CN109635074A - A kind of entity relationship analysis method and terminal device based on public feelings information - Google Patents
A kind of entity relationship analysis method and terminal device based on public feelings information Download PDFInfo
- Publication number
- CN109635074A CN109635074A CN201811343920.8A CN201811343920A CN109635074A CN 109635074 A CN109635074 A CN 109635074A CN 201811343920 A CN201811343920 A CN 201811343920A CN 109635074 A CN109635074 A CN 109635074A
- Authority
- CN
- China
- Prior art keywords
- entity
- entity relationship
- network
- node
- merging
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 17
- 239000000284 extract Substances 0.000 claims abstract description 7
- 238000004590 computer program Methods 0.000 claims description 16
- 238000010586 diagram Methods 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 9
- 239000000203 mixture Substances 0.000 claims 1
- 238000010921 in-depth analysis Methods 0.000 abstract description 15
- 238000012216 screening Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000000536 complexating effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000003012 network analysis Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007596 consolidation process Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of entity relationship analysis method and terminal device based on public feelings information, suitable for technical field of data processing, this method comprises: being analyzed respectively a plurality of public feelings information got, multiple initial entity relationship networks corresponding with public feelings information are obtained, record has the entity relationship between multiple entity nodes and multiple entity node in entity relationship network；Extract the common node for including in entity relationship network, wherein common node is the entity node being at least while present in two entity relationship networks；Based on common node between processing is merged entity relationship network, common node, the entity relationship network after being merged are not included in obtained entity relationship network until merging.The embodiment of the present invention adequately achieves the in-depth analysis for all entity relationships that may relate to entity, realizes and carries out in-depth analysis tracking to entity relationship network.
Description
Technical field
The invention belongs to technical field of data processing, more particularly to entity relationship analysis method and end based on public feelings information
End equipment.
Background technique
Public sentiment system can provide the query function of entity relationship, the entity that user inquires needed for only needing to input for user
Title, the entity relationship that the public feelings information that public sentiment system can provide channel source carry out entity to be checked is analyzed, and output pair
The entity relationship analysis result answered.Wherein, entity refers to people, place and mechanism in public feelings information etc., and entity relationship refers to this
Relationship between people, place and mechanism a bit, if Zhang San is the wife of Li Si, Beijing is the capital etc. of China.
In actual conditions, existing public sentiment system is only able to achieve to the entity relationship analysis in single public feelings information, but by
It is extremely limited in the information content that single public feelings information can be provided, and the confidence level of single public feelings information also tends to be difficult to obtain very
Therefore good guarantee often can only obtain the relational network between limited several entities according only to the analysis of single public feelings information,
It is shallower to the depth of relational network analysis tracking between entity and entity, and obtained entity relationship network confidence level is relatively low,
It is unable to satisfy the increasingly increased actual demand of user.
Summary of the invention
In view of this, the entity relationship analysis method and terminal that the embodiment of the invention provides a kind of based on public feelings information are set
It is standby, in-depth analysis tracking is carried out to entity relationship network to solve the problems, such as that public sentiment system cannot achieve in the prior art.
The first aspect of the embodiment of the present invention provides a kind of entity relationship analysis method based on public feelings information, comprising:
The a plurality of public feelings information got is analyzed respectively, is obtained corresponding with the public feelings information multiple initial
Entity relationship network, record has the entity between multiple entity nodes and multiple entity node in the entity relationship network
Relationship；
Extract the common node for including in the entity relationship network, wherein common node is at least while to be present in two
Entity node in a entity relationship network；
Processing is merged between the entity relationship network based on the common node, is closed until merging obtained entity
It is not include common node, the entity relationship network after being merged in network.
The second aspect of the embodiment of the present invention provides a kind of terminal device, and the terminal device includes memory, processing
Device, the computer program that can be run on the processor is stored on the memory, and the processor executes the calculating
Following steps are realized when machine program.
The a plurality of public feelings information got is analyzed respectively, is obtained corresponding with the public feelings information multiple initial
Entity relationship network, record has the entity between multiple entity nodes and multiple entity node in the entity relationship network
Relationship；
Extract the common node for including in the entity relationship network, wherein common node is at least while to be present in two
Entity node in a entity relationship network；
Processing is merged between the entity relationship network based on the common node, is closed until merging obtained entity
It is not include common node, the entity relationship network after being merged in network.
The third aspect of the embodiment of the present invention provides a kind of entity relationship analytical equipment based on public feelings information, comprising:
Nework analysis module obtains believing with the public sentiment for analyzing a plurality of public feelings information got respectively
Cease corresponding multiple initial entity relationship networks, record there are multiple entity nodes and multiple in the entity relationship network
Entity relationship between entity node；
Node extraction module, for extracting the common node for including in the entity relationship network, wherein common node is
The entity node being at least while present in two entity relationship networks；
Network merging module, for merging processing to the entity relationship network based on the common node, directly
Common node is not included in obtained entity relationship network to merging, the entity relationship network after being merged.
The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, comprising: is stored with computer
Program, which is characterized in that realize when the computer program is executed by processor as described above based on the entity of public feelings information
The step of relationship analysis method.
