CN109255035A - Method and apparatus for constructing knowledge mapping - Google Patents
Method and apparatus for constructing knowledge mapping Download PDFInfo
- Publication number
- CN109255035A CN109255035A CN201811011403.0A CN201811011403A CN109255035A CN 109255035 A CN109255035 A CN 109255035A CN 201811011403 A CN201811011403 A CN 201811011403A CN 109255035 A CN109255035 A CN 109255035A
- Authority
- CN
- China
- Prior art keywords
- information
- identification information
- target
- video
- target identification
- 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
- 238000013507 mapping Methods 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000012512 characterization method Methods 0.000 claims abstract description 54
- 238000010276 construction Methods 0.000 claims abstract description 43
- 230000004044 response Effects 0.000 claims abstract description 33
- 208000001491 myopia Diseases 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 230000006854 communication Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- 230000005291 magnetic effect Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000005304 joining Methods 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present application discloses the method and apparatus for constructing knowledge mapping.One specific embodiment of this method includes: the selection target identification information from preset target identification information set；It executes following construction step: determining target identification information as target entity；Obtain the attribute information that the video information of target identification information characterization includes；Based on acquired attribute information, the attribute information of target entity is determined；The attribute information of target entity and target entity is added in initial knowledge map；It determines in target identification information set with the presence or absence of non-selected target identification information；It is not present in response to determination, initial knowledge map is determined as to final knowledge mapping.The embodiment helps to improve the comprehensive and flexibility of the incidence relation between characterization video information.
Description
Technical field
The invention relates to field of computer technology, and in particular to the method and apparatus for constructing knowledge mapping.
Background technique
Knowledge mapping (Knowledge Graph) is the knowledge that one kind is called semantic network (semantic network)
Library has a knowledge base of digraph structure, wherein the node on behalf entity (entity) or concept of figure
(concept), and the side of figure represents the various semantic relations between entity/concept.Knowledge mapping can be applied to various fields,
Such as the fields such as information search, information recommendation.Using knowledge mapping, available characterization and the entity associated of a certain information its
His entity, so as to accurately obtain the other information with the information association.
Summary of the invention
The embodiment of the present application proposes the method and apparatus for constructing knowledge mapping.
In a first aspect, the embodiment of the present application provides a kind of method for constructing knowledge mapping, this method comprises: from pre-
If target identification information set in, selection target identification information, wherein target identification information is for characterizing preset video letter
The target video information in library is ceased, target video information includes the attribute information for characterizing video attribute；Based on selected
Target identification information executes following construction step: determining target identification information as target entity；Obtain target identification information table
The attribute information that the video information of sign includes；Based on acquired attribute information, the attribute information of target entity is determined；By target
The attribute information of entity and target entity is added in initial knowledge map；Determine in target identification information set with the presence or absence of not by
The target identification information of selection；It is not present in response to determination, initial knowledge map is determined as to final knowledge mapping.
In some embodiments, this method further include: there are unselected in target identification information set in response to determining
Target identification information reselect target identification information from non-selected target identification information；Utilize what is reselected
Target identification information and the last initial knowledge map that entity and attribute information is added, continue to execute construction step.
In some embodiments, based on acquired attribute information, the attribute information of target entity is determined, comprising: response
In determining target identification information at least two video informations of characterization, the attribute information for including by two acquired video informations is closed
It and is new attribute information；Obtained new attribute information is determined as to the attribute information of target entity.
In some embodiments, based on acquired attribute information, the attribute information of target entity is determined, comprising: response
In determining target identification information one video information of characterization, using acquired attribute information as the attribute information of target entity.
In some embodiments, target identification information set is contained in preset identification information set；And in determination
Before whether there is non-selected target identification information in target identification information set, construction step further include: believe from mark
In breath set, select have the identification information of preset incidence relation as association identification information with target identification information；It will close
Joining identification information as associated entity associated with target entity, and by the video information of association identification information representation includes
Attribute information of the attribute information as associated entity, be added in initial knowledge map.
In some embodiments, attribute information and target identification information that the video information of association identification information representation includes
The attribute information that the video information of characterization includes matches.
In some embodiments, the video information of target identification information characterization is the video information labeled as long video, is closed
The video information of connection identification information characterization is the video information labeled as short-sighted frequency.
Second aspect, the embodiment of the present application provide a kind of for constructing the device of knowledge mapping, which includes: first
Selecting unit is configured to from preset target identification information set, selection target identification information, wherein target identification letter
For breath for characterizing the target video information in preset video information library, target video information includes for characterizing video attribute
Attribute information；Construction unit is configured to be executed following construction step based on selected target identification information: being determined target
Identification information is as target entity；Obtain the attribute information that the video information of target identification information characterization includes；Based on acquired
Attribute information, determine the attribute information of target entity；Initial knowledge is added in the attribute information of target entity and target entity
In map；It determines in target identification information set with the presence or absence of non-selected target identification information；It is not present in response to determination,
Initial knowledge map is determined as to final knowledge mapping.
In some embodiments, device further include: the second selecting unit is configured in response to determine the target mark
There are non-selected target identification informations in knowledge information aggregate reselects mesh from non-selected target identification information
Mark identification information；Utilize the target identification information reselected and the last initial knowledge figure that entity and attribute information is added
Spectrum, continues to execute construction step.
In some embodiments, construction unit includes: merging module, is configured in response to determine target identification information table
At least two video informations are levied, the attribute information that two acquired video informations include is merged into new attribute information；The
One determining module is configured to for obtained new attribute information being determined as the attribute information of target entity.
In some embodiments, construction unit includes: the second determining module, is configured in response to determine target identification letter
Breath one video information of characterization, using acquired attribute information as the attribute information of target entity.
