affects the priority ranking of the associated concepts, the grading calculation formula is equivalent to the grading calculation of the full-text search engine, and the grading calculation formula is as follows:
score(q,d)=coord(q,d)×queryNorm(q)×∑t_in_q(tf(t_in_d)×idf(t)2×t.getBoost()×norm(t,d))
⑤ : defining and storing an intention scene; defining and storing the intended scene, and if various association results exist after the scene is stored, continuing to add association concepts to repeat the step;
The knowledge graph ontology model is used in combination with a full-text search engine based on search configuration, and the knowledge graph ontology model is specifically as follows:
Processing the search; as shown in fig. 5, the specific steps are as follows:
① : searching by a user; submitting a search request by a user;
② : word segmentation; the method comprises the steps of carrying out natural semantic word segmentation on search sentences requested by a user, and extracting part of speech of each word segmentation result at the same time, wherein in the method, jieba plug-in based on Python is adopted for word segmentation and part of speech extraction, and in actual application, the word segmentation plug-in is not limited to only one plug-in;
③ : named entity and intention recognition; combining word segmentation results, using a deep learning technology to identify named entities and search intentions for search sentences requested by a user by using a trained natural semantic identification model, obtaining concepts of the entities, modifying, expanding and training by using a lexical _analysis pre-training model based on PADDLEPADDLE frames, and carrying out Chinese lexical analysis and named entity identification on trained model results;
④ : acquiring a search configuration; acquiring configured concept search configuration according to the identified intention concept;
⑤ : searching a graph data path; obtaining an associated entity result by using a graph data path algorithm according to the obtained concept configuration;
⑥ : searching the full text; according to word segmentation results of the user request search statement, using a full-text search engine to perform full-text search of text resources;
⑦ : data fusion; the method comprises the following sub-steps of data merging and fusion of a path searching result of a graph database and a full text searching result of a search engine, and then sorting of the weight reverse sequence fusion result through a weight set by a configuration system, wherein the data merging process comprises the following sub-steps:
Sub-step 1: the path result a of the graph data prioritizes the result of the full text search b;
Sub-step 2: the result a is ranked in the reverse order from the big to the small after scoring is calculated item by item;
Sub-step 3: the result a and the result b are formatted into a unified array data format;
sub-step 4: combining the array a with the array b to obtain an array c (arrc [ ] = [ arra, arrb ]);
sub-step 5: performing duplicate removal cleaning on the array c;
⑧ : outputting a result; and outputting the fusion result packaging unified interface return format to the client.
In a preferred embodiment of the present invention, the named entity and the intention recognition method for fusing the knowledge graph ontology model and the full-text search engine based on the search configuration are not limited to only the one method.
As a preferred embodiment of the invention, the concept relation dictionary of the knowledge graph ontology model in the culture field is a basis for setting the relation between model concepts, for example, a character comprises the relations of father, mother, son, brother, sister, tert-nephew and the like, and a mechanism comprises the relations of collection, excavation, flow and the like.
While the fundamental and principal features of the invention and advantages of the invention have been shown and described, it will be apparent to those skilled in the art that the invention is not limited to the details of the foregoing exemplary embodiments, but may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is provided for clarity only, and that the disclosure is not limited to the embodiments described in detail below, and that the embodiments described in the examples may be combined as appropriate to form other embodiments that will be apparent to those skilled in the art.