Existing beneficial effect is the embodiment of the present invention compared with prior art: the embodiment of the present invention passes through to each public sentiment
The simple entity relationship network that information analysis obtains carries out the extraction of common node, and according to these common nodes that these are simple
Single entity relationship network merges, and until all not including common node between all entity relationship networks, i.e., will
Until all entity relationship network depth maximize, just terminates the analysis to entity relationship network and merge, adequately achieve to reality
The in-depth analysis for all entity relationships that body may relate to realizes and carries out in-depth analysis tracking to entity relationship network.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is the implementation process signal for the entity relationship analysis method based on public feelings information that the embodiment of the present invention one provides
Figure；
Fig. 2 is the implementation process signal of the entity relationship analysis method provided by Embodiment 2 of the present invention based on public feelings information
Figure；
Fig. 3 is the implementation process signal for the entity relationship analysis method based on public feelings information that the embodiment of the present invention three provides
Figure；
Fig. 4 is the implementation process signal for the entity relationship analysis method based on public feelings information that the embodiment of the present invention four provides
Figure；
Fig. 5 is the implementation process signal for the entity relationship analysis method based on public feelings information that the embodiment of the present invention five provides
Figure；
Fig. 6 is the implementation process signal for the entity relationship analysis method based on public feelings information that the embodiment of the present invention six provides
Figure；
Fig. 7 is the structural schematic diagram for the entity relationship analytical equipment based on public feelings information that the embodiment of the present invention seven provides；
Fig. 8 is the schematic diagram for the terminal device that the embodiment of the present invention eight provides.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
In order to make it easy to understand, be first briefly described to the embodiment of the present invention herein: the prior art is carrying out public feelings information
In entity relationship analysis when, be all directly to be handled using some existing natural language analysis algorithms, due to existing
Natural language analysis algorithm single article content can only be all analyzed and processed so that being only able to achieve in the prior art
Entity relationship analysis to single public feelings information, and then result in the progress that cannot achieve in the prior art to entity relationship network
Analyse in depth tracking.
In view of analysing whether that enough deeply most intuitive standard is exactly the entity relationship network to entity relationship network
In include all entities, if all can not set up entity relationship with the entity in other entity relationship networks, i.e. the entity
Relational network and other entity relationship networks do not have any public entity node, for example, it is assumed that shared entity relationship network A
With two entity relationship networks of entity relationship network B, wherein in entity relationship network A comprising personage a, personage b, personage c and
Character relation between personage d is closed comprising the personage between personage d, personage e, personage f and personage g in entity relationship network B
System illustrates that the two can also be by personage d and its at this time due to all including common node personage d in two entity relationship networks
Existing relationship further merges into a network between his entity, therefore, illustrates two entity relationship networks point at this time
That analyses is not deep enough, and if assuming only to close comprising the personage between personage e, personage f and personage g in entity relationship network B
System, at this point, due between two entity relationship networks and not having common node, it can not be by entity node by two realities
Body relational network connects, that is, illustrates that two entity relationship networks have been accomplished to go deep into all entity relationships being related to
Analysis, realizes and carries out in-depth analysis tracking to entity relationship network.
Therefore, in order to realize the in-depth analysis to entity relationship network, the embodiment of the present invention on the basis of existing technology,
The simple entity relationship network that can be also analyzed based on single public feelings information carries out common node extraction, and further ground
The merging of entity relationship network is carried out in these common nodes, until not including between finally obtained entity relationship network
Until any common node, in-depth analysis tracking is carried out to entity relationship network to realize, details are as follows:
Fig. 1 shows the implementation process of the entity relationship analysis method based on public feelings information of the offer of the embodiment of the present invention one
Figure, details are as follows:
S101 analyzes a plurality of public feelings information got respectively, obtains corresponding with the public feelings information multiple
Initial entity relationship network, recording in the entity relationship network has between multiple entity nodes and multiple entity node
Entity relationship.
Wherein, public feelings information refers to the information such as the news, blog and information got from channel source.In the embodiment of the present invention
Obtain public feelings information channel source selection setting is carried out by technical staff according to the actual situation, including but not limited to some social activities
Media, news website and forum etc..
In embodiments of the present invention, the analysis of entity relationship can be carried out respectively to each public feelings information got first,
The entity relationship network for including in each public feelings information is obtained, as assumed to illustrate that personage a has a friend in a public feelings information
The entity relationship network of friends each other between friendly b, corresponding personage a and personage b available at this time, it is to be understood that
A public sentiment letter is such as assumed due to being not the entity relationship comprising between multiple entities that is bound in each public feelings information in ground
It is a singer that personage a is only illustrated in breath, and does not mention its relationship between other any entities, is believed at this time the public sentiment
Breath, which carries out analysis, cannot get any entity relationship network, therefore the entity relationship network analyzed of the embodiment of the present invention
Total quantity, be necessarily smaller than or equal to the public feelings information got total quantity.Wherein, it is contemplated that have in the prior art it is more can
To carry out the natural language analysis algorithm of entity relationship analysis, such as common entity relationship parser neural network based
Deng, therefore specifically used entity relationship analysis method is not defined in the embodiment of the present invention, can by technical staff according to
Actual demand sets itself.
S102 extracts the common node for including in the entity relationship network, wherein common node is at least while to exist
Entity node in two entity relationship networks.
The entity node that common node refers to several entity relationship networks while all having, in examples detailed above, it is assumed that real
Include the character relation between personage a, personage b, personage c and personage d in body relational network A, includes in entity relationship network B
Character relation between personage d, personage e, personage f and personage g, then personage d is exactly the public affairs in two entity relationship networks
Conode.Since the quantity for the simple entity relationship network analyzed in the embodiment of the present invention is unknown, and these entities close
It is that the concrete condition of the entity for including can not also be predicted in advance, therefore can extract the quantity of obtained common node at this time in network
And can not predict in advance, it need to be determined according to the actual conditions of entity relationship network.
S103 merges processing to the entity relationship network based on the common node, until what merging obtained
Common node, the entity relationship network after being merged are not included in entity relationship network.
It is found in practical application, when an entity relationship network and other any entity relationship networks all do not have public section
When point, illustrates the relationship between other entities that each entity can be extended out in the entity relationship network, be comprised in
It in the entity relationship network, that is, realizes under the conditions of existing public feelings information, relational network between entity and entity is analyzed
Maximization most deepization.Therefore, after the common node for including in determining entity relationship network, in order to realize to entity
The depth analysis of relational network, the embodiment of the present invention can merge the entity relationship network comprising common node, until most
Between all entity relationship networks obtained eventually, any common node is not included.