In some embodiments, target identification information set is contained in preset identification information set；And building is single
Member includes: selecting module, is configured to from identification information set, and selection has preset incidence relation with target identification information
Identification information as association identification information；Adding module is configured to using association identification information as related to target entity
The associated entity of connection, and the attribute information for including using the video information of association identification information representation is as the attribute of associated entity
Information is added in initial knowledge map.
In some embodiments, attribute information and target identification information that the video information of association identification information representation includes
The attribute information that the video information of characterization includes matches.
In some embodiments, the video information of target identification information characterization is the video information labeled as long video, is closed
The video information of connection identification information characterization is the video information labeled as short-sighted frequency.
The third aspect, the embodiment of the present application provide a kind of server, which includes: one or more processors；
Storage device is stored thereon with one or more programs；When one or more programs are executed by one or more processors, so that
One or more processors realize the method as described in implementation any in first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer-readable medium, are stored thereon with computer program, should
The method as described in implementation any in first aspect is realized when computer program is executed by processor.
Method and apparatus provided by the embodiments of the present application for constructing knowledge mapping, by from preset identification information collection
Then selection target identification information in conjunction executes following construction step: determining that target identification information as target entity, then obtains
The attribute information that the video information of target identification information characterization includes, and based on acquired attribute information, determine target reality
The attribute information of body then the attribute information of target entity and target entity is added in initial knowledge map, in response to determination
Non-selected target identification information is not present in identification information set, initial knowledge map is determined as to final knowledge graph
Spectrum.Help to mention using the knowledge mapping of building so as to construct the knowledge mapping of the entity including characterizing video information
The comprehensive and flexibility of incidence relation between high characterization video information.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that one embodiment of the application can be applied to exemplary system architecture figure therein；
Fig. 2 is the flow chart according to one embodiment of the method for constructing knowledge mapping of the embodiment of the present application；
Fig. 3 is the schematic diagram according to an application scenarios of the method for constructing knowledge mapping of the embodiment of the present application；
Fig. 4 is the flow chart according to another embodiment of the method for constructing knowledge mapping of the embodiment of the present application；
Fig. 5 is the structural representation according to one embodiment of the device for constructing knowledge mapping of the embodiment of the present application
Figure；
Fig. 6 is adapted for the structural schematic diagram for the computer system for realizing the server of the embodiment of the present application.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can be using the embodiment of the present application for constructing the method for knowledge mapping or for constructing knowledge graph
The exemplary system architecture 100 of the device of spectrum.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 101,102,103 and be interacted by network 104 with server 105, to receive or send out
Send message etc..Various applications, such as video playback class application, web page browsing can be installed on terminal device 101,102,103
Device application, searching class application, instant messaging tools, social platform software etc..
Terminal device 101,102,103 can be hardware, be also possible to software.When terminal device 101,102,103 is hard
When part, it can be various electronic equipments, including but not limited to smart phone, tablet computer, E-book reader, MP3 player
(Moving Picture Experts Group Audio Layer III, dynamic image expert's compression standard audio level 3),
MP4 (Moving Picture Experts Group Audio Layer IV, dynamic image expert's compression standard audio level
4) player, pocket computer on knee and desktop computer etc..It, can be with when terminal device 101,102,103 is software
It is mounted in above-mentioned cited electronic equipment.Multiple softwares or software module may be implemented into (such as providing distribution in it
The software or software module of formula service), single software or software module also may be implemented into.It is not specifically limited herein.
Server 105 can be to provide the server of various services, such as to the view that terminal device 101,102,103 uploads
The background information processing server that frequency information is handled.Background information processing server can be to the identification information of video information
It carries out the processing such as analyzing with attribute information, and obtains processing result and (such as construct and know including the entity for characterizing video information
Know map).
It should be noted that for constructing the method for knowledge mapping generally by server provided by the embodiment of the present application
105 execute, and correspondingly, the device for constructing knowledge mapping is generally positioned in server 105.
It should be noted that server can be hardware, it is also possible to software.When server is hardware, may be implemented
At the distributed server cluster that multiple servers form, individual server also may be implemented into.It, can when server is software
To be implemented as multiple softwares or software module (such as providing the software of Distributed Services or software module), also may be implemented
At single software or software module.It is not specifically limited herein.
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.It is not required in the identification information and attribute information of video information
It will be in the case where long-range obtain, above system framework can not include terminal device.
With continued reference to Fig. 2, the stream of one embodiment of the method for constructing knowledge mapping according to the application is shown
Journey 200.The method for being used to construct knowledge mapping, comprising the following steps:
Step 201, from preset target identification information set, selection target identification information.
It in the present embodiment, can for constructing the executing subject (such as server shown in FIG. 1) of the method for knowledge mapping
With from preset target identification information set, in various ways (such as random selection, according to the pre-set choosing that puts in order
The modes such as select) selection target identification information.Target identification information set can be stored in advance in above-mentioned executing subject, can also be with
It is stored in advance in other electronic equipments communicated to connect with above-mentioned executing subject.In the present embodiment, target identification information is used
Target video information in the preset video information library of characterization.Target video information includes the attribute for characterizing video attribute
Information.Wherein, the form of target identification information can include but is not limited to following at least one: number, text, symbol, picture
Deng.Target video information can be the information for characterizing target video, including but not limited to following at least one information: target
Video file, the title of target video, author, classification, description information (such as profile information, evaluation information etc.), show time
Etc. information.Target video can be the view that executing subject that technical staff specifies or above-mentioned is extracted from preset video collection
Frequently.
It should be appreciated that the video of target video information characterization can be various types of videos, for example, film, TV play,
The small video etc. that user uploads.Target video information may include the video of target video information characterization, can not also include mesh
The video (such as only including the comment of the title and user of the video that video information characterizes to video) of mark video information characterization.
Attribute information can be information relevant to target video, can include but is not limited to following at least one: target
The relevant personage of target video (such as video production person, performer, director etc.) information, target video information of video information characterization
The target of the target video of characterization relevant time (such as show time, shooting time etc.) information, target video information characterization
The information such as the relevant description information of video (such as brief introduction, stage photo, poster picture etc.).
