CN102982076A - Multi-dimensionality content labeling method based on semanteme label database - Google Patents
Multi-dimensionality content labeling method based on semanteme label database Download PDFInfo
- Publication number
- CN102982076A CN102982076A CN 201210424525 CN201210424525A CN102982076A CN 102982076 A CN102982076 A CN 102982076A CN 201210424525 CN201210424525 CN 201210424525 CN 201210424525 A CN201210424525 A CN 201210424525A CN 102982076 A CN102982076 A CN 102982076A
- Authority
- CN
- China
- Prior art keywords
- label
- resource
- tag
- mark
- standard
- 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
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a multi-dimensionality content labeling method based on a semaneteme label database. The multi-dimensionality content labeling method based on the semaneteme label database comprises the steps of establishing the semaneteme label database, configuring extensible resource types, establishing a multi-level configurable content labeling dimensionality, dividing dimensionalities of resources according to content features to establish a multi-level content dimensionality, establishing corresponding relationship between the configurable and revisable resource types and the content labeling dimensionality, conducting resource content labeling based on the semaneteme label database, processing temporary labels, conducting resource search based on the semaneteme label database, inputting index words by a user, and conducting automatic match in the extensible database by the system. If the match is successful, the system searches corresponding images according to corresponding label labeling codes. If the match is unsuccessful, the system can match the index words with resource description information, and at the same time the system saves the index words into a temporary label database. Precision and efficiency of resource labeling are effectively improved, and good base is founded for resource search and data analysis.
Description
Technical field
The present invention relates to data mining, data analysis and knowledge reasoning field, designed and Implemented and a kind of resource content has been carried out various dimensions, semantization, structurized mask method.
Background technology
In recent years, along with the high speed development of economic society, the quantity of resource increases sharply, and the development of resource mark is relatively slow, and the search problem of resource becomes increasingly conspicuous.The resources for research mask method can effectively solve the management and retrieval problem of resource, improve the utilization rate of resource, satisfied resource in efficient, use and managerial requirement, this will be to the research and development of China's present stage intelligent dimension, rationally efficient utilization of resource played positive impetus.
At present, the resource mask method has a lot, mainly can be divided into method based on Resource Properties mark, based on the character injecting method of resource content, based on the label for labelling method of resource content with based on the semanteme marking method of the body of resource specific area.
Mainly realize by the mode for the corresponding value of attributive character mark of resource based on the method for Resource Properties mark.This mode is simple and easy to usefulness, can describe preferably the important attribute information of resource, can be used as the basic data of resource retrieval, but attribute information is the fraction of the contained information of resource only, lacks the description to the resource content semantic information; Attribute item needs to determine when system, is difficult for revising, and extendability is relatively poor; The semantic ambiguity that the simple text coupling of non-standardization causes is difficult to avoid.
Character injecting method based on resource content mainly is that generic features or the domain-specific feature of extracting resource marks resource.This mode is generally processed with computer automation, and takes full advantage of the abundant content information that resource itself comprises, and is good in domain specific application, but how to utilize the feature of resource to represent that effectively resource content becomes the problem of needing solution badly.
Label for labelling method based on resource content mainly is to mark resource with label.This mode has broken through the limitation of attribute labeling, content and the theme feature of resource have been disclosed, definition is not strict, variable, unwatched deficiency but common socialized label exists, so that the subjectivity of label for labelling is strong, polysemant and synonym cause semanteme to obscure easily, mark efficient is low, and retrieval is difficult to coincide with the word coupling of mark.
Semanteme marking method based on the body of resource specific area mainly is to carry out the resource mark by the ontology in the semantic net.The resource relationship that this mode will isolate is originally got up, and has strengthened the degree of coupling between the different resource, and resource ontology provides the formalization basis for the standardization mark, and the resource behind the mark is corresponding with domain body, can realize the intelligent retrieval of resource; But the structure of domain body is not overnight just can finish, and the category that resource relates to is very extensive, relies on body fully and carries out the general of resource and mark completely do not have at present actual operation.
Summary of the invention
The objective of the invention is to propose a kind of various dimensions content mask method of semantic-based tag library, to reach higher resource mark efficient, improve the precision of mark, for efficiently resource retrieval lays the foundation.
