CN109726253A - Construction method, device, equipment and the medium of talent's map and talent's portrait - Google Patents
Construction method, device, equipment and the medium of talent's map and talent's portrait Download PDFInfo
- Publication number
- CN109726253A CN109726253A CN201811570090.2A CN201811570090A CN109726253A CN 109726253 A CN109726253 A CN 109726253A CN 201811570090 A CN201811570090 A CN 201811570090A CN 109726253 A CN109726253 A CN 109726253A
- Authority
- CN
- China
- Prior art keywords
- talent
- name entity
- entity
- map
- conceptual level
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of talent's map construction methods, including, the information in talents information library is subjected to cutting, obtains multiple phrases, multiple resumes, interview evaluation and/or performance appraisal table are wherein included in talents information library；According to predefined classification, conceptual level name entity is identified from phrase and is sorted out；Verb-object pair is extracted from the information in talents information library, obtains the corresponding verb of each conceptual level name entity；And verb is mapped as the relationship between each conceptual level name entity using model trained in advance, it obtains naming entity as node using conceptual level, the relationship between each conceptual level name entity is talent's map on side.Compared with prior art, the present invention constructs talent's map by talents information library, establishes the talent and portrays system, for the subsequent talent evaluation and portray and provide good basis.The construction method moreover, it relates to which the talent draws a portrait.
Description
Technical field
The present invention relates to construction method, device, equipment and media that a kind of talent's map and the talent are drawn a portrait.
Background technique
In the development process of enterprise, the ability quality of the talent is the key link, with advances in technology, the enterprise talent
The quantization of ability quality more show important.Talent's portrait or talent ability model are constructed, talent ability quality is quantified, is
One important tool in human resource management field is originated from the ability mould that David's mcmillan proposes in the sixties in last century
Type becomes popular tool since it portrays the validity of enterprises recruit persons for jobs demand, this model also after introducing China gradually
The method being widely used as large and medium-sized enterprise.
A kind of popular approach of the knowledge mapping as representation of knowledge is derived from the ontology and research of semantic web wave of beginning of the century
Tide, have to people it is readable, to the computable double grading of machine, it is enabled sufficiently to be competent at the knowledge token field of various complexity
Scape, and become one that major search engine web site and AI service facility at this stage are widely used when needing knowledge reasoning ability
Standard technique.And the knowledge of knowledge based map, effective information is extracted from the resume of the talent or interview evaluation etc., and therefrom
The range for rationally inferring its technical ability and ability to work is exactly key problem to be solved by this invention.
Summary of the invention
The invention proposes a set of knowledge based maps to carry out depth reasoning to data such as the resumes of the talent, to obtain the talent
Talent's portrait building system of each dimension quantized data of full capacity quality model, to quantify the ability quality mould of the output talent
Type, and support is provided for subsequent talent screening.
The first aspect of the present invention provides a kind of talent's map construction method, including,
Information in talents information library is subjected to cutting, obtains multiple phrases, wherein includes multiple letters in talents information library
It goes through, interview evaluation and/or performance appraisal table；
According to predefined classification, conceptual level name entity is identified from phrase and is sorted out；
Verb-object pair is extracted from the information in talents information library, and it is corresponding dynamic to obtain each conceptual level name entity
Word；And
Verb is mapped as the relationship between each conceptual level name entity using model trained in advance, is obtained with conceptual level
Name entity is node, and the relationship between each conceptual level name entity is talent's map on side.
Compared with prior art, the present invention constructs talent's map by talents information library, establishes the talent and portrays system, is
It the evaluation of the subsequent talent and portrays and provides good basis.
Further, predefined classification may include, school, profession, industry, company, function, technical ability, project, in work
It is any one or more in appearance and/or certificate.
Further, identifying that conceptual level names the model of entity that can carry out by Bi-LSTM neural network from phrase
Training.
The second aspect of the present invention provides a kind of method drawn a portrait using talent's map construction talent above-mentioned, including,
Material is received, wherein material includes resume, interview evaluation, any one or more in feedback on performance table；
The information in material is extracted, and cutting is carried out to the information in material, obtains multiple phrases；
According to predefined classification, instance layer name entity is identified from phrase and is sorted out；
Instance layer name entity is mapped in talent's map as constructed by claim 1, is obtained with each instance layer
Name the closure centered on entity；And
The conceptual level name entity covered in the intersection of statistics instance layer name entity and at least two closures, obtains
Entity sets are named, name entity sets are extracted and the relationship between each name entity in entity sets is named to draw as the talent
Picture.