Specifically, when carrying out entity relationship diagram complexing simultaneously, it is contemplated that the reality that a common node may be simultaneously present
The quantity of body relational network is indefinite, and the quantity of existing common node can not also determine between different entity relationship networks,
Since the entity relationship network quantity for analyzing public feelings information is more i.e. in actual conditions, cause finally to analyze obtained reality
The case where common node, is also complex between body relational network, therefore when carrying out entity relationship diagram complexing simultaneously, for difference
Actual demand, technical staff can choose or set the merging method for meeting its actual demand, not limit herein, for example,
When technical staff, which wishes, reduces technical difficulty when merging, the entity relationship network from one comprising common node can choose
It sets out, chooses one and its other entity relationship network with common node, and the common node of the two is merged to realize
Whether the network of the two merges, after the entity relationship network after being merged, then detect and wherein include and other entity relationships
The common node of network, if comprising aforesaid operations being repeated, until not including any common node in finally obtained merging network
Until, and when technical staff wishes to improve combined speed, then multiple entities comprising common node can be chosen simultaneously to close
It is network, and based on these entity relationship networks, the merging of Lai Jinhang entity relationship diagram, and detect and close after each merge
And whether comprising common node with other entity relationship networks in obtained entity relationship network, if continuing to merge comprising if,
Until not including any common node in finally obtained merging network.
Because ought explanatorily, since the public feelings information data volume that public sentiment system can get in actual conditions is extremely huge,
In include physical quantities it is also extremely huge, and and not all entity all centainly can directly or indirectly have certain reality
Body relationship, therefore, in embodiments of the present invention, the quantity of the finally obtained entity relationship network not comprising common node is nothing
What method determined, that is, it is possible to only one, it is also possible to while having multiple.
The embodiment of the present invention carries out public section by the simple entity relationship network analyzed each public feelings information
The extraction of point, and merged these simple entity relationship networks according to these common nodes, until all entities close
It is until maximizing all entity relationship network depth, just to be terminated to reality until all not including common node between network
The analysis of body relational network merges, and adequately achieves the in-depth analysis for all entity relationships that may relate to entity, realizes
In-depth analysis tracking is carried out to entity relationship network.
As the embodiment of the present invention two, it is contemplated that be all directly to be analyzed in each public feelings information in the embodiment of the present invention one
On the basis of the entity relationship network arrived, based on the final entity relationship network that common node merges, although in this way
Realize the combined analysis to entity relationship network, the more deep entity relationship network of an available analysis, but reality
In the entity relationship network merged in this way in situation, only it is able to achieve and the entity that public feelings information directly records and analyzes is closed
The record of system, and can not obtain in public feelings information there is no direct-recording entity relationship, it is assumed for example that finally obtained entity closes
Be in network, Zhang San has son Zhang Si, there is a father to open five, at this time according to embodiments of the present invention first is that can not obtain Zhang Si and
The entity relationship between five is opened, so that the analysis of a pair of entity relationship network of the embodiment of the present invention is deep not enough, is
Realize the analysis tracking more deep to entity relationship network, the embodiment of the present invention two can obtain not in the embodiment of the present invention one
On the basis of entity relationship network comprising common node, the entity relationship between entity node wherein included is carried out into one
The analysis of step ground, as shown in Figure 2, comprising:
S201 carries out random combine two-by-two to the entity node in the entity relationship network after merging, and parses every
The entity relationship between 2 entity nodes in a combination.
In view of already having corresponding entity relationship between many entity nodes in the entity relationship network after merging,
Therefore in order to reduce the task amount in the embodiment of the present invention, when carrying out combination of two analysis, can not consider to have existed reality
The entity node of body relationship combines, such as Zhang San and Zhang Si in examples detailed above, five has all been respectively provided with entity relationship, this
Shi Ruo carries out combination of two analyses to three nodes, combination that can only to the Zhang Si of entity relationship+five is wherein not present
It is analyzed, two combinations without regard to Zhang San+Zhang Si and Zhang San+five.
In order to realize the entity relationship point to script between the entity node combination for not having entity relationship in public feelings information
Analysis, the embodiment of the present invention can carry out presetting for entity relationship rule according to the possible situation of entity relationship in real life,
Such as a relationship rule can be set according to actual relationship, then combine come these entity nodes judged
Between whether meet the entity relationship rule of setting, as above-mentioned can be found between Zhang Si and five according to relationship rule is
There are grandfather grandson's relationships, and the entity relationship between the two combination can be obtained at this time.Wherein specific preset entity relationship rule
It can be by technical staff's sets itself, it is preferable that in order to realize the in-depth analysis to entity relationship network, these entity relationships rule
What is be arranged is The more the better.
S202, the entity relationship between 2 entity nodes in each combination obtained based on parsing, to the institute after merging
The entity relationship stated in entity relationship network is updated.
After obtaining the entity relationship between entity node, these entity relationships are directly recorded in the embodiment of the present invention
Among entity relationship network after one obtained merging, the update to it can be realized.
The embodiment of the present invention, which breaches, to be only capable of by single public feelings information solution in the prior art and the embodiment of the present invention one
Analysis is to obtain the limitation of the relationship between determining entity node, even realizing the reality occurred in different public feelings informations
Body can still be parsed by reasonable entity relationship reasoning, its corresponding entity relationship be obtained, so that the embodiment of the present invention
More deep entity relationship network analysis tracking may be implemented.
A kind of specific implementation of entity relationship diagram complexing simultaneously is carried out based on common node as in the embodiments of the present invention
Mode, it is contemplated that the data volume for the public feelings information that public sentiment system can be got in actual conditions is extremely huge, therefore is being closed
And when handling its workload be also it is very big, can simultaneously will be more in order to improve the working efficiency of merging, in the embodiment of the present invention
A common node synchronizes the merging for carrying out entity relationship network belonging to multiple common nodes, such as Fig. 3 institute as starting point is merged
Show, the embodiment of the present invention three, comprising:
S301 randomly selects multiple common nodes, and to belonging to each common node in multiple common nodes
The entity relationship network merge respectively, the entity relationship network after obtaining multiple merging.
Wherein, the common node particular number of selection can be met by technical staff's sets itself and be greater than or equal to 2.