Claims (2)
1. The semantic search method for the knowledge graph in the cultural field is characterized by comprising a knowledge graph ontology model in the cultural field, wherein the knowledge graph ontology model is used for integrating a search engine with a full-text search engine based on the ontology model in combination with search intention configuration of recommended associated vocabulary entries, recommended vocabulary entry weights and result ordering, and the knowledge graph ontology model is specifically as follows:
Building a knowledge graph body model; the related culture field metadata ontology model is an ontology model obtained by optimization on the basis of a concept reference model CIDOC-CRM of the International literature working Commission, is suitable for the construction of a knowledge graph database of a conventional related thematic knowledge base, and consists of two parts, namely ontology concept classification and concept relation dictionary; the concept relation dictionary of the knowledge graph ontology model in the cultural field is a basis for setting the relation between the model concept and the concept, wherein ' persona ' - ' persona ' comprises father-son, mother-son, brothers, sister and child-child relations, and ' mechanism ' - ' movable cultural relics ' comprises collection, excavation and flow relations, an ' ancient historical persona ' model is added in a semantic searching method of the knowledge graph in the cultural field, persona concept classification is set, persona instance information and persona relations are simultaneously imported, persona searching is added to configure that the first three persona items are relatives items, the middle three items are social items, and the later three items are user's literary items;
The related recommended vocabulary entry, the recommended vocabulary entry weight and the result ordering of the search are configured based on the ontology model and the search intention, and the specific steps are as follows:
the search query structure is configured for different concepts using a search configuration system, the configuration steps being as follows:
① Selecting a search intention concept: selecting concepts to be configured with search intents from the configuration page, wherein the concepts are the attributions of the preset search terms to the concepts of which the intention is to identify hits;
② : adding an associated concept; selecting concepts to be configured from the configuration page, wherein the concepts are attributed to the concepts of the identified hits of the preset search term;
③ : setting the number of the result strips; setting the number of the related concept query results;
④ : setting a result weight coefficient; the weight coefficient can participate in a formula to calculate a grading value of each result, the grading value affects the priority ranking of the associated concepts, the grading calculation formula is equivalent to the grading calculation of the full-text search engine, and the grading calculation formula is as follows:
score(q,d)=coord(q,d)×queryNorm(q)×∑t_in_q(tf(t_in_d)×idf(t)2×t.getBoost()×norm(t,d))
Wherein, chord is a scoring factor, queryNorm is a correction factor, (t_in_d) is word segmentation hit times, (t) is reverse document frequency, norm is a length factor;
⑤ : defining and storing an intention scene; defining and storing the intended scene, and if various association results exist after the scene is stored, continuing to add association concepts to repeat the step;
The knowledge graph ontology model is used in combination with a full-text search engine based on search configuration, and the knowledge graph ontology model is specifically as follows:
Processing the search; the method comprises the following specific steps:
① : searching by a user; submitting a search request by a user;
② : word segmentation; performing natural semantic word segmentation on search sentences requested by a user, extracting part of speech of each word segmentation result, performing word segmentation by adopting a Jieba plug-in based on Python, and extracting the part of speech;
③ : named entity and intention recognition; combining word segmentation results, using a deep learning technology to identify named entities and search intentions for search sentences requested by a user by using a trained natural semantic identification model, obtaining concepts of the entities, modifying, expanding and training by using a lexical _analysis pre-training model based on PADDLEPADDLE frames, and carrying out Chinese lexical analysis and named entity identification on trained model results;
④ : acquiring a search configuration; acquiring configured concept search configuration according to the identified intention concept;
⑤ : searching a graph data path; obtaining an associated entity result by using a graph data path algorithm according to the obtained concept configuration;
⑥ : searching the full text; according to word segmentation results of the user request search statement, using a full-text search engine to perform full-text search of text resources;
⑦ : data fusion; the method comprises the following sub-steps of data merging and fusion of a path searching result of a graph database and a full text searching result of a search engine, and then sorting of the weight reverse sequence fusion result through a weight set by a configuration system, wherein the data merging process comprises the following sub-steps:
Sub-step 1: the path result a of the graph data prioritizes the result of the full text search b;
Sub-step 2: the result a is ranked in the reverse order from the big to the small after scoring is calculated item by item;
Sub-step 3: the result a and the result b are formatted into a unified array data format;
sub-step 4: combining the array a with the array b to obtain an array c (arrc [ ] = [ arra, arrb ]);
sub-step 5: performing duplicate removal cleaning on the array c;
⑧ : outputting a result; and outputting the fusion result packaging unified interface return format to the client.