The concrete steps that the various dimensions content mask method of a kind of semantic-based tag library of the present invention is realized are described below:
(1) sets up the semantic label storehouse; The semantic label storehouse refers to the semantic system of label that is made of standard tag library, extension tag storehouse, interim tag library, label correlation database and label data analysis, and wherein the extension tag storehouse comprises the content of standard tag library.
Store the formal label of mark resource in the standard tag library, i.e. the standard label.Only have the standard label just to be assigned with the mark code.The standard label adopts the grouping-hierarchy management: at first press the grouping of word category division, then to the layering of every group of standard label, make up the tag set of a tree structure, and be that each standard label distributes a mark code automatically.Be the polysemant label with this label of the different representation of word, represent that with a code dissenting words this group label is the synonym set of tags.In addition, can use the mark code that the label of different language is mapped, realize the multi-language tag expansion.
Store extension tag and whole standard label in the extension tag storehouse.Extension tag refers to a series of expansion words of corresponding certain standard label, itself does not have the mark code.Extension tag and resource do not have the direct correlation relation, but have the indirect association relation by its corresponding standard label.Extension tag is bound to have incidence relation with certain or a plurality of standard label, namely can obtain one group of extension tag of its correspondence by the standard label, and vice versa.Extension tag storehouse main application comprises two aspects: during the mark resource, when the indexer inputted word, standard label corresponding to this word mated in system from the extension tag storehouse, be prompted to the indexer.During retrieve resources, when the user inputted keyword and retrieves, standard label corresponding to this word and mark code thereof were mated in system from the extension tag storehouse, and then searched the resource of this mark code correspondence.
Interim label is the interim word that does not belong to standard label and extension tag that adds of indexer in resource mark process, does not have the mark code.Because the standard tag library is improved gradually along with the work of resource mark and is expanded, so indexer or other unprofessional users are when the mark resource, the keyword that does not have in operating specification tag library and the extension tag storehouse according to actual needs (being interim label) marks resource.
The label data analysis mainly is to analyze to get the information such as the outgoing label degree of association, label temperature (comprehensive label be used to mark and retrieve frequency), with the semantic information of label abundantization more, is that resource marks and retrieval service.Can carry out data analysis from following three aspects: (1) carries out the label Co-occurrence Analysis to label that certain resource marks; Used label records and analyzes during (2) to the user search resource; (3) similar resource (method by manual setting and the automatically identification is determined) label of annotating is carried out statistical study.
The result of label correlation database stored tag data analysis, the intelligent recommendation when being used for label for labelling and retrieval.
(2) the extendible resource kind of configuration.
Wherein, resource is supported the multimedia resource kinds such as picture, audio frequency, video, and allows it is dynamically adjusted.
(3) set up multistage, configurable content mark dimension.Resource according to the content characteristic partition dimension, is set up multi-level content dimension.
Wherein, content mark dimension refers to a plurality of gradable mark dimensions, supports the mark dimension that different types of resource is corresponding different, is used for the label for labelling of resource is retrained and standard.
(4) set up the corresponding relation that configurable, revisable resource kind and content mark dimension.
(5) carry out the resource content mark of semantic-based tag library.During the mark resource, the indexer can directly choose the standard label and mark from the standard tag library, also can input index term, system automatic benchmarking draws word and mates in the extension tag storehouse: if the match is successful, then in the standard tag library, obtain standard label and mark code thereof, set up resource and the corresponding relation that marks code; If mate unsuccessfully, then index term is deposited in interim tag library and keep this word and be marked the corresponding relation of resource.System carries out intelligent recommendation according to the label correlation database in the mark process.
(6) interim tag processes.
Tag control person examines one by one to interim label, adopts two kinds of main processing modes: the one, according to the standard of standard label and extension tag, interim label directly is set as standard label or extension tag; The 2nd, directly delete this interim label.In addition, can also select existing standard label or extension tag to replace this interim label.
(7) resource retrieval of semantic-based tag library.The user inputs term, and system mates in the extension tag storehouse automatically; If the match is successful, corresponding picture is retrieved according to the label for labelling code of correspondence by system; If mate unsuccessfully, system can mate term and resource description information, and simultaneity factor deposits this term in interim tag library.
