CN110457536A - A kind of knowledge mapping construction method and device - Google Patents
A kind of knowledge mapping construction method and device Download PDFInfo
- Publication number
- CN110457536A CN110457536A CN201910760043.2A CN201910760043A CN110457536A CN 110457536 A CN110457536 A CN 110457536A CN 201910760043 A CN201910760043 A CN 201910760043A CN 110457536 A CN110457536 A CN 110457536A
- Authority
- CN
- China
- Prior art keywords
- label
- feature label
- fisrt feature
- target person
- feature
- 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
- 238000013507 mapping Methods 0.000 title claims abstract description 60
- 238000010276 construction Methods 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 claims abstract description 13
- 238000000605 extraction Methods 0.000 claims description 12
- 238000001228 spectrum Methods 0.000 claims 1
- 230000008520 organization Effects 0.000 description 15
- 238000010586 diagram Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 4
- 238000009412 basement excavation Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- 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)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This specification provides a kind of knowledge mapping construction method and device, the method comprise the steps that determine at least one target person and at least two region names, obtains the corresponding personage's history data of each target person at least one described target person；Time interval and the corresponding characteristic information of the fisrt feature label existing for fisrt feature label corresponding with the target person and the fisrt feature label are obtained from personage's history data；Time interval and the corresponding characteristic information of the second feature label existing for second feature label corresponding with the target person and second feature label are obtained from personage's history data；Knowledge mapping is constructed based on the target person, region name, fisrt feature label, second feature label, the time interval and characteristic information.
Description
Technical field
This specification is related to computer science and technology field, in particular to a kind of knowledge mapping construction method, device, calculating
Equipment and computer readable storage medium.
Background technique
With the development of internet, the situation of explosive growth is presented in network data content, big due to internet content
Scale, heterogeneous feature polynary, institutional framework is loose, effectively obtain information to people and knowledge propose challenge, knowledge mapping
(Knowledge Graph) is more educated group of Internet era with its powerful semantic processing ability and open organizational capacity
It knits and lays a good foundation with intelligent use.Typical character relation knowledge mapping is mainly using family relationship, social networks as base at present
Plinth, the duties such as the father and son for including, mothers and sons, friend, partner, lovers' relationship work, position, technical ability that still professional social graph includes
Industry social networks, however, the character relation in existing character relation knowledge mapping be mostly it is static, cannot support from time dimension
Degree and region dimension excavate the deep relationship between personage.
Summary of the invention
In view of this, this specification embodiment provides a kind of knowledge mapping construction method, device, calculates equipment and calculating
Machine readable storage medium storing program for executing, to solve technological deficiency existing in the prior art.
According to this specification embodiment in a first aspect, providing a kind of knowledge mapping construction method, comprising:
It determines at least one target person and at least two region names, obtains each at least one described target person
The corresponding personage's history data of the target person；
Fisrt feature label corresponding with the target person and described first are obtained from personage's history data
Time interval existing for feature tag and the corresponding characteristic information of the fisrt feature label；
Second feature label corresponding with the target person and second feature are obtained from personage's history data
Time interval existing for label and the corresponding characteristic information of the second feature label；
Based on the target person, region name, fisrt feature label, second feature label, the fisrt feature label
Time interval existing for existing time interval and the corresponding characteristic information of the fisrt feature label and second feature label
Characteristic information corresponding with the second feature label constructs knowledge mapping.
According to the second aspect of this specification embodiment, a kind of knowledge mapping construction device is provided, comprising:
Entity determining module, is configured to determine that at least one target person and at least two region names, described in acquisition
The corresponding personage's history data of each target person at least one target person；
Fisrt feature label acquisition module is configured as obtaining and the target person pair from personage's history data
Time interval existing for the fisrt feature label and the fisrt feature label answered and the corresponding spy of the fisrt feature label
Reference breath；
Second feature label acquisition module is configured as obtaining and the target person pair from personage's history data
Time interval existing for the second feature label and second feature label answered and the corresponding feature letter of the second feature label
Breath；
Knowledge mapping constructs module, is configured as based on the target person, region name, fisrt feature label, second
Time interval existing for feature tag, the fisrt feature label and the corresponding characteristic information of the fisrt feature label and
Time interval existing for two feature tags and the corresponding characteristic information of the second feature label construct knowledge mapping.
According to the third aspect of this specification embodiment, a kind of calculating equipment is provided, including memory, processor and deposit
The computer instruction that can be run on a memory and on a processor is stored up, is known described in realization when the processor executes described instruction
The step of knowing map construction method.
According to the fourth aspect of this specification embodiment, a kind of computer readable storage medium is provided, is stored with meter
The step of calculation machine instruction, which realizes knowledge mapping construction method when being executed by processor.
The application by the corresponding personage's history data of at least one target person carry out feature tag extraction, according to
Support feature tag goes out the social relationships of the target person from multiple dimension maps, meanwhile, by corresponding from extraction feature label
Time interval and feature tag and region name inclusion relation, enable the application construct knowledge mapping support to use
Family carries out the excavation of depth from time dimension and region dimension to the particular social relationship between target person, infers specific mesh
The social relationships having between mark personage in special time period or specific region, to further excavate tacit knowledge and enrich
Extend knowledge mapping.