Above-mentioned video information library can be pre-set in above-mentioned executing subject, also can be set in above-mentioned executing subject
In other electronic equipments of communication connection.It should be appreciated that the quantity in video information library can be one, such as video information library can
To include the video information for characterizing the offer of certain video website；The quantity in video information library be also possible to it is multiple, such as each
Video information library includes the video information that a video website provides.
Step 202, it is based on selected target identification information, executes following construction step: determining that target identification information is made
For target entity；Obtain the attribute information that the video information of target identification information characterization includes；Based on acquired attribute information,
Determine the attribute information of target entity；The attribute information of target entity and target entity is added in initial knowledge map；It determines
It whether there is non-selected target identification information in target identification information set；It is not present in response to determination, by initial knowledge
Map is determined as final knowledge mapping.
In the present embodiment, based on the target identification information selected in step 201, above-mentioned executing subject can execute as follows
Construction step:
Step 2021, determine target identification information as target entity.
Wherein, entity is contained in knowledge mapping, for characterizing certain information (such as characterization personage, place, time, thing
The information of object etc.).In the present embodiment, entity can be the identification information of characterization video information.
Step 2022, the attribute information that the video information of target identification information characterization includes is obtained.
Specifically, above-mentioned executing subject can be from video information packet that is long-range or characterizing from local acquisition target identification information
The attribute information included.
Step 2023, based on acquired attribute information, the attribute information of target entity is determined.
Specifically, above-mentioned executing subject can determine the attribute information of target entity in various manners.For example, can be from
The attribute information of target property information (such as text information) as target entity is extracted in acquired attribute information.
In some optional implementations of the present embodiment, based on acquired attribute information, above-mentioned executing subject can
To determine the attribute information of target entity in accordance with the following steps:
Firstly, two acquired videos are believed in response to determining that target identification information characterizes at least two video informations
The attribute information that breath includes merges into new attribute information.Specifically, at least two video informations of target identification information characterization
The same or similar video can be characterized respectively.
For example, target identification information characterizes two video informations, respectively A and B.Wherein, A is for characterizing film " XXX "
Chinese dub version.The English that B is used to characterize film " XXX " dubs version.The attribute information of A includes the Chinese name of film " XXX "
Title, Introduction in Chinese, Chinese match the chained address of audio-video；The attribute information of B includes the English name of film " XXX ", English letter
It is situated between, chained address of the English with audio-video.Attribute information after then merging may include: the Chinese of film " XXX ", Chinese
Brief introduction, Chinese chained address, English name, English brief introduction, chained address of the English with audio-video with audio-video.
For another example assuming the attribute information content having the same of two video informations A and B (for example including identical letter
Jie's information), then one of them that can retain in identical content (such as retains wherein the one of two identical profile informations
Item).
Then, obtained new attribute information is determined as to the attribute information of target entity.Specifically, in knowledge mapping
In, entity can correspond to attribute information.Attribute information can be used for describing corresponding entity.In general, in knowledge mapping, it is real
The corresponding relationship of body and attribute information can indicate with the data structure of triple form, i.e., " entity-attribute-attribute value ",
Wherein, entity attributes information may include above-mentioned attribute-attribute value.For example, certain triple can be " abc123- title-
XXX ", wherein " abc123 " is the entity for characterizing film " XXX ", and " title " is an attribute, and " XXX " is attribute value.It is logical
It crosses and executes this implementation, the same or similar video can be corresponded in the entity that knowledge mapping includes, be conducive to pass through
The mode of knowledge mapping embodies the incidence relation between different videos.
In some optional implementations of the present embodiment, based on acquired attribute information, above-mentioned executing subject can
To determine the attribute information of target entity in accordance with the following steps:
In response to determining that target identification information characterizes a video information, using acquired attribute information as target entity
Attribute information.At this point, target entity characterizes a video information.
Step 2024, the attribute information of target entity and target entity is added in initial knowledge map.
Specifically, initial knowledge map can be knowledge mapping pre-establishing, not including any information, be also possible to
Knowledge mapping pre-establishing, including initial entity and initial attribute information.Also, initial entity can characterize view
Frequency information can also characterize other kinds of information, here without limitation.
Step 2025, it determines in target identification information set with the presence or absence of non-selected target identification information.
Step 2026, non-selected target identification information is not present in target identification information set in response to determining, it will
Initial knowledge map is determined as final knowledge mapping.
In some optional implementations of the present embodiment, above-mentioned executing subject can be in response to determining target identification letter
There are non-selected target identification informations in breath set, first from non-selected target identification information, reselect mesh
Mark identification information.Then known using the target identification information reselected and the last addition entity and the initial of attribute information
Know map, continues to execute above-mentioned construction step.As an example it is supposed that target identification information set include target identification information A and
Target identification information B, executing target identification information used in construction step for the first time is target identification information A, initial knowledge figure
Spectrum is C, and above-mentioned executing subject is after having executed construction step for the first time, due to joined entity and attribute information in knowledge mapping C,
Initial knowledge map C becomes initial knowledge map C ', and above-mentioned executing subject recycles target identification information B and initial knowledge map
C ' continues to execute above-mentioned construction step.
By executing above-mentioned construction step repeatedly, the video information and video that each target identification information can be characterized are believed
Incidence relation between breath is characterized by knowledge mapping.The knowledge mapping of building can be applied to video recommendations, video search etc.
Field.In these areas using building knowledge mapping, can be improved video recommendations, video search accuracy and comprehensively
Property.It, can be in order to the mutual exchange of different technical fields meanwhile using knowledge mapping.For example, certain video display comments on website and certain
Video display playback website can share the video information of other side using knowledge mapping simultaneously, make video search result, video recommendations letter
It ceases more comprehensive.