2. The semantic search method for knowledge graph in cultural domain according to claim 1, wherein the semantic search method comprises the following steps: the named entity and the intention recognition which are used by fusing the knowledge graph ontology model and the full-text search engine based on search configuration are in practical application.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111525616.7A CN114186075B (en) | 2021-12-14 | 2021-12-14 | Semantic search method for knowledge graph in cultural domain |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111525616.7A CN114186075B (en) | 2021-12-14 | 2021-12-14 | Semantic search method for knowledge graph in cultural domain |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114186075A CN114186075A (en) | 2022-03-15 |
CN114186075B true CN114186075B (en) | 2024-04-26 |
Family
ID=80543739
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111525616.7A Active CN114186075B (en) | 2021-12-14 | 2021-12-14 | Semantic search method for knowledge graph in cultural domain |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114186075B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109522465A (en) * | 2018-10-22 | 2019-03-26 | 国家电网公司 | The semantic searching method and device of knowledge based map |
JP2019074843A (en) * | 2017-10-13 | 2019-05-16 | ヤフー株式会社 | Information providing apparatus, information providing method, and program |
CN110704743A (en) * | 2019-09-30 | 2020-01-17 | 北京科技大学 | Semantic search method and device based on knowledge graph |
CN113190593A (en) * | 2021-05-12 | 2021-07-30 | 《中国学术期刊(光盘版)》电子杂志社有限公司 | Search recommendation method based on digital human knowledge graph |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170024375A1 (en) * | 2015-07-26 | 2017-01-26 | Microsoft Technology Licensing, Llc | Personal knowledge graph population from declarative user utterances |
-
2021
- 2021-12-14 CN CN202111525616.7A patent/CN114186075B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2019074843A (en) * | 2017-10-13 | 2019-05-16 | ヤフー株式会社 | Information providing apparatus, information providing method, and program |
CN109522465A (en) * | 2018-10-22 | 2019-03-26 | 国家电网公司 | The semantic searching method and device of knowledge based map |
CN110704743A (en) * | 2019-09-30 | 2020-01-17 | 北京科技大学 | Semantic search method and device based on knowledge graph |
CN113190593A (en) * | 2021-05-12 | 2021-07-30 | 《中国学术期刊(光盘版)》电子杂志社有限公司 | Search recommendation method based on digital human knowledge graph |
Non-Patent Citations (1)
Title |
---|
基于多源异构数据挖掘的"红色记忆"知识图谱构建;郭嘉欣;;知识管理论坛;20200228(01);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN114186075A (en) | 2022-03-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108763333B (en) | Social media-based event map construction method | |
CN107180045B (en) | Method for extracting geographic entity relation contained in internet text | |
CN111143479A (en) | Knowledge graph relation extraction and REST service visualization fusion method based on DBSCAN clustering algorithm | |
CN111177591B (en) | Knowledge graph-based Web data optimization method for visual requirements | |
CN106156272A (en) | A kind of information retrieval method based on multi-source semantic analysis | |
CN104408173A (en) | Method for automatically extracting kernel keyword based on B2B platform | |
CN102637192A (en) | Method for answering with natural language | |
CN110888991B (en) | Sectional type semantic annotation method under weak annotation environment | |
CN114254653A (en) | Scientific and technological project text semantic extraction and representation analysis method | |
CN113505209A (en) | Intelligent question-answering system for automobile field | |
CN112036178A (en) | Distribution network entity related semantic search method | |
CN114090861A (en) | Education field search engine construction method based on knowledge graph | |
CN112307182A (en) | Question-answering system-based pseudo-correlation feedback extended query method | |
CN114064901B (en) | Book comment text classification method based on knowledge graph word meaning disambiguation | |
CN116775812A (en) | Traditional Chinese medicine patent analysis and excavation tool based on natural voice processing | |
Anoop et al. | A topic modeling guided approach for semantic knowledge discovery in e-commerce | |
CN111597349A (en) | Rail transit standard entity relation automatic completion method based on artificial intelligence | |
CN114707516A (en) | Long text semantic similarity calculation method based on contrast learning | |
CN112417170B (en) | Relationship linking method for incomplete knowledge graph | |
Watrin et al. | An N-gram frequency database reference to handle MWE extraction in NLP applications | |
CN112084312A (en) | Intelligent customer service system constructed based on knowledge graph | |
CN107818078B (en) | Semantic association and matching method for Chinese natural language dialogue | |
CN114186075B (en) | Semantic search method for knowledge graph in cultural domain | |
CN112445887B (en) | Method and device for realizing machine reading understanding system based on retrieval | |
Xue et al. | Sentiment analysis based on weibo comments |
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 |