In view of the data volume of public feelings information in actual conditions is very big, the simple entity relationship network analyzed is also very more,
When being therefore related to the operation of screening lookup etc, required workload is all very big.In order to reduce work when merging
It measures, in the embodiment of the present invention when choosing common node, using the method randomly selected, with the sieve that is avoided as much as having ready conditions
Workload brought by selecting.
After selecting common node, inquire the corresponding entity relationship network of each common node, and by these
Corresponding entity relationship network is based on the common node and merges, as common node a is existed simultaneously in entity relationship diagram
Network A, entity relationship network B and entity relationship network C three entity relationship diagrams can be complexed by common node a at this time
And.Wherein, it is contemplated that an entity relationship network may include several common nodes being selected simultaneously, at this time can by its with
Machine is distributed to one of common node.
S302 whether there is common node in the entity relationship network after detecting multiple merging.
Due to may simultaneously include multiple common nodes in an entity relationship network, only pass through the conjunction of a common node
And it can not also once realize merging to all entity relationship networks comprising identical common node, such as common node a is simultaneously
It is present in entity relationship network A, entity relationship network B and entity relationship network C, but entity relationship network A is also closed with entity
It is that there are common node b by network D, if at this time according to common node a by entity relationship network A, entity relationship network B and entity
Relational network C merge, at this time merge after entity relationship network in must there is also the common node b with entity relationship network D,
Entity relationship network i.e. after the merging can still continue further to analyse in depth.
S303, if there are common nodes in the entity relationship network after multiple merging, based on the institute after multiple merging
Entity relationship network is stated, the operation for extracting the common node for including in the entity relationship network described in executing is returned.
There are still when common node in entity relationship diagram after merging, entity relationship network after illustrating the merging can be with
Continue combined analysis, therefore the embodiment of the present invention will continue to return and carry out common node extraction in the embodiment of the present invention one
Operation, to continue to merge it, until finally merging obtained entity relationship network, there is no until any common node.
And the entity relationship network after merging is when being not present common node, illustrating it can not merge, and have been completed pair
Its in-depth analysis tracking.
Since the public feelings information data volume that public sentiment system can get in actual conditions is extremely huge, entity wherein included
Quantity is also extremely huge, and and not all entity all centainly can directly or indirectly have certain entity relationship, therefore
When merging, it is also possible in the entity relationship network after the multiple merging occurred, a part of entity relationship network
There is no common nodes, but then there are still common nodes for another part, are only needed at this time by there are still the entity of common node passes
It is that network is back to the operating procedure that common node extraction is carried out in the embodiment of the present invention one.
As the embodiment of the present invention four, it is contemplated that single public feelings information is not necessarily true in actual conditions, so that right
The confidence level for the entity relationship that single public feelings information is analyzed is difficult to be guaranteed, and two public feelings informations very likely occurs
The case where analyzing obtained entity relationship conflict, such as analyzed to obtain the father that personage a is personage b, but root according to public feelings information A
It is personage grandfather b according to another public feelings information B analysis personage a that gets back, it is evident that the two entity relationships, which exist, to conflict,
In there will necessarily be mistake entity relationship, therefore, in order to guarantee in entity relationship network obtained in the embodiments of the present invention
True and reliable, true and reliable in-depth analysis of the realization to entity relationship between entity of entity relationship, meeting of the embodiment of the present invention
To there are the combinations of the entity node of two or more entity relationship to analyze, and propose wherein entity relationship of problems,
As shown in Figure 4, comprising:
S401, finds out the first node group in the entity relationship network after merging, and the first node group is pair
The combination of 2 entity node of the entity relationship quantity answered more than or equal to 2.
There is different entities relationship existing for identical two entity nodes as that may record in different public feelings informations, this
A little node relationships be both likely to be the relationship that there is conflict in above-mentioned analysis, it is also possible to and it is the node relationships that conflict is not present,
Such as assume to be analyzed to obtain the father that personage a is personage b according to public feelings information A, the personage that gets back is analyzed according to another public feelings information C
A is personage b colleague, is at this time there is no conflict between two entity relationships, these relationships are all recorded in after consolidation
Among entity relationship network after merging, in order to find out the entity node combination that wherein there is conflict, the embodiment of the present invention is first
Entity node of all entity relationship quantity more than or equal to 2 can first be found out to combine, entity node combination here all refers to reality
Combination between body node two-by-two only can include two entity nodes.
S402, filters out second node group from the first node group, the second node group be comprising entity close
There are the first node groups of preset relation combination in system.
Such as above-mentioned analysis, all there is conflict in not every entity relationship, therefore even if deposit between two entity nodes
It also not necessarily there is conflict relationship in a plurality of entity relationship.Therefore, in order to reject unreasonable conflict relationship, the present invention is implemented
In example the entity relationship in the presence of conflict can be filtered out from the entity node combination comprising a plurality of entity relationship.Wherein, for reality
The better entity relationship that there is conflict can be preset now to the screening for the entity relationship that there is conflict, in the embodiment of the present invention
Combination, i.e. preset relation combines, such as father and son+grandfather grandson/mothers and sons/brother/sister etc. is the entity relationship combination of conflict, then root
It combines and is inquired according to the preset relation, judge whether entity relationship that entity relationship group includes has the entity relationship group of conflict
It closes, if so, then screening this entity relationship group.Such as public feelings information A analyzes to obtain personage a to be personage in examples detailed above
The father of b, it is personage b colleague that another public feelings information C, which analyzes the personage a that gets back, at this time the reality of entity node a and entity node b
In body node combination, it there is the father and son+grandfather grandson conflict relationship combination for meeting preset relation combination, can will give entity node
Combined sorting comes out.Wherein specific default care combination settings rule, can be configured according to the actual situation by technical staff.
S403, based on the corresponding public feelings information of entity relationship each in preset relation combination, to described
Preset relation combination is analyzed, filter out wherein with the unique corresponding entity of two entity nodes in the second node group
Relationship, and based on unique corresponding entity relationship, the entity relationship network after merging is updated.