It is one of the application scenarios of the method according to the present embodiment for constructing knowledge mapping with continued reference to Fig. 3, Fig. 3
Schematic diagram.In the application scenarios of Fig. 3, target identification information set 302, target identification letter are previously stored in server 301
Breath set 302 includes target identification information A, B, C.Server 301 is based on target identification information A and corresponding attribute information D, raw
It is added in initial knowledge map 303 at the attribute information d of entity a and entity a, and by entity a and attribute information d；Based on target
Identification information B and corresponding attribute information E generates the attribute information e of entity b and entity b, and entity b and attribute information e are added
Enter in initial knowledge map 303；The attribute of entity c and entity c are generated based on target identification information C and corresponding attribute information F
Information f, and entity c and attribute information f is added in initial knowledge map 303, generate final knowledge mapping 304.
The method provided by the above embodiment of the application passes through the selection target mark letter from preset identification information set
Breath, then execute following construction step: determine target identification information as target entity, then obtain target identification information characterize
The attribute information that video information includes, and based on acquired attribute information, determine the attribute information of target entity, then will
The attribute information of target entity and target entity is added in initial knowledge map, is not present in response to determining in identification information set
Initial knowledge map is determined as final knowledge mapping by non-selected target identification information.So as to construct including
The knowledge mapping for characterizing the entity of video information is helped to improve between characterization video information using the knowledge mapping of building
The comprehensive and flexibility of incidence relation.
With further reference to Fig. 4, it illustrates the processes 400 of another embodiment of the method for constructing knowledge mapping.
This is used to construct the process 400 of the method for knowledge mapping, comprising the following steps:
Step 401, from preset target identification information set, selection target identification information.
In the present embodiment, step 401 and the step 201 in Fig. 2 corresponding embodiment are almost the same, and which is not described herein again.
In the present embodiment, selected target identification information, the execution master of the method for constructing knowledge mapping are based on
Body (such as server shown in FIG. 1) can execute construction step (i.e. step 402- step 409).
Step 402, determine target identification information as target entity.
In the present embodiment, step 402 and the step 2021 in Fig. 2 corresponding embodiment are almost the same, and which is not described herein again.
Step 403, the attribute information that the video information of target identification information characterization includes is obtained.
In the present embodiment, step 403 and the step 2022 in Fig. 2 corresponding embodiment are almost the same, and which is not described herein again.
Step 404, based on acquired attribute information, the attribute information of target entity is determined.
In the present embodiment, step 404 and the step 2023 in Fig. 2 corresponding embodiment are almost the same, and which is not described herein again.
Step 405, the attribute information of target entity and target entity is added in initial knowledge map.
In the present embodiment, step 405 and the step 2024 in Fig. 2 corresponding embodiment are almost the same, and which is not described herein again.
Step 406, from identification information set, selection with target identification information there is the mark of preset incidence relation to believe
Breath is used as association identification information.
In the present embodiment, above-mentioned executing subject can select to have with target identification information from identification information set
The identification information of preset incidence relation is as association identification information.Wherein, identification information set can be stored in advance in above-mentioned
In executing subject, it can also be stored in advance in other electronic equipments communicated to connect with above-mentioned executing subject.Identification information collection
Identification information in conjunction is used to characterize the video information in preset video information library, and video information includes for characterizing video category
The attribute information of property.Above-mentioned target identification information set may include in above-mentioned identification information set.Target identification information can
To be that in identification information set, characterization video has certain default features (such as the playing duration of the video of characterization is in
In preset range, the source of the video of characterization be preset source) identification information.Above-mentioned executing subject can be according to technology people
Member's is specified, and identification information is extracted from above-mentioned identification information set as target identification information；Or it is based on identification information table
Certain features (such as playing duration) of the video of sign, extract at least one identification information conduct from above-mentioned identification information set
Target identification information set.For example, the playing duration for extracting the video of characterization is in preset duration model from identification information set
Identification information in enclosing is as target identification information.
In the present embodiment, the incidence relation between identification information and target identification information can be by pre-set right
Relation table is answered to characterize.In mapping table, target identification information and corresponding association identification information can store,
Above-mentioned executing subject can search target identification information and corresponding association identification information from mapping table.It needs to illustrate
It is the method that the mode of the incidence relation between identification information and target identification information is not limited to mapping table that characterizes, may be used also
So that (such as passing through the data structures such as chained list) characterizes the incidence relation between identification information in other ways.
In some optional implementations of the present embodiment, the video information of target identification information characterization can be characterization
Video be long video video information, the video that the video information of association identification information representation can be characterization is short-sighted frequency
Video information.Specifically, long video can be the video that play time is more than or equal to preset time threshold；Alternatively, long video can
To be that the quantity for the picture frame for including is more than or equal to the video of preset quantity threshold value.Correspondingly, short-sighted frequency can be play time
Less than the video of preset time threshold；Alternatively, short-sighted frequency can be including the quantity of picture frame be less than preset quantity threshold value
Video.It should be appreciated that the short-sighted frequency of association identification information instruction can be and intercept from the long video that target identification information indicates
Video clip；Alternatively, the short-sighted frequency of association identification information instruction can be short-sighted frequency producer and be referred to based on target identification information
Video made by the long video shown (such as the video or target for the comment that the long video of target identification information instruction is carried out
The long video of identification information instruction delete the video of processing).