Detailed description of the invention
Fig. 1 is the structural block diagram provided by the embodiments of the present application for calculating equipment；
Fig. 2 is the flow chart of knowledge mapping construction method provided by the embodiments of the present application；
Fig. 3 is another flow chart of knowledge mapping construction method provided by the embodiments of the present application；
Fig. 4 is another flow chart of knowledge mapping construction method provided by the embodiments of the present application；
Fig. 5 is another flow chart of knowledge mapping construction method provided by the embodiments of the present application；
Fig. 6 is another flow chart of knowledge mapping construction method provided by the embodiments of the present application；
Fig. 7 is the schematic diagram of knowledge mapping provided by the embodiments of the present application；
Fig. 8 is the structural schematic diagram of knowledge mapping construction device provided by the embodiments of the present application.
Specific embodiment
Many details are explained in the following description in order to fully understand the application.But the application can be with
Much it is different from other way described herein to implement, those skilled in the art can be without prejudice to the application intension the case where
Under do similar popularization, therefore the application is not limited by following public specific implementation.
The term used in this specification one or more embodiment be only merely for for the purpose of describing particular embodiments,
It is not intended to be limiting this specification one or more embodiment.In this specification one or more embodiment and appended claims
The "an" of singular used in book, " described " and "the" are also intended to including most forms, unless context is clearly
Indicate other meanings.It is also understood that term "and/or" used in this specification one or more embodiment refers to and includes
One or more associated any or all of project listed may combine.
It will be appreciated that though may be retouched using term first, second etc. in this specification one or more embodiment
Various information are stated, but these information should not necessarily be limited by these terms.These terms are only used to for same type of information being distinguished from each other
It opens.For example, first can also be referred to as second, class in the case where not departing from this specification one or more scope of embodiments
As, second can also be referred to as first.Depending on context, word as used in this " if " can be construed to
" ... when " or " when ... " or " in response to determination ".
Firstly, the vocabulary of terms being related to one or more embodiments of the invention explains.
Knowledge mapping: substantially knowledge mapping is intended to describe various entities or concept and its pass present in real world
System constitutes a huge semantic network figure, and node presentation-entity or concept, side are then made of attribute or relationship.
Entity: referring to distinguishability and certain self-existent things, such as a certain individual, some city, certain
A kind of plant etc., a certain commodity etc., world's all things on earth is made of specific things, this refers to entity, for example, " China ", " U.S. ",
" Japan " etc., entity are the most basic elements in knowledge mapping, and there are different relationships between different entities.
Relationship: between different entities certain connection, such as people-" living in "-Beijing, Zhang San and Li Si be " friend ",
Logistic regression is deep learning " guide's knowledge " etc..
Attribute: being directed toward its attribute from an entity, and different attribute types corresponds to the side of different type attribute, such as
" area ", " population ", " capital " are several different attributes, and attribute value refers mainly to the value of object specified attribute, such as 9,600,000 flat
Fang Gongli etc..
In this application, it provides a kind of knowledge mapping construction method, device, calculate equipment and computer-readable storage medium
Matter is described in detail one by one in the following embodiments.
Fig. 1 shows the structural block diagram of the calculating equipment 100 according to one embodiment of this specification.The calculating equipment 100
Component includes but is not limited to memory 110 and processor 120.Processor 120 is connected with memory 110 by bus 130, number
According to library 150 for saving data.
Calculating equipment 100 further includes access device 140, access device 140 enable calculate equipment 100 via one or
Multiple networks 160 communicate.The example of these networks includes public switched telephone network (PSTN), local area network (LAN), wide area network
(WAN), the combination of the communication network of personal area network (PAN) or such as internet.Access device 140 may include wired or wireless
One or more of any kind of network interface (for example, network interface card (NIC)), such as IEEE802.11 wireless local area
Net (WLAN) wireless interface, worldwide interoperability for microwave accesses (Wi-MAX) interface, Ethernet interface, universal serial bus (USB) connect
Mouth, cellular network interface, blue tooth interface, near-field communication (NFC) interface, etc..
In one embodiment of this specification, other unshowned portions in the above-mentioned component and Fig. 1 of equipment 100 are calculated
Part can also be connected to each other, such as pass through bus.It should be appreciated that calculating device structure block diagram shown in FIG. 1 merely for the sake of
Exemplary purpose, rather than the limitation to this specification range.Those skilled in the art can according to need, and increases or replaces it
His component.
Calculating equipment 100 can be any kind of static or mobile computing device, including mobile computer or mobile meter
Calculate equipment (for example, tablet computer, personal digital assistant, laptop computer, notebook computer, net book etc.), movement
Phone (for example, smart phone), wearable calculating equipment (for example, smartwatch, intelligent glasses etc.) or other kinds of shifting
Dynamic equipment, or the static calculating equipment of such as desktop computer or PC.Calculating equipment 100 can also be mobile or state type
Server.
Wherein, processor 120 can execute the step in method shown in Fig. 2.Fig. 2 is to show to be implemented according to the application one
The schematic flow chart of the knowledge mapping construction method of example, including step 202 is to step 208.
Step 202: determining at least one target person and at least two region names, obtain at least one described target person
The corresponding personage's history data of each target person in object.