The present invention compared with prior art has following obvious advantage and beneficial effect:
At first, the present invention has proposed the various dimensions mark system of resource content on the basis of abundant resources for research content, and further the resource content dimension of refinement helps more accurate content mark and retrieves.Secondly, for fear of the impact of semantic ambiguity for the resource mark, the present invention is proposing the semantic Intelligent Support system in semantic label storehouse first aspect the resource mark: the design specifications label is supported polysemant, synonym and multilingual, extension tag effectively raises the accuracy of mark and the universality of retrieval, and the label correlation database has further been strengthened excavation and the utilization of label semantic information.Again, this method all is suitable for for all kinds of resources, support the personalization of different resource to set, the mark dimension can manage, can join, can expand, each ingredient all has good extendability in the semantic label storehouse, wherein the data analysis of label can be adopted day by day perfect data analysis technique, obtains better analytical effect.Experimental results show that the method effectively raises degree of accuracy and the efficient of resource mark, for resource retrieval and data analysis are had laid a good foundation.
Description of drawings
Fig. 1 is the various dimensions content mask method process flow diagram of semantic-based tag library;
Fig. 2 is semantic label library structure synoptic diagram;
Fig. 3 is the various dimensions content mask method structural representation of semantic-based tag library;
Fig. 4 is resource content mark process flow diagram;
Fig. 5 is the resource retrieval process flow diagram.
Embodiment
Below in conjunction with Figure of description specific embodiments of the invention are illustrated.
The present invention as the basis, carries out various dimensions, semantization, structurized mark to resource content take the semantic label storehouse, for effective retrieval and the application of resource provides safeguard.The deficiencies such as the semantic label storehouse has remedied that the subjectivity that traditional society's Focus label exists is strong, ambiguousness, dispersion are unordered, be one can manage, can expansion, the label system of structuring, semantization.
See also shown in Figure 1ly, be the various dimensions content mask method process flow diagram of semantic-based tag library.
Sequentially comprise: (1) sets up the semantic label storehouse of picture; (2) the extendible picture kind of configuration; (3) set up multistage, configurable image content mark dimension; (4) set up the corresponding relation that configurable, revisable picture kind and image content mark dimension; (5) image content of semantic-based tag library mark; (6) interim tag processes; (7) picture retrieval of semantic-based tag library.
As shown in Figure 3, the various dimensions content mask method structural representation of semantic-based tag library.
The method consists of the semantic label storehouse by standard tag library, extension tag storehouse, interim tag library, label correlation database, realizes resource mark and resource retrieval on basis, semantic label storehouse.
Below be described in detail:
(1) sets up the semantic label storehouse of picture.
Set up the semantic label storehouse of picture, as shown in Figure 2, the semantic label storehouse is made of standard tag library, extension tag storehouse, interim tag library, label correlation database and label data analytical approach.
(a) standard tag library: the standard label has comprised the semantic concept of set of tags, mark code, synonym label, polysemant label and multi-language tag.
At first according to the image content feature with labeled packet, such as set of tags such as action, particular persons, region, politics, physical culture;
Secondly also be mark code of each standard label distribution to each set of tags layering, can be divided into the one-level labels such as China, the world, city, rural area such as the set of tags region, China can be divided into the secondary labels such as east, western part, middle part etc.; The mark code can oneself be formulated the code value rule, is mark code of each standard label distribution according to rule.
In the standard tag library, be the polysemant label with this label of the different representation of word, represent that with the code dissenting words this group label is the synonym label, and can use the mark code that the label of different language is mapped, realize the support of multi-language tag." Li Na " such as the different labeled code can be athletic Li Na, also can be the Li Na that sings, and the two is the polysemant label, can be distinguished by different mark codes, parent label even set of tags; " happiness " and " happiness " of identical mark code indicates both is synonym labels.
(b) extension tag storehouse: the extension tag in the picture expanding library and picture do not have the direct correlation relation, but set up the indirect association relation by its corresponding standard label and picture.
As, the corresponding one group of extension tag of standard label " happiness " possibility comprises " happiness " " pleasure " " excitedly " " happily " etc.Extension tag is the expansion explanation of standard label, has strengthened the semantic connotation of label.
(c) interim tag library: interim label just can use after examining through tag control person.Because the standard tag library is improved gradually along with the work of picture mark and is expanded, so indexer or other unprofessional users are when the mark picture, the keyword that does not have in operating specification tag library and the extension tag storehouse according to actual needs (being interim label) marks picture.
(d) label correlation database: what deposit in the label correlation database is semantic association relation between the standard label, this incidence relation is to be drawn by the label data analysis result, the auxiliary intelligent recommendation function of improving of label correlation database improves mark and effectiveness of retrieval and quality.