In some optional implementations of the present embodiment, attribute that the video information of association identification information representation includes
The attribute information that the video information that information is characterized with target identification information includes matches.Specifically, above-mentioned executing subject or its
His electronic equipment can in advance according to various methods determine attribute information that the video information of association identification information representation includes with
Whether the attribute information that the video information of target identification information characterization includes matches.For example, attribute information may include text envelope
Breath (such as each performer title, to description of video content etc.), above-mentioned executing subject can use existing calculating text
The method of similarity, calculates the similarity of text information, if the similarity being calculated is more than or equal to preset similarity threshold
Value, it is determined that two attribute information matchings.For another example the attribute information that video information includes may include image, image can be with
It is the truncated picture from the video that video information characterizes, is also possible to the poster image etc. of video.Above-mentioned executing subject or its
His electronic equipment (such as Histogram distance algorithm, average can be breathed out according to the algorithm of the similarity between existing determining image
Uncommon algorithm, perceptual hash algorithm etc.), the similarity of image is determined, if identified similarity is more than or equal to preset similar
Spend threshold value, it is determined that two attribute information matchings.In turn, above-mentioned executing subject or other electronic equipments can will be mutually matched
The identification information of video information belonging to attribute information is determined as with incidence relation.
Step 407, using association identification information as associated entity associated with target entity, and association identification believed
Attribute information of the attribute information that the video information of breath characterization includes as associated entity, is added in initial knowledge map.
In the present embodiment, above-mentioned executing subject can be using association identification information as association associated with target entity
Entity, and the attribute information for including using the video information of association identification information representation add as the attribute information of associated entity
Enter in initial knowledge map.In knowledge mapping, target entity and pass can be characterized by the data structure of triple form
Join the incidence relation of entity, i.e., " target entity-relationship-associated entity ".As an example it is supposed that target entity characterizes certain film
" XXX ", associated entity are used to characterize the segment of film " XXX ", and the triple for characterizing the two incidence relation can be
" abc123- segment-abc456 ", wherein " abc123 " is the entity for characterizing film " XXX ", and " abc456 " is for table
The entity of the segment of film " XXX " is levied, " segment " is used to characterize the segment that the two is complete video and intercepts from complete video
Relationship.
Step 408, it determines in target identification information set with the presence or absence of non-selected target identification information.
In the present embodiment, step 408 and the step 2025 in Fig. 2 corresponding embodiment are almost the same, and which is not described herein again.
Step 409, it is not present in response to determination, initial knowledge map is determined as to final knowledge mapping.
In the present embodiment, step 409 and the step 2026 in Fig. 2 corresponding embodiment are almost the same, and which is not described herein again.
Step 410, exist in response to determining, from non-selected target identification information, reselect target identification letter
Breath；Using the target identification information reselected and the last initial knowledge map that entity and attribute information is added, continue
Execute step 402- step 409.
In the present embodiment, above-mentioned executing subject can there are unselected in target identification information set in response to determining
Target identification information reselect target identification information first from non-selected target identification information.Then weight is utilized
The target identification information and the last initial knowledge map that entity and attribute information is added newly selected, continues to execute above-mentioned structure
Build step.As an example it is supposed that target identification information set includes target identification information A and target identification information B, execute for the first time
Target identification information used in construction step is target identification information A, and initial knowledge map is C, and above-mentioned executing subject is in head
It is secondary executed construction step after, due to joined entity and attribute information in knowledge mapping C, initial knowledge map C becomes initial
Knowledge mapping C ', above-mentioned executing subject recycle target identification information B and initial knowledge map C ', continue to execute above-mentioned building step
Suddenly (i.e. step 402- step 409).
Figure 4, it is seen that being used to construct knowledge mapping in the present embodiment compared with the corresponding embodiment of Fig. 2
The process 400 of method highlights selection association identification information corresponding with target identification information, and mesh is added to knowledge mapping
The step of marking entity and associated entity.The scheme of the present embodiment description can be further improved the view of knowledge mapping characterization as a result,
Frequency information it is comprehensive, facilitate by knowledge mapping improve video search, recommendation comprehensive and accuracy.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, this application provides one kind to know for constructing
Know one embodiment of the device of map, the Installation practice is corresponding with embodiment of the method shown in Fig. 2, which specifically may be used
To be applied in various electronic equipments.
As shown in figure 5, the present embodiment includes: first selecting unit 501, quilt for constructing the device 500 of knowledge mapping
It is configured to from preset target identification information set, selection target identification information, wherein target identification information is pre- for characterizing
If video information library in target video information, target video information includes the attribute information for characterizing video attribute；Structure
Unit 502 is built, is configured to execute following construction step based on selected target identification information: determining target identification information
As target entity；Obtain the attribute information that the video information of target identification information characterization includes；Believed based on acquired attribute
Breath, determines the attribute information of target entity；The attribute information of target entity and target entity is added in initial knowledge map；Really
It whether there is non-selected target identification information in the identification information set that sets the goal；It is not present, will initially know in response to determination
Know map and is determined as final knowledge mapping.
In the present embodiment, first selecting unit 501 can be from preset target identification information set, in various ways
(such as the modes such as random selection, sequential selection) selection target identification information.Target identification information set can be stored in advance in
In above-mentioned apparatus 500, it can also be stored in advance in other electronic equipments communicated to connect with above-mentioned apparatus 500.In this implementation
In example, target identification information is used to characterize the target video information in preset video information library, and target video information includes using
In the attribute information of characterization video attribute.Wherein, the form of identification information can include but is not limited to following at least one: number
Word, text, symbol, picture etc..Target video information can be the information for characterizing target video, including but not limited to following
At least one information: target video file, the title of target video, author, classification, description information (such as profile information, evaluation
Information etc.), the information such as show time.Target video can be technical staff specifies or above-mentioned apparatus 500 from preset video
The video extracted in set.
Attribute information can be information relevant to target video information, can include but is not limited to following at least one:
The relevant personage of target video (such as video production person, performer, director etc.) information, target video of target video information characterization
The target video of information representation relevant time (such as show time, shooting time etc.) information, target video information characterize
The information such as the relevant description information of target video (such as brief introduction, stage photo, poster picture etc.).
Above-mentioned video information library can be pre-set in above-mentioned apparatus 500, also can be set in logical with above-mentioned apparatus 500
In other electronic equipments for believing connection.It should be appreciated that the quantity in video information library can be one, such as video information library can be with
Including the video information for characterizing the offer of certain video website；The quantity in video information library is also possible to multiple, such as each view
Frequency information bank includes the video information that a video website provides.
In the present embodiment, the target identification information selected based on first selecting unit 501, above-mentioned construction unit 502 can
To execute construction step.Wherein, construction step can refer to the step 2021- step 2026 of Fig. 2 corresponding embodiment, here no longer
It repeats.
In some optional implementations of the present embodiment, device 500 can also include 503 (figure of the second selecting unit
In be not shown), be configured in response to determine in the target identification information set there are non-selected target identification information,
From non-selected target identification information, target identification information is reselected；Using the target identification information that reselects and
The initial knowledge map of entity and attribute information is added in the last time, continues to execute construction step.As an example it is supposed that target mark
Knowing information aggregate includes target identification information A and target identification information B, executes the letter of target identification used in construction step for the first time
Breath is target identification information A, and initial knowledge map is C, and above-mentioned apparatus 500 is after having executed construction step for the first time, due to knowledge
Map is that joined entity and attribute information in C, and initial knowledge map C becomes initial knowledge map C ', and above-mentioned apparatus recycles
Target identification information B and initial knowledge map C ', continues to execute above-mentioned construction step.
In some optional implementations of the present embodiment, construction unit 502 may include: merging module (in figure not
Show), it is configured in response to determine that target identification information characterizes at least two video informations, two acquired videos is believed
The attribute information that breath includes merges into new attribute information；First determining module (not shown), being configured to will be acquired
New attribute information be determined as the attribute information of target entity.
In some optional implementations of the present embodiment, construction unit 502 may include: the second determining module (figure
In be not shown), be configured in response to determine that target identification information characterizes a video information, acquired attribute information made
For the attribute information of target entity.
In some optional implementations of the present embodiment, target identification information set be may include in preset mark
In information aggregate；And construction unit 502 may include: selecting module (not shown), be configured to from identification information collection
In conjunction, select have the identification information of preset incidence relation as association identification information with target identification information；Adding module
(not shown) is configured to using association identification information as associated entity associated with target entity, and will association
Attribute information of the attribute information that the video information of identification information characterization includes as associated entity, is added initial knowledge map
In.
In some optional implementations of the present embodiment, attribute that the video information of association identification information representation includes
The attribute information that the video information that information is characterized with target identification information includes matches.
In some optional implementations of the present embodiment, the video information of target identification information characterization is labeled as length
The video information of video, the video information of association identification information representation are the video informations labeled as short-sighted frequency.
Device provided by the embodiments of the present application, by the selection target identification information from preset identification information set, so
After execute following construction step: determine target identification information as target entity, then obtain target identification information characterization video
The attribute information that information includes, and based on acquired attribute information, determine the attribute information of target entity, then by target
The attribute information of entity and target entity be added initial knowledge map in, in response to determine identification information set in there is no not by
Initial knowledge map is determined as final knowledge mapping by the target identification information of selection.So as to construct including characterization
The knowledge mapping of the entity of video information helps to improve the association between characterization video information using the knowledge mapping of building
The comprehensive and flexibility of relationship.
Below with reference to Fig. 6, it illustrates the computer systems 600 for the server for being suitable for being used to realize the embodiment of the present application
Structural schematic diagram.Server shown in Fig. 6 is only an example, should not function and use scope band to the embodiment of the present application
Carry out any restrictions.
As shown in fig. 6, computer system 600 includes central processing unit (CPU) 601, it can be read-only according to being stored in
Program in memory (ROM) 602 or be loaded into the program in random access storage device (RAM) 603 from storage section 608 and
Execute various movements appropriate and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data.
CPU 601, ROM 602 and RAM 603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to always
Line 604.
I/O interface 605 is connected to lower component: the importation 606 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 608 including hard disk etc.；
And the communications portion 609 of the network interface card including LAN card, modem etc..Communications portion 609 via such as because
The network of spy's net executes communication process.Driver 610 is also connected to I/O interface 605 as needed.Detachable media 611, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 610, in order to read from thereon
Computer program be mounted into storage section 608 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 609, and/or from detachable media
611 are mounted.When the computer program is executed by central processing unit (CPU) 601, limited in execution the present processes
Above-mentioned function.
It should be noted that computer-readable medium described herein can be computer-readable signal media or meter
Calculation machine readable medium either the two any combination.Computer-readable medium for example may be-but not limited to-
Electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.It is computer-readable
The more specific example of medium can include but is not limited to: have electrical connection, the portable computer magnetic of one or more conducting wires
Disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM or sudden strain of a muscle
Deposit), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device or above-mentioned appoint
The suitable combination of meaning.In this application, computer-readable medium can be any tangible medium for including or store program, the journey
Sequence can be commanded execution system, device or device use or in connection.And in this application, it is computer-readable
Signal media may include in a base band or as carrier wave a part propagate data-signal, wherein carrying computer can
The program code of reading.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal, optical signal or
Above-mentioned any appropriate combination.Computer-readable signal media can also be any calculating other than computer-readable medium
Machine readable medium, the computer-readable medium can be sent, propagated or transmitted for by instruction execution system, device or device
Part uses or program in connection.The program code for including on computer-readable medium can use any Jie appropriate
Matter transmission, including but not limited to: wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The calculating of the operation for executing the application can be write with one or more programming languages or combinations thereof
Machine program code, described program design language include object oriented program language-such as Java, Smalltalk, C+
+, it further include conventional procedural programming language-such as " C " language or similar programming language.Program code can
Fully to execute, partly execute on the user computer on the user computer, be executed as an independent software package,
Part executes on the remote computer or executes on a remote computer or server completely on the user computer for part.
In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network (LAN)
Or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize Internet service
Provider is connected by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit also can be set in the processor, for example, can be described as: a kind of processor packet
Include first selecting unit and construction unit.Wherein, the title of these units is not constituted to the unit itself under certain conditions
Restriction, for example, first selecting unit be also described as " from preset target identification information set, selection target mark
Know the unit of information ".