In embodiments herein, system is determined according to the request of user or the demand of user to need to wrap in knowledge mapping
At least one target person and at least two region names contained, and from some disclosed semi-structured, unstructured and thirds
The corresponding personage of each target person at least one described target person is collected in the data of square structure database to carry out
It counts evidence one by one, includes that the target person in certain dimensions can map out the target person in each personage's history data
Social relationships feature tag, if such as some target person attended school in the education experience of certain special time periods
Gan Ge universities and colleges, or on several social organizations for taking office of work experience of certain special time periods, at least two ground
Domain name claim include the multiple and different levels obtained by administrative division administrative region, such as xxx province, the city xxx or xxx be administrative
Area etc..
Step 204: obtained from personage's history data corresponding with target person fisrt feature label and
Time interval existing for the fisrt feature label and the corresponding characteristic information of the fisrt feature label.
In embodiments herein, system obtains corresponding with the target person from personage's history data
Time interval existing for one feature tag and the fisrt feature label and the corresponding characteristic information of the fisrt feature label,
For example, the fisrt feature label can be several universities and colleges that the target person was attended school, then the fisrt feature label
Existing time interval can be the target person in the learning time of each universities and colleges, the corresponding spy of the fisrt feature label
Reference breath can be the educational background for attending school profession and obtain in each universities and colleges.
Step 206: obtained from personage's history data corresponding with target person second feature label and
Time interval existing for second feature label and the corresponding characteristic information of the second feature label.
In embodiments herein, system obtains corresponding with the target person from personage's history data
Time interval existing for two feature tags and second feature label and the corresponding characteristic information of the second feature label, example
Such as, the second feature label can be several organizations that the target person was taken office, then the second feature mark
Signing corresponding time interval can be the target person in the working time of each organization, the second feature label pair
The characteristic information answered can be the position in each organization.
Step 208: being based on the target person, region name, fisrt feature label, second feature label, described first
Existing for time interval existing for feature tag and the corresponding characteristic information of the fisrt feature label and second feature label
Time interval and the corresponding characteristic information of the second feature label construct knowledge mapping.
In embodiments herein, system is by each target person, each region name and each target person pair
The fisrt feature label and second feature label answered are as entity node, with the corresponding fisrt feature mark of each target person
Sign between second feature label specific connection and each region name and fisrt feature label and second feature label
Specific connection is relationship, and using the time interval and characteristic information as time attribute and other attributes, building is carried out based on personage
The knowledge mapping structure gone through.
Optionally, the target person, region name, fisrt feature label, second feature label, described first are being based on
Existing for time interval existing for feature tag and the corresponding characteristic information of the fisrt feature label and second feature label
After time interval and the corresponding characteristic information building knowledge mapping of the second feature label, further includes:
It stores by the knowledge mapping into chart database.
In embodiments herein, system stores the knowledge mapping that building is completed into chart database, such as neo4j
Graphic data base etc..
The application by the corresponding personage's history data of at least one target person carry out feature tag extraction, according to
Support feature tag goes out the social relationships of the target person from multiple dimension maps, meanwhile, by corresponding from extraction feature label
Time interval and feature tag and region name inclusion relation, enable the application construct knowledge mapping support to use
Family carries out the excavation of depth from time dimension and region dimension to the particular social relationship between target person, infers specific mesh
The social relationships having between mark personage in special time period or specific region, to further excavate tacit knowledge and enrich
Extend knowledge mapping.
In one embodiment of the application, as shown in figure 3, determining at least one target person and at least two regions
Title further includes after obtaining the corresponding personage's history data of each target person at least one described target person
Step 302 is to step 306:
Step 302: each region name at least two region name is constructed according to the zone data prestored
Between inclusion relation.
In embodiments herein, system can obtain disclosed zone data and be constructed according to the zone data prestored
Inclusion relation between each region name, so that the level of each region name is represented, for example, xxx province includes
The city xxx, the city xxx include administrative area xxx etc..
Step 304: the region name and described first is constructed based on the corresponding label data of the fisrt feature label
Inclusion relation between feature tag.
In embodiments herein, system can obtain the corresponding label data of the disclosed fisrt feature label,
And it is constructed between the region name and the fisrt feature label based on the corresponding label data of the fisrt feature label
Inclusion relation, in the case where the fisrt feature label is several universities and colleges that the target person was attended school, system can be with
Based on the inclusion relation of disclosed universities and colleges' data building region name and universities and colleges, for example, the city xxx includes xxx university.
Step 306: the region name and described second is constructed based on the corresponding label data of the second feature label
Inclusion relation between feature tag.
In embodiments herein, system can obtain the corresponding label data of the disclosed second feature label,
And it is constructed between the region name and the second feature label based on the corresponding label data of the second feature label
Inclusion relation, in the case where the second feature label is several organizations that the target person was taken office, system
The inclusion relation of region name and organization can be constructed based on disclosed organization's data, for example, the city xxx includes xxx
Company.
The application is incited somebody to action by being based on all kinds of disclosed data acquisition zone datas and the corresponding label data of feature tag
Zone data is associated with feature tag establishes inclusion relation respectively, ties up so that the knowledge spectrogram of the application has from region
The ability of the deep layer social relationships of degree analysis target person.