(e) label data analysis: can carry out data analysis from following aspect: label that picture marks is carried out the label Co-occurrence Analysis; Used label records and analyzes during to the user search picture; Similar pictures (method by manual setting and the automatically identification is determined) label of annotating is carried out statistical study.By the incidence relation between data analysis and the excavation standard label, set up the semantic association between the label, improve picture mark and effectiveness of retrieval and quality.
(2) the extendible picture kind of configuration.
According to picture feature, picture is divided into editor's class picture and intention class picture.
(3) set up multistage, configurable image content mark dimension.
According to picture feature, picture is divided into the one-level dimensions such as attribute layer, content layer, the content layer dimension can be divided into the secondary dimensions such as personage, spot for photography; Personage's dimension can be divided into three grades of dimensions such as particular persons, sex, age; Can set up as required the multistage content dimension of picture.
(4) set up the corresponding relation that configurable, revisable picture kind and image content mark dimension.
Dispose voluntarily the corresponding relation of picture kind and dimension, can set up corresponding relation with personage, spot for photography etc. such as editor's class picture; Can revise according to actual needs the corresponding relation of safeguarding kind and dimension.
(5) image content of semantic-based tag library mark.
The picture mark is based on the various dimensions content mark process in semantic label storehouse, as shown in Figure 4, can be divided into following steps:
During the mark picture, the indexer can directly choose the standard label and mark from the standard tag library, also can input index term, system automatic benchmarking draws word and mates in the extension tag storehouse: if the match is successful, then in the standard tag library, obtain standard label and mark code thereof, set up picture and the corresponding relation that marks code; If mate unsuccessfully, then index term is deposited in interim tag library and keep this word and be marked the corresponding relation of picture.System carries out intelligent recommendation according to the label correlation database in the mark process.
(6) interim tag processes.
Interim label is examined through tag control person could formally be used for the image content mark, and the one, according to the standard of standard label and extension tag, interim label directly is set as standard label or extension tag; The 2nd, directly delete this interim label.In addition, can also select existing standard label or extension tag to replace this interim label.
(7) picture retrieval of semantic-based tag library.
Picture retrieval is based on the semantic label storehouse, and the retrieval use procedure through behind the various dimensions mark as shown in Figure 5, can be divided into following steps:
During retrieving image, the user inputs term, and system mates in the extension tag storehouse automatically: if the match is successful, then obtain the mark code of this term, system's utilization mark code intelligent recommendation and retrieving image; If mate unsuccessfully, then with term and picture description information, to mate such as keyword etc., simultaneity factor deposits this term in interim tag library;
Wherein, intelligent recommendation refers to according to the mark code, the standard label that finds all to have this mark code, the standard label with semantic association that the label expansion relation that label is related and the extension tag storehouse provides that then finding provides through the label correlation database is recommended is according to these label search pictures.
Claims (8)
1. the various dimensions content mask method of a semantic-based tag library is characterized in that, may further comprise the steps:
1.1 set up the semantic label storehouse; The semantic label storehouse is made of standard tag library, extension tag storehouse, interim tag library, label correlation database and label data analysis, and wherein the extension tag storehouse comprises the content of standard tag library;
1.2 dispose extendible resource kind;
1.3 set up multistage, configurable content mark dimension; Resource according to the content characteristic partition dimension, is set up multi-level content dimension;
1.4 set up the corresponding relation of configurable, revisable resource kind and content mark dimension;
1.5 carry out the resource content mark of semantic-based tag library; During the mark resource, directly choosing the standard label from the standard tag library marks, also can input index term, system automatic benchmarking draws word and mates in the extension tag storehouse: if the match is successful, then in the standard tag library, obtain standard label and mark code thereof, set up resource and the corresponding relation that marks code; If mate unsuccessfully, then index term is deposited in interim tag library and keep this word and be marked the corresponding relation of resource; System carries out intelligent recommendation according to the label correlation database in the mark process;
1.6 interim tag processes; Tag control person will examine interim label one by one, perhaps be set as new standard label or extension tag, perhaps with its deletion;
1.7 the resource retrieval of semantic-based tag library; The user inputs term, and system mates in the extension tag storehouse automatically: if the match is successful, corresponding picture is retrieved according to the label for labelling code of correspondence by system; If mate unsuccessfully, system can mate term and resource description information, and simultaneity factor deposits this term in interim tag library.
