CN106777340A

CN106777340A - The determination method and relevant device of a kind of label

Info

Publication number: CN106777340A
Application number: CN201710026167.9A
Authority: CN
Inventors: 焦健; 周华斌
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2017-01-13
Filing date: 2017-01-13
Publication date: 2017-05-31

Abstract

The invention discloses the determination method and relevant device of a kind of label.Method in the embodiment of the present invention includes：The inquiry target of input is received, inquiry target is generated according to the first label for receiving by terminal；Inquiry is made inferences to ontology model by ontology inference machine according to inquiry target, target labels set is determined, target labels set is ontology inference machine by setting up the set that the relation of the first label and second label related to the first label is formed；Output target labels set.The embodiment of the present invention additionally provides a kind of server and a kind of terminal, in the embodiment of the present invention, the function that tag system is simply screened, inquired about is breached from semantic level, the excavation and reasoning of profound level can be carried out to the semanteme of label, so that the target labels for determining are more accurate, it is also more intelligent.

Description

The determination method and relevant device of a kind of label

Technical field

The present invention relates to field of computer technology, and in particular to the determination method and relevant device of a kind of label.

Background technology

Tag system can be used family that screening is reached by clicking on label and it is checked as a kind of mode of Content Organizing Its purpose with same label substance, the related content for making user screen product brings great convenience.

In usual method, user can jump to the details page of other similar labels by clicking on label.For example, at certain In a little shopping websites, user clicks on " SK-II facial treatment essence " label, and system background is to the key in " SK-II facial treatment essence " label Word " SK-II " is redirected, and " SK-II facial treatment essence " label can be redirected to " SK-II " label, such that it is able to see user The corresponding content of " SK-II " label.Or in a scene for specific field of play, including label " LOL ", " MOBA game ", " heroic alliance ", in these three labels between contact can be：" LOL " is a " MOBA " game；" English Male alliance " is the game of Tengxun's operation；" LOL " is " heroic alliance ".When user clicks on " LOL " label, system will be redirected To the page of " heroic alliance " label.Or, when user clicks on " MOBA " list of labels, the list of labels includes " LOL " label Content.Or, user clicks on " Tengxun's game " and can see " heroic alliance ".

In usual way, when user clicks on a label, can be recommended and the label according to the simple rule that redirects Another corresponding label, the result of label recommendations is inaccurate.

The content of the invention

The embodiment of the invention provides the determination method and relevant device of a kind of label.Depth is carried out for the semanteme to label The excavation and reasoning of level, so that the target labels for determining are more accurate, it is also more intelligent.

In a first aspect, a kind of determination method of label is the embodiment of the invention provides, including：

The inquiry target of input is received, the inquiry target is generated according to the first label for receiving by terminal；

Inquiry is made inferences to ontology model by ontology inference machine according to the inquiry target, target labels collection is determined Close, the target labels set is the ontology inference machine by setting up first label and related to first label The second label the set that is formed of relation；

Export the target labels set.

Receive the label of input；

According to label generation inquiry target；

The target labels set that server sends is obtained, the target labels set is looked into according to by the server Ask target and inquiry is made inferences to ontology model by ontology inference machine, determine target labels set, the target labels set It is the ontology inference machine by setting up the relation institute of first label and second label related to first label The set of formation.

The third aspect, the embodiment of the invention provides a kind of server, including：

Receiver module, the inquiry target for receiving input, the inquiry target is according to the first mark for receiving by terminal Sign generation；

Enquiry module, the inquiry target for being received according to the receiver module passes through ontology inference machine to body mould Type makes inferences inquiry, determines target labels set, and the target labels set is the ontology inference machine described by setting up The set that the relation of the first label and second label related to first label is formed；

Output module, for exporting the target labels set that the enquiry module determines.

Fourth aspect, the embodiment of the invention provides a kind of terminal, including：

Receiver module, the label for receiving input；

Generation module, for the label generation inquiry target received according to the receiver module；

Acquisition module, the target labels set for obtaining server transmission, the target labels set is by the clothes Business device makes inferences inquiry to ontology model according to the inquiry target by ontology inference machine, determines target labels set, institute It is the ontology inference machine by setting up first label and related to first label to state target labels set The set that the relation of two labels is formed.

In the embodiment of the present invention, the function that tag system is simply screened, inquired about will be breached from semantic level, can be right The semanteme of label carries out the excavation and reasoning of profound level, so that the target labels for determining are more accurate, it is also more intelligent.

Brief description of the drawings

Technical scheme in order to illustrate more clearly the embodiments of the present invention, below will be to that will make needed for embodiment description Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for For those skilled in the art, other accompanying drawings can also be obtained according to these accompanying drawings.

Fig. 1 is the block schematic illustration of the one embodiment for the system that the label in the embodiment of the present invention determines；

Fig. 2 is the block schematic illustration of another embodiment of the system that the label in the embodiment of the present invention determines；

Fig. 3 is a kind of schematic flow sheet of one embodiment of the determination method of the label in the embodiment of the present invention；

Fig. 4 is a kind of schematic flow sheet of another embodiment of the determination method of label in the embodiment of the present invention；

The step of Fig. 5 in the embodiment of the present invention to set up ontology model schematic diagram；

Fig. 6 is hand trip community interface schematic diagram in the embodiment of the present invention；

The step of Fig. 7 is in the embodiment of the present invention to label real-time query schematic diagram；

Fig. 8 is the schematic diagram of one embodiment of terminal display interface in the embodiment of the present invention；

Fig. 9 is a kind of structural representation of one embodiment of server in the embodiment of the present invention；

Figure 10 is a kind of structural representation of another embodiment of server in the embodiment of the present invention；

Figure 11 is a kind of structural representation of another embodiment of server in the embodiment of the present invention；

Figure 12 is a kind of structural representation of another embodiment of server in the embodiment of the present invention；

Figure 13 is a kind of structural representation of another embodiment of server in the embodiment of the present invention；

Figure 14 is a kind of structural representation of another embodiment of server in the embodiment of the present invention；

Figure 15 is a kind of structural representation of one embodiment of terminal in the embodiment of the present invention；

Figure 16 is a kind of structural representation of another embodiment of terminal in the embodiment of the present invention.

Specific embodiment

The determination method and relevant device of a kind of label are the embodiment of the invention provides, for breaching mark from semantic level Screening, the function of inquiry of simple system are signed, the excavation and reasoning of profound level can be carried out to the semanteme of label, so that really Fixed target labels are more accurate, also more intelligent.

In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention Accompanying drawing, is clearly and completely described to the technical scheme in the embodiment of the present invention, it is clear that described embodiment is only The embodiment of a part of the invention, rather than whole embodiments.Based on the embodiment in the present invention, ordinary skill people The every other embodiment that member is obtained, should all belong to the scope of protection of the invention.

Term " first ", " second ", " the 3rd " " in description and claims of this specification and above-mentioned accompanying drawing Four " etc. (if present) is for distinguishing similar object, without for describing specific order or precedence.Should manage The data that solution is so used can be exchanged in the appropriate case, so that the embodiments described herein can be with except illustrating herein Or the order beyond the content of description is implemented.Additionally, term " comprising " and " having " and their any deformation, it is intended that Covering is non-exclusive to be included, for example, the process, method, system, product or the equipment that contain series of steps or unit need not be limited In those steps or unit for clearly listing, but may include not list clearly or for these processes, method, product Product or other intrinsic steps of equipment or unit.

A kind of determination method of label is the embodiment of the invention provides, in order to make it easy to understand, first to the embodiment of the present invention In the word that is related to explain.

Body (Ontology)：Body is a kind of conceptual model of relation between knowledge description term and term.

OWL(web Ontology Lguage)：Be W3C recommend ontology description language standard, be progressively from RDF, The latest edition description language (being issued by W3C.org for 2 months 2004) that RDFS, DAML+OIL develop next, it is intended that provide more First language to support the semantic meaning representation for more enriching, and preferably support reasoning.

A kind of determination method of label provided in an embodiment of the present invention is applied to the system that a kind of label determines, incorporated by reference to figure Shown in 1, Fig. 1 is the block schematic illustration of the system, and the system includes inquiry service module 110, Ontology Modeling module 120 and body Reasoning module 130, inquiry service module 110 is communicated by Ontology Query service interface 140 with ontology inference module 130, body MBM 120 is communicated by ontology model operate interface 150 with ontology inference module 130.Wherein, inquiry service mould The function of block 110 can be performed by first terminal, and the first terminal can be：The first terminal can include smart mobile phone, Panel computer, personal digital assistant (Personal Digital Assistant, abbreviation：PDA).Inquiry service module 110 is used In the label according to input, for different application scenarios, the generation of Ontology Query sentence is carried out, generation result is pushed away for body Manage the reasoning task of module 130.Ontology inference module 130 is used to make inferences ontology model according to query statement, and will The target labels set for inquiring returns to inquiry service module 110.The mould that Ontology Modeling module 120 is safeguarded to ontology model Block, when there is new knowledge to produce or old knowledge revision when, ontology model is updated by this module.Inquiry service mould The function of block 110 and Ontology Modeling module 120 is desirably integrated into server, is performed by server, or, inquiry service mould The function of block 110 is performed by server, and the function of Ontology Modeling module 120 is performed by second terminal.

The reasoning task of ontology inference module 130 is performed by inference machine completely.The ontology inference machine increased income can be at present Pellet, FaCT++, Hermit etc., can use Hermit inference machines in the embodiment of the present invention.Hermit is used " hypertableau " is calculated, there is provided more effective inference service, can well support that OWL2 is widely used in ontology inference System, and there is provided all traditional standard inference services, it is provided includes consistency detection, concept satisfiability, classification Reasoning, succession detection, cognitive calculating, explanation etc. are serviced.Two specific application scenarios wherein in the embodiment of the present invention, respectively The categorical reasoning and cognitive estimated performance of inference machine are used.

Optionally, with reference to the system framework figure of Fig. 1, to the machine reasoning mould on the basis of the corresponding system framework figures of Fig. 1 Block is improved, and is understood incorporated by reference to Fig. 2, and Fig. 2 is the schematic diagram of another embodiment of system framework.Fig. 2 is Spark Content tab ontology inference system under cluster.Can there are a large amount of concurrent reasoning requests during concrete application, in system, Because ontology inference computation complexity is of a relatively high, in order to improve the availability of system, can be used in the embodiment of the present invention Spark cluster computings, real-time ontology inference calculating is carried out using SparkStreaming.

The working node of each of which Spark can all be responsible for a part of reasoning task, and each working node includes one Individual actuator Spark Executor and caching cache, its HDFS planted agent preserves the OWL files of ontology model.The driving of Spark Program can be allocated to the reasoning task of real-time input, give a Spark Executor, most result output at last.System Performance is improved as node increases, and the need for the scheme after improvement can better meet actual scene, future can be according to product Customer volume, the situation of enlivening realize elastic calculation, reduces cost.

In the embodiment of the present invention, can be illustrated by taking scene of game as an example, be understood incorporated by reference to Fig. 3.

Step 301, first terminal receive the first label of user input, and first label is the label for treating reasoning, for example, First label can be " heroic alliance " label.

Step 302, first terminal can be understood as this according to first label generation inquiry target, the inquiry target Body query statement, the Ontology Query sentence is used to determine the content of inquiry, for example, the content can be to inquire about to a game class The inquiry of type, or the content can also be the inquiry to the synonym of label.

Step 303, first terminal are sent to server by target is inquired about.

Step 304, server make inferences inquiry to ontology model according to first label by ontology inference machine, really Set the goal tag set, the target labels set be the ontology inference machine by set up first label and with it is described The set that the relation of the second related label of the first label is formed.

Step 305, server export the target labels set to first terminal.

In actual applications, the equipment included by the system can specifically be laid according to different application scenarios, this hair It is bright not limit, in the embodiment of the present invention, can be integrated by taking with the function of the function of ontology inference module and Ontology Modeling module Device is engaged in perform as example is illustrated.Following examples can be illustrated with server side.

A kind of determination method to label is described in detail below, refers to shown in Fig. 4, a kind of in the embodiment of the present invention One embodiment of the determination method of label includes：

In the embodiment of the present invention, the process of process and real-time query to label can be set up including ontology model.

First, the process that ontology model is set up：

Step 401, obtain knowledge information collection for setting up ontology model.

The knowledge information collection includes being associated with first label knowledge in field.For example, the field can be game Field.

Understood incorporated by reference to Fig. 5, Fig. 5 is schematic diagram the step of setting up ontology model.Ontology model is used for by OWL texts Part maintenance knowledge information collection, when there is new knowledge to produce or old knowledge revision when, ontology model is updated.Need It is bright, knowledge can be carried out by Ontology engineering teacher concluding acquisition knowledge information collection, or participle, depth can also be used The knowledge that carried out to magnanimity document of the technical intelligences such as habit is extracted to obtain knowledge information collection.

For example, illustrating knowledge information collection by taking scene of game as an example.The knowledge information integrates the information collection as field of play. There is knowledge for example in Shou You communities ontology model：During game class product use, game name, the name of game role Lexical terms in the game such as title, stage property, often play the pet name, to facilitate user to link up by user.First label can be " grandson Realize sky ".

Understood incorporated by reference to Fig. 6, Fig. 6 is that hand swims community interface schematic diagram." realizing sky " in " king's honor " game is exactly The another name of " Sun Wukong ", the knowledge information collection can be that the word produced according to user is constantly updated, for example, " grandson realizes The another name of sky " is " monkey ", and backstage is appreciated that its semantic and " Sun Wukong " and " monkey " phase by carrying out ontology inference to it Together, synonym is belonged to, when again user generates new word to " Sun Wukong ", it is " Monkey King ", " U.S. to be somebody's turn to do the another name of " Sun Wukong " Monkey King ".Continue to be updated the knowledge that the knowledge information is concentrated in backstage, that is to say, that " realize in being played for " king's honor " The synonymous word of sky " can be " realizing sky ", " monkey ", " Monkey King " and " Monkey King ".Then knowledge information collection is carried out learning To the ontology model.It is understood that after having the addition of new knowledge, inference machine can update the ontology model.Knowledge is got over Abundant ontology model, the reasoning results are more accurate, therefore enriching with knowledge base, and ontology inference machine reasoning is more accurate.

In another scene of game, the knowledge information collection of acquisition can include the knowledge shown in following 1：

Table 1

Rule	Description
		1	LOL is a MOBA game
2	Heroic alliance is the game of Tengxun's operation
		3	LOL is heroic alliance

It should be noted that, it is above-mentioned to concentrate included knowledge to be merely illustrative for knowledge information, do not cause to this The limited explanation of invention.

Step 402, formalization treatment is carried out to the knowledge information collection, the object knowledge information after being formalized.

Need to formalize knowledge after to obtaining knowledge information collection, so as to conveniently set up ontology model.With above-mentioned table 1 In knowledge as a example by, the object knowledge collection after formalization is as shown in table 2 below：

Table 2

Step 403, Ontology Modeling is carried out to the object knowledge information by ontology modeling tool obtain ontology model.

Specific method includes：The object knowledge information classify by the ontology modeling tool and obtains class pass System, and for the rule between class sets up corresponding relation on attributes, and for class sets up example relationship with object included by the class；So Afterwards, according to the class relation, relation on attributes and the example relationship carry out Ontology Modeling and obtain the ontology model.

For example, classifying to the knowledge information of field of play, class relation is it can be appreciated that each game classification is built " class " element in vertical ontology model, such as including " MOBA " class, " shooting " class, " intelligence development " class, " action " class, " risk " class, " plan Slightly " class, " experience " class.Because game taxonomic hierarchies is a relative complex system, there are certain coupling and layer between classifying more Secondary relation.Therefore also need to set up corresponding relation on attributes to the rule between class, for example, " MOBA " class belongs to " shooting " class, " risk " class and the coupling of " action " class can be " risk action " class.Then and for class sets up example with object included by the class Relation, the object that for example " shooting " class includes is " passing through live wire ", then " pass through live wire " and can be understood as such " example ", then It is example relationship that " passing through live wire " is somebody's turn to do with " shooting " class.

Ontology modeling tool Protege can be used in the embodiment of the present invention.Using inference machine to model after the completion of modeling Entirety is verified, and determines that whether model, containing contradictory rule, if the rule of noncontradictory, sets up body OWL files.

It should be noted that step 401 is to the process that step 403 is that ontology model is set up, if the ontology model has been set up Into, can not perform, and directly perform step 404.

2nd, the process of real-time query

Step 404, the inquiry target for receiving input, the inquiry target is the inquiry language generated according to the first label by terminal Sentence.

Understood incorporated by reference to Fig. 7, schematic diagram the step of Fig. 7 is to label real-time query.

The inquiry target can be inquiry type of play, or inquire about synonym.

Step 405, according to it is described inquiry target inquiry is made inferences to ontology model by ontology inference machine, determine target Tag set, the target labels set is the ontology inference machine by setting up first label and being marked with described first Sign the set that the relation of the second related label is formed；

In the first concrete implementation scene, if the inquiry target is inquiry type of play.According to first label Ontology model is made inferences by ontology inference machine, it is determined that the target labels set with the first label semantic similarity.I.e. " class " belonging to inquiry " example ", query statement can include " game name ".Ontology inference machine loads ontology model OWL files Inference machine is updated afterwards, it is necessary to add an example, and after binding rule, cognitive calculating is carried out according to query statement, can return to The affiliated type of body.By taking concrete scene as an example, it is necessary to give the trip after there is a new MOBA game " heroic alliance " restocking Game classification is stamped in play, now in Ontology Query, adds example " heroic alliance ", and itself and type " MOBA " are set up into category Property, then update inference machine state.If it is a kind of " strategy game " that ontology model has had knowledge " MOBA ", then according to Inference rule, by " cognition is calculated " inquiry " heroic alliance ", can return to its affiliated class label should also include " strategy game ".This In the second label can be " strategy game ".

In the first second example for implementing scene, gaming platform class product generally requires to divide game Class loading, and more have flexibility than single mode classification using tagged manner, more preferably meet the demand of product.In game storehouse system Game can be obtained by the way of artificial, semi- or fully automated by contents such as game introduction, information during a game of frame Type keyword, will obtain keyword in the form of a label with game bind.Game taxonomic hierarchies is one relative complex System, has certain coupling and hierarchical relationship more between classifying.And type of play keyword can be obtained well under the present invention Using in the experience of game search function.For example there are following knowledge：

Knowledge 1：" FPS " game is the another name of " first person shooting " game.

Knowledge 2：" first person shooting " game is a kind of " shooting " game.

Knowledge 3：" shooting " game is a kind of " action " game.

Knowledge 4：" third person shooting " game is a kind of " shooting " game

After a new game of storehouse system typing of playing, by taking " passing through live wire " as an example, by keyword extraction, system is given " passing through live wire " has stamped the label of " first person shooting " class game.Ontology inference machine will be " passing through live wire " this game Stamp " action ", " shooting ", " first person shooting " three labels simultaneously so that user can see from three classification respectively The game, it is ensured that the completeness of game classification.

In second concrete implementation scene, it is determined that target labels collection be combined into it is synonymous with the first label semantic similarity Word.Further, the corresponding content of the target labels set can be merged treatment, is obtained and the target labels collection Close corresponding object content.For example, synonym is inquired about, that is, inquire about " equivalence class " of " class ", query statement is directly " class name ".Push away After reason machine loading ontology model OWL files, inference machine is updated, categorical reasoning is carried out according to query statement, you can return to body Equivalence class.By taking concrete scene as an example, when user clicks on game classification " FPS " label, inference machine loading OWL files, such as Included knowledge " FPS " is " first person shooting " to fruit ontology model, then after inference machine state is updated, and is directly inquired about " FPS ", can directly obtain, all equivalence classes of FPS such as " first person shooting ", i.e., " synonym ".Further, can be by The content of the label of " first person shooting " and other synonyms merges treatment, the object content after being merged.

In second example in second concrete implementation scene, then " realizing sky " mark is clicked under " king's honor " During label, backstage is appreciated that it is semantic identical with " Sun Wukong " by carrying out ontology inference to it, belongs to synonym, therefore the page Redirect or both need to be merged with treatment when content is pulled, obtain " Sun Wukong " and " realizing sky " merges content.

It should be noted that because " synonym " of application scenarios label at this stage is inquired about and is swum in the embodiment of the present invention " type of play " of play inquires about two angles, and for convenience of description, query statement is relatively easy, but ontology inference in practical application Machine has stronger comprehension, can carry out more complicated inquiry and expand, for example, inquire about the similar game of certain money game, or follow-up Characteristic query goes out game name etc..Illustration in the embodiment of the present invention does not cause limitation of the invention explanation. Both the organizing again, redirect of the content of user's production in game community, screening function can have been met in the embodiment of the present invention, also can be Following enriching constantly with ontology model, knowledge reasoning ability is gradually become strong, and realizes more intelligent recommendation.

It is understood that this module makes inferences according to query statement to ontology model, and result set is returned to Backstage is further processed.

Step 406, the output target labels set.

In the first concrete implementation scene, the target labels collection of output is combined into " action ", " shooting ", " first person Shooting ".

In second concrete implementation scene, the target labels of output can be " realizing sky ", " Sun Wukong " and to output The corresponding object content of the target labels set.

It should be noted that being understood incorporated by reference to Fig. 8, Fig. 8 shows for one embodiment of first terminal display interface It is intended to.After first terminal receives target labels set, such as, when one classification of game of inquiry, the first label is " to pass through Live wire ", inquiry should " passing through live wire " classification when, then the target labels collection be combined into " action ", " shooting ", " first person is penetrated Hit ", that is to say, that in first terminal, no matter user clicks on which label in " action ", " shooting ", " first person shooting ", " passing through live wire " will be included.

Or, in first terminal, when user clicks on " realizing sky " label under " king's honor ", first terminal is received Object content after the corresponding content merging of the label such as " Sun Wukong ", " realizing sky ", " Monkey King ".

In the embodiment of the present invention, the present invention is innovatively applied in internet gaming community ontology, by collecting With the relational language and domain knowledge of combing field of play and rule, set up ontology model, and the content produced with user group One of stretching frame structure " tag system " is combined, and realizes producing user the knowledge reasoning of content, is finally applied to game society The aspect such as the organizing again, redirect, screening of content, intelligent recommendation of user's production in area.Label system is breached from semantic level The simple screening of system, the function of inquiry, can carry out the excavation and reasoning of profound level to the semanteme of label, so that determine Target labels are more accurate, also more intelligent.

Above to the embodiment of the present invention in a kind of determination method of label be described, refer to shown in Fig. 9, this hair Bright embodiment is described to the server 900 that a kind of determination method of label is applied, and is provided in the embodiment of the present invention One embodiment includes：

Receiver module 901, the inquiry target for receiving input, the inquiry target is according to first for receiving by terminal Label is generated.

Enquiry module 902, the inquiry target for being received according to the receiver module 901 passes through ontology inference machine pair Ontology model makes inferences inquiry, determines target labels set, and the target labels set is the ontology inference machine by building The set that the relation of vertical first label and second label related to first label is formed.

Output module 903, the target labels set for exporting the determination of the enquiry module 902.

On the basis of the corresponding embodiments of Fig. 9, please participate in shown in Figure 10, the embodiment of the invention provides server 1000 Another embodiment include：

Also include acquisition module 904, formal layout module 905 and ontology model set up module 906；

The acquisition module 904, for obtaining the knowledge information collection for setting up ontology model, the knowledge information includes With the knowledge that first label associates field；

The formal layout module 905, for carrying out form to the knowledge information collection that the acquisition module 904 is obtained Change is processed, the object knowledge information after being formalized；

The ontology model sets up module 906, for being obtained to the formal layout module 905 by ontology modeling tool The object knowledge information carry out Ontology Modeling and obtain ontology model.

On the basis of the corresponding embodiments of Figure 10, please participate in shown in Figure 11, the embodiment of the invention provides server Another embodiment includes：

The ontology model sets up module 906 and sets up unit 9061 including first, and second sets up unit 9062, and the 3rd sets up Unit 9063 and model set up unit 9064；

Described first sets up unit 9061, for being divided the object knowledge information by the ontology modeling tool Class obtains class relation；

Described second sets up unit 9062, for setting up corresponding relation on attributes for the rule between class；

Described 3rd sets up unit 9063, for setting up example relationship with object included by the class for class；

The model sets up unit 9064, the class relation for setting up the foundation of unit 9061 according to described first, institute State the second relation on attributes for setting up the foundation of unit 9062 and the described 3rd and set up the example relationship of the foundation of unit 9063 Carry out Ontology Modeling and obtain the ontology model.

On the basis of the corresponding embodiments of Fig. 9, please participate in shown in Figure 12, the embodiment of the invention provides the another of server One embodiment includes：

The enquiry module 902 includes：

First determining unit 9021, first label for being received according to the receiver module 901 determines described Target class belonging to one label；

Second determining unit 9022, for what is determined according to first determining unit 9021 by the ontology inference machine Ontology model described in the class pair makes inferences, and obtains the target labels set being associated with the target class, described Body Model includes the target labels for having class relation, relation on attributes and example relationship with the target class.

Optionally, the enquiry module 902, first label for being additionally operable to be received according to the receiver module 901 leads to Cross ontology inference machine to make inferences ontology model, it is determined that the target labels set with the first label semantic similarity.

On the basis of the corresponding embodiments of Fig. 9, please participate in shown in Figure 13, the embodiment of the invention provides the another of server One embodiment includes：

The output module 903 includes merging treatment unit 9031 and output unit 9032；

The merging treatment unit 9031, for the target labels set correspondence for determining the enquiry module 902 Content merge treatment, obtain object content corresponding with the target labels set；

Output unit 9032, it is corresponding for exporting the target labels set that the merging treatment unit 9031 obtains The object content.

Further, server in Fig. 9 to Figure 13 is presented in the form of functional module.Here " module " can be with Refer to ASIC (application-specific integrated circuit, ASIC), circuit performs one The processor and memory of individual or multiple softwares or firmware program, integrated logic circuit, and/or other can provide above-mentioned functions Device.In a simple embodiment, the server in Fig. 9 to Figure 13 can be in the form of shown in Figure 14.

Figure 14 is a kind of server architecture schematic diagram provided in an embodiment of the present invention, and the server 1400 can be because of configuration or property Can the different and larger difference of producing ratio, one or more central processing units (central processing can be included Units, CPU) 1422 (for example, one or more processors) and memory 1432, one or more storage applications The storage medium 1430 (such as one or more mass memory units) of program 1442 or data 1444.Wherein, memory 1432 and storage medium 1430 can be it is of short duration storage or persistently storage.The program stored in storage medium 1430 can include one Individual or more than one module (diagram is not marked), each module can be included to the series of instructions operation in server.More enter One step ground, central processing unit 1422 be could be arranged to be communicated with storage medium 1430, and storage medium is performed on server 1400 Series of instructions operation in 1430.

Server 1400 can also include one or more power supplys 1426, one or more wired or wireless nets Network interface 1450, one or more input/output interfaces 1458, and/or, one or more operating systems 1441, example Such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM etc..

Central processing unit (central processing units, CPU) 1422 is additionally operable to perform Fig. 3, Fig. 4, Fig. 5 correspondence Embodiment in server performed by specific method.

Refer to shown in Figure 15, the embodiment of the present invention additionally provides a kind of terminal 1500, one embodiment bag of the terminal Include：

Receiver module 1501, the label for receiving input；

Generation module 1502, for the label generation inquiry target received according to the receiver module 1501；

Acquisition module 1503, the target labels set for obtaining server transmission, the target labels set is by institute State server and inquiry is made inferences to ontology model by ontology inference machine according to the inquiry target, determine target labels collection Close, the target labels set is the ontology inference machine by setting up first label and related to first label The second label the set that is formed of relation.

Optionally, the acquisition module 1503, the shown goal set for being additionally operable to receive the server transmission is corresponding Object content, the object content will merge treatment for the server to the corresponding content of the target labels set, Obtain content corresponding with the target labels set.

Further, server in Figure 15 is presented in the form of functional module.Here " module " can refer to spy Determine application integrated circuit (application-specific integrated circuit, ASIC), circuit, perform one or The processor and memory of multiple softwares or firmware program, integrated logic circuit, and/or other can provide the device of above-mentioned functions Part.In a simple embodiment, the server in Figure 15 can be in the form of shown in Figure 16.

The embodiment of the present invention additionally provides a kind of another embodiment of terminal, as shown in figure 16, for convenience of description, only The part related to the embodiment of the present invention is shown, particular technique details is not disclosed, and refer to present invention method portion Point.The terminal can be to include that (Personal Digital Assistant, individual digital is helped for mobile phone, panel computer, PDA Reason), POS (Point of Sales, point-of-sale terminal), any terminal device such as vehicle-mounted computer, so that terminal is as mobile phone as an example：

Figure 16 is illustrated that the block diagram of the part-structure of the mobile phone related to terminal provided in an embodiment of the present invention.With reference to figure 16, mobile phone includes：Radio frequency (Radio Frequency, RF) circuit 1610, memory 1620, input block 1630, display unit 1640th, sensor 1650, voicefrequency circuit 1660, Wireless Fidelity (wireless fidelity, WiFi) module 1670, processor The part such as 1680 and power supply 1690.It will be understood by those skilled in the art that the handset structure shown in Figure 16 do not constitute it is right The restriction of mobile phone, can include part more more or less than diagram, or combine some parts, or different part cloth Put.

Each component parts of mobile phone is specifically introduced with reference to Figure 16：

RF circuits 1610 can be used to receiving and sending messages or communication process in, the reception and transmission of signal, especially, by base station After downlink information is received, processed to processor 1680；In addition, up data is activation will be designed to base station.Generally, RF circuits 1610 include but is not limited to antenna, at least one amplifier, transceiver, coupler, low-noise amplifier (Low Noise Amplifier, LNA), duplexer etc..Additionally, RF circuits 1610 can also be led to by radio communication and network and other equipment Letter.Above-mentioned radio communication can use any communication standard or agreement, including but not limited to global system for mobile communications (Global System of Mobile communication, GSM), general packet radio service (General Packet Radio Service, GPRS), CDMA (Code Division Multiple Access, CDMA), WCDMA (Wideband Code Division Multiple Access, WCDMA), Long Term Evolution (Long Term Evolution, LTE), Email, Short Message Service (Short Messaging Service, SMS) etc..

Memory 1620 can be used to store software program and module, and processor 1680 is by running storage in memory 1620 software program and module, so as to perform various function application and the data processing of mobile phone.Memory 1620 can be led To include storing program area and storage data field, wherein, storing program area can be needed for storage program area, at least one function Application program (such as sound-playing function, image player function etc.) etc.；Storage data field can store the use institute according to mobile phone Data (such as voice data, phone directory etc.) of establishment etc..Additionally, memory 1620 can be stored including high random access Device, can also include nonvolatile memory, and for example, at least one disk memory, flush memory device or other volatibility are consolidated State memory device.

Input block 1630 can be used to receive the numeral or character information of input, and produce with the user of mobile phone set with And the relevant key signals input of function control.Specifically, input block 1630 may include contact panel 1631 and other inputs Equipment 1632.Contact panel 1631, also referred to as touch-screen, can collect user thereon or neighbouring touch operation (such as user Use the behaviour of any suitable object such as finger, stylus or annex on contact panel 1631 or near contact panel 1631 Make), and corresponding attachment means are driven according to formula set in advance.Optionally, contact panel 1631 may include touch detection Two parts of device and touch controller.Wherein, touch detecting apparatus detect the touch orientation of user, and detect touch operation band The signal for coming, transmits a signal to touch controller；Touch controller receives touch information from touch detecting apparatus, and by it Contact coordinate is converted into, then gives processor 1680, and the order sent of receiving processor 1680 and can be performed.Additionally, Contact panel 1631 can be realized using polytypes such as resistance-type, condenser type, infrared ray and surface acoustic waves.Except touch surface Plate 1631, input block 1630 can also include other input equipments 1632.Specifically, other input equipments 1632 can include But it is not limited in physical keyboard, function key (such as volume control button, switch key etc.), trace ball, mouse, action bars etc. One or more.

Display unit 1640 can be used for show by user input information or be supplied to user information and mobile phone it is each Plant menu.Display unit 1640 may include display panel 1641, optionally, can use liquid crystal display (Liquid Crystal Display, LCD), the form such as Organic Light Emitting Diode (Organic Light-Emitting Diode, OLED) To configure display panel 1641.Further, contact panel 1631 can cover display panel 1641, when contact panel 1631 is detected Arrive thereon or after neighbouring touch operation, processor 1680 is sent to determine the type of touch event, with preprocessor 1680 provide corresponding visual output according to the type of touch event on display panel 1641.Although in figure 16, touch surface Plate 1631 and display panel 1641 are input and the input function that mobile phone is realized as two independent parts, but at some In embodiment, can by contact panel 1631 and display panel 1641 be integrated input that realize mobile phone and output function.

Mobile phone may also include at least one sensor 1650, such as optical sensor, motion sensor and other sensors. Specifically, optical sensor may include ambient light sensor and proximity transducer, wherein, ambient light sensor can be according to ambient light Light and shade adjust the brightness of display panel 1641, proximity transducer can close display panel when mobile phone is moved in one's ear 1641 and/or backlight.Used as one kind of motion sensor, (generally three axles) add in the detectable all directions of accelerometer sensor The size of speed, can detect that size and the direction of gravity when static, can be used to recognize application (the such as horizontal/vertical screen of mobile phone attitude Switching, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, tap) etc.；As for mobile phone also The other sensors such as configurable gyroscope, barometer, hygrometer, thermometer, infrared ray sensor, will not be repeated here.

Voicefrequency circuit 1660, loudspeaker 1661, microphone 1662 can provide the COBBAIF between user and mobile phone.Audio Electric signal after the voice data conversion that circuit 1660 will can be received, is transferred to loudspeaker 1661, is changed by loudspeaker 1661 For voice signal is exported；On the other hand, the voice signal of collection is converted to electric signal by microphone 1662, by voicefrequency circuit 1660 Voice data is converted to after reception, then after voice data output processor 1680 is processed, through RF circuits 1610 being sent to ratio Such as another mobile phone, or voice data is exported to memory 1620 so as to further treatment.

WiFi belongs to short range wireless transmission technology, and mobile phone can help user's transceiver electronicses postal by WiFi module 1670 Part, browse webpage and access streaming video etc., it has provided the user wireless broadband internet and has accessed.Although Figure 16 shows WiFi module 1670, but it is understood that, it is simultaneously not belonging to must be configured into for mobile phone, can not change as needed completely Become in the essential scope of invention and omit.

Processor 1680 is the control centre of mobile phone, using various interfaces and the various pieces of connection whole mobile phone, By running or performing software program and/or module of the storage in memory 1620, and storage is called in memory 1620 Interior data, perform the various functions and processing data of mobile phone, so as to carry out integral monitoring to mobile phone.Optionally, processor 1680 may include one or more processing units；Preferably, processor 1680 can integrated application processor and modulation /demodulation treatment Device, wherein, application processor mainly processes operating system, user interface and application program etc., and modem processor is mainly located Reason radio communication.It is understood that above-mentioned modem processor can not also be integrated into processor 1680.

Mobile phone also includes the power supply 1690 (such as battery) powered to all parts, it is preferred that power supply can be by power supply Management system is logically contiguous with processor 1680, so as to realize management charging, electric discharge and power consumption pipe by power-supply management system The functions such as reason.

Although not shown, mobile phone can also will not be repeated here including camera, bluetooth module etc..

In embodiments of the present invention, the processor 1680 included by the terminal is also with the corresponding embodiments of execution Fig. 3 Terminal performed by method.

It is apparent to those skilled in the art that, for convenience and simplicity of description, the system of foregoing description, The specific work process of device and unit, may be referred to the corresponding process in preceding method embodiment, will not be repeated here.

In several embodiments provided herein, it should be understood that disclosed system, apparatus and method can be with Realize by another way.For example, device embodiment described above is only schematical, for example, the unit Divide, only a kind of division of logic function there can be other dividing mode when actually realizing, for example multiple units or component Can combine or be desirably integrated into another system, or some features can be ignored, or do not perform.It is another, it is shown or The coupling each other for discussing or direct-coupling or communication connection can be the indirect couplings of device or unit by some interfaces Close or communicate to connect, can be electrical, mechanical or other forms.

The unit that is illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit The part for showing can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple On NE.Some or all of unit therein can be according to the actual needs selected to realize the mesh of this embodiment scheme 's.

In addition, during each functional unit in each embodiment of the invention can be integrated in a processing unit, it is also possible to It is that unit is individually physically present, it is also possible to which two or more units are integrated in a unit.Above-mentioned integrated list Unit can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.

If the integrated unit is to realize in the form of SFU software functional unit and as independent production marketing or use When, can store in a computer read/write memory medium.Based on such understanding, technical scheme is substantially The part for being contributed to prior art in other words or all or part of the technical scheme can be in the form of software products Embody, the computer software product is stored in a storage medium, including some instructions are used to so that a computer Equipment (can be personal computer, server, or network equipment etc.) performs the complete of each embodiment methods described of the invention Portion or part steps.And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey The medium of sequence code.

The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to preceding Embodiment is stated to be described in detail the present invention, it will be understood by those within the art that：It still can be to preceding State the technical scheme described in each embodiment to modify, or equivalent is carried out to which part technical characteristic；And these Modification is replaced, and does not make the spirit and scope of the essence disengaging various embodiments of the present invention technical scheme of appropriate technical solution.

Claims

1. a kind of determination method of label, it is characterised in that including：

Inquiry is made inferences to ontology model by ontology inference machine according to the inquiry target, target labels set, institute is determined It is the ontology inference machine by setting up first label and related to first label to state target labels set The set that the relation of two labels is formed；

Export the target labels set.

2. the determination method of label according to claim 1, it is characterised in that the inquiry target of the reception input it Before, methods described also includes：

The knowledge information collection for setting up ontology model is obtained, the knowledge information includes associating field with first label Knowledge；

Formalization treatment is carried out to the knowledge information collection, the object knowledge information after being formalized；

Ontology Modeling is carried out to the object knowledge information by ontology modeling tool and obtains ontology model.

3. the determination method of label according to claim 2, it is characterised in that it is described by ontology modeling tool to described Object knowledge information carries out Ontology Modeling and obtains ontology model, including：

The object knowledge information classify by the ontology modeling tool and obtains class relation；And

For the rule between class sets up corresponding relation on attributes；And

For class sets up example relationship with object included by the class；

According to the class relation, relation on attributes and the example relationship carry out Ontology Modeling and obtain the ontology model.

4. the determination method of the label according to any one of claims 1 to 3, it is characterised in that described according to the inquiry Target makes inferences inquiry to ontology model by ontology inference machine, determines target labels set, including：

Target class according to belonging to the inquiry target determines first label；

Made inferences by ontology inference machine ontology model according to the class pair, obtained and the target class phase The target labels set of association, the ontology model includes thering is class relation with the target class, and relation on attributes and example are closed The target labels of system.

5. the determination method of the label according to any one of claims 1 to 3, it is characterised in that described according to the inquiry Target makes inferences inquiry to ontology model by ontology inference machine, determines target labels set, including：

Ontology model is made inferences by ontology inference machine according to the inquiry target, it is determined that with the semantic phase of first label Near target labels set.

6. the determination method of label according to claim 5, it is characterised in that described to export the target to the terminal Tag set, including：

Treatment is merged to the corresponding content of the target labels set, target corresponding with the target labels set is obtained Content；

The corresponding object content of the target labels set is exported to the terminal.

7. a kind of determination method of label, it is characterised in that including：

Receive the label of input；

According to label generation inquiry target；

The target labels set that server sends is obtained, the target labels set is according to the inquiry mesh by the server Mark makes inferences inquiry to ontology model by ontology inference machine, determines target labels set, and the target labels set is institute State ontology inference machine and formed by setting up the relation of first label and second label related to first label Set.

8. method according to claim 7, it is characterised in that the target labels set that the acquisition server sends, bag Include：

The corresponding object content of the target labels set that the server sends is received, the object content is the service Device will merge treatment to the corresponding content of the target labels set, obtain in corresponding with the target labels set Hold.

9. a kind of server, it is characterised in that including：

Receiver module, the inquiry target for receiving input, the inquiry target is given birth to according to the first label for receiving by terminal Into；

Enquiry module, the inquiry target for being received according to the receiver module is entered by ontology inference machine to ontology model Row reasoning is inquired about, and determines target labels set, and the target labels set is the ontology inference machine by setting up described first The set that the relation of label and second label related to first label is formed；

10. server according to claim 9, it is characterised in that also including acquisition module, formal layout module and body Model building module；

The acquisition module, for obtaining for setting up the knowledge information collection of ontology model, the knowledge information include with it is described First label associates the knowledge in field；

The formal layout module, for carrying out formalization treatment to the knowledge information collection that the acquisition module is obtained, obtains Object knowledge information after to formalization；

The ontology model sets up module, for the target obtained to the formal layout module by ontology modeling tool Knowledge information carries out Ontology Modeling and obtains ontology model.

11. servers according to claim 10, it is characterised in that the ontology model is set up module and set up including first Unit, second sets up unit, and the 3rd sets up unit and model sets up unit；

Described first sets up unit, for classify obtaining class to the object knowledge information by the ontology modeling tool Relation；

Described second sets up unit, for setting up corresponding relation on attributes for the rule between class；

Described 3rd sets up unit, for setting up example relationship with object included by the class for class；

The model sets up unit, the class relation for setting up unit foundation according to described first, and described second sets up single The relation on attributes of unit's foundation and the described 3rd example relationship for setting up unit foundation carry out Ontology Modeling and obtain described Ontology model.

12. server according to any one of claim 9 to 11, it is characterised in that the enquiry module includes：

First determining unit, belonging to first label for being received according to the receiver module determines first label Target class；

Second determining unit, for the class pair determined according to first determining unit by the ontology inference machine The ontology model makes inferences, and obtains the target labels set being associated with the target class, and the ontology model includes With the target labels that the target class has class relation, relation on attributes and example relationship.

13. server according to any one of claim 9 to 11, it is characterised in that the enquiry module, is additionally operable to basis First label that the receiver module is received is made inferences by ontology inference machine to ontology model, it is determined that with described first The target labels set of label semantic similarity.

14. servers according to claim 13, it is characterised in that the output module includes merging treatment unit and defeated Go out unit；

The merging treatment unit, the corresponding content of the target labels set for the enquiry module to be determined is closed And process, obtain object content corresponding with the target labels set；

Output unit, for exporting in the corresponding target of the target labels set that the merging treatment unit is obtained Hold.

A kind of 15. terminals, it is characterised in that including：

Receiver module, the label for receiving input；

Acquisition module, the target labels set for obtaining server transmission, the target labels set is by the server Inquiry is made inferences to ontology model by ontology inference machine according to the inquiry target, target labels set, the mesh is determined Mark tag set is the ontology inference machine by setting up first label and second mark related to first label The set that the relation of label is formed.

16. terminals according to claim 15, it is characterised in that

The acquisition module, is additionally operable to receive the corresponding object content of shown goal set that the server sends, the mesh Mark content will merge treatment for the server to the corresponding content of the target labels set, obtain and the target mark Sign the corresponding content of set.