Further, entity is named for the instance layer being unable to map in talent's map, verb-can be extracted from material
Object pair obtains the corresponding verb of each instance layer name entity, verb is mapped as each example using model trained in advance
Relationship between layer name entity；And utilize the pass between obtained instance layer name entity and each instance layer name entity
System updates talent's map.
The third aspect of the present invention provides a kind of talent's map construction device, including,
Information cutting unit is configured as the information in talents information library carrying out cutting, obtains multiple phrases, wherein people
Include multiple resumes, interview evaluation and/or performance appraisal table in ability information bank；
It names Entity recognition and sorts out unit, be configured as according to predefined classification, conceptual level life is identified from phrase
Name entity is simultaneously sorted out；
Dynamic guest's Phrase extraction unit is configured as extracting verb-object pair from the information in talents information library, obtains each
A conceptual level names the corresponding verb of entity；
Relationship map unit, be configured as using model trained in advance by verb be mapped as each conceptual level name entity it
Between relationship, obtain naming entity as node using conceptual level, the relationship between each conceptual level name entity is that the talent on side schemes
Spectrum.
The fourth aspect of the present invention provides a kind of talent's portrait construction device, including,
Material receiving unit is configured as receiving material, and wherein material includes resume, interviews and evaluate, in feedback on performance table
Any one or more；
Information cutting unit, is configured as extracting the information in material, carries out cutting to the information in material, obtains multiple
Phrase；
It names Entity recognition and sorts out unit, be configured as according to predefined classification, instance layer life is identified from phrase
Name entity is simultaneously sorted out；
Closure recognition unit is configured as instance layer name entity being mapped to the figure of the talent as constructed by claim 6
In spectrum, the closure centered on each instance layer name entity is obtained；With
Talent's portrait construction unit, is configured as institute in the intersection of statistics instance layer name entity and at least two closures
The conceptual level name entity covered, obtains name entity sets, extracts name entity sets and names each in entity sets
The relationship between entity is named to draw a portrait as the talent.
The fifth aspect of the present invention provides a kind of equipment, which includes processor, memory, processor and memory
Establish communication connection；
Processor, for reading the program in memory, to execute aforementioned first aspect or second aspect and its any reality
The method that existing mode provides.
The sixth aspect of the present invention provides a kind of non-volatile memory medium, stores in the non-volatile memory medium
Program when the program is run by calculating equipment, calculates equipment and executes aforementioned first aspect or second aspect and its any realization side
The method that formula provides.
The present invention is based on the knowledge of knowledge mapping, extract effective information from the resume of the talent and interview evaluation etc.,
And the confident inferences of the technical ability range except the knowledge expertise referred in resume etc. to people are capable of forming, it can establish deep complete
The talent in face draws a portrait, and forms the good system for portraying the talent.
Detailed description of the invention
Fig. 1 is the flow chart of the method for building talent's map of embodiment according to the present invention.
Fig. 2 is the flow chart of the method for building talent's portrait of embodiment according to the present invention.
Fig. 3 is the configuration diagram of the Human Resource Management System of embodiment according to the present invention.
Fig. 4 is the structural schematic diagram of talent's map of embodiment according to the present invention.
Fig. 5 is the closure schematic diagram of embodiment according to the present invention.
Specific embodiment
The present invention will be further described with attached drawing combined with specific embodiments below.It is understood that described herein
Specific embodiment is of the invention just for the sake of explaining, rather than limitation of the invention.In addition, for ease of description, in attached drawing only
Show part related to the present invention and not all structure or process.
According to one embodiment of present invention, a kind of Human Resource Management System is provided, as shown in Figure 3.The system includes
Talent's map construction system 10 and talent's portrait building system 20.
Talent's map construction system 10 includes information cutting unit 101, name Entity recognition and sorts out unit 102, moves guest
Phrase extraction unit 103 and relationship map unit 104.Wherein, be configured as will be in talents information library for information cutting unit 101
Information carry out cutting, obtain multiple phrases, wherein in talents information library comprising multiple resumes, interview evaluation and/or performance examine
Core table；Name Entity recognition and classification unit 102 are configured as according to predefined classification, and conceptual level name is identified from phrase
Entity (Conception Level Named Entity Recognition) is simultaneously sorted out；Dynamic guest's Phrase extraction unit 103 is matched
It is set to the extraction verb-object pair from the information in talents information library, obtains the corresponding verb of each conceptual level name entity；It closes
It is that map unit 104 is configured as the pass being mapped as verb using model trained in advance between each conceptual level name entity
System obtains naming entity as node using conceptual level, and the relationship between each conceptual level name entity is talent's map on side.
And talent's portrait building system 20 includes material receiving unit 205, information cutting unit 101, name Entity recognition
And sort out unit 102, closure recognition unit 206 and talent's portrait construction unit 207.Wherein material receiving unit 205 is matched
It is set to and receives all kinds of manpower management materials such as resume, evaluation, feedback on performance table.Information cutting unit 101 and name Entity recognition
And sort out that unit 102 is identical as the function in talent's map construction system 10, just for be that newly receive certain part is specific
The materials such as resume or evaluation are handled, and details are not described herein again, will be received from 205 institute of material receiving unit in order to distinguish
The name entity identified in material names entity (Instance level Named Entity as instance layer
Recognition).And closure recognition unit 206 is configured as that Entity recognition will be named and sorts out the instance layer identified in unit
Name entity is mapped in talent's map constructed by talent's map construction system 10, available to be named in fact with each instance layer
Closure centered on body.Talent's portrait construction unit 207 is configured as statistics instance layer name entity and at least two closures
Intersection in covered conceptual level name entity, obtain name entity sets, extract name entity sets and name entity
The relationship between each name entity in set is drawn a portrait as the talent.
Selectively, in some embodiments, some instance layer lives being unable to map in talent's map be might have
Name entity, talent's portrait building system 20 can also include dynamic guest's Phrase extraction unit 103 and relationship map unit 104, divide
It is not configured as extracting verb-object pair from material, obtains the corresponding verb of each instance layer name entity, and using in advance
First verb is mapped as the relationship between each instance layer name entity by trained model, to be named using obtained instance layer real
Relationship between body and each instance layer name entity updates talent's map.
Note that the Human Resource Management System illustrated above in conjunction with Fig. 3, can be used as entirety and carrys out design and use, it can also
To separately design and use.Such as those skilled in the art can individually designed and use talent's map construction system therein
10, or according to existing talent's map construction system 10 it is individually designed and using the talent draw a portrait building system 20.It should be noted that
Whether the two is individually designed or carrys out design and use as a whole using or by the two, should all belong to of the invention
Range.Using system above carry out talent's map construction and the talent draw a portrait building method hereinafter in conjunction with Fig. 1 and Fig. 2 into
Row is described in detail.
As shown in Figure 1, according to one embodiment of present invention, providing a kind of talent's map construction method, this method is specific
The following steps are included:
Information in talents information library is carried out cutting, obtains multiple phrases, wherein talents information library Zhong Bao by step S101
Containing multiple resumes, interview evaluation and/or performance appraisal table.Realize the model with piecemeal (Chunking) function, subordinate clause
The noun phrase that should not be cut is marked in son, Chunking model can realize that the present invention is not right using various generic ways
This is limited.
Then, step S102 identifies conceptual level name entity and is sorted out from above-mentioned phrase according to predefined classification.
For example, classification can be pre-defined according to human resources field general classification, for example, school, profession, row can be defined
9 industry, company, function, technical ability, project, action, certificate classifications will be in step S101 using preparatory trained model
Obtained phrase is named Entity recognition (Named Entity Recognition, abbreviation NER), and is grouped into above-mentioned 9 respectively
In class.In the method based on machine learning, NER can be taken as sequence labelling problem, learn using large-scale corpus
Marking model, so that each position to sentence is labeled.Herein, NER model can be using production model HMM, differentiation
Formula MODEL C RF etc., for example, NER model can be trained by Bi-LSTM neural network.
Based on two models described in previous step S101 and step S102, can from talents information library at Duan Wen
Each name entity is extracted in this, that is, conceptual level names entity.
Then, step S103 extracts verb-object pair from the information in talents information library, obtains each conceptual level life
The corresponding verb of name entity.Then, verb is mapped as each conceptual level using model trained in advance and names entity by step S104
Between relationship, the role of verb reflection distinguishes, and can improve the relationship between each conceptual level name entity.For example, conforming to the principle of simplicity
The name entity such as name, project may be extracted in going through, and verb corresponding to project is mapped out after coming, can clearly be obtained
Candidate's role in the project, for example be participation project or project is pushed to realize etc..
Then, step S105 obtains naming entity as node using conceptual level, the relationship between each conceptual level name entity
For talent's map on side.For example, as shown in fig. 4-5, wherein a kind of structure of talent's map is schematically illustrated in Fig. 4,
Centered on this name entity of certain position A, 2 node layers are shown, but in different embodiments, there can also be one layer or more
Node layer, and the relationship between the quantity of the node in Fig. 4, type and each node is all exemplary illustration, is not constituted
Limitation of the present invention, in practical applications, each node may continue to extend other interdependent nodes.For example, such as Fig. 5 institute
Show, it is available multiple by the massive information in talents information library for this name entity of machine learning algorithm engineer
The network of directly related or indirect correlation name entity composition therewith.
The construction method of talent's map is illustrated above in conjunction with Fig. 1, after talent's map construction is good, can be used as an enterprise
The spectrum library of industry or human resources platform comes using then when receiving new resume, can be turned out talents portrait with Rapid Inference.Specifically
Method is referring to fig. 2.
As shown in Fig. 2, wherein material includes resume, interview evaluation, feedback on performance table firstly, step S201, receives material
In any one or more.
Then, step S202-S203 extracts the information in material, carries out cutting to the information in material, obtains multiple words
Group；And according to predefined classification, instance layer name entity is identified from phrase and is sorted out.This two step and step S101-S102
It is similar, just for material it is different, step S202-S203 is directed to new received material, and step S101-S102 is directed to
Be content in talents information library, for simplicity, omit description herein.
Then, the name entity of instance layer obtained in above step is mapped to the talent hereinbefore constructed by step S204
In map, after having mapped, according to the extension and derivation relationship between each node in talent's map, to each node or portion
Key node is divided to carry out extension reasoning, the closure centered on the available name entity by each instance layer, that is, be based on each life
Name entity, menostasis steamed stuffed bun figure reasoning obtain more complete range.
In the present invention, closure refers to extending after reasoning and obtaining from node centered on some name entity in map
Node adjacent node in be more than that half belongs to the set of all nodes of same circle and its relationship, for example, such as Fig. 5 institute
Show, illustrate the knowledge that a machine learning algorithm engineer may have, it can be seen from the figure that being calculated with machine learning
Centered on this node of method engineer, it can deduce that it may have artificial intelligence, MATLAB, machine learning, Python, nerve
Network, the various knowledge of data mining ... infer first layer and extend node；Extend the Python section in node with first layer
Point for, from Python node, but can infer statistical and analytical tool, Data Mining Tools, scripting language, programming language,
Programming language, computer programming etc. node, these are all the adjacent nodes of Python node, and in these adjacent nodes
Most of node can also extend reasoning by MATLAB node, the Java platform node etc. in the first-level nodes and obtain, or
Extend reasoning by this central node of machine learning algorithm engineer to obtain, i.e., they belong to same circle.Therefore, Python
This node is included in closure, can similarly deduce that other belong to the node of the closure, such as each hollow node in figure
It is shown.Thus, it is possible to obtain each hollow node in central node (machine learning algorithm engineer) and Fig. 5 and they it
Between relationship constitute set, which is the closure of knowledge required for machine learning algorithm engineer.Equally, scheme
5 schematic diagrames shown just for the sake of being exemplarily illustrated the concept of closure, quantity, type and each section of node therein
Relationship between point is all exemplary illustration, is not construed as limiting the invention.In various embodiments, can have various
Different type, quantity, extension node.
Then, step S205 statistics instance layer name entity and at least two is with aforementioned instance layer name entity
Covered in the intersection of the closure of the heart conceptual level name entity, obtain name entity sets, extract name entity sets and
The relationship between each name entity in entity sets is named to draw a portrait as the talent.
In some embodiments, there may be some instance layer name entities for being unable to map talent's map, that is,
The name entity except entity range is named more than the conceptual level in protoplast's ability map, for being unable to map in talent's map
Instance layer names entity, can repeat step S103-S104, and verb-object pair is extracted from material, obtains each instance layer life
The verb is mapped as the pass between each instance layer name entity using model trained in advance by the corresponding verb of name entity
System.Scheme to update the talent using the relationship between obtained instance layer name entity and each instance layer name entity
Spectrum.
In some embodiments, dialogue robot system can be integrated in the present invention, it is logical using dialogue robot
It crosses and puts question to obtain more information to candidate, talent's portrait building system of the invention is sent to as material, so as to
More fully deduce the whole capability of candidate.
For example, dialogue robot can extract core vocabulary as special by syntactic analysis by received interview corpus
Sign obtains some competencies of people by classifier and regulation engine, handles logic and result can be with advisory agent's
It is similar with result height to handle logic.In addition it can input the information such as the work experience of candidate by deep neural network,
The various mental states, including motivation, phychology, expectation etc. of each behavior behind of candidate are obtained, party's personality is extracted
The various features of layer and quality layer are aggregated into material and are input in talent's portrait building system of the invention.
Working knowledge graphical spectrum technology of the present invention, so that talent's portrait is capable of forming in resume or other materials to people and refers to
The confident inferences of technical ability range except knowledge expertise can overcome resume or tradition evaluation text to compare in terms of portraying the talent
Single weakness forms comprehensive model of the levels such as the slave technical ability, psychology, quality of the covering talent.Portrait can be formed simultaneously
The digitlization assignment of each dimension of people preferably serves human resources field for use in subsequent machine learning model.
Some exemplary embodiments are described as the processing or method described as flow chart.Although flow chart grasps items
It is described into the processing of sequence, but many of these operations can be implemented concurrently, concomitantly or simultaneously.In addition, each
The sequence of item operation can be rearranged.The processing can be terminated when its operations are completed, it is also possible to have not
Including additional step in the accompanying drawings.The processing can correspond to method, function, regulation, subroutine, subprogram etc..
According to another embodiment of the invention, a kind of calculating equipment, including processor and memory are additionally provided, is handled
Device and memory establish communication connection, the processor, for reading the program in memory, to execute shown in Fig. 1 and Fig. 2
Method.
According to another embodiment of the invention, a kind of non-volatile memory medium is additionally provided, it is described non-volatile to deposit
Program is stored in storage media, when which is run by calculating equipment, the calculating equipment executes Fig. 1 and side shown in Fig. 2
Method.
System/method provided by the invention can arbitrarily calculate equipment in implement, including personal computer, work station,
Server, portable computing device (PCD), such as cellular phone, portable digital-assistant (PDA), portable game machine, palm
Computer or tablet computer etc..
The embodiment of the present invention is elaborated above in conjunction with attached drawing, but the use of technical solution of the present invention is not only
The various applications referred in this patent embodiment are confined to, various structures and modification can be with reference to technical solution of the present invention easily
Ground is implemented, to reach various beneficial effects mentioned in this article.Within the knowledge of a person skilled in the art,
The various change made without departing from the purpose of the present invention should all belong to the invention patent covering scope.
Claims (12)
1. a kind of talent's map construction method, which is characterized in that including,
Information in talents information library is subjected to cutting, obtains multiple phrases, wherein including multiple letters in the talents information library
It goes through, interview evaluation and/or performance appraisal table；
According to predefined classification, conceptual level name entity is identified from the phrase and is sorted out；
Verb-object pair is extracted from the information in the talents information library, and it is corresponding dynamic to obtain each conceptual level name entity
Word；And
The verb is mapped as the relationship between each conceptual level name entity using model trained in advance, is obtained with conceptual level
Name entity is node, and the relationship between each conceptual level name entity is talent's map on side.
2. the method according to claim 1, wherein the predefined classification includes, school, profession, industry,
It is any one or more in company, function, technical ability, project, action and/or certificate.
3. the method according to claim 1, wherein in the mould for identifying conceptual level name entity from the phrase
Type is trained by Bi-LSTM neural network.
4. a kind of method drawn a portrait using talent's map construction talent as described in claim 1, which is characterized in that including,
Material is received, wherein the material includes resume, interview evaluation, any one or more in feedback on performance table；
The information in the material is extracted, and cutting is carried out to the information in the material, obtains multiple phrases；
According to predefined classification, instance layer name entity is identified from the phrase and is sorted out；
Instance layer name entity is mapped in talent's map as constructed by claim 1, is obtained with each instance layer
Name the closure centered on entity；And
The conceptual level name entity covered in the intersection of the instance layer name entity and at least two closures is counted,
Name entity sets are obtained, the pass between each name entity in the name entity sets and the name entity sets is extracted
System draws a portrait as the talent.
5. the method for building talent portrait according to claim 4, which is characterized in that further include,
Entity is named for the instance layer being unable to map in talent's map, verb-guest is extracted from the material
Language pair obtains the corresponding verb of each instance layer name entity, the verb is mapped as each reality using model trained in advance
Relationship between example layer name entity；
Talent's map is updated using the relationship between obtained instance layer name entity and each instance layer name entity.
6. a kind of talent's map construction device, which is characterized in that including,
Information cutting unit is configured as the information in talents information library carrying out cutting, multiple phrases is obtained, wherein the people
Include multiple resumes, interview evaluation and/or performance appraisal table in ability information bank；
It names Entity recognition and sorts out unit, be configured as according to predefined classification, conceptual level life is identified from the phrase
Name entity is simultaneously sorted out；
Dynamic guest's Phrase extraction unit is configured as extracting verb-object pair from the information in the talents information library, obtains each
A conceptual level names the corresponding verb of entity；
Relationship map unit, be configured as using model trained in advance by the verb be mapped as each conceptual level name entity it
Between relationship, obtain naming entity as node using conceptual level, the relationship between each conceptual level name entity is that the talent on side schemes
Spectrum.
7. talent's map construction device according to claim 6, which is characterized in that the predefined classification includes learning
It is any one or more in school, profession, industry, company, function, technical ability, project, action and/or certificate.
8. talent's map construction device according to claim 6, which is characterized in that identifying conceptual level from the phrase
The model of name entity is trained by Bi-LSTM neural network.
The construction device 9. a kind of talent draws a portrait, which is characterized in that including,
Material receiving unit is configured as receiving material, wherein the material includes resume, interviews and evaluate, in feedback on performance table
Any one or more；
Information cutting unit is configured as extracting the information in the material, carries out cutting to the information in the material, obtains
Multiple phrases；
It names Entity recognition and sorts out unit, be configured as according to predefined classification, instance layer life is identified from the phrase
Name entity is simultaneously sorted out；
Closure recognition unit is configured as instance layer name entity being mapped to the figure of the talent as constructed by claim 6
In spectrum, the closure centered on each instance layer name entity is obtained；With
Talent's portrait construction unit is configured as counting the intersection of the instance layer name entity and at least two closures
Middle covered conceptual level names entity, obtains name entity sets, extracts the name entity sets and the name is real
The relationship between each name entity in body set is drawn a portrait as the talent.
The construction device 10. talent according to claim 9 draws a portrait, which is characterized in that further include,
Dynamic guest's Phrase extraction unit is configured as real for the instance layer name being unable to map in talent's map
Body extracts verb-object pair from the material, obtains the corresponding verb of each instance layer name entity, and
Relationship map unit, be configured as using model trained in advance by the verb be mapped as each instance layer name entity it
Between relationship；And the people is updated using the relationship between obtained instance layer name entity and each instance layer name entity
Ability map.
11. a kind of equipment, which is characterized in that including processor, memory, the processor and the memory establish communication link
It connects；
The processor, for reading the program in the memory, to execute side according to any one of claims 1 to 5
Method.
12. a kind of non-volatile memory medium, which is characterized in that store program in the non-volatile memory medium, the journey
When sequence is run by calculating equipment, the calculating equipment executes method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811570090.2A CN109726253B (en) | 2018-12-21 | 2018-12-21 | Talent map and talent portrait construction method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811570090.2A CN109726253B (en) | 2018-12-21 | 2018-12-21 | Talent map and talent portrait construction method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109726253A true CN109726253A (en) | 2019-05-07 |
| CN109726253B CN109726253B (en) | 2021-03-09 |
Family
ID=66296295
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811570090.2A Expired - Fee Related CN109726253B (en) | 2018-12-21 | 2018-12-21 | Talent map and talent portrait construction method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109726253B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443571A (en) * | 2019-07-16 | 2019-11-12 | 阿里巴巴集团控股有限公司 | The method, device and equipment of knowledge based map progress resume assessment |
| CN111177283A (en) * | 2019-12-31 | 2020-05-19 | 广东轩辕网络科技股份有限公司 | Intelligent personnel model construction method and device based on reinforcement learning |
| CN111242565A (en) * | 2019-12-31 | 2020-06-05 | 广州轩辕研究院有限公司 | Resume optimization method and device based on intelligent personnel model |
| CN111666377A (en) * | 2020-06-03 | 2020-09-15 | 贵州航天云网科技有限公司 | Talent portrait construction method and system based on big data modeling |
| CN115330363A (en) * | 2022-10-17 | 2022-11-11 | 北京智鼎管理咨询有限公司 | Talent identification method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105468605A (en) * | 2014-08-25 | 2016-04-06 | 济南中林信息科技有限公司 | Entity information map generation method and device |
| CN107967267A (en) * | 2016-10-18 | 2018-04-27 | 中兴通讯股份有限公司 | A kind of knowledge mapping construction method, apparatus and system |
| CN108595708A (en) * | 2018-05-10 | 2018-09-28 | 北京航空航天大学 | A kind of exception information file classification method of knowledge based collection of illustrative plates |
-
2018
- 2018-12-21 CN CN201811570090.2A patent/CN109726253B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105468605A (en) * | 2014-08-25 | 2016-04-06 | 济南中林信息科技有限公司 | Entity information map generation method and device |
| CN107967267A (en) * | 2016-10-18 | 2018-04-27 | 中兴通讯股份有限公司 | A kind of knowledge mapping construction method, apparatus and system |
| CN108595708A (en) * | 2018-05-10 | 2018-09-28 | 北京航空航天大学 | A kind of exception information file classification method of knowledge based collection of illustrative plates |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443571A (en) * | 2019-07-16 | 2019-11-12 | 阿里巴巴集团控股有限公司 | The method, device and equipment of knowledge based map progress resume assessment |
| CN111177283A (en) * | 2019-12-31 | 2020-05-19 | 广东轩辕网络科技股份有限公司 | Intelligent personnel model construction method and device based on reinforcement learning |
| CN111242565A (en) * | 2019-12-31 | 2020-06-05 | 广州轩辕研究院有限公司 | Resume optimization method and device based on intelligent personnel model |
| CN111666377A (en) * | 2020-06-03 | 2020-09-15 | 贵州航天云网科技有限公司 | Talent portrait construction method and system based on big data modeling |
| CN115330363A (en) * | 2022-10-17 | 2022-11-11 | 北京智鼎管理咨询有限公司 | Talent identification method and device, electronic equipment and storage medium |
| CN115330363B (en) * | 2022-10-17 | 2023-02-14 | 北京智鼎管理咨询有限公司 | Talent identification method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109726253B (en) | 2021-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107368468B (en) | Operation and maintenance knowledge map generation method and system | |
| CN109726253A (en) | Construction method, device, equipment and the medium of talent's map and talent's portrait | |
| CN110597988A (en) | Text classification method, device, equipment and storage medium | |
| CN109271506A (en) | A kind of construction method of the field of power communication knowledge mapping question answering system based on deep learning | |
| CN109189942A (en) | A kind of construction method and device of patent data knowledge mapping | |
| CN106709754A (en) | Power user grouping method based on text mining | |
| Liu et al. | A new method for knowledge and information management domain ontology graph model | |
| CN107368521B (en) | Knowledge recommendation method and system based on big data and deep learning | |
| CN111177322A (en) | Ontology model construction method of domain knowledge graph | |
| CN112632239A (en) | Brain-like question-answering system based on artificial intelligence technology | |
| CN117271767B (en) | Operation and maintenance knowledge base establishing method based on multiple intelligent agents | |
| Sadr et al. | Unified topic-based semantic models: a study in computing the semantic relatedness of geographic terms | |
| Gerhana et al. | Comparison of naive Bayes classifier and C4. 5 algorithms in predicting student study period | |
| CN116304308A (en) | Research and development partner recommendation method based on technical innovation knowledge situation super network | |
| Fariha et al. | A new framework for mining frequent interaction patterns from meeting databases | |
| CN115617960A (en) | Post recommendation method and device | |
| CN116432965B (en) | Post capability analysis method and tree diagram generation method based on knowledge graph | |
| Kaur et al. | Research on Artificial Intelligence in Human Resource Management: Trends and Prospects | |
| CN110990530A (en) | Microblog owner character analysis method based on deep learning | |
| CN105787072A (en) | Field knowledge extracting and pushing method oriented to progress | |
| CN116401338A (en) | Design feature extraction and attention mechanism based on data asset intelligent retrieval input and output requirements and method thereof | |
| CN111259106A (en) | Relation extraction method combining neural network and feature calculation | |
| CN116644148A (en) | Keyword recognition method and device, electronic equipment and storage medium | |
| Chauhan et al. | Implementing lda topic modelling technique to study user reviews in tourism | |
| CN113987126A (en) | Retrieval method and device based on knowledge graph |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210309 Termination date: 20211221 |