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in server described in above-described embodiment；It is also possible to individualism, and without in the supplying server.It is above-mentioned
Computer-readable medium carries one or more program, when said one or multiple programs are executed by the server,
So that the server: from preset target identification information set, selection target identification information, wherein target identification information is used
In characterizing the target video information in preset video information library, target video information includes the attribute for characterizing video attribute
Information；Based on selected target identification information, following construction step is executed: determining target identification information as target entity；
Obtain the attribute information that the video information of target identification information characterization includes；Based on acquired attribute information, target reality is determined
The attribute information of body；The attribute information of target entity and target entity is added in initial knowledge map；Determine that target identification is believed
It whether there is non-selected target identification information in breath set；It is not present in response to determination, initial knowledge map is determined as
Final knowledge mapping.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (16)
1. a kind of method for constructing knowledge mapping, comprising:
From preset target identification information set, selection target identification information, wherein target identification information is default for characterizing
Video information library in target video information, target video information includes the attribute information for characterizing video attribute；
Based on selected target identification information, following construction step is executed: determining target identification information as target entity；It obtains
The attribute information that the video information for taking target identification information to characterize includes；Based on acquired attribute information, target entity is determined
Attribute information；The attribute information of target entity and target entity is added in initial knowledge map；Determine the target identification
It whether there is non-selected target identification information in information aggregate；It is not present in response to determination, initial knowledge map is determined
For final knowledge mapping.
2. according to the method described in claim 1, wherein, the method also includes:
In response to there are non-selected target identification informations in the determination target identification information set, from non-selected mesh
It marks in identification information, reselects target identification information；It is real using the target identification information reselected and the last addition
The initial knowledge map of body and attribute information, continues to execute the construction step.
3. it is described based on acquired attribute information according to the method described in claim 1, wherein, determine the category of target entity
Property information, comprising:
In response to determining that target identification information characterizes at least two video informations, the category for including by two acquired video informations
Property information merges into new attribute information；
Obtained new attribute information is determined as to the attribute information of target entity.
4. it is described based on acquired attribute information according to the method described in claim 1, wherein, determine the category of target entity
Property information, comprising:
In response to determining that target identification information characterizes a video information, using acquired attribute information as the category of target entity
Property information.
5. method described in one of -4 according to claim 1, wherein the target identification information set is contained in preset mark
In information aggregate；And
Before whether there is non-selected target identification information in the determination target identification information set, the structure
Build step further include:
From the identification information set, select have the identification information of preset incidence relation as pass with target identification information
Join identification information；
Using association identification information as associated entity associated with target entity, and by the video of association identification information representation
Attribute information of the attribute information that information includes as associated entity is added in initial knowledge map.
6. according to the method described in claim 5, wherein, attribute information that the video information of association identification information representation includes with
The attribute information that the video information of target identification information characterization includes matches.
7. according to the method described in claim 5, wherein, the video information of target identification information characterization is labeled as long video
Video information, the video information of association identification information representation are the video informations labeled as short-sighted frequency.
8. a kind of for constructing the device of knowledge mapping, comprising:
First selecting unit is configured to from preset target identification information set, selection target identification information, wherein mesh
Mark identification information is used to characterize the target video information in preset video information library, and target video information includes for characterizing view
The attribute information of frequency attribute；
Construction unit is configured to execute following construction step based on selected target identification information: determining that target identification is believed
Breath is used as target entity；Obtain the attribute information that the video information of target identification information characterization includes；Based on acquired attribute
Information determines the attribute information of target entity；The attribute information of target entity and target entity is added in initial knowledge map；
It determines in the target identification information set with the presence or absence of non-selected target identification information；It is not present in response to determination, it will
Initial knowledge map is determined as final knowledge mapping.
9. device according to claim 8, wherein described device further include:
Second selecting unit is configured in response to determine that there are non-selected target marks in the target identification information set
Know information and reselects target identification information from non-selected target identification information；Utilize the target identification reselected
Information and the last initial knowledge map that entity and attribute information is added, continue to execute the construction step.
10. device according to claim 8, wherein the construction unit includes:
Merging module is configured in response to determine that target identification information characterizes at least two video informations, by acquired two
The attribute information that a video information includes merges into new attribute information；
First determining module is configured to for obtained new attribute information being determined as the attribute information of target entity.
11. device according to claim 8, wherein the construction unit includes:
Second determining module is configured in response to determine that target identification information characterizes a video information, by acquired category
Attribute information of the property information as target entity.
12. the device according to one of claim 8-11, wherein the target identification information set is contained in preset mark
Know in information aggregate；And
The construction unit includes:
Selecting module is configured to from the identification information set, and selection is closed with target identification information with preset association
The identification information of system is as association identification information；
Adding module is configured to using association identification information as associated entity associated with target entity, and will association
Attribute information of the attribute information that the video information of identification information characterization includes as associated entity, is added initial knowledge map
In.
13. device according to claim 12, wherein the attribute information that the video information of association identification information representation includes
The attribute information that video information with target identification information characterization includes matches.
14. device according to claim 12, wherein the video information of target identification information characterization is labeled as long video
Video information, the video information of association identification information representation is the video information labeled as short-sighted frequency.
15. a kind of server, comprising:
One or more processors；
Storage device is stored thereon with one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any in claim 1-7.
16. a kind of computer-readable medium, is stored thereon with computer program, wherein the realization when program is executed by processor
Method as described in any in claim 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811011403.0A CN109255035B (en) | 2018-08-31 | 2018-08-31 | Method and device for constructing knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811011403.0A CN109255035B (en) | 2018-08-31 | 2018-08-31 | Method and device for constructing knowledge graph |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109255035A true CN109255035A (en) | 2019-01-22 |
| CN109255035B CN109255035B (en) | 2024-03-26 |
Family
ID=65050509
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811011403.0A Active CN109255035B (en) | 2018-08-31 | 2018-08-31 | Method and device for constructing knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109255035B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110674360A (en) * | 2019-09-27 | 2020-01-10 | 厦门美亚亿安信息科技有限公司 | Method and system for constructing data association graph and tracing data |
| CN110737779A (en) * | 2019-09-18 | 2020-01-31 | 北京三快在线科技有限公司 | Knowledge graph construction method and device, storage medium and electronic equipment |
| CN113220896A (en) * | 2021-04-27 | 2021-08-06 | 北京大数医达科技有限公司 | Multi-source knowledge graph generation method and device and terminal equipment |
| CN113254668A (en) * | 2021-06-11 | 2021-08-13 | 云南大学 | Knowledge graph construction method and system based on scene latitude |
| CN113704483A (en) * | 2021-06-29 | 2021-11-26 | 中国科学院微生物研究所 | Coronavirus knowledge graph generation method and device, electronic equipment and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462507A (en) * | 2014-12-19 | 2015-03-25 | 北京奇虎科技有限公司 | Method and device for establishing knowledge graph based on movie songs |
| CN106331778A (en) * | 2015-07-06 | 2017-01-11 | 腾讯科技（深圳）有限公司 | Video recommendation method and device |
| US20170161391A1 (en) * | 2015-12-08 | 2017-06-08 | Le Holdings (Beijing) Co., Ltd. | Method and electronic device for video recommendation |
| CN107748799A (en) * | 2017-11-08 | 2018-03-02 | 四川长虹电器股份有限公司 | A kind of method of multi-data source movie data entity alignment |
| CN107783973A (en) * | 2016-08-24 | 2018-03-09 | 慧科讯业有限公司 | The methods, devices and systems being monitored based on domain knowledge spectrum data storehouse to the Internet media event |
-
2018
- 2018-08-31 CN CN201811011403.0A patent/CN109255035B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462507A (en) * | 2014-12-19 | 2015-03-25 | 北京奇虎科技有限公司 | Method and device for establishing knowledge graph based on movie songs |
| CN106331778A (en) * | 2015-07-06 | 2017-01-11 | 腾讯科技（深圳）有限公司 | Video recommendation method and device |
| US20170161391A1 (en) * | 2015-12-08 | 2017-06-08 | Le Holdings (Beijing) Co., Ltd. | Method and electronic device for video recommendation |
| CN107783973A (en) * | 2016-08-24 | 2018-03-09 | 慧科讯业有限公司 | The methods, devices and systems being monitored based on domain knowledge spectrum data storehouse to the Internet media event |
| CN107748799A (en) * | 2017-11-08 | 2018-03-02 | 四川长虹电器股份有限公司 | A kind of method of multi-data source movie data entity alignment |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110737779A (en) * | 2019-09-18 | 2020-01-31 | 北京三快在线科技有限公司 | Knowledge graph construction method and device, storage medium and electronic equipment |
| CN110737779B (en) * | 2019-09-18 | 2021-05-04 | 北京三快在线科技有限公司 | Knowledge graph construction method and device, storage medium and electronic equipment |
| CN110674360A (en) * | 2019-09-27 | 2020-01-10 | 厦门美亚亿安信息科技有限公司 | Method and system for constructing data association graph and tracing data |
| CN113220896A (en) * | 2021-04-27 | 2021-08-06 | 北京大数医达科技有限公司 | Multi-source knowledge graph generation method and device and terminal equipment |
| CN113220896B (en) * | 2021-04-27 | 2024-03-19 | 北京大数医达科技有限公司 | Multi-source knowledge graph generation method, device and terminal equipment |
| CN113254668A (en) * | 2021-06-11 | 2021-08-13 | 云南大学 | Knowledge graph construction method and system based on scene latitude |
| CN113254668B (en) * | 2021-06-11 | 2022-02-18 | 云南大学 | Knowledge graph construction method and system based on scene latitude |
| CN113704483A (en) * | 2021-06-29 | 2021-11-26 | 中国科学院微生物研究所 | Coronavirus knowledge graph generation method and device, electronic equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109255035B (en) | 2024-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7123122B2 (en) | Navigating Video Scenes Using Cognitive Insights | |
| CN109255035A (en) | Method and apparatus for constructing knowledge mapping | |
| CN109189938A (en) | Method and apparatus for updating knowledge mapping | |
| CN108153901A (en) | The information-pushing method and device of knowledge based collection of illustrative plates | |
| CN109271556A (en) | Method and apparatus for output information | |
| CN109033464A (en) | Method and apparatus for handling information | |
| WO2020042376A1 (en) | Method and apparatus for outputting information | |
| US11188543B2 (en) | Utilizing social information for recommending an application | |
| CN106919711B (en) | Method and device for labeling information based on artificial intelligence | |
| CN109862100B (en) | Method and device for pushing information | |
| US11800201B2 (en) | Method and apparatus for outputting information | |
| US20200409998A1 (en) | Method and device for outputting information | |
| CN108509611A (en) | Method and apparatus for pushed information | |
| CN110737824B (en) | Content query method and device | |
| CN110019948A (en) | Method and apparatus for output information | |
| CN111897950A (en) | Method and apparatus for generating information | |
| CN108038172B (en) | Search method and device based on artificial intelligence | |
| CN109582825A (en) | Method and apparatus for generating information | |
| CN113204691A (en) | Information display method, device, equipment and medium | |
| CN109614327A (en) | Method and apparatus for output information | |
| CN108959642A (en) | Method and apparatus for information to be written | |
| CN109241344A (en) | Method and apparatus for handling information | |
| CN112182255A (en) | Method and apparatus for storing media files and for retrieving media files | |
| CN110188113A (en) | Method, device and storage medium for comparing data by using complex expression | |
| CN107483595B (en) | Information pushing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |