CN109918452A - A kind of method, apparatus of data processing, computer storage medium and terminal - Google Patents
A kind of method, apparatus of data processing, computer storage medium and terminal Download PDFInfo
- Publication number
- CN109918452A CN109918452A CN201910113903.3A CN201910113903A CN109918452A CN 109918452 A CN109918452 A CN 109918452A CN 201910113903 A CN201910113903 A CN 201910113903A CN 109918452 A CN109918452 A CN 109918452A
- Authority
- CN
- China
- Prior art keywords
- data
- relationship
- entity
- event
- kinds
- 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.)
- Pending
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A kind of method, apparatus of data processing, computer storage medium and terminal, comprising: according to the data information for including entity, relationship and event, establish data model；Knowledge mapping is constructed according to the data model of foundation；Data retrieval is carried out by the knowledge mapping of building.The embodiment of the present invention improves the analysis quality of knowledge mapping.
Description
Technical field
Present document relates to but be not limited to knowledge mapping technology, espespecially a kind of method, apparatus of data processing, computer storage be situated between
Matter and terminal.
Background technique
Knowledge mapping can be divided into world knowledge map and domain knowledge map from its service field.Most current is
Issued opening knowledge mapping is all world knowledge map, its data source opens data typically from internet, it
It is emphasised that range, and the more entities of fusion；Compared with domain knowledge map, world knowledge map accuracy is not high enough, and by general
The influence for reading range is difficult by ontology library to the tenability specification of axiom, rule and constraint condition its entity, attribute, reality
Relationship between body；World knowledge map is mainly used in the fields such as intelligent search.Domain knowledge map is usually required by specific
The data of industry construct, and have specific industry meaning.In domain knowledge map, entity attributes often compare with data pattern
It is relatively abundant, it needs in view of different business scenarios and user of service.Therefore, the data model of world knowledge map is known in field
Know in map construction and has many limitations.
Currently, the knowledge mapping data model of public safety industry it is more mature have entity-link-attribute (ELP,
Entity-Link-Property) data model and dynamic ontology (Dynamic Ontology) data model；Wherein, in ELP
In data model, entity: a true object is represented；Including but not limited to: people, vehicle etc.；Link: it indicates between two entities
Connection and related information；It is associated with as people belongs to possess with Che；Attribute: for storage entity or the characteristic information of link；With
Entity is behaved as an example, its attribute may include: name, date of birth, hair color etc.；Dynamic ontology data model needs
Flexibly building object (Object) and subject component (Object Components)；Wherein, in dynamic ontology data model, belong to
Property (Properties) refers to the attribute value of text class；Media (Media) refer to: picture, video, document, binary data etc.
File；It annotates (Notes) are as follows: the container of structureless free text；Relationship (Relationship) is used for: describing different objects
Between connection.
Above two data model is substantially similar, is all entity attribute based on " entity-relation-attribute " data model
Wide in range, relationship is simply and entity-relation topological structure is more superficial, affects the analytical effect of knowledge mapping.
Summary of the invention
It is the general introduction to the theme being described in detail herein below.This general introduction is not the protection model in order to limit claim
It encloses.
The embodiment of the present invention provides the method, apparatus, computer storage medium and terminal of a kind of data processing, is able to ascend
The analysis quality of knowledge mapping.
The embodiment of the invention provides a kind of methods of data processing, comprising:
According to the data information for including entity, relationship and event, data model is established；
Knowledge mapping is constructed according to the data model of foundation；
Data retrieval is carried out by the knowledge mapping of building.
Optionally, described to establish before data model, the method also includes obtaining the entity in the following manner:
After handling pre-stored source data, the knowledge base for obtaining the data information is established；
When the source data for including in the knowledge base is structural data, after being pre-processed to the source data,
The entity is constructed by preset Entities Matching rule；
When the source data for including in the knowledge base is unstructured data, pass through Text Mining Technology or entity
After mark and identification technology handle the source data, the entity is constructed.
Optionally, the entity includes: physical entity and/or pseudo-entity；
Wherein, the physical entity includes following one or more kinds of entities: people, vehicle, house；The pseudo-entity
Including following one or more kinds of entities: organization, virtual identity.
Optionally, the entity includes following one or more kinds of attributes:
Tag attributes, natural quality, one or more primary key attributes；
Wherein, the primary key attribute is for distinguishing each entity；The tag attributes include calculating or returning according to business datum
The following one or more kinds of features received out: foundation characteristic, behavioural characteristic, relationship characteristic, geographical location；The natural quality
It include: the attribute value extracted from the data information；The attribute value includes following one or more kinds of attribute informations: body
Height, age, native place；The natural quality includes the primary attribute and/or sub-attribute divided according to preset strategy.
Optionally, the relationship includes following one or more kinds of relationships:
Dominance relation, recessive relationship；
Wherein, the dominance relation includes the relationship obtained by the direct correlation building between data；The recessive pass
System includes the association based on time, space, semanteme and/or characteristic between data, passes through preset relationship match rule
Or the relationship that machine learning mode obtains.
Optionally, when the relationship includes the dominance relation, the dominance relation includes following one or more
Relationship: set membership, conjugal relation, classmate's relationship, property belonging relation；
When the relationship includes the recessive relationship, the recessiveness relationship includes following one or more kinds of relationships: same
Row relationship lives relationship, accompanying relationship, accomplice relationship together.
Optionally, described to establish before data model, the method also includes:
The event is obtained based on streaming message queue；
Wherein, the event includes following one or more kinds of contents: train trip event, vehicle bayonet event, net
Event, lodging event.
Optionally, described to include: based on the streaming message queue acquisition event
Based on streaming message queue, the event is obtained from the behavioral data of the entity；
Wherein, the behavioral data includes following one or more kinds of data: main body, object, time, place, time
Section and event content；The event includes following one or more kinds of information: main body, object, time dimension information, geographical dimension
Spend information.
Optionally, described to include: by the knowledge mapping progress data retrieval of building
Receive the retrieval information for carrying out data retrieval；
The retrieval process of data is carried out to the knowledge mapping of building according to the retrieval information received；
Wherein, the retrieval information includes the information comprising following one or more kinds of contents: the entity attributes,
The content of the type of the relationship, and/or the event.
On the other hand, the embodiment of the present invention also provides a kind of device of data processing, comprising: modeling unit, Tupu unit
And retrieval unit；Wherein,
Modeling unit is used for: according to the data information for including entity, relationship and event, establishing data model；
Tupu unit is used for: constructing knowledge mapping according to the data model of foundation；
Retrieval unit is used for: carrying out data retrieval by the knowledge mapping of building.
Optionally, described device further includes entity acquiring unit, is used for:
After handling pre-stored source data, the knowledge base for obtaining the data information is established；
When the source data for including in the knowledge base is structural data, after being pre-processed to the source data,
The entity is constructed by preset Entities Matching rule；
When the source data for including in the knowledge base is unstructured data, pass through Text Mining Technology or entity
After mark and identification technology handle the source data, the entity is constructed.
Optionally, the entity includes: physical entity and/or pseudo-entity；
Wherein, the physical entity includes following one or more kinds of entities: people, vehicle, house；The pseudo-entity
Including following one or more kinds of entities: organization, virtual identity.
Optionally, the entity includes following one or more kinds of attributes:
Tag attributes, natural quality, one or more primary key attributes；
Wherein, the primary key attribute is for distinguishing each entity；The tag attributes include calculating or returning according to business datum
The following one or more kinds of features received out: foundation characteristic, behavioural characteristic, relationship characteristic, geographical location；The natural quality
It include: the attribute value extracted from the data information；The attribute value includes following one or more kinds of attribute informations: body
Height, age, native place；The natural quality includes the primary attribute and/or sub-attribute divided according to preset strategy.
Optionally, the relationship includes following one or more kinds of relationships:
Dominance relation, recessive relationship；
Wherein, the dominance relation includes the relationship obtained by the direct correlation building between data；The recessive pass
System includes the association based on time, space, semanteme and/or characteristic between data, passes through preset relationship match rule
Or the relationship that machine learning mode obtains.
Optionally, when the relationship includes the dominance relation, the dominance relation includes following one or more
Relationship: set membership, conjugal relation, classmate's relationship, property belonging relation；
When the relationship includes the recessive relationship, the recessiveness relationship includes following one or more kinds of relationships: same
Row relationship lives relationship, accompanying relationship, accomplice relationship together.
Optionally, described device further includes event acquiring unit, is used for:
The event is obtained based on streaming message queue；
Wherein, the event includes following one or more kinds of contents: train trip event, vehicle bayonet event, net
Event, lodging event.
Optionally, the event acquiring unit is specifically used for:
Based on streaming message queue, the event is obtained from the behavioral data of the entity；
Wherein, the behavioral data includes following one or more kinds of data: main body, object, time, place, time
Section and event content；The event includes following one or more kinds of information: main body, object, time dimension information, geographical dimension
Spend information.
Optionally, the retrieval unit is specifically used for:
Receive the retrieval information for carrying out data retrieval；
The retrieval process of data is carried out to the knowledge mapping of building according to the retrieval information received；
Wherein, the retrieval information includes the information comprising following one or more kinds of contents: the entity attributes,
The content of the type of the relationship, and/or the event.
In another aspect, the embodiment of the present invention also provides a kind of computer storage medium, deposited in the computer storage medium
Contain computer executable instructions, the method that the computer executable instructions are used to execute above-mentioned data processing.
Also on the one hand, the embodiment of the present invention also provides a kind of terminal, comprising: memory and processor；Wherein,
Processor is configured as executing the program instruction in memory；
Program instruction reads in processor and executes following operation:
According to the data information for including entity, relationship and event, data model is established；
Knowledge mapping is constructed according to the data model of foundation；
Data retrieval is carried out by the knowledge mapping of building.
Compared with the relevant technologies, technical scheme includes: the data information that basis includes entity, relationship and event,
Establish data model；Knowledge mapping is constructed according to the data model of foundation；Data retrieval is carried out by the knowledge mapping of building.This
Inventive embodiments improve the analysis quality of knowledge mapping.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention can be by specification, right
Specifically noted structure is achieved and obtained in claim and attached drawing.
Detailed description of the invention
Attached drawing is used to provide to further understand technical solution of the present invention, and constitutes part of specification, with this
The embodiment of application technical solution for explaining the present invention together, does not constitute the limitation to technical solution of the present invention.
Fig. 1 is the flow chart of the method for data processing of the embodiment of the present invention；
Fig. 2 is the structural block diagram of the device of data processing of the embodiment of the present invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention
Embodiment be described in detail.It should be noted that in the absence of conflict, in the embodiment and embodiment in the application
Feature can mutual any combination.
Step shown in the flowchart of the accompanying drawings can be in a computer system such as a set of computer executable instructions
It executes.Also, although logical order is shown in flow charts, and it in some cases, can be to be different from herein suitable
Sequence executes shown or described step.
Present inventor's analysis finds that the data model of current knowledge map has the disadvantage in that 1, entity attribute does not have
It distinguishes, is not easy to find analysis emphasis in numerous attributes, reduces the analysis efficiency of knowledge mapping；2, relationship type
Traffic differentiation is not carried out, and is all directly established, the deep excavation to industry data feature is lacked；3, simple entity-relation
Topological structure can not embody the temporal aspect of public safety field track data, be unfavorable for the in-depth analysis of relational network.
Fig. 1 is the flow chart of the method for data processing of the embodiment of the present invention, as shown in Figure 1, comprising:
Step 101, basis include the data information of entity, relationship and event, establish data model；
Optionally, it establishes before data model, present invention method further includes obtaining the reality in the following manner
Body:
After handling pre-stored source data, the knowledge base for obtaining the data information is established；
When the source data for including in the knowledge base is structural data, after being pre-processed to the source data,
The entity is constructed by preset Entities Matching rule；
When the source data for including in the knowledge base is unstructured data, pass through Text Mining Technology or entity
After mark and identification technology handle the source data, the entity is constructed.
Optionally, entity of the embodiment of the present invention includes: physical entity and/or pseudo-entity；
Wherein, the physical entity includes following one or more kinds of entities: people, vehicle, house；The pseudo-entity
Including following one or more kinds of entities: organization, virtual identity.
Optionally, entity of the embodiment of the present invention includes following one or more kinds of attributes:
Tag attributes, natural quality, one or more primary key attributes；
Wherein, the primary key attribute is for distinguishing each entity；The tag attributes include calculating or returning according to business datum
The following one or more kinds of features received out: foundation characteristic, behavioural characteristic, relationship characteristic, geographical location；The natural quality
It include: the attribute value extracted from the data information；The attribute value includes following one or more kinds of attribute informations: body
Height, age, native place；The natural quality includes the primary attribute and/or sub-attribute divided according to preset strategy.
Optionally, relationship of the embodiment of the present invention includes following one or more kinds of relationships:
Dominance relation, recessive relationship；
Wherein, the dominance relation includes the relationship obtained by the direct correlation building between data；The recessive pass
System includes the association based on time, space, semanteme and/or characteristic between data, passes through preset relationship match rule
Or the relationship that machine learning mode obtains.
Optionally, recessiveness of embodiment of the present invention relationship by time between data, space, semanteme and characteristic pass
Connection includes: according to space-time trajectory data and behavioral data, using regulation engine according to default by the acquisition of preset matching rule
Match parameter matching obtain.Recessive relationship is led to by the association of time, space, semanteme and characteristic between data
Crossing machine learning mode and obtaining includes: to obtain positive sample and negative sample, the positive sample that will acquire and negative sample according to preset ratio
Be added to machine learning be in learnt, obtain the recessive relationship.The ratio of positive sample of the embodiment of the present invention and negative sample
Example is referred to correlation theory and determines；Such as positive sample and negative sample ratio can be 4:1, the number of positive sample and negative sample
Analysis can be carried out according to total sample number by those skilled in the art to determine.
Optionally, when relationship described in the embodiment of the present invention includes the dominance relation, the dominance relation includes with next
Kind or more than one relationships: set membership, conjugal relation, classmate's relationship, property belonging relation；
When the relationship includes the recessive relationship, the recessiveness relationship includes following one or more kinds of relationships: same
Row relationship lives relationship, accompanying relationship, accomplice relationship together.
Optionally, it establishes before data model, present invention method further include:
The event is obtained based on streaming message queue；
Wherein, the event includes following one or more kinds of contents: train trip event, vehicle bayonet event, net
Event, lodging event.
It should be noted that the embodiment of the present invention includes: to use using the acquisition that streaming message queue carries out the event
Key assignments (Key-Value) is storage architecture of the Nosql (database that Nosql refers to non-relational) of core as event；Base
The secondary index of event is established in Nosql, to meet Search Requirement；The embodiment of the present invention is counted according to the preset time cycle
According to update.
Optionally, the embodiment of the present invention includes: based on the streaming message queue acquisition event
Based on streaming message queue, the event is obtained from the behavioral data of the entity；
Wherein, the behavioral data includes following one or more kinds of data: main body, object, time, place, time
Section and event content；The event includes following one or more kinds of information: main body, object, time dimension information, geographical dimension
Spend information.
Step 102 constructs knowledge mapping according to the data model of foundation；
It should be noted that the method based on data model building knowledge mapping is referred to phase after establishing data model
Existing theory is designed realization in the technology of pass；
Optionally, data model of the embodiment of the present invention may include the data information based on public safety field, foundation
Data model.
Step 103 carries out data retrieval by the knowledge mapping of building.
Optionally, the embodiment of the present invention includes: by the knowledge mapping progress data retrieval constructed
Receive the retrieval information for carrying out data retrieval；
The retrieval process of data is carried out to the knowledge mapping of building according to the retrieval information received；
Wherein, the retrieval information includes the information comprising following one or more kinds of contents: the entity attributes,
The content of the type of the relationship, and/or the event.
Compared with the relevant technologies, technical scheme includes: the data information that basis includes entity, relationship and event,
Establish data model；Knowledge mapping is constructed according to the data model of foundation；Data retrieval is carried out by the knowledge mapping of building.This
Inventive embodiments improve the analysis quality of knowledge mapping.
Fig. 2 is the structural block diagram of the device of data processing of the embodiment of the present invention, as shown in Figure 2, comprising: modeling unit, figure
Compose unit and retrieval unit；Wherein,
Modeling unit is used for: according to the data information for including entity, relationship and event, establishing data model；
Optionally, the device of that embodiment of the invention further includes entity acquiring unit, is used for:
After handling pre-stored source data, the knowledge base for obtaining the data information is established；
When the source data for including in the knowledge base is structural data, after being pre-processed to the source data,
The entity is constructed by preset Entities Matching rule；
When the source data for including in the knowledge base is unstructured data, pass through Text Mining Technology or entity
After mark and identification technology handle the source data, the entity is constructed.
Optionally, entity of the embodiment of the present invention includes: physical entity and/or pseudo-entity；
Wherein, the physical entity includes following one or more kinds of entities: people, vehicle, house；The pseudo-entity
Including following one or more kinds of entities: organization, virtual identity.
Optionally, entity of the embodiment of the present invention includes following one or more kinds of attributes:
Tag attributes, natural quality, one or more primary key attributes；
Wherein, the primary key attribute is for distinguishing each entity；The tag attributes include calculating or returning according to business datum
The following one or more kinds of features received out: foundation characteristic, behavioural characteristic, relationship characteristic, geographical location；The natural quality
It include: the attribute value extracted from the data information；The attribute value includes following one or more kinds of attribute informations: body
Height, age, native place；The natural quality includes the primary attribute and/or sub-attribute divided according to preset strategy.
Optionally, relationship of the embodiment of the present invention includes following one or more kinds of relationships:
Dominance relation, recessive relationship；
Wherein, the dominance relation includes the relationship obtained by the direct correlation building between data；The recessive pass
System includes the association based on time, space, semanteme and/or characteristic between data, passes through preset relationship match rule
Or the relationship that machine learning mode obtains.
Optionally, recessiveness of embodiment of the present invention relationship by time between data, space, semanteme and characteristic pass
Connection includes: according to space-time trajectory data and behavioral data, using regulation engine according to default by the acquisition of preset matching rule
Match parameter matching obtain.Recessive relationship is led to by the association of time, space, semanteme and characteristic between data
Crossing machine learning mode and obtaining includes: to obtain positive sample and negative sample, the positive sample that will acquire and negative sample according to preset ratio
Be added to machine learning be in learnt, obtain the recessive relationship.The ratio of positive sample of the embodiment of the present invention and negative sample
Example is referred to correlation theory and determines；Such as positive sample and negative sample ratio can be 4:1, the number of positive sample and negative sample
Analysis can be carried out according to total sample number by those skilled in the art to determine.
Optionally, when relationship described in the embodiment of the present invention includes the dominance relation, the dominance relation includes with next
Kind or more than one relationships: set membership, conjugal relation, classmate's relationship, property belonging relation；
When the relationship includes the recessive relationship, the recessiveness relationship includes following one or more kinds of relationships: same
Row relationship lives relationship, accompanying relationship, accomplice relationship together.
Optionally, described device of the embodiment of the present invention further includes event acquiring unit, is used for:
The event is obtained based on streaming message queue；
Wherein, the event includes following one or more kinds of contents: train trip event, vehicle bayonet event, net
Event, lodging event.
It should be noted that the embodiment of the present invention includes: to use using the acquisition that streaming message queue carries out the event
Key assignments (Key-Value) is storage architecture of the Nosql (database that Nosql refers to non-relational) of core as event；Base
The secondary index of event is established in Nosql, to meet Search Requirement；The embodiment of the present invention is counted according to the preset time cycle
According to update.
Optionally, event acquiring unit described in the embodiment of the present invention is specifically used for:
Based on streaming message queue, the event is obtained from the behavioral data of the entity；
Wherein, the behavioral data includes following one or more kinds of data: main body, object, time, place, time
Section and event content；The event includes following one or more kinds of information: main body, object, time dimension information, geographical dimension
Spend information.
Tupu unit is used for: constructing knowledge mapping according to the data model of foundation；
Retrieval unit is used for: carrying out data retrieval by the knowledge mapping of building.
Optionally, retrieval unit of the embodiment of the present invention is specifically used for:
Receive the retrieval information for carrying out data retrieval；
The retrieval process of data is carried out to the knowledge mapping of building according to the retrieval information received；
Wherein, the retrieval information includes the information comprising following one or more kinds of contents: the entity attributes,
The content of the type of the relationship, and/or the event.
Compared with the relevant technologies, technical scheme includes: the data information that basis includes entity, relationship and event,
Establish data model；Knowledge mapping is constructed according to the data model of foundation；Data retrieval is carried out by the knowledge mapping of building.This
Inventive embodiments improve the analysis quality of knowledge mapping.
The embodiment of the present invention also provides a kind of computer storage medium, is stored with computer in the computer storage medium
Executable instruction, the method that the computer executable instructions are used to execute above-mentioned data processing.
The embodiment of the present invention also provides a kind of terminal, comprising: memory and processor；Wherein,
Processor is configured as executing the program instruction in memory；
Program instruction reads in processor and executes following operation:
According to the data information for including entity, relationship and event, data model is established；
Knowledge mapping is constructed according to the data model of foundation；
Data retrieval is carried out by the knowledge mapping of building.
Present invention method is carried out to understand detailed description below by way of using example, is only used for using example old
The present invention is stated, is not intended to limit the scope of protection of the present invention.
Using example
Present invention application example public safety field knowledge mapping (hereinafter referred to as public safety knowledge mapping) is with public
Based on safety net, internet, Internet of Things, committee do the data of the systems such as office, reflection natural person is including social life, warp
The knowledge mapping of feature, behavior and relationship in Ji activity and the network life.Present invention application exemplary data model includes entity-
Relationship-event data model；Wherein,
Entity in present invention application example includes the object with independent meaning of necessary being；This application example will be every
The characteristic information of a entity is known as entity attribute.In public safety knowledge mapping, entity includes: that natural person and natural person exist
The necessary being that can be touched in social life, the network life and economic activity and the things that can distinguish one another, can be object
It manages in entity (people, vehicle, house etc.), is also possible to pseudo-entity, such as organization (company, association), virtual identity (mail
Account, blog account, telephone number, instant messaging account etc.), Bank Account Number etc..Entity attribute is arranged in present invention application example
Comprising one or more primary key attributes, it is used to uniquely distinguish an entity；Also according to significance level and usage frequency, to reality
Other attributes of body are classified, such as entity attributes are defined as tag attributes and natural quality；Present invention application example
Tag attributes may include the feature for calculating or summarizing according to business datum；Such as foundation characteristic, behavioural characteristic, relationship are special
Sign, geographical location etc.；Natural quality includes the attribute value directly generated by data, such as height, age, native place, according to nature
The significance level of attribute in practical applications is different, and above-mentioned attribute can be divided into primary attribute and secondary category by present invention application example
Property；The example that 1 present invention application example of table classifies to entity attribute determines the attributive classification that entity is people referring to table 1
Justice is major key, primary attribute (natural quality), sub-attribute (natural quality), tag attributes；
| Attribute-name | Value type | Attribute type |
| Identification card number | Character string (string) | Major key |
| Name | string | Primary attribute |
| Former name | string | Primary attribute |
| Household register address | string | Sub-attribute |
| Recessive emphasis people | Boolean (bool) | Tag attributes |
| Repeatedly abnormal trip | bool | Tag attributes |
Table 1
Relationship is the present invention using the basic element in example knowledge mapping, and there are different relationships between different entities.
Relationship can define the semantic interlink between entity, reflect the correlation between different entities, and the attribute of relationship can describe relationship
Power, type, the frequency etc..Relationship is divided into dominance relation, recessive pass according to the forming process of relationship by present invention application example
System；Wherein, dominance relation can be constructed by the direct correlation between data；Such as conjugal relation, classmate's relationship, property
Belonging relation etc..Recessive relationship can by association in time, space correlation, semantic association and the feature association etc. between data,
It is determining by certain matching rule or is obtained according to machine learning method etc., such as relationship of going together, live relationship, accompanying relationship together
Deng.
Present invention application example recessiveness relationship is different from weak contextual definition.Present invention application example recessiveness relationship includes: root
According to space-time trajectory data and behavioral data, is obtained using regulation engine according to the matching of preset match parameter, compare dominance relation
With stronger timeliness and reliability.The building quantity of recessive relationship is typically larger than the building quantity of dominance relation.It is recessive
The foundation of building relationship is generally included in relationship, present invention application example is defined as relationship details.
It is gone together below using multiple train as the example of recessive relationship, table 2 illustrates type, description and the relationship of relationship
Details:
Table 2
There are also many limitations and deficiencies for domain knowledge map at present, one of them is that the modeling to entity timing attribute lacks
It loses.Especially in public safety field, other than the data of two kinds of objects of entity and relationship, some track data, tool
There are stronger space-time characteristic and timeliness.This kind of data, although the building and relationship building to entity both provide information, its
Strong space-time characteristic itself, can not be embodied directly in the topological structure or attribute of entity-relation.In addition, time and space conduct
Most important dimension often relates to a large amount of interval computation and converging operation.Therefore, present invention application example is known in public safety
Know in spectrum data model, devises third class object: event (event)；The behavioral data of entity object, i.e., according to main body,
The various aspects information structuring event such as object, time, place, period and event content.One in event description real world
The behavior that entity occurs in a time point (section) or spatial point (range), event have the characteristics that one it is important: attribute value
Constant, therefore, the storage for event data calculates, and can be optimized according to this feature.
Event is very extensive in public safety field, is all defined in all kinds of different entities, such as: it is directed to a nature
People, used during taking train record constitute a train trip event；For a vehicle, vehicle passes through the data structure of traffic block port
At a vehicle bayonet event.Event is different from entity, and entity belongs to partially static description, and event have strong timeliness and
The characteristics of incremental.In addition, present invention application example event is the important foundation for calculating recessive relationship, with relation data one
Sample, event are necessarily dependent upon the main body in entity, that is, event.Reasonable construction event, to promotion public safety knowledge mapping
Service efficiency it is most important.
Table 3 is the example that the present invention applies example event, referring to table 3, all kinds of events of present invention application example, including master
Body, object, dimensional information (wherein, dimension may include time dimension and/or geography dimensionality):
| Event title | Main body | Object | Dimension |
| Train trip | People | Train | Time |
| Aircraft departure from port | People | Flight | Time |
| It stays | People | Hotel | Time, place |
| Vehicle bayonet | Vehicle | Bayonet | Time, place |
| Vehicle violation | Vehicle | Number violating the regulations | Time, place |
| Call | Phone | Phone | Time |
Table 3
For public safety knowledge mapping, present invention application example according to entity-relation-event carry out data model
Building includes:
The connection between data source and data is combed, public safety knowledge base is established；Optionally, present invention application example pair
Entity, relationship, event are such as given a definition respectively:
Entity may include following one or more kinds of contents: people, vehicle, case, cell-phone number etc.；
Relationship may include following one or more kinds of content: set membership, with family relationship, accomplice relationship, Tong Hangguan
Be, live relationship together etc.；
Event may include following one or more kinds of contents: train trip event, Internet bar's event, vehicle bayonet thing
Part, lodging event etc.；
The data of public safety industry generally comprise the unstructured data of internal structural data and outside, for
Different types of data, present invention application example carry out entity building in the following ways: 1, being directed to structural data, pass through number
According to detect, data understanding, data cleansing, data normalization, data mapping, data correlation, the processing such as data fusion, using preparatory
The matching rule of definition completes the building of entity；2, it is directed to unstructured data, rule-based text mining skill can be used
The building of art or entity mark and identification technology completion entity based on Active Learning, deep learning；Based on building entity
Purpose, those skilled in the art are referred to and the method for above-mentioned building entity realizes the building of entity, such as based on the above method
What realizes that entity building is referred to correlation theory design and realizes.
According to the definition of relationship, present invention application example carries out the building of relationship using following manner；Application of the present invention is shown
Example can directly extract dominance relation from data, and the rule for extracting dominance relation can be based on correlation by those skilled in the art
Theory determines；Present invention application example can determine recessive relationship in the following manner: 1, being closed based on the setting of event data feature
After the matching rule of system, recessive relationship is determined according to the relationship match rule of setting；By taking hotel lodging event data as an example, data
Format is " personnel identity demonstrate,proves m- check-out time when number-personnel's name-hotel title-room number-is moved in ".By room number and
The time is moved in as matching field, the personnel for determining and moving on the same day in same room can be matched, there is the pass of " roomate lives together "
System.It is similar can be by the matched data of matching rule also: train is ridden data (m- vehicle when rider-riding time-booking
Secondary number-coach number-seat number-starting station-destination)；Internet bar's Internet data (upper netizen-on-line time-downtime-Internet bar
Title-uses identification number) etc..2, recessive relationship is determined based on machine learning；Present invention application example, which is checked on, joins computational problem
Specification constituent class problem.When present invention application example determines recessive relationship based on machine learning, positive sample and negative sample ratio can
To determine referring to correlation theory, such as positive sample and negative sample ratio can be 4:1, and the number of positive sample and negative sample can be with
Analysis is carried out according to total sample number by those skilled in the art to determine；Present invention application example is obtained according to social inquiry report
The relation loop data of 5000 people or so, whole relation total amount will have the positive sample of strong relationship at 15.3 ten thousand in these data.?
It samples from national demographic data and 30,000 people and randomly selects 30 people for everyone, establish the personnel's relationship pair being not in contact with, as
Negative sample.Meanwhile using feature, associated event data feature and the relevant statistical nature in personnel's entity as core, construction
Eigenvectors matrix.Based on above-mentioned sample and feature, classification based training and cross validation are carried out using random forests algorithm.The present invention
When relationship threshold using example setting random forests algorithm is 0.85, the precision of data model result can achieve 0.81, call together
The rate of returning can reach 0.72.
Definition of the present invention application example according to event, extracts corresponding event data, due to the event class of public safety
Data have the characteristics that generate that speed is fast, total amount of data is big, real-time incremental updates, present invention application example in the following ways into
It acts the building of part: completing the improvement and landing of event data using streaming message queue；It the use of key assignments (Key-Value) is core
Storage architecture of the Nosql (database that Nosql refers to non-relational) of the heart as event；The two of event are established based on Nosql
Grade index, to meet Search Requirement；Data update is carried out according to the preset time cycle.
The entity built, relationship, event are imported into knowledge mapping tool in the related technology, entity and relationship are with relationship
The form of figure show in the figure can pop-up check the list of thing of some entity, entity or relationship are clicked in figure, also can be on the right side
Its attribute relevant information is checked in side.
" entity-relation-event " object data model is utilized, present invention application example is by the various seas of public safety field
Amount data summarization be fused into for people, thing, the entities such as object, tissue, virtual identity, joined according to attribute relationship therein, space-time
System, semantic relation, feature connection etc., establish the own event trace of mutual relationship and entity, ultimately form one by people,
Thing, the public safety knowledge mappings of the compositions such as object, tissue, virtual identity.
Data and business characteristic based on public safety field define a kind of " entity-pass of the knowledge mapping of public safety
System-event " data model, abundant public safety knowledge mapping simultaneously promote its service efficiency.
Present invention application example can be scanned for using the major key in entity as keyword, can also be with relationship, event
In some information scanned for as search term.
For public safety field data and business characteristic, the present invention is devised based on " entity-relation-event " data mould
Type: entity, that is, people in the real world, thing, object, tissue, the point in corresponding knowledge mapping graph data structure；Relationship such as people with
Kinship, call relationship between people etc. correspond to the side in knowledge mapping graph data structure；Event refers to entity at some
Between put or a behavior that spatial point occurs such as someone in certain day taken certain time train, be us for public safety business number
The class object specially designed in comprising a large amount of track datas is different from " entity-relation " topology of general graph data structure
Structure.By introducing event data, heavy Bian Wenti of the world knowledge map for public safety business scenario not only can solve, separately
On the one hand more potential relationships can be calculated and excavated using event data, promote the analysis effect of public safety knowledge mapping
Rate.
Those of ordinary skill in the art will appreciate that all or part of the steps in the above method can be instructed by program
Related hardware (such as processor) is completed, and described program can store in computer readable storage medium, as read-only memory,
Disk or CD etc..Optionally, one or more integrated circuits also can be used in all or part of the steps of above-described embodiment
It realizes.Correspondingly, each module/unit in above-described embodiment can take the form of hardware realization, such as pass through integrated electricity
Its corresponding function is realized on road, can also be realized in the form of software function module, such as is stored in by processor execution
Program/instruction in memory realizes its corresponding function.The present invention is not limited to the hardware and softwares of any particular form
In conjunction with.
Although disclosed herein embodiment it is as above, the content only for ease of understanding the present invention and use
Embodiment is not intended to limit the invention.Technical staff in any fields of the present invention is taken off not departing from the present invention
Under the premise of the spirit and scope of dew, any modification and variation, but the present invention can be carried out in the form and details of implementation
Scope of patent protection, still should be subject to the scope of the claims as defined in the appended claims.
Claims (20)
1. a kind of method of data processing characterized by comprising
According to the data information for including entity, relationship and event, data model is established；
Knowledge mapping is constructed according to the data model of foundation；
Data retrieval is carried out by the knowledge mapping of building.
2. the method according to claim 1, wherein described establish before data model, the method also includes
The entity is obtained in the following manner:
After handling pre-stored source data, the knowledge base for obtaining the data information is established；
When the source data for including in the knowledge base is structural data, after being pre-processed to the source data, pass through
Preset Entities Matching rule constructs the entity；
When the source data for including in the knowledge base is unstructured data, marked by Text Mining Technology or entity
After handling with identification technology the source data, the entity is constructed.
3. method according to claim 1 or 2, which is characterized in that the entity includes: physical entity and/or virtual reality
Body；
Wherein, the physical entity includes following one or more kinds of entities: people, vehicle, house；The pseudo-entity includes
Following one or more entity: organization, virtual identity.
4. method according to claim 1 or 2, which is characterized in that the entity includes following one or more kinds of categories
Property:
Tag attributes, natural quality, one or more primary key attributes；
Wherein, the primary key attribute is for distinguishing each entity；The tag attributes include calculating or summarizing according to business datum
Following one or more kinds of features: foundation characteristic, behavioural characteristic, relationship characteristic, geographical location；The natural quality packet
It includes: the attribute value extracted from the data information；The attribute value includes following one or more kinds of attribute informations: height,
Age, native place；The natural quality includes the primary attribute and/or sub-attribute divided according to preset strategy.
5. the method according to claim 1, wherein the relationship includes following one or more kinds of relationships:
Dominance relation, recessive relationship；
Wherein, the dominance relation includes the relationship obtained by the direct correlation building between data；The recessiveness relationship packet
The association based on time, space, semanteme and/or characteristic between data is included, preset relationship match rule or machine are passed through
The relationship that device mode of learning obtains.
6. according to the method described in claim 5, it is characterized in that,
When the relationship includes the dominance relation, the dominance relation includes following one or more kinds of relationships: Fu Ziguan
System, conjugal relation, classmate's relationship, property belonging relation；
When the relationship includes the recessive relationship, the recessiveness relationship includes following one or more kinds of relationships: Tong Hangguan
It is, lives relationship, accompanying relationship, accomplice relationship together.
7. according to claim 1, method described in 2,5 or 6, which is characterized in that described to establish before data model, the method
Further include:
The event is obtained based on streaming message queue；
Wherein, the event includes following one or more kinds of contents: train trip event, vehicle bayonet event, Internet bar's thing
Part, lodging event.
8. the method according to the description of claim 7 is characterized in that described obtain the event package based on streaming message queue
It includes:
Based on streaming message queue, the event is obtained from the behavioral data of the entity；
Wherein, the behavioral data includes following one or more kinds of data: main body, object, the time, place, the period and
Event content；The event includes following one or more kinds of information: main body, object, time dimension information, geography dimensionality letter
Breath.
9. according to method described in right 1,2,5 or 6, which is characterized in that the knowledge mapping by building carries out data inspection
Rope includes:
Receive the retrieval information for carrying out data retrieval；
The retrieval process of data is carried out to the knowledge mapping of building according to the retrieval information received；
Wherein, the retrieval information includes the information comprising following one or more kinds of contents: the entity attributes, described
The content of the type of relationship, and/or the event.
10. a kind of device of data processing characterized by comprising modeling unit, Tupu unit and retrieval unit；Wherein,
Modeling unit is used for: according to the data information for including entity, relationship and event, establishing data model；
Tupu unit is used for: constructing knowledge mapping according to the data model of foundation；
Retrieval unit is used for: carrying out data retrieval by the knowledge mapping of building.
11. device according to claim 10, which is characterized in that described device further includes entity acquiring unit, is used for:
After handling pre-stored source data, the knowledge base for obtaining the data information is established；
When the source data for including in the knowledge base is structural data, after being pre-processed to the source data, pass through
Preset Entities Matching rule constructs the entity；
When the source data for including in the knowledge base is unstructured data, marked by Text Mining Technology or entity
After handling with identification technology the source data, the entity is constructed.
12. device described in 0 or 11 according to claim 1, which is characterized in that the entity includes: physical entity and/or virtual
Entity；
Wherein, the physical entity includes following one or more kinds of entities: people, vehicle, house；The pseudo-entity includes
Following one or more entity: organization, virtual identity.
13. device described in 0 or 11 according to claim 1, which is characterized in that the entity includes following one or more
Attribute:
Tag attributes, natural quality, one or more primary key attributes；
Wherein, the primary key attribute is for distinguishing each entity；The tag attributes include calculating or summarizing according to business datum
Following one or more kinds of features: foundation characteristic, behavioural characteristic, relationship characteristic, geographical location；The natural quality packet
It includes: the attribute value extracted from the data information；The attribute value includes following one or more kinds of attribute informations: height,
Age, native place；The natural quality includes the primary attribute and/or sub-attribute divided according to preset strategy.
14. device according to claim 10, which is characterized in that the relationship includes following one or more kinds of passes
System:
Dominance relation, recessive relationship；
Wherein, the dominance relation includes the relationship obtained by the direct correlation building between data；The recessiveness relationship packet
The association based on time, space, semanteme and/or characteristic between data is included, preset relationship match rule or machine are passed through
The relationship that device mode of learning obtains.
15. device according to claim 14, which is characterized in that
When the relationship includes the dominance relation, the dominance relation includes following one or more kinds of relationships: Fu Ziguan
System, conjugal relation, classmate's relationship, property belonging relation；
When the relationship includes the recessive relationship, the recessiveness relationship includes following one or more kinds of relationships: Tong Hangguan
It is, lives relationship, accompanying relationship, accomplice relationship together.
16. device described in 0,11,14 or 15 according to claim 1, which is characterized in that described device further includes that event obtains list
Member is used for:
The event is obtained based on streaming message queue；
Wherein, the event includes following one or more kinds of contents: train trip event, vehicle bayonet event, Internet bar's thing
Part, lodging event.
17. device according to claim 16, which is characterized in that the event acquiring unit is specifically used for:
Based on streaming message queue, the event is obtained from the behavioral data of the entity；
Wherein, the behavioral data includes following one or more kinds of data: main body, object, the time, place, the period and
Event content；The event includes following one or more kinds of information: main body, object, time dimension information, geography dimensionality letter
Breath.
18. device described in 0,11,14 or 15 according to claim 1, which is characterized in that the retrieval unit is specifically used for:
Receive the retrieval information for carrying out data retrieval；
The retrieval process of data is carried out to the knowledge mapping of building according to the retrieval information received；
Wherein, the retrieval information includes the information comprising following one or more kinds of contents: the entity attributes, described
The content of the type of relationship, and/or the event.
19. a kind of computer storage medium, computer executable instructions, the calculating are stored in the computer storage medium
Method of the machine executable instruction for data processing described in any one of perform claim requirement 1~9.
20. a kind of terminal, comprising: memory and processor；Wherein,
Processor is configured as executing the program instruction in memory；
Program instruction reads in processor and executes following operation:
According to the data information for including entity, relationship and event, data model is established；Knowledge is constructed according to the data model of foundation
Map；
Data retrieval is carried out by the knowledge mapping of building.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910113903.3A CN109918452A (en) | 2019-02-14 | 2019-02-14 | A kind of method, apparatus of data processing, computer storage medium and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910113903.3A CN109918452A (en) | 2019-02-14 | 2019-02-14 | A kind of method, apparatus of data processing, computer storage medium and terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109918452A true CN109918452A (en) | 2019-06-21 |
Family
ID=66961566
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910113903.3A Pending CN109918452A (en) | 2019-02-14 | 2019-02-14 | A kind of method, apparatus of data processing, computer storage medium and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109918452A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110472107A (en) * | 2019-08-22 | 2019-11-19 | 腾讯科技（深圳）有限公司 | Multi-modal knowledge mapping construction method, device, server and storage medium |
| CN110491106A (en) * | 2019-07-22 | 2019-11-22 | 深圳壹账通智能科技有限公司 | Data early warning method, device and the computer equipment of knowledge based map |
| CN110580269A (en) * | 2019-09-06 | 2019-12-17 | 中科院合肥技术创新工程院 | public safety event-oriented spatio-temporal data dynamic evolution diagram generation method and dynamic evolution system thereof |
| CN111309828A (en) * | 2020-03-27 | 2020-06-19 | 广东省智能制造研究所 | Knowledge graph construction method and device for large-scale equipment |
| CN111563170A (en) * | 2020-04-30 | 2020-08-21 | 北京明略软件系统有限公司 | Knowledge graph generation method and device, computer storage medium and terminal |
| CN111666419A (en) * | 2020-05-27 | 2020-09-15 | 北京北大软件工程股份有限公司 | Knowledge graph construction method and device for legal data |
| CN111930860A (en) * | 2020-08-14 | 2020-11-13 | 广州大学 | Multidimensional data association and analysis method and device, storage medium and computer equipment |
| CN112445889A (en) * | 2020-11-30 | 2021-03-05 | 杭州海康威视数字技术股份有限公司 | Method for storing data and retrieving data and related equipment |
| CN112836511A (en) * | 2021-01-27 | 2021-05-25 | 北京计算机技术及应用研究所 | Knowledge graph context embedding method based on cooperative relationship |
| CN113297388A (en) * | 2021-04-25 | 2021-08-24 | 中国人民解放军军事科学院战争研究院 | Game analysis-oriented strategic event chain-lapping visualization method |
| CN113326345A (en) * | 2020-02-28 | 2021-08-31 | 拓尔思天行网安信息技术有限责任公司 | Knowledge graph analysis and application method, platform and equipment based on dynamic ontology |
| CN113360674A (en) * | 2021-06-23 | 2021-09-07 | 浪潮软件科技有限公司 | Cognitive atlas analysis method based on dynamic ontology model |
| CN113689697A (en) * | 2021-08-13 | 2021-11-23 | 南京理工大学 | Traffic incident influence analysis method based on rule matching and knowledge graph |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107665252A (en) * | 2017-09-27 | 2018-02-06 | 深圳证券信息有限公司 | A kind of method and device of creation of knowledge collection of illustrative plates |
| 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 |
| US10083228B2 (en) * | 2014-05-06 | 2018-09-25 | Baidu Online Network Technology (Beijing) Co., Ltd. | Searching method and apparatus |
| CN108596439A (en) * | 2018-03-29 | 2018-09-28 | 北京中兴通网络科技股份有限公司 | A kind of the business risk prediction technique and system of knowledge based collection of illustrative plates |
| CN109145153A (en) * | 2018-07-02 | 2019-01-04 | 北京奇艺世纪科技有限公司 | It is intended to recognition methods and the device of classification |
| CN109255031A (en) * | 2018-09-20 | 2019-01-22 | 苏州友教习亦教育科技有限公司 | The data processing method of knowledge based map |
| CN109710701A (en) * | 2018-12-14 | 2019-05-03 | 浪潮软件股份有限公司 | A kind of automated construction method for public safety field big data knowledge mapping |
-
2019
- 2019-02-14 CN CN201910113903.3A patent/CN109918452A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10083228B2 (en) * | 2014-05-06 | 2018-09-25 | Baidu Online Network Technology (Beijing) Co., Ltd. | Searching method and apparatus |
| 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 |
| CN107665252A (en) * | 2017-09-27 | 2018-02-06 | 深圳证券信息有限公司 | A kind of method and device of creation of knowledge collection of illustrative plates |
| CN108596439A (en) * | 2018-03-29 | 2018-09-28 | 北京中兴通网络科技股份有限公司 | A kind of the business risk prediction technique and system of knowledge based collection of illustrative plates |
| CN109145153A (en) * | 2018-07-02 | 2019-01-04 | 北京奇艺世纪科技有限公司 | It is intended to recognition methods and the device of classification |
| CN109255031A (en) * | 2018-09-20 | 2019-01-22 | 苏州友教习亦教育科技有限公司 | The data processing method of knowledge based map |
| CN109710701A (en) * | 2018-12-14 | 2019-05-03 | 浪潮软件股份有限公司 | A kind of automated construction method for public safety field big data knowledge mapping |
Non-Patent Citations (1)
| Title |
|---|
| 杨威: "AI如何实现从个体赋能到全局智能", 《HTTPS://MYSLIDE.CN/SLIDES/6640》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110491106B (en) * | 2019-07-22 | 2022-03-18 | 深圳壹账通智能科技有限公司 | Data early warning method and device based on knowledge graph and computer equipment |
| CN110491106A (en) * | 2019-07-22 | 2019-11-22 | 深圳壹账通智能科技有限公司 | Data early warning method, device and the computer equipment of knowledge based map |
| CN110472107A (en) * | 2019-08-22 | 2019-11-19 | 腾讯科技（深圳）有限公司 | Multi-modal knowledge mapping construction method, device, server and storage medium |
| CN110472107B (en) * | 2019-08-22 | 2024-01-30 | 腾讯科技（深圳）有限公司 | Multi-mode knowledge graph construction method, device, server and storage medium |
| CN110580269A (en) * | 2019-09-06 | 2019-12-17 | 中科院合肥技术创新工程院 | public safety event-oriented spatio-temporal data dynamic evolution diagram generation method and dynamic evolution system thereof |
| CN113326345A (en) * | 2020-02-28 | 2021-08-31 | 拓尔思天行网安信息技术有限责任公司 | Knowledge graph analysis and application method, platform and equipment based on dynamic ontology |
| CN111309828A (en) * | 2020-03-27 | 2020-06-19 | 广东省智能制造研究所 | Knowledge graph construction method and device for large-scale equipment |
| CN111309828B (en) * | 2020-03-27 | 2024-02-20 | 广东省智能制造研究所 | Knowledge graph construction method and device for large-scale equipment |
| CN111563170A (en) * | 2020-04-30 | 2020-08-21 | 北京明略软件系统有限公司 | Knowledge graph generation method and device, computer storage medium and terminal |
| CN111666419A (en) * | 2020-05-27 | 2020-09-15 | 北京北大软件工程股份有限公司 | Knowledge graph construction method and device for legal data |
| CN111930860A (en) * | 2020-08-14 | 2020-11-13 | 广州大学 | Multidimensional data association and analysis method and device, storage medium and computer equipment |
| CN112445889A (en) * | 2020-11-30 | 2021-03-05 | 杭州海康威视数字技术股份有限公司 | Method for storing data and retrieving data and related equipment |
| CN112836511A (en) * | 2021-01-27 | 2021-05-25 | 北京计算机技术及应用研究所 | Knowledge graph context embedding method based on cooperative relationship |
| CN112836511B (en) * | 2021-01-27 | 2024-01-30 | 北京计算机技术及应用研究所 | Knowledge graph context embedding method based on cooperative relationship |
| CN113297388B (en) * | 2021-04-25 | 2023-08-11 | 中国人民解放军军事科学院战争研究院 | Strategic event chained visualization method oriented to game analysis |
| CN113297388A (en) * | 2021-04-25 | 2021-08-24 | 中国人民解放军军事科学院战争研究院 | Game analysis-oriented strategic event chain-lapping visualization method |
| CN113360674A (en) * | 2021-06-23 | 2021-09-07 | 浪潮软件科技有限公司 | Cognitive atlas analysis method based on dynamic ontology model |
| CN113689697A (en) * | 2021-08-13 | 2021-11-23 | 南京理工大学 | Traffic incident influence analysis method based on rule matching and knowledge graph |
| CN113689697B (en) * | 2021-08-13 | 2022-06-28 | 南京理工大学 | Traffic incident influence analysis method, system, equipment and readable storage medium based on rule matching and knowledge graph |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109918452A (en) | A kind of method, apparatus of data processing, computer storage medium and terminal | |
| CN109710701B (en) | Automatic construction method for big data knowledge graph in public safety field | |
| CN109918511B (en) | BFS and LPA based knowledge graph anti-fraud feature extraction method | |
| CN107229708B (en) | Personalized travel service big data application system and method | |
| CN110413707A (en) | The excavation of clique's relationship is cheated in internet and checks method and its system | |
| CN106548381A (en) | Intelligent subscriber tag systems and implementation method | |
| CN108460136A (en) | Electric power O＆M information knowledge map construction method | |
| CN104573130B (en) | The entity resolution method and device calculated based on colony | |
| CN110457404A (en) | Social media account-classification method based on complex heterogeneous network | |
| CN107515915A (en) | User based on user behavior data identifies correlating method | |
| CN108647800A (en) | A kind of online social network user missing attribute forecast method based on node insertion | |
| CN111191099B (en) | User activity type identification method based on social media | |
| CN109408821A (en) | A kind of corpus generation method, calculates equipment and storage medium at device | |
| CN110489565A (en) | Based on the object root type design method and system in domain knowledge map ontology | |
| CN115238688B (en) | Method, device, equipment and storage medium for analyzing association relation of electronic information data | |
| CN115794803A (en) | Engineering audit problem monitoring method and system based on big data AI technology | |
| CN107767280A (en) | A kind of high-quality node detecting method based on element of time | |
| CN110019820A (en) | Main suit and present illness history symptom Timing Coincidence Detection method in a kind of case history | |
| CN101295388A (en) | Credit estimation method and system | |
| CN110222180A (en) | A kind of classification of text data and information mining method | |
| Yu et al. | Research on situational perception of power grid business based on user portrait | |
| CN109828995A (en) | A kind of diagram data detection method, the system of view-based access control model feature | |
| CN115099680A (en) | Risk management method, device, equipment and storage medium | |
| CN111737594B (en) | Virtual network role behavior modeling method based on unsupervised label generation | |
| CN114896977A (en) | Dynamic evaluation method for entity service trust value of Internet of things |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190621 |
|
| RJ01 | Rejection of invention patent application after publication |