2. the various dimensions content mask method of a kind of semantic-based tag library according to claim 1 is characterized in that: store the formal label of mark resource in the described standard tag library, i.e. the standard label; Only have the standard label just to be assigned with the mark code; The standard label adopts the grouping-hierarchy management: at first press the grouping of word category division, then to the layering of every group of standard label, make up the tag set of a tree structure, and be that each standard label distributes a mark code automatically; Be the polysemant label with this label of the different representation of word, represent that with a code dissenting words this group label is the synonym set of tags; In addition, can use the mark code that the label of different language is mapped, realize the multi-language tag expansion.
3. the various dimensions content mask method of a kind of semantic-based tag library according to claim 1 is characterized in that: store extension tag and whole standard label in the described extension tag storehouse; Extension tag is a series of expansion words of corresponding certain standard label, itself does not have the mark code; Extension tag and resource do not have the direct correlation relation, but have the indirect association relation by its corresponding standard label; Extension tag is bound to have incidence relation with certain or a plurality of standard label, namely can obtain one group of extension tag of its correspondence by the standard label, and vice versa; The extension tag storehouse comprises two aspects: during the mark resource, when the indexer inputted word, standard label corresponding to this word mated in system from the extension tag storehouse, be prompted to the indexer; During retrieve resources, when the user inputted keyword and retrieves, standard label corresponding to this word and mark code thereof were mated in system from the extension tag storehouse, and then searched the resource of this mark code correspondence.
4. the various dimensions content mask method of a kind of semantic-based tag library according to claim 1, it is characterized in that: described interim tag library is the interim word that does not belong to standard label and extension tag that adds of indexer in resource mark process, does not have the mark code; The keyword mark resource that does not have in operating specification tag library and the extension tag storehouse according to actual needs.
5. the various dimensions content mask method of a kind of semantic-based tag library according to claim 1 is characterized in that: the result of described label correlation database stored tag data analysis, the intelligent recommendation when being used for label for labelling and retrieval.
6. the various dimensions content mask method of a kind of semantic-based tag library according to claim 1 is characterized in that: the extendible resource kind of described configuration, and support picture, audio frequency, video multimedia resource kind, and allow it is dynamically adjusted.
7. the various dimensions content mask method of a kind of semantic-based tag library according to claim 1, it is characterized in that: described multistage, the configurable content mark dimension of setting up, a plurality of gradable mark dimensions, support the mark dimension that different types of resource is corresponding different, be used for the label for labelling of resource is retrained and standard.
8. the various dimensions content mask method of a kind of semantic-based tag library according to claim 1, it is characterized in that: tag control person examines described interim label, employing is according to the standard of standard label and extension tag, interim label directly is set as standard label or extension tag, or directly deletes this interim label; Can also select existing standard label or extension tag to replace this interim label.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210424525.9A CN102982076B (en) | 2012-10-30 | 2012-10-30 | Based on the various dimensions content mask method in semantic label storehouse |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210424525.9A CN102982076B (en) | 2012-10-30 | 2012-10-30 | Based on the various dimensions content mask method in semantic label storehouse |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102982076A true CN102982076A (en) | 2013-03-20 |