After determining that these have the combination of the entity node of the entity relationship of conflict, the embodiment of the present invention can deposit these
It is screened in the entity relationship of conflict, determines the wherein corresponding entity relationship of only one.Wherein, ground is understood because working as, this
In screening only just for exist conflict entity relationship, to other there is no conflict entity relationship be not to locate herein
Reason, therefore, the direct entity relationship of finally obtained two entity nodes may not be unique, only wherein will not again there are
The entity relationship of conflict, for example, public feelings information A analyzes to obtain the father that personage a is personage b, another public sentiment letter in examples detailed above
The breath C analysis personage a that gets back is personage b colleague, i.e., during entity node a is combined with the entity node of entity node b, shared father and son
Three entity relationships of+grandfather grandson+colleague, the embodiment of the present invention can only carry out wherein father and son+grandfather grandson conflict entity relationship unique
Screening, is handled, the entity node group of finally obtained entity node a and entity node b without the entity relationship to colleague
In conjunction, two entity relationships of father and son/grandfather grandson+colleague are also had.Wherein, specifically the screening technique of conflict entity relationship is not herein
Restriction is given, setting can be chosen according to the actual situation by technical staff, including but not limited to such as randomly selects one of reservation, or
Person is handled with reference to the embodiment of the present invention five.
As a kind of specific implementation screened in the embodiment of the present invention four to the entity relationship of conflict, it is contemplated that
The channel source of public feelings information is numerous and jumbled, and there are larger differences, such as government website for significance level of the different channel sources to entity relationship
The public feelings information confidence level of publication is much higher than some entertainment news websites, therefore analyzes from this channel source with a high credibility
The confidence level of the entity relationship arrived is also much higher than the lower channel source of some confidence levels, on the other hand, due to the reality of public feelings information
When property feature is more obvious, and the relationship of entity relationship wherein included and time are more close, therefore the corresponding carriage of entity relationship
The issuing time of feelings information, and determine a key factor of entity relationship confidence level, in order to guarantee that the entity to conflict closes
The accurate screening of system, as shown in figure 5, the embodiment of the present invention five, comprising:
S501 obtains the channel source that the preset relation combines the corresponding public feelings information of interior each entity relationship
And issuing time, the channel source are to provide the channel source of public feelings information.
Since each entity relationship is to analyze to obtain from public feelings information, directly believed according to its corresponding public sentiment
Breath can inquire the issuing time in the channel source and the public feelings information that provide the public feelings information.
S502 is based on the channel source, the issuing time and preset weight coefficient, calculates the preset relation group
The corresponding weighted value of interior each entity relationship is closed, and two realities with the second node group are filtered out based on the weighted value
The unique corresponding entity relationship of body node.
Wherein, in order to realize the screening according to channel source and issuing time to the entity relationship of conflict, the present invention is implemented
Example first can quantify the two, such as corresponding confidence level score can be arranged for each channel source in advance, such as can be set
It is 100 for the relevant website score of government, entertainment news website score is 60, other websites are 80, while being different publications
Corresponding confidence level score is arranged in time, such as can be set in issuing time half a year not 100,80 in half a year to 1 year, 1 year
The above are 60 etc., while also corresponding weight coefficient can be arranged to the two in advance by technical staff, then be based on the weight coefficient, with
And the respective channel source score of each entity relationship and issuing time score, to realize the quantization to entity relationship confidence level point
Number calculates, and obtains corresponding weighted value.Finally, further according to the highest entity relationship of confidence level, as in the entity relationship of conflict
The entity relationship uniquely retained.Wherein channel source and the corresponding weight coefficient occurrence of issuing time, by technical staff according to reality
The setting of border situation.
As the embodiment of the present invention six, use in order to facilitate subsequent user to entity relationship query function, the present invention is real
Applying in example can classify to finally obtained each entity relationship network, for example, character relation network, place relational network with
And event relation network etc., as shown in Figure 6, comprising:
S601, the kind of type and entity relationship based on the entity for including in the entity relationship network after merging
Class, the corresponding relational network type of the entity relationship network after identification merging.
Here it can classify first to entity relationship network, can such as be divided into above-mentioned character relation network, place is closed
It is network and event relation network etc., and sets corresponding entity and reality according to the actual conditions of every kind of entity relationship network
The body relationship criteria for classifying, such as character relation network, internal entity only includes people, and entity relationship is also only closed comprising personage
System, for place relational network, internal entity only includes place, and entity relationship also only includes place relationship, and for thing
Part relational network, internal entity can include people, place and mechanism simultaneously, entity relationship also may include it is a variety of, therefore can
With according to the actual conditions of above-mentioned various entity relationship networks, set to preset the actual conditions of every kind of entity relationship network
Fixed corresponding entity and the entity relationship criteria for classifying, the case where further according to the entity relationship network actually obtained, to classify.
S602, according to the corresponding relational network type of the entity relationship network after merging, for the reality after merging
Body relational network adds corresponding type label.
After the type for determining finally obtained each entity relationship network, the embodiment of the present invention can also be to each reality
Body relational network adds corresponding type label, such as can add " character relation " label to character relation network, closes to place
It is network addition " place relationship ", to event relation network addition " event relation " label etc., so that user is carrying out in fact
When body relational query, classified inquiry can be fast implemented according to the type of the entity relationship of required inquiry.
The embodiment of the present invention carries out public section by the simple entity relationship network analyzed each public feelings information
The extraction of point, and merged these simple entity relationship networks according to these common nodes, until all entities close
It is until maximizing all entity relationship network depth, just to be terminated to reality until all not including common node between network
The analysis of body relational network merges, and adequately achieves the in-depth analysis for all entity relationships that may relate to entity, realizes
In-depth analysis tracking is carried out to entity relationship network.Simultaneously on this basis, the embodiment of the present invention is also to entity relationship network
In the combination of each entity node carry out the analysis of entity relationship respectively, to guarantee each may be used in finally obtained entity relationship network
The entity relationship of energy can be repeated mining analysis processing, and sieve to the entity relationship that there is conflict between entity node
Choosing only retains a highest entity relationship of confidence level, thus ensure that the true and reliable of finally obtained entity relationship network,
The embodiment of the present invention finally realizes the comprehensive analysis to public feelings information, realize to entity relationship network more it is true and reliable more
Deep analysis tracking.
Corresponding to the method for foregoing embodiments, Fig. 7 shows the entity provided in an embodiment of the present invention based on public feelings information
The structural block diagram of relationship analysis apparatus, for ease of description, only parts related to embodiments of the present invention are shown.Fig. 7 example
The entity relationship analytical equipment based on public feelings information the entity based on public feelings information of the offer of previous embodiment one be provided close
It is the executing subject of analysis method.
Referring to Fig. 7, being somebody's turn to do the entity relationship analytical equipment based on public feelings information includes:
Nework analysis module 71 obtains and the public sentiment for being analyzed respectively a plurality of public feelings information got
The corresponding multiple initial entity relationship networks of information, record has multiple entity nodes in the entity relationship network and this is more
Entity relationship between a entity node.
Node extraction module 72, for extracting the common node for including in the entity relationship network, wherein common node
For the entity node being at least while present in two entity relationship networks.
Network merging module 73, for merging processing to the entity relationship network based on the common node,
Common node, the entity relationship network after being merged are not included in obtained entity relationship network until merging.
Further, it is somebody's turn to do the entity relationship analytical equipment based on public feelings information, further includes:
Combination of nodes module, for carrying out random groups two-by-two to the entity node in the entity relationship network after merging
It closes, and parses the entity relationship between 2 entity nodes in each combination.
Relationship update module, the entity relationship between 2 entity nodes in each combination for being obtained based on parsing,
Entity relationship in the entity relationship network after merging is updated.
Further, network merging module 73, comprising:
Randomly select multiple common nodes, and to described in belonging to each common node in multiple common nodes
Entity relationship network merges respectively, the entity relationship network after obtaining multiple merging.
It whether there is common node in the entity relationship network after detecting multiple merging.
If there are common nodes in the entity relationship network after multiple merging, based on the entity after multiple merging
Relational network returns to the operation that the common node for including in the entity relationship network is extracted described in executing.
Further, it is somebody's turn to do the entity relationship analytical equipment based on public feelings information, further includes:
More relationship node checks modules, for finding out the first node group in the entity relationship network after merging,
The first node group is the combination of 2 entity node of the corresponding entity relationship quantity more than or equal to 2.
Relationship group screening module, for filtering out second node group, the second node group from the first node group
For comprising entity relationship in there are preset relation combination first node group.
Node relationships update module, it is corresponding described for each entity relationship in being combined based on the preset relation
Public feelings information, to the preset relation combination analyze, filter out wherein with two entity sections in the second node group
The unique corresponding entity relationship of point, and based on unique corresponding entity relationship, to the entity relationship network after merging into
Row updates.
Further, node relationships update module, comprising:
Obtain the corresponding public feelings information of each entity relationship in preset relation combination channel source and
Issuing time, the channel source are to provide the channel source of public feelings information.
Based on the channel source, the issuing time and preset weight coefficient, calculate in the preset relation combination
The corresponding weighted value of each entity relationship, and two entity sections with the second node group are filtered out based on the weighted value
The unique corresponding entity relationship of point.
Further, it is somebody's turn to do the entity relationship analytical equipment based on public feelings information, further includes:
The type of type and entity relationship based on the entity for including in the entity relationship network after merging, identification
The corresponding relational network type of the entity relationship network after merging.
According to the corresponding relational network type of the entity relationship network after merging, for the entity relationship after merging
Network adds corresponding type label.
Each module realizes respective function in entity relationship analytical equipment provided in an embodiment of the present invention based on public feelings information
Process, specifically refer to the description of aforementioned embodiment illustrated in fig. 1 one, details are not described herein again.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Although will also be appreciated that term " first ", " second " etc. are used in some embodiment of the present invention in the text
Various elements are described, but these elements should not be limited by these terms.These terms are used only to an element
It is distinguished with another element.For example, the first table can be named as the second table, and similarly, the second table can be by
It is named as the first table, without departing from the range of various described embodiments.First table and the second table are all tables, but
It is them is not same table.
Fig. 8 is the schematic diagram for the terminal device that one embodiment of the invention provides.As shown in figure 8, the terminal of the embodiment is set
Standby 8 include: processor 80, memory 81, and the computer that can be run on the processor 80 is stored in the memory 81
Program 82.The processor 80 realizes above-mentioned each entity relationship based on public feelings information point when executing the computer program 82
The step in embodiment of the method, such as step 101 shown in FIG. 1 are analysed to 103.Alternatively, the processor 80 executes the calculating
The function of each module/unit in above-mentioned each Installation practice, such as the function of module 71 to 73 shown in Fig. 7 are realized when machine program 82
Energy.
The terminal device 8 can be the calculating such as desktop PC, notebook, palm PC and cloud server and set
It is standby.The terminal device may include, but be not limited only to, processor 80, memory 81.It will be understood by those skilled in the art that Fig. 8
The only example of terminal device 8 does not constitute the restriction to terminal device 8, may include than illustrating more or fewer portions
Part perhaps combines certain components or different components, such as the terminal device can also include input sending device, net
Network access device, bus etc..
Alleged processor 80 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 81 can be the internal storage unit of the terminal device 8, such as the hard disk or interior of terminal device 8
It deposits.The memory 81 is also possible to the External memory equipment of the terminal device 8, such as be equipped on the terminal device 8
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card dodge
Deposit card (Flash Card) etc..Further, the memory 81 can also both include the storage inside list of the terminal device 8
Member also includes External memory equipment.The memory 81 is for storing needed for the computer program and the terminal device
Other programs and data.The memory 81, which can be also used for temporarily storing, have been sent or data to be sent.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program generation
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium
It may include: any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic that can carry the computer program code
Dish, CD, computer storage, read-only memory (Read-Only Memory, ROM), random access memory (Random
Access Memory, RAM), electric carrier signal, telecommunication signal and software distribution medium etc..
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the essence of corresponding technical solution is departed from the spirit and scope of the technical scheme of various embodiments of the present invention, it should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of entity relationship analysis method based on public feelings information characterized by comprising
The a plurality of public feelings information got is analyzed respectively, obtains multiple initial entities corresponding with the public feelings information
Relational network, record has the entity between multiple entity nodes and multiple entity node to close in the entity relationship network
System；
Extract the common node for including in the entity relationship network, wherein common node is at least while to be present in two realities
Entity node in body relational network；
Processing is merged between the entity relationship network based on the common node, until merging obtained entity relationship diagram
Common node, the entity relationship network after being merged are not included in network.
2. the entity relationship analysis method based on public feelings information as described in claim 1, which is characterized in that closed described
After the entity relationship network after and, further includes:
Random combine two-by-two is carried out to the entity node in the entity relationship network after merging, and is parsed in each combination
Entity relationship between 2 entity nodes；
The entity relationship between 2 entity nodes in each combination obtained based on parsing, closes the entity after merging
It is that entity relationship in network is updated.
3. the entity relationship analysis method based on public feelings information as claimed in claim 1 or 2, which is characterized in that described to be based on
The common node merges processing to the entity relationship network, does not wrap in obtained entity relationship network until merging
The entity relationship network containing common node, after being merged, comprising:
Multiple common nodes are randomly selected, and to the entity belonging to each common node in multiple common nodes
Relational network merges respectively, the entity relationship network after obtaining multiple merging；
It whether there is common node in the entity relationship network after detecting multiple merging；
If there are common nodes in the entity relationship network after multiple merging, based on the entity relationship after multiple merging
Network returns to the operation that the common node for including in the entity relationship network is extracted described in executing.
4. the entity relationship analysis method based on public feelings information as claimed in claim 1 or 2, which is characterized in that obtained described
After the entity relationship network after to merging, further includes:
The first node group in the entity relationship network after merging is found out, the first node group is corresponding entity pass
The combination of 2 entity node of the coefficient amount more than or equal to 2；
Filter out second node group from the first node group, the second node group be comprising entity relationship in exist it is pre-
If the first node group of composition of relations；
Based on the corresponding public feelings information of entity relationship each in preset relation combination, to the preset relation group
Conjunction is analyzed, filter out wherein with two entity node uniquely corresponding entity relationships, and base in the second node group
In unique corresponding entity relationship, the entity relationship network after merging is updated.
5. the entity relationship analysis method based on public feelings information as claimed in claim 4, which is characterized in that described based on described
Preset relation combines the corresponding public feelings information of interior each entity relationship, analyzes preset relation combination,
Filter out wherein with the unique corresponding entity relationship of two entity nodes in the second node group, comprising:
Obtain channel source and publication that the preset relation combines the corresponding public feelings information of interior each entity relationship
Time, the channel source are to provide the channel source of public feelings information；
Based on the channel source, the issuing time and preset weight coefficient, calculate each in the preset relation combination
The corresponding weighted value of entity relationship, and filtered out with two entity nodes of the second node group only based on the weighted value
One corresponding entity relationship.
6. the entity relationship analysis method based on public feelings information as claimed in claim 1 or 2, which is characterized in that obtained described
After the entity relationship network after to merging, further includes:
The type of type and entity relationship based on the entity for including in the entity relationship network after merging, identification merge
The corresponding relational network type of the entity relationship network afterwards；
According to the corresponding relational network type of the entity relationship network after merging, for the entity relationship network after merging
Add corresponding type label.
7. a kind of terminal device, which is characterized in that the terminal device includes memory, processor, is stored on the memory
There is the computer program that can be run on the processor, the processor realizes following step when executing the computer program
It is rapid:
The a plurality of public feelings information got is analyzed respectively, obtains multiple initial entities corresponding with the public feelings information
Relational network, record has the entity between multiple entity nodes and multiple entity node to close in the entity relationship network
System；
Extract the common node for including in the entity relationship network, wherein common node is at least while to be present in two realities
Entity node in body relational network；
Processing is merged between the entity relationship network based on the common node, until merging obtained entity relationship diagram
Common node, the entity relationship network after being merged are not included in network.
8. terminal device as claimed in claim 6, which is characterized in that the processor goes back reality when executing the computer program
Existing following steps:
Random combine two-by-two is carried out to the entity node in the entity relationship network after merging, and is parsed in each combination
Entity relationship between 2 entity nodes；
The entity relationship between 2 entity nodes in each combination obtained based on parsing, closes the entity after merging
It is that entity relationship in network is updated.
9. a kind of entity relationship analytical equipment based on public feelings information characterized by comprising
Nework analysis module obtains and the public feelings information pair for being analyzed respectively a plurality of public feelings information got
The multiple initial entity relationship networks answered, record has multiple entity nodes and multiple entity in the entity relationship network
Entity relationship between node；
Node extraction module, for extracting the common node for including in the entity relationship network, wherein common node is at least
Exist simultaneously the entity node in two entity relationship networks；
Network merging module, for merging processing to the entity relationship network based on the common node, until closing
And common node, the entity relationship network after being merged are not included in obtained entity relationship network.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In when the computer program is executed by processor the step of any one of such as claim 1 to 5 of realization the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811343920.8A CN109635074B (en) | 2018-11-13 | 2018-11-13 | Entity relationship analysis method and terminal equipment based on public opinion information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811343920.8A CN109635074B (en) | 2018-11-13 | 2018-11-13 | Entity relationship analysis method and terminal equipment based on public opinion information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109635074A true CN109635074A (en) | 2019-04-16 |
| CN109635074B CN109635074B (en) | 2024-05-07 |
Family
ID=66067864
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811343920.8A Active CN109635074B (en) | 2018-11-13 | 2018-11-13 | Entity relationship analysis method and terminal equipment based on public opinion information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109635074B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022227196A1 (en) * | 2021-04-27 | 2022-11-03 | 平安科技（深圳）有限公司 | Data analysis method and apparatus, computer device, and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103207860A (en) * | 2012-01-11 | 2013-07-17 | 北大方正集团有限公司 | Method and device for extracting entity relationships of public sentiment events |
| CN103544255A (en) * | 2013-10-15 | 2014-01-29 | 常州大学 | Text semantic relativity based network public opinion information analysis method |
| US20140108152A1 (en) * | 2012-10-12 | 2014-04-17 | Google Inc. | Managing Social Network Relationships Between A Commercial Entity and One or More Users |
| CN104268271A (en) * | 2014-10-13 | 2015-01-07 | 北京建筑大学 | Interest and network structure double-cohesion social network community discovering method |
| US20150178372A1 (en) * | 2013-12-19 | 2015-06-25 | OpenGov, Inc. | Creating an ontology across multiple semantically-related data sets |
| CN105302823A (en) * | 2014-06-27 | 2016-02-03 | 首都师范大学 | Overlapped community parallel discovery method and system |
| CN105373619A (en) * | 2015-12-03 | 2016-03-02 | 中国联合网络通信集团有限公司 | User big data based user group analysis method and system |
| US20160142266A1 (en) * | 2014-11-19 | 2016-05-19 | Battelle Memorial Institute | Extracting dependencies between network assets using deep learning |
| CN106204161A (en) * | 2016-07-26 | 2016-12-07 | 郑州郑大智能科技股份有限公司 | A kind of power consumer group analytic method under internet environment |
| CN106991090A (en) * | 2016-01-20 | 2017-07-28 | 北京国双科技有限公司 | The analysis method and device of public sentiment event entity |
| WO2018023981A1 (en) * | 2016-08-03 | 2018-02-08 | 平安科技（深圳）有限公司 | Public opinion analysis method, device, apparatus and computer readable storage medium |
-
2018
- 2018-11-13 CN CN201811343920.8A patent/CN109635074B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103207860A (en) * | 2012-01-11 | 2013-07-17 | 北大方正集团有限公司 | Method and device for extracting entity relationships of public sentiment events |
| US20140108152A1 (en) * | 2012-10-12 | 2014-04-17 | Google Inc. | Managing Social Network Relationships Between A Commercial Entity and One or More Users |
| CN103544255A (en) * | 2013-10-15 | 2014-01-29 | 常州大学 | Text semantic relativity based network public opinion information analysis method |
| US20150178372A1 (en) * | 2013-12-19 | 2015-06-25 | OpenGov, Inc. | Creating an ontology across multiple semantically-related data sets |
| CN105302823A (en) * | 2014-06-27 | 2016-02-03 | 首都师范大学 | Overlapped community parallel discovery method and system |
| CN104268271A (en) * | 2014-10-13 | 2015-01-07 | 北京建筑大学 | Interest and network structure double-cohesion social network community discovering method |
| US20160142266A1 (en) * | 2014-11-19 | 2016-05-19 | Battelle Memorial Institute | Extracting dependencies between network assets using deep learning |
| CN105373619A (en) * | 2015-12-03 | 2016-03-02 | 中国联合网络通信集团有限公司 | User big data based user group analysis method and system |
| CN106991090A (en) * | 2016-01-20 | 2017-07-28 | 北京国双科技有限公司 | The analysis method and device of public sentiment event entity |
| CN106204161A (en) * | 2016-07-26 | 2016-12-07 | 郑州郑大智能科技股份有限公司 | A kind of power consumer group analytic method under internet environment |
| WO2018023981A1 (en) * | 2016-08-03 | 2018-02-08 | 平安科技（深圳）有限公司 | Public opinion analysis method, device, apparatus and computer readable storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022227196A1 (en) * | 2021-04-27 | 2022-11-03 | 平安科技（深圳）有限公司 | Data analysis method and apparatus, computer device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109635074B (en) | 2024-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102591421B1 (en) | Intent recommendation method, apparatus, device and storage medium | |
| US11727481B2 (en) | Systems and user interfaces for dynamic and interactive investigation of bad actor behavior based on automatic clustering of related data in various data structures | |
| Strotmann et al. | Author name disambiguation: What difference does it make in author‐based citation analysis? | |
| US9202249B1 (en) | Data item clustering and analysis | |
| US20190138372A1 (en) | System for managing an instructure with security | |
| CN104731842B (en) | For electronic communication data to be used to carry out the method and system of mapping relations | |
| US11113317B2 (en) | Generating parsing rules for log messages | |
| Miller | Automated detection of Chinese government astroturfers using network and social metadata | |
| Hashmi et al. | Are all social networks structurally similar? | |
| CN104965846B (en) | Visual human's method for building up in MapReduce platform | |
| TeBlunthuis et al. | Identifying competition and mutualism between online groups | |
| Keyvanpour | A survey on community detection methods based on the nature of social networks | |
| Wlodarczyk et al. | Current trends in predictive analytics of big data | |
| CN109635074A (en) | A kind of entity relationship analysis method and terminal device based on public feelings information | |
| Hou et al. | Research on the behaviour and law of quantity growth of followers based on WeChat official account | |
| CN115329078B (en) | Text data processing method, device, equipment and storage medium | |
| Huang | An analysis of the intellectual structure of the cloud patents of SaaS | |
| US10833964B2 (en) | Visual analytical method and system for network system structure and network communication mode | |
| CN116028467A (en) | Intelligent service big data modeling method, system, storage medium and computer equipment | |
| CN116089490A (en) | Data analysis method, device, terminal and storage medium | |
| Li | [Retracted] Research on the Social Security and Elderly Care System under the Background of Big Data | |
| Oliveira et al. | Citizens and information and communication technologies | |
| CN111026705B (en) | Building engineering file management method, system and terminal equipment | |
| Preotiuc-Pietro | Temporal models of streaming social media data | |
| Borges et al. | Event detection for smarter cities |
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 |