In another embodiment of the application, as shown in figure 4, it is described from personage's history data obtain with it is described
Time interval existing for the corresponding fisrt feature label of target person and the fisrt feature label and the fisrt feature mark
Signing corresponding characteristic information includes step 402 to step 406:
Step 402: at least one fisrt feature list is constructed based on the corresponding label data of the fisrt feature label.
In embodiments herein, system is based on the corresponding label data of the fisrt feature label and constructs at least one
Fisrt feature list, includes the characteristic information of the same category in each fisrt feature list, is in the fisrt feature label
In the case where several universities and colleges that the target person was attended school, system can construct one based on disclosed universities and colleges' data and include
There are the professional list of multiple universities and colleges' titles, such as xxx university and/or xxx institute etc., it is special that system is also based on disclosed subject
Industry data construct one comprising there are many professional list of specialized information, such as department of law and/or department of computer science etc., system may be used also
To construct one comprising there are many academic lists of academic information, such as undergraduate course, Master degree candidate based on disclosed academic data
With doctoral candidate etc..
Step 404: it is special that described first is extracted from personage's history data according to each fisrt feature list
Levy label and the corresponding characteristic information of the fisrt feature label.
In embodiments herein, described first is special involved in personage's history data of the system for each target person
A relevant information for levying label, by carrying out personage's history data of each fisrt feature list and each target person
Match, the fisrt feature label and the corresponding feature letter of the fisrt feature label are extracted from personage's history data
Breath, for example, system is directed to people in the case where the fisrt feature label is several universities and colleges that the target person was attended school
Data: " attending department of law, xxx university Master degree candidate at 2000 to 2004 " are undergone in education in object history data, are led to
Education experience data are matched after the universities and colleges' list built in advance, professional list and academic list, to take out
Take out universities and colleges' title (xxx university), major name (department of law) and the academic title (Master degree candidate) of the target person.
Step 406: the fisrt feature label is extracted from personage's history data based on preset time rule
Corresponding starting and end time obtains time interval existing for the fisrt feature label.
In embodiments herein, described first is special involved in personage's history data of the system for each target person
The relevant information for levying label obtains time interval existing for the fisrt feature label based on preset time rule, for example, In
In the case that the fisrt feature label is several universities and colleges that the target person was attended school, system is directed to personage's history data
In education undergo data: " attending department of law, xxx university Master degree candidate at 2000 to 2004 ", based on it is preset when
Between the time interval attended school in " xxx university " of Rule be 2000 to 2004.
The application is characterized label by the education experience to target person and carries out to personage's history data of target person
Knowledge is extracted, so as to have identical school year to target person with regard to read time and universities and colleges location by target person
Other personages of classmate's relationship excavate and reasoning.
In another embodiment of the application, as shown in figure 5, it is described from personage's history data obtain with it is described
Time interval existing for the corresponding second feature label of target person and second feature label and the second feature label pair
The characteristic information answered includes step 502 to step 506:
Step 502: at least one second feature list is constructed based on the corresponding label data of the second feature label.
In embodiments herein, system is based on the corresponding label data of the second feature label and constructs at least one
Second feature list, includes the characteristic information of the same category in each second feature list, is in the second feature label
In the case where several organizations that the target person was taken office, system can be based on disclosed organization's data structure
Build one include multiple organization's titles organization's list, such as xxx company and/or xxx office etc., system is also
One can be constructed based on disclosed job data comprising there are many professional lists of job information, such as consultant and/or manager
Deng.
Step 504: it is special that described second is extracted from personage's history data according to each second feature list
Levy label and the corresponding characteristic information of the second feature label.
In embodiments herein, described second is special involved in personage's history data of the system for each target person
A relevant information for levying label, by carrying out personage's history data of each second feature list and each target person
Match, the second feature label and the corresponding feature letter of the second feature label are extracted from personage's history data
Breath, for example, in the case where the second feature label is several organizations that the target person was attended school, system needle
To the work experience data in personage's history data: " at 2004 to 2010 in xxx company tenure legal adviser ", by pre-
The organization's list and professional list first built matches the work experience data, to extract the mesh
Mark the organization's title (xxx company) and position title (legal adviser) of personage.
Step 506: the second feature label is extracted from personage's history data based on preset time rule
Corresponding starting and end time obtains time interval existing for the second feature label.
In embodiments herein, described second is special involved in personage's history data of the system for each target person
The relevant information for levying label obtains time interval existing for the second feature label based on preset time rule, for example, In
In the case that the second feature label is several organizations that the target person was attended school, system is directed to personage's resume
Work experience data in data: " at 2004 to 2010 in xxx company tenure legal adviser " are advised based on the preset time
Then obtaining in " xxx company " inaugural time interval is 2004 to 2010.
The application is characterized label by the work experience to target person and carries out to personage's history data of target person
Knowledge is extracted, so as to by inaugural time of target person and organization location to target person have work together through
Other personages gone through excavate and reasoning.
In another embodiment of the application, as shown in fig. 6, described be based on the target person, region name, first
Feature tag, second feature label, time interval and the fisrt feature label existing for the fisrt feature label are corresponding
Time interval existing for characteristic information and second feature label and the corresponding characteristic information building of the second feature label are known
Knowing map includes step 602 to step 608:
Step 602: using the target person, region name, fisrt feature label and second feature label as entity.
In embodiments herein, system is by the target person, region name, fisrt feature label and second feature
Label is as entity, for example, the second feature label can be as shown in fig. 7, the fisrt feature label can be universities and colleges
Organization.
Step 604: constructing between the region name and the fisrt feature label and second feature label includes to close
System.
In embodiments herein, system by between region name and the fisrt feature label inclusion relation and
Inclusion relation between region name and the second feature label is integrated, and the region name and first spy are obtained
Levy the inclusion relation between label and second feature label, for example, as shown in fig. 7, the fisrt feature label be universities and colleges and
In the case that the second feature label is organization, " xxx university " both may include in region name " city xxx ",
It may include " xxx company ".
Step 606: constructing the fisrt feature relationship between the target person and the fisrt feature label, and will be described
Time interval existing for fisrt feature label and the corresponding characteristic information of the fisrt feature label are closed as the fisrt feature
The attribute of system.
In embodiments herein, system constructs the first spy between the target person and the fisrt feature label
Sign relationship, and using time interval existing for the fisrt feature label and the corresponding characteristic information of the fisrt feature label as
The attribute of the fisrt feature relationship, for example, as shown in fig. 7, being universities and colleges and the second feature in the fisrt feature label
In the case that label is organization, system establishes study relationship between each target person and its universities and colleges attended school,
And the time interval attended school for extracting the target person obtained, major name and academic name are referred to as the study relationship
Attribute.
Step 608: constructing the second feature relationship between the target person and the second feature label, and will be described
Time interval existing for second feature label and the corresponding characteristic information of the second feature label are closed as the second feature
The attribute of system.
In embodiments herein, system constructs the second spy between the target person and the second feature label
Sign relationship, and using time interval existing for the second feature label and the corresponding characteristic information of the second feature label as
The attribute of the second feature relationship, for example, as shown in fig. 7, being universities and colleges and the second feature in the fisrt feature label
In the case that label is organization, system establishes work pass between each target person and its inaugural organization
System, and the inaugural time interval and position of the target person obtained will be extracted as the attribute of the work relationship.
Knowledge mapping of the application by building comprising time attribute and Regional Property, to the target person in knowledge mapping
Social relationships carry out dynamical min, the deep layer social relationships between personage can be inferred, for example, some target person in
Master degree candidate's study is carried out in department of law, xxx university within 2000 to 2004, held a post in 2004 to 2010 in xxx company
Legal adviser, then by the knowledge mapping that the application constructs can further excavate to obtain in 2000 to 2004
Other personages of xxx university study and the target person had classmate's relationship of unified school year, in 2004 to 2010
There are the Peer Relationships for experience of working together in other personages of xxx company tenure and the target person, be based on existing personage's map
It can not excavate to obtain these deep relationships.
Corresponding with above method embodiment, this specification additionally provides knowledge mapping construction device embodiment, and Fig. 8 is shown
The structural schematic diagram of the knowledge mapping construction device of this specification one embodiment.As shown in figure 8, the device includes:
Entity determining module 801 is configured to determine that at least one target person and at least two region names, obtains institute
State the corresponding personage's history data of each target person at least one target person；
Fisrt feature label acquisition module 802 is configured as obtaining and the target person from personage's history data
Time interval existing for the corresponding fisrt feature label of object and the fisrt feature label and the fisrt feature label are corresponding
Characteristic information；
Second feature label acquisition module 803 is configured as obtaining and the target person from personage's history data
Time interval existing for the corresponding second feature label of object and second feature label and the corresponding spy of the second feature label
Reference breath；
Knowledge mapping constructs module 804, is configured as based on the target person, region name, fisrt feature label, the
Time interval existing for two feature tags, the fisrt feature label and the corresponding characteristic information of the fisrt feature label and
Time interval existing for second feature label and the corresponding characteristic information of the second feature label construct knowledge mapping.
Optionally, described device further include:
Zone data constructs module, is configured as being constructed at least two region name according to the zone data prestored
Inclusion relation between each region name；
First label data constructs module, is configured as based on the fisrt feature label corresponding label data building institute
State the inclusion relation between region name and the fisrt feature label；
Second label data constructs module, is configured as based on the second feature label corresponding label data building institute
State the inclusion relation between region name and the second feature label.
Optionally, the fisrt feature label acquisition module 802 includes:
First list construction unit is configured as based on the corresponding label data building at least one of the fisrt feature label
A fisrt feature list；
First instance extracting unit is configured as according to each fisrt feature list from personage's history data
Extract the fisrt feature label and the corresponding characteristic information of the fisrt feature label；
First time extracting unit is configured as extracting from personage's history data based on preset time rule
The fisrt feature label corresponding starting and end time, obtain time interval existing for the fisrt feature label.
Optionally, the second feature label acquisition module 803 includes:
Second list construction unit is configured as based on the corresponding label data building at least one of the second feature label
A second feature list；
Second instance extracting unit is configured as according to each second feature list from personage's history data
Extract the second feature label and the corresponding characteristic information of the second feature label；
Second decimation in time unit is configured as extracting from personage's history data based on preset time rule
The second feature label corresponding starting and end time, obtain time interval existing for the second feature label.
Optionally, the knowledge mapping building module 804 includes:
Entity names unit, is configured as the target person, region name, fisrt feature label and second feature mark
Label are used as entity；
First Relation extraction unit is configured as constructing the region name and the fisrt feature label and second feature
Inclusion relation between label；
Second Relation extraction unit is configured as constructing first between the target person and the fisrt feature label
Characteristic relation, and time interval existing for the fisrt feature label and the corresponding characteristic information of the fisrt feature label are made
For the attribute of the fisrt feature relationship；
Attribute extraction unit is configured as constructing the second feature between the target person and the second feature label
Relationship, and using time interval existing for the second feature label and the corresponding characteristic information of the second feature label as institute
State the attribute of second feature relationship.
Optionally, described device further include:
Memory module is configured as storing the knowledge mapping into chart database.
The application by the corresponding personage's history data of at least one target person carry out feature tag extraction, according to
Support feature tag goes out the social relationships of the target person from multiple dimension maps, meanwhile, by corresponding from extraction feature label
Time interval and feature tag and region name inclusion relation, enable the application construct knowledge mapping support to use
Family carries out the excavation of depth from time dimension and region dimension to the particular social relationship between target person, infers specific mesh
The social relationships having between mark personage in special time period or specific region, to further excavate tacit knowledge and enrich
Extend knowledge mapping.
One embodiment of the application also provides a kind of calculating equipment, including memory, processor and storage are on a memory simultaneously
The computer instruction that can be run on a processor, the processor perform the steps of when executing described instruction
It determines at least one target person and at least two region names, obtains each at least one described target person
The corresponding personage's history data of the target person；
Fisrt feature label corresponding with the target person and described first are obtained from personage's history data
Time interval existing for feature tag and the corresponding characteristic information of the fisrt feature label；
Second feature label corresponding with the target person and second feature are obtained from personage's history data
Time interval existing for label and the corresponding characteristic information of the second feature label；
Based on the target person, region name, fisrt feature label, second feature label, the fisrt feature label
Time interval existing for existing time interval and the corresponding characteristic information of the fisrt feature label and second feature label
Characteristic information corresponding with the second feature label constructs knowledge mapping.
One embodiment of the application also provides a kind of computer readable storage medium, is stored with computer instruction, the instruction
The step of knowledge mapping construction method as previously described is realized when being executed by processor.
A kind of exemplary scheme of above-mentioned computer readable storage medium for the present embodiment.It should be noted that the meter
The technical solution of calculation machine readable storage medium storing program for executing and the technical solution of above-mentioned knowledge mapping construction method belong to same design, calculate
The detail content that the technical solution of machine readable storage medium storing program for executing is not described in detail may refer to above-mentioned knowledge mapping construction method
The description of technical solution.
It is above-mentioned that this specification specific embodiment is described.Other embodiments are in the scope of the appended claims
It is interior.In some cases, the movement recorded in detail in the claims or step can be come according to the sequence being different from embodiment
It executes and desired result still may be implemented.In addition, process depicted in the drawing not necessarily require show it is specific suitable
Sequence or consecutive order are just able to achieve desired result.In some embodiments, multitasking and parallel processing be also can
With or may be advantageous.
The computer instruction includes computer program code, the computer program code can for source code form,
Object identification code form, executable file or certain intermediate forms etc..The computer-readable medium may include: that can carry institute
State any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic disk, CD, the computer storage of computer program code
Device, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory),
Electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that the computer-readable medium include it is interior
Increase and decrease appropriate can be carried out according to the requirement made laws in jurisdiction with patent practice by holding, such as in certain jurisdictions of courts
Area does not include electric carrier signal and telecommunication signal according to legislation and patent practice, computer-readable medium.
It should be noted that for the various method embodiments described above, describing for simplicity, therefore, it is stated as a series of
Combination of actions, but those skilled in the art should understand that, the application is not limited by the described action sequence because
According to the application, certain steps can use other sequences or carry out simultaneously.Secondly, those skilled in the art should also know
It knows, the embodiments described in the specification are all preferred embodiments, and related actions and modules might not all be this Shen
It please be necessary.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, it may refer to the associated description of other embodiments.
The application preferred embodiment disclosed above is only intended to help to illustrate the application.There is no detailed for alternative embodiment
All details are described, are not limited the invention to the specific embodiments described.Obviously, according to the content of this specification,
It can make many modifications and variations.These embodiments are chosen and specifically described to this specification, is in order to preferably explain the application
Principle and practical application, so that skilled artisan be enable to better understand and utilize the application.The application is only
It is limited by claims and its full scope and equivalent.
Claims (14)
1. a kind of knowledge mapping construction method characterized by comprising
It determines at least one target person and at least two region names, obtains each described at least one described target person
The corresponding personage's history data of target person；
Fisrt feature label corresponding with the target person and the fisrt feature are obtained from personage's history data
Time interval existing for label and the corresponding characteristic information of the fisrt feature label；
Second feature label corresponding with the target person and second feature label are obtained from personage's history data
Existing time interval and the corresponding characteristic information of the second feature label；
Existed based on the target person, region name, fisrt feature label, second feature label, the fisrt feature label
Time interval and the corresponding characteristic information of the fisrt feature label and second feature label existing for time interval and institute
State the corresponding characteristic information building knowledge mapping of second feature label.
2. the method according to claim 1, wherein determining at least one target person and at least two regions
Title, after obtaining the corresponding personage's history data of each target person at least one described target person, further includes:
According to the zone data prestored construct at least two region name between each region name comprising closing
System；
It is constructed between the region name and the fisrt feature label based on the corresponding label data of the fisrt feature label
Inclusion relation；
It is constructed between the region name and the second feature label based on the corresponding label data of the second feature label
Inclusion relation.
3. the method according to claim 1, wherein described obtain and the mesh from personage's history data
Mark time interval and the fisrt feature label existing for the corresponding fisrt feature label of personage and the fisrt feature label
Corresponding characteristic information includes:
At least one fisrt feature list is constructed based on the corresponding label data of the fisrt feature label；
The fisrt feature label and institute are extracted from personage's history data according to each fisrt feature list
State the corresponding characteristic information of fisrt feature label；
At the beginning of the fisrt feature label correspondence is extracted from personage's history data based on preset time rule
Between and the end time, obtain time interval existing for the fisrt feature label.
4. the method according to claim 1, wherein described obtain and the mesh from personage's history data
It marks time interval existing for the corresponding second feature label of personage and second feature label and the second feature label is corresponding
Characteristic information include:
At least one second feature list is constructed based on the corresponding label data of the second feature label；
The second feature label and institute are extracted from personage's history data according to each second feature list
State the corresponding characteristic information of second feature label；
At the beginning of the second feature label correspondence is extracted from personage's history data based on preset time rule
Between and the end time, obtain time interval existing for the second feature label.
5. the method according to claim 1, wherein described based on the target person, region name, the first spy
Levy label, second feature label, time interval and the corresponding spy of the fisrt feature label existing for the fisrt feature label
Time interval existing for reference breath and second feature label and the corresponding characteristic information of the second feature label construct knowledge
Map includes:
Using the target person, region name, fisrt feature label and second feature label as entity；
Construct the inclusion relation between the region name and the fisrt feature label and second feature label；
Construct the fisrt feature relationship between the target person and the fisrt feature label, and by the fisrt feature label
The attribute of existing time interval and the corresponding characteristic information of the fisrt feature label as the fisrt feature relationship；
Construct the second feature relationship between the target person and the second feature label, and by the second feature label
The attribute of existing time interval and the corresponding characteristic information of the second feature label as the second feature relationship.
6. the method according to claim 1, wherein being based on the target person, region name, fisrt feature
Label, second feature label, time interval and the corresponding feature of the fisrt feature label existing for the fisrt feature label
Time interval existing for information and second feature label and the corresponding characteristic information of the second feature label construct knowledge graph
After spectrum, further includes:
The knowledge mapping is stored into chart database.
7. a kind of knowledge mapping construction device characterized by comprising
Entity determining module, is configured to determine that at least one target person and at least two region names, and acquisition is described at least
The corresponding personage's history data of each target person in one target person；
Fisrt feature label acquisition module is configured as obtaining from personage's history data corresponding with the target person
Time interval existing for fisrt feature label and the fisrt feature label and the corresponding feature letter of the fisrt feature label
Breath；
Second feature label acquisition module is configured as obtaining from personage's history data corresponding with the target person
Time interval existing for second feature label and second feature label and the corresponding characteristic information of the second feature label；
Knowledge mapping constructs module, is configured as based on the target person, region name, fisrt feature label, second feature
Time interval existing for label, the fisrt feature label and the corresponding characteristic information of the fisrt feature label and the second spy
It levies time interval existing for label and the corresponding characteristic information of the second feature label constructs knowledge mapping.
8. device according to claim 7, which is characterized in that further include:
Zone data constructs module, is configured as being constructed according to the zone data prestored each at least two region name
Inclusion relation between the region name；
First label data constructs module, is configured as based on the corresponding label data building of the fisrt feature label describedly
Domain name claims the inclusion relation between the fisrt feature label；
Second label data constructs module, is configured as based on the corresponding label data building of the second feature label describedly
Domain name claims the inclusion relation between the second feature label.
9. device according to claim 7, which is characterized in that the fisrt feature label acquisition module includes:
First list construction unit, be configured as constructing based on the corresponding label data of the fisrt feature label at least one the
One feature list；
First instance extracting unit is configured as being extracted from personage's history data according to each fisrt feature list
The fisrt feature label and the corresponding characteristic information of the fisrt feature label out；
First time extracting unit is configured as extracting from personage's history data based on preset time rule described
Fisrt feature label corresponding starting and end time obtains time interval existing for the fisrt feature label.
10. device according to claim 7, which is characterized in that the second feature label acquisition module includes:
Second list construction unit, be configured as constructing based on the corresponding label data of the second feature label at least one the
Two feature lists；
Second instance extracting unit is configured as being extracted from personage's history data according to each second feature list
The second feature label and the corresponding characteristic information of the second feature label out；
Second decimation in time unit is configured as extracting from personage's history data based on preset time rule described
Second feature label corresponding starting and end time obtains time interval existing for the second feature label.
11. device according to claim 7, which is characterized in that the knowledge mapping constructs module and includes:
Entity names unit, is configured as making on the target person, region name, fisrt feature label and second feature label
For entity；
First Relation extraction unit is configured as constructing the region name and the fisrt feature label and second feature label
Between inclusion relation；
Second Relation extraction unit is configured as constructing the fisrt feature between the target person and the fisrt feature label
Relationship, and using time interval existing for the fisrt feature label and the corresponding characteristic information of the fisrt feature label as institute
State the attribute of fisrt feature relationship；
Attribute extraction unit is configured as constructing the second feature between the target person and the second feature label and closes
System, and using time interval existing for the second feature label and the corresponding characteristic information of the second feature label as described in
The attribute of second feature relationship.
12. device according to claim 7, which is characterized in that further include:
Memory module is configured as storing the knowledge mapping into chart database.
13. a kind of calculating equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine instruction, which is characterized in that the processor realizes the step of claim 1-6 any one the method when executing described instruction
Suddenly.
14. a kind of computer readable storage medium, is stored with computer instruction, which is characterized in that the instruction is held by processor
The step of claim 1-6 any one the method is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910760043.2A CN110457536A (en) | 2019-08-16 | 2019-08-16 | A kind of knowledge mapping construction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910760043.2A CN110457536A (en) | 2019-08-16 | 2019-08-16 | A kind of knowledge mapping construction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110457536A true CN110457536A (en) | 2019-11-15 |
Family
ID=68487217
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910760043.2A Pending CN110457536A (en) | 2019-08-16 | 2019-08-16 | A kind of knowledge mapping construction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110457536A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111260526A (en) * | 2020-01-20 | 2020-06-09 | 北京明略软件系统有限公司 | Figure track behavior analysis and estimation method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106777331A (en) * | 2017-01-11 | 2017-05-31 | 北京航空航天大学 | Knowledge mapping generation method and device |
| 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 |
| CN108509614A (en) * | 2018-04-03 | 2018-09-07 | 中山大学 | A kind of task record management and analysis method based on chart database |
| CN109271525A (en) * | 2018-08-08 | 2019-01-25 | 北京百度网讯科技有限公司 | For generating the method, apparatus, equipment and computer readable storage medium of knowledge mapping |
| CN109857753A (en) * | 2018-12-28 | 2019-06-07 | 考拉征信服务有限公司 | User data verification method, device, electronic equipment and storage medium |
-
2019
- 2019-08-16 CN CN201910760043.2A patent/CN110457536A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106777331A (en) * | 2017-01-11 | 2017-05-31 | 北京航空航天大学 | Knowledge mapping generation method and device |
| 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 |
| CN108509614A (en) * | 2018-04-03 | 2018-09-07 | 中山大学 | A kind of task record management and analysis method based on chart database |
| CN109271525A (en) * | 2018-08-08 | 2019-01-25 | 北京百度网讯科技有限公司 | For generating the method, apparatus, equipment and computer readable storage medium of knowledge mapping |
| CN109857753A (en) * | 2018-12-28 | 2019-06-07 | 考拉征信服务有限公司 | User data verification method, device, electronic equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111260526A (en) * | 2020-01-20 | 2020-06-09 | 北京明略软件系统有限公司 | Figure track behavior analysis and estimation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jacoby et al. | Cross-cultural work in music cognition: Challenges, insights, and recommendations | |
| KR101667415B1 (en) | Apparatus and method for managing personal social network in a mobile terminal | |
| Urbina-Cardona et al. | Species distribution modeling in Latin America: a 25-year retrospective review | |
| Janta | Polish migrant workers in the UK hospitality industry: Profiles, work experience and methods for accessing employment | |
| Bowers | Developing sustainable tourism through ecomuseology: a case study in the Rupununi region of Guyana | |
| CN109816111A (en) | Reading understands model training method and device | |
| Roman et al. | Urban tree mortality: a primer on demographic approaches | |
| CN109947949A (en) | Knowledge information intelligent management, device and server | |
| CN109213831A (en) | Event detecting method and device calculate equipment and storage medium | |
| CN107077504A (en) | Supplemental information is asked | |
| CN106570014A (en) | Method and device for determining home attribute information of user | |
| CN109800354A (en) | A kind of resume modification intension recognizing method and system based on the storage of block chain | |
| Quandt et al. | A standardized land capability classification system for land evaluation using mobile phone technology | |
| CN110298597A (en) | A kind of assessment method, device and storage medium | |
| CN109191167A (en) | A kind of method for digging and device of target user | |
| Meeus et al. | More than a bit of fun: the multiple outcomes of a bioblitz | |
| CN110457536A (en) | A kind of knowledge mapping construction method and device | |
| KR100938830B1 (en) | Method constructing knowledge base and thereof server | |
| Mensch | Museality at breakfast: the concept of museality in contemporary museological discourse | |
| GB2569951A (en) | Method and system for managing network of field-specific entity records | |
| Garcia-Perez et al. | Knowledge capabilities–roles, responsibilities, placement | |
| Valjarević et al. | GIS analysis of land cover changes on the territory of the Prokuplje municipality | |
| CN113537263B (en) | Training method and device for two-class model, and entity linking method and device | |
| Maudet et al. | DIOGEN, a multi-level oriented model for cartographic generalization | |
| Caine et al. | Mobile phone applications for weather and climate information for smallholder farmer decision making. |
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 |