| CN102982076B CN102982076B (en) | 2015-08-19 |
Family
ID=47856096
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210424525.9A Active CN102982076B (en) | 2012-10-30 | 2012-10-30 | Based on the various dimensions content mask method in semantic label storehouse |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102982076B (en) |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484328A (en) * | 2014-10-23 | 2015-04-01 | 安徽教育网络出版有限公司 | Educational resource semantic annotation method |
| CN105095288A (en) * | 2014-05-14 | 2015-11-25 | 腾讯科技（深圳）有限公司 | Data analysis method and data analysis device |
| CN105279208A (en) * | 2014-07-25 | 2016-01-27 | 北京龙源创新信息技术有限公司 | Data marking method and management system |
| CN105630835A (en) * | 2014-11-07 | 2016-06-01 | 中兴通讯股份有限公司 | Content management method and device |
| CN105701139A (en) * | 2015-11-26 | 2016-06-22 | 中国传媒大学 | Holographic video material indexing method |
| CN105787015A (en) * | 2016-02-23 | 2016-07-20 | 浪潮软件集团有限公司 | Method for querying data resources based on labels |
| CN106202292A (en) * | 2016-06-30 | 2016-12-07 | 中国电力科学研究院 | A kind of standard information based on structural data model analyzes method |
| CN106354857A (en) * | 2016-09-06 | 2017-01-25 | 中国传媒大学 | News tag management system |
| CN106528633A (en) * | 2016-10-11 | 2017-03-22 | 杭州电子科技大学 | Method for improving social attention of video based on keyword recommendation |
| CN106919695A (en) * | 2017-03-07 | 2017-07-04 | 维沃移动通信有限公司 | A kind of information recommendation method and terminal |
| CN106919711A (en) * | 2017-03-13 | 2017-07-04 | 北京百度网讯科技有限公司 | The method and apparatus of the markup information based on artificial intelligence |
| CN107330069A (en) * | 2017-06-30 | 2017-11-07 | 北京金山安全软件有限公司 | Multimedia data processing method and device, server and storage medium |
| CN107347163A (en) * | 2017-06-13 | 2017-11-14 | 中国传媒大学 | A kind of TV play content characteristic obtains system and tag library |
| CN107368529A (en) * | 2017-06-13 | 2017-11-21 | 中国传媒大学 | Documentary film data content feature obtains system and tag library |
| CN107404671A (en) * | 2017-06-13 | 2017-11-28 | 中国传媒大学 | Movie contents feature obtains system and application system |
| CN107491479A (en) * | 2017-07-05 | 2017-12-19 | 上海大学 | A kind of label management method based on ontology library |
| CN107992513A (en) * | 2017-10-25 | 2018-05-04 | 中兴通讯股份有限公司 | A kind of information processing system and its method for realizing information processing |
| CN108205590A (en) * | 2017-12-29 | 2018-06-26 | 北京奇元科技有限公司 | A kind of method and device for establishing point of interest network level topological diagram |
| CN108255907A (en) * | 2017-06-30 | 2018-07-06 | 勤智数码科技股份有限公司 | A kind of catalogue generation method, system and the management method based on the catalogue generation method |
| CN108491774A (en) * | 2018-03-12 | 2018-09-04 | 北京地平线机器人技术研发有限公司 | The method and apparatus that multiple targets in video are marked into line trace |
| CN108563642A (en) * | 2018-03-20 | 2018-09-21 | 孙跃 | A kind of Chinese knot-type cultural spreading overseas trade method and system |
| CN109522424A (en) * | 2018-10-16 | 2019-03-26 | 北京达佳互联信息技术有限公司 | Processing method, device, electronic equipment and the storage medium of data |
| CN109816047A (en) * | 2019-02-19 | 2019-05-28 | 北京达佳互联信息技术有限公司 | Method, apparatus, equipment and the readable storage medium storing program for executing of label are provided |
| CN110110224A (en) * | 2019-04-16 | 2019-08-09 | 中科金联（北京）科技有限公司 | A kind of data migration method and system based on the multiple label of data |
| CN110457155A (en) * | 2019-07-31 | 2019-11-15 | 清华大学 | A kind of modification method, device and the electronic equipment of sample class label |
| CN110489649A (en) * | 2019-08-19 | 2019-11-22 | 北京创鑫旅程网络技术有限公司 | The method and device of label association content |
| CN111680219A (en) * | 2020-06-09 | 2020-09-18 | 腾讯科技（深圳）有限公司 | Content recommendation method, device, equipment and readable storage medium |
| CN113312493A (en) * | 2021-05-25 | 2021-08-27 | 珠海沃德尔软件科技有限公司 | Label dictionary generating system and method |
| CN115600577A (en) * | 2022-10-21 | 2023-01-13 | 文灵科技（北京）有限公司（Cn） | Event segmentation method and system for news manuscript labeling |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102073692B (en) * | 2010-12-16 | 2016-04-27 | 北京农业信息技术研究中心 | Based on the semantic retrieval system and method for agriculture field ontology library |
| CN102521242A (en) * | 2011-11-14 | 2012-06-27 | 江苏联著实业有限公司 | Automatic classification system based on OWL (Ontology of Web Language) ontology analysis |
| CN102622453A (en) * | 2012-04-20 | 2012-08-01 | 北京邮电大学 | Body-based food security event semantic retrieval system |
-
2012
- 2012-10-30 CN CN201210424525.9A patent/CN102982076B/en active Active
Cited By (42)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095288A (en) * | 2014-05-14 | 2015-11-25 | 腾讯科技（深圳）有限公司 | Data analysis method and data analysis device |
| CN105095288B (en) * | 2014-05-14 | 2020-02-07 | 腾讯科技（深圳）有限公司 | Data analysis method and data analysis device |
| CN105279208A (en) * | 2014-07-25 | 2016-01-27 | 北京龙源创新信息技术有限公司 | Data marking method and management system |
| CN104484328A (en) * | 2014-10-23 | 2015-04-01 | 安徽教育网络出版有限公司 | Educational resource semantic annotation method |
| CN105630835A (en) * | 2014-11-07 | 2016-06-01 | 中兴通讯股份有限公司 | Content management method and device |
| CN105701139A (en) * | 2015-11-26 | 2016-06-22 | 中国传媒大学 | Holographic video material indexing method |
| CN105787015A (en) * | 2016-02-23 | 2016-07-20 | 浪潮软件集团有限公司 | Method for querying data resources based on labels |
| CN106202292A (en) * | 2016-06-30 | 2016-12-07 | 中国电力科学研究院 | A kind of standard information based on structural data model analyzes method |
| CN106202292B (en) * | 2016-06-30 | 2022-03-18 | 中国电力科学研究院 | Standard information analysis method based on structured data model |
| CN106354857A (en) * | 2016-09-06 | 2017-01-25 | 中国传媒大学 | News tag management system |
| CN106528633A (en) * | 2016-10-11 | 2017-03-22 | 杭州电子科技大学 | Method for improving social attention of video based on keyword recommendation |
| CN106528633B (en) * | 2016-10-11 | 2019-07-02 | 杭州电子科技大学 | A kind of video society attention rate improvement method recommended based on keyword |
| CN106919695A (en) * | 2017-03-07 | 2017-07-04 | 维沃移动通信有限公司 | A kind of information recommendation method and terminal |
| CN106919711A (en) * | 2017-03-13 | 2017-07-04 | 北京百度网讯科技有限公司 | The method and apparatus of the markup information based on artificial intelligence |
| CN107347163A (en) * | 2017-06-13 | 2017-11-14 | 中国传媒大学 | A kind of TV play content characteristic obtains system and tag library |
| CN107404671A (en) * | 2017-06-13 | 2017-11-28 | 中国传媒大学 | Movie contents feature obtains system and application system |
| CN107368529A (en) * | 2017-06-13 | 2017-11-21 | 中国传媒大学 | Documentary film data content feature obtains system and tag library |
| CN108255907A (en) * | 2017-06-30 | 2018-07-06 | 勤智数码科技股份有限公司 | A kind of catalogue generation method, system and the management method based on the catalogue generation method |
| CN107330069B (en) * | 2017-06-30 | 2020-10-23 | 北京金山安全软件有限公司 | Multimedia data processing method and device, server and storage medium |
| CN107330069A (en) * | 2017-06-30 | 2017-11-07 | 北京金山安全软件有限公司 | Multimedia data processing method and device, server and storage medium |
| CN107491479A (en) * | 2017-07-05 | 2017-12-19 | 上海大学 | A kind of label management method based on ontology library |
| CN107992513A (en) * | 2017-10-25 | 2018-05-04 | 中兴通讯股份有限公司 | A kind of information processing system and its method for realizing information processing |
| CN107992513B (en) * | 2017-10-25 | 2021-07-13 | 中兴通讯股份有限公司 | Information processing system and method for realizing information processing |
| WO2019080910A1 (en) * | 2017-10-25 | 2019-05-02 | 中兴通讯股份有限公司 | Information processing system and method thereof for implementing information processing |
| CN108205590A (en) * | 2017-12-29 | 2018-06-26 | 北京奇元科技有限公司 | A kind of method and device for establishing point of interest network level topological diagram |
| CN108205590B (en) * | 2017-12-29 | 2022-01-28 | 北京奇元科技有限公司 | Method and device for establishing network level topological graph of interest points |
| CN108491774B (en) * | 2018-03-12 | 2020-06-26 | 北京地平线机器人技术研发有限公司 | Method and device for tracking and labeling multiple targets in video |
| CN108491774A (en) * | 2018-03-12 | 2018-09-04 | 北京地平线机器人技术研发有限公司 | The method and apparatus that multiple targets in video are marked into line trace |
| CN108563642A (en) * | 2018-03-20 | 2018-09-21 | 孙跃 | A kind of Chinese knot-type cultural spreading overseas trade method and system |
| CN109522424A (en) * | 2018-10-16 | 2019-03-26 | 北京达佳互联信息技术有限公司 | Processing method, device, electronic equipment and the storage medium of data |
| CN109522424B (en) * | 2018-10-16 | 2020-04-24 | 北京达佳互联信息技术有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN109816047A (en) * | 2019-02-19 | 2019-05-28 | 北京达佳互联信息技术有限公司 | Method, apparatus, equipment and the readable storage medium storing program for executing of label are provided |
| CN109816047B (en) * | 2019-02-19 | 2022-05-24 | 北京达佳互联信息技术有限公司 | Method, device and equipment for providing label and readable storage medium |
| CN110110224A (en) * | 2019-04-16 | 2019-08-09 | 中科金联（北京）科技有限公司 | A kind of data migration method and system based on the multiple label of data |
| CN110457155B (en) * | 2019-07-31 | 2020-09-11 | 清华大学 | Sample class label correction method and device and electronic equipment |
| CN110457155A (en) * | 2019-07-31 | 2019-11-15 | 清华大学 | A kind of modification method, device and the electronic equipment of sample class label |
| CN110489649A (en) * | 2019-08-19 | 2019-11-22 | 北京创鑫旅程网络技术有限公司 | The method and device of label association content |
| CN110489649B (en) * | 2019-08-19 | 2023-06-27 | 北京创鑫旅程网络技术有限公司 | Method and device for associating content with tag |
| CN111680219A (en) * | 2020-06-09 | 2020-09-18 | 腾讯科技（深圳）有限公司 | Content recommendation method, device, equipment and readable storage medium |
| CN111680219B (en) * | 2020-06-09 | 2023-10-20 | 深圳市雅阅科技有限公司 | Content recommendation method, device, equipment and readable storage medium |
| CN113312493A (en) * | 2021-05-25 | 2021-08-27 | 珠海沃德尔软件科技有限公司 | Label dictionary generating system and method |
| CN115600577A (en) * | 2022-10-21 | 2023-01-13 | 文灵科技（北京）有限公司（Cn） | Event segmentation method and system for news manuscript labeling |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102982076B (en) | 2015-08-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102982076A (en) | Multi-dimensionality content labeling method based on semanteme label database | |
| CN109492077B (en) | Knowledge graph-based petrochemical field question-answering method and system | |
| CN109710701B (en) | Automatic construction method for big data knowledge graph in public safety field | |
| CN107609052B (en) | A kind of generation method and device of the domain knowledge map based on semantic triangle | |
| CN104239513B (en) | A kind of semantic retrieving method of domain-oriented data | |
| CN108959431A (en) | Label automatic generation method, system, computer readable storage medium and equipment | |
| CN104021198B (en) | The relational database information search method and device indexed based on Ontology | |
| CN104281702B (en) | Data retrieval method and device based on electric power critical word participle | |
| CN110298033A (en) | Keyword corpus labeling trains extracting tool | |
| CN101593200A (en) | Chinese Web page classification method based on the keyword frequency analysis | |
| CN104794242A (en) | Searching methods | |
| CN105718585B (en) | Document and label word justice correlating method and its device | |
| CN113190687B (en) | Knowledge graph determining method and device, computer equipment and storage medium | |
| CN106547893A (en) | A kind of photo sort management system and photo sort management method | |
| Remi et al. | Domain ontology driven fuzzy semantic information retrieval | |
| CN102819600B (en) | Keyword search methodology towards relational database of power production management system | |
| CN103761286B (en) | A kind of Service Source search method based on user interest | |
| CN101957860B (en) | Method and device for releasing and searching information | |
| CN103914486B (en) | Document search and display system | |
| Wang et al. | Probabilistic declarative information extraction | |
| CN106503246A (en) | Method for establishing ancient book intelligent digital document library | |
| Wang et al. | Seeft: Planned social event discovery and attribute extraction by fusing twitter and web content | |
| CN107391690B (en) | Method for processing document information | |
| CN103365960A (en) | Off-line searching method of structured data of electric power multistage dispatching management | |
| Wang et al. | Semi-supervised chinese open entity relation extraction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |