CN110399476A - Generation method, device, equipment and the storage medium of talent's portrait - Google Patents
Generation method, device, equipment and the storage medium of talent's portrait Download PDFInfo
- Publication number
- CN110399476A CN110399476A CN201910524634.XA CN201910524634A CN110399476A CN 110399476 A CN110399476 A CN 110399476A CN 201910524634 A CN201910524634 A CN 201910524634A CN 110399476 A CN110399476 A CN 110399476A
- Authority
- CN
- China
- Prior art keywords
- talent
- target
- portrait
- resume
- text
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
Abstract
The present invention relates to artificial intelligence field more particularly to natural language processing fields, disclose generation method, device, equipment and the storage medium of a kind of talent's portrait, for being refined to the core skills in resume, talent's portrait is generated, is checked convenient for recruiter, improves resume selection efficiency.The method of the present invention includes: to obtain target resume;Resume data are extracted from the target resume;Text classification algorithm based on natural language processing NLP cleans the resume data, obtains target text, the core skills of the target text instruction target talent;It calls preset training pattern to analyze the target text, generates prediction label, each prediction label corresponds to the core skills of the target talent;Talent's portrait of the target talent is generated according to the prediction label.
Description
Technical field
A kind of draw a portrait the present invention relates to natural language processing field more particularly to talent generation method, device, equipment and
Storage medium.
Background technique
Currently, in some large enterprises' Outsourcing of recruitment personnel, it is usually straight by human resources (human resource, HR)
Screening resume is connect, then sends specialized department, the job applicant that the specialized department of enterprise need to send HR for the resume after screening
Member's resume is confirmed, then starts to carry out hiring process.However, HR can not know about all Position Responsibilities, therefore HR
The resume of undesirable personnel may be sent, the personnel for not meeting employing unit's requirement is recommended to have an interview.
HR needs oneself to refine the key message of resume when checking the resume of candidate, for oneself uncomprehending industry,
Then extracting key message is a time-consuming and laborious work, low efficiency.
Summary of the invention
The present invention provides generation method, device, equipment and the storage mediums of a kind of talent portrait, for in resume
Core skills is refined, and is generated talent's portrait, is checked convenient for recruiter, improve resume selection efficiency.
The first aspect of the embodiment of the present invention provides a kind of generation method of talent's portrait, comprising: obtains target resume;From
Resume data are extracted in the target resume;Text classification algorithm based on natural language processing NLP to the resume data into
Row cleaning obtains target text, the core skills of the target text instruction target talent;Call preset training pattern to institute
It states target text to be analyzed, generates prediction label, each prediction label corresponds to the core skills of the target talent;
Talent's portrait of the target talent is generated according to the prediction label.
Optionally, described to call preset training mould in the first implementation of first aspect of the embodiment of the present invention
Type analyzes the target text, generates prediction label, and each prediction label corresponds to the core of the target talent
Heart technical ability includes: the every application information successively traversed in the target text, and every application information all corresponds to the target person
One core skills of;Every application information is segmented based on preset training pattern, obtains word segmentation result;According to institute
It states word segmentation result to be retrieved in business bag of words, obtains the business keyword of every application information;By the business keyword
It arranges to obtain ranking results according to frequency descending;The keyword of preset number forward in the ranking results is determined as predicting
Label.
Optionally, described according to the prediction label in second of implementation of first aspect of the embodiment of the present invention
The talent's portrait for generating the target talent includes: one target class of creation, and the target class includes multiple attributes;According to described
Prediction label determines each attribute in the target class, the corresponding prediction label of each attribute;Determine the target
The output of class is as a result, the output result includes multiple prediction labels;According to each prediction label in the output result
Label value generate the target talent the talent portrait.
Optionally, described to be based on natural language processing in the third implementation of first aspect of the embodiment of the present invention
The text classification algorithm of NLP cleans the resume data, obtains target text, and the target text indicates the target talent
Core skills after, it is described that preset training pattern is called to analyze the target text, generate prediction label, each
Before prediction label all corresponds to the core skills of the target talent, the method also includes: generate preset training mould
Type, the preset training pattern are used to generate prediction label according to text data.
Optionally, described to generate preset training mould in the 4th kind of implementation of first aspect of the embodiment of the present invention
Type, it includes: to obtain the resume data of preset quantity that the preset training pattern, which is used to generate prediction label according to text data,;
The resume data of the preset quantity are cleaned, valid data are obtained;Corresponding label is determined for each valid data, is obtained
To corpus;The corpus is input in text training pattern;Parameter adjustment is carried out to the text training pattern, is generated
Preset training pattern, the preset training pattern are used to generate prediction label according to text data.
Optionally, described to the text training mould in the 5th kind of implementation of first aspect of the embodiment of the present invention
Type carries out parameter adjustment, generates preset training pattern, and the preset training pattern is used to be generated according to text data and predict
After label, the method also includes: determine the accurate rate P and recall rate R of the preset training pattern;According to described accurate
The rate P and recall rate R generates the F α value of the preset training pattern, and the F α value meets formula: F α=(α2+1)PR/(α2P+R), wherein the α is greater than or equal to 1;Whether it is greater than preset threshold according to the accuracy of the F α value training of judgement model
Value;If the accuracy of the training pattern is greater than preset threshold value, it is determined that the preset training pattern meets production requirement.
Optionally, described according to the prediction label in the 6th kind of implementation of first aspect of the embodiment of the present invention
After the talent's portrait for generating the target talent, the method also includes: it draws a portrait the talent of the target talent according to pre-
Bidding standard is scored to obtain target score;It is preset to judge whether the target score of talent's portrait of the target talent is greater than
Score value;If the target score that the talent of the target talent draws a portrait is greater than preset score value, it is determined that the people of the target talent
Just portrait is met the requirements, and the talent of target talent portrait is saved;If what the talent of the target talent drew a portrait
Target score is less than or equal to the preset score value, it is determined that talent's portrait of the target talent is unsatisfactory for requiring, and will
Talent's portrait of the target talent is marked.
The second aspect of the embodiment of the present invention provides a kind of generating means of talent's portrait, comprising: acquiring unit is used for
Obtain target resume;Extraction unit, for extracting resume data from the target resume;Cleaning unit, for being based on nature
The text classification algorithm of Language Processing NLP cleans the resume data, obtains target text, the target text instruction
The core skills of the target talent;First generation unit, for calling preset training pattern to analyze the target text,
Prediction label is generated, each prediction label corresponds to the core skills of the target talent;Second generation unit is used for root
Talent's portrait of the target talent is generated according to the prediction label.
Optionally, in the first implementation of second aspect of the embodiment of the present invention, the first generation unit is specifically used for:
Every application information in the target text is successively traversed, every application information all corresponds to the core of the target talent
Technical ability;Every application information is segmented based on preset training pattern, obtains word segmentation result;Existed according to the word segmentation result
It is retrieved in business bag of words, obtains the business keyword of every application information;By the business keyword according to frequency descending
Arrangement obtains ranking results;The keyword of preset number forward in the ranking results is determined as prediction label.
Optionally, in second of implementation of second aspect of the embodiment of the present invention, the second generation unit is specifically used for:
A target class is created, the target class includes multiple attributes;It is determined according to the prediction label each in the target class
Attribute, the corresponding prediction label of each attribute;The output of the target class is determined as a result, the output result includes more
A prediction label;It is drawn according to the talent that the label value of each prediction label in the output result generates the target talent
Picture.
Optionally, in the third implementation of second aspect of the embodiment of the present invention, the generating means of talent's portrait are also
It include: third generation unit, for generating preset training pattern, the preset training pattern is used for raw according to text data
At prediction label.
Optionally, in the 4th kind of implementation of second aspect of the embodiment of the present invention, third generation unit includes: to obtain
Module, for obtaining the resume data of preset quantity;Cleaning module carries out clear for the resume data to the preset quantity
It washes, obtains valid data;First determining module obtains corpus for determining corresponding label for each valid data;Input
Module, for the corpus to be input in text training pattern;Generation module is adjusted, for the text training pattern
Parameter adjustment is carried out, preset training pattern is generated, the preset training pattern is used to generate pre- mark according to text data
Label.
Optionally, in the 5th kind of implementation of second aspect of the embodiment of the present invention, third generation unit further include: the
Two determining modules, for determining the accurate rate P and recall rate R of the preset training pattern;Generation module, for according to
The accurate rate P and recall rate R generates the F α value of the preset training pattern, and the F α value meets formula: F α=(α2+1)
PR/(α2P+R), wherein the α is greater than or equal to 1;Judgment module, for according to the correct of the F α value training of judgement model
Whether rate is greater than preset threshold value;Third determining module is used for if the accuracy of the training pattern is greater than preset threshold value
Determine that the preset training pattern meets production requirement.
Optionally, in the 6th kind of implementation of second aspect of the embodiment of the present invention, the generating means of talent's portrait are also
Include: scoring unit, is scored to obtain target score according to preset standard for talent's portrait to the target talent;Sentence
Whether disconnected unit, the target score for judging that the talent of the target talent draws a portrait are greater than preset score value;Storage unit, if
The target score of talent's portrait of the target talent is greater than preset score value, then for determining that the talent of the target talent draws
It is saved as meeting the requirements, and by the talent of target talent portrait;Marking unit, if the talent of the target talent draws
The target score of picture is less than or equal to the preset score value, then for determining that talent's portrait of the target talent is unsatisfactory for wanting
It asks, and the talent of target talent portrait is marked.
The third aspect of the embodiment of the present invention provides a kind of generating device of talent's portrait, including memory, processor
And it is stored in the computer program that can be run on the memory and on the processor, the processor executes the calculating
The generation method of the portrait of the talent described in any of the above-described embodiment is realized when machine program.
The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, including instruction, when the finger
When order is run on computers, so that computer executes the step of the generation method of the portrait of the talent described in any of the above-described embodiment
Suddenly.
In technical solution provided in an embodiment of the present invention, target resume is obtained;Resume data are extracted from target resume;Base
Resume data are cleaned in the text classification algorithm of natural language processing NLP, obtain target text, target text indicates mesh
Mark the core skills of the talent;It calls preset training pattern to analyze target text, generates prediction label, each pre- mark
Label all correspond to the core skills of the target talent;Talent's portrait of the target talent is generated according to prediction label.The present invention is implemented
Example, refines the core skills in resume, generates talent's portrait, checks convenient for recruiter, improves resume selection effect
Rate.
Detailed description of the invention
Fig. 1 is one embodiment schematic diagram of the generation method of talent's portrait in the embodiment of the present invention;
Fig. 2 is another embodiment schematic diagram of the generation method of talent's portrait in the embodiment of the present invention;
Fig. 3 is one embodiment schematic diagram of the generating means of talent's portrait in the embodiment of the present invention;
Fig. 4 is another embodiment schematic diagram of the generating means of talent's portrait in the embodiment of the present invention;
Fig. 5 is one embodiment schematic diagram of the generating device of talent's portrait in the embodiment of the present invention.
Specific embodiment
The present invention provides generation method, device, equipment and the storage mediums of a kind of talent portrait, for each product
The score value of risk investigation questionnaire project decomposed, according to the score summation of topic option selected by user in risk investigation questionnaire
Risk class is defined to user, improves testing efficiency, and all application scenarios can be covered.
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
The embodiment of the present invention is described in attached drawing.
Description and claims of this specification and term " first ", " second ", " third ", " in above-mentioned attached drawing
The (if present)s such as four " are to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should manage
The data that solution uses in this way are interchangeable under appropriate circumstances, so that the embodiments described herein can be in addition to illustrating herein
Or the sequence other than the content of description is implemented.In addition, term " includes " or " having " and its any deformation, it is intended that covering is not
Exclusive includes, for example, the process, method, system, product or equipment for containing a series of steps or units be not necessarily limited to it is clear
Step or unit those of is listed on ground, but is not clearly listed or for these process, methods, product or is set
Standby intrinsic other step or units.
Referring to Fig. 1, the flow chart of the generation method of talent's portrait provided in an embodiment of the present invention, specifically includes:
101, target resume is obtained.
Terminal obtains target resume.Wherein, terminal is selected from the resume of magnanimity and is met according to preset screening conditions
It is required that resume.Goal resume can be one, be also possible to multiple, and for ease of description, the present invention is with a mesh
It is illustrated for mark resume.
Specifically, terminal obtains the resume of magnanimity according to practical situation, and filter out the target letter for meeting basic demand
It goes through, wherein target resume can be different types of resume.Target resume can be directed to different groups, to the format of resume
It is adjusted.For example, if target resume is graduating student's resume, then may include: 1 in the target resume, personal basic
Information may include name, age, gender, nationality, telephone number, native place etc. in personal essential information;2, education background, religion
Educate in background may include secondary school education experience and university education experience, wherein secondary school education experience includes school's title and
Duration is practised, university education experience includes school's title, study duration, study profession;3, major courses, major courses may include
English, higher mathematics, linear algebra, College Physics etc., can also include Architectural Mechanics, the mechanics of materials, contract management etc. other
Course, specifically herein without limitation;4, self-assessment, self-assessment include hobby etc..
For example, if target resume is social personnel's resume, then may include: 1, personal basic letter in the target resume
It ceases, may include name, age, gender, nationality, telephone number, native place etc. in personal essential information;2, education background, education
It may include secondary school education experience and university education experience in background, wherein secondary school education experience includes school's title and study
Duration, university education experience include school's title, study duration, study profession;3, working experience, working experience may include work
Office's title, operating time, action and work unit's property etc.;4, self-assessment, self-assessment include hobby,
Working attitude etc..5, honor awards, honor awards include study awards, work awards and government's awards etc., specifically herein not
It limits.6, language is grasped, grasping language may include Chinese, English, French, Guangdong language etc., specifically herein without limitation.
It should be noted that the resume of different types, the group of adaptation is also different, in the resume for including in target resume
Hold also not identical.Resume can also be customized, simultaneously can include graduating student's resume and social personnel's resume in resume
In comprising some or all of content, specifically herein without limitation.
It is understood that the executing subject of the embodiment of the present invention can be the generating means of talent's portrait, can also be
Terminal or server, specifically herein without limitation.The present invention is illustrated so that terminal is executing subject as an example.
102, resume data are extracted from target resume.
Terminal extracts resume data from target resume.Specifically, terminal extracts resume data from target resume,
In, which includes the essential information and specialized information of the target talent, wherein essential information includes name, age, property
Not, contact method etc., specialized information include work unit, length of service, graduated school, graduation profession, the certificate obtained, profession
Technical ability, objective etc..
Wherein, resume data are the respective option for including in above-mentioned steps, for example, extracting for a copy of it resume
Resume data include name: Li Yi;Age: 18;Gender: female;Contact method: 151XXXXXX54 can also include other
Information, such as graduated school: Massachusetts science and engineering, specifically herein without limitation.
103, the text classification algorithm based on natural language processing NLP cleans resume data, obtains target text,
The core skills of the target text instruction target talent.
Terminal is based on the text classification algorithm pair of natural language processing (natural language processing, NLP)
Resume data are cleaned, and target text is obtained, and target text indicates the core skills of the target talent.Specifically, terminal is called
Convolutional neural networks CNN algorithm (TextCNN) or logistic regression (logistic regression, LR) algorithm are to resume data
Carry out text classification.It is understood that regardless of classification, it is most important that it is to be understood which is characterized in most reflecting this
The characteristics of a classification, that is, Feature Selection, the feature that text classification uses are exactly the word that can most represent this classification.For example,
Resume data can be divided into two classes, i.e. valid data and invalid data, wherein valid data may include work unit, surname
Name, age, gender etc., invalid data may include objective, length of service etc., specifically herein without limitation.
Wherein, the text classification algorithm of NLP is preset convolutional neural networks CNN algorithm or LR algorithm, according to practical need
It wants, after resume data classification, is screened, delete invalid data, retain valid data, have the target talent in the valid data
Core skills information valid data " good English-speaking " is used as target text for example, good English-speaking etc..
It should be noted that text classification can also be part-of-speech tagging, sentence segmentation, know in addition to can be document classification
Other conversation activity type and identification text contain, and specifically may refer to the prior art, details are not described herein again.
104, it calls preset training pattern to analyze target text, generates prediction label, each prediction label
The core skills of the corresponding target talent.
Terminal calls preset training pattern to analyze target text, generates prediction label, each prediction label
The core skills of the corresponding target talent.Specifically, terminal successively traverses every application information in target text, every is answered
Information is engaged all to correspond to the core skills of the target talent;Terminal divides every application information based on preset training pattern
Word obtains word segmentation result;Terminal is retrieved in business bag of words according to word segmentation result, and the business for obtaining every application information is closed
Keyword;Business keyword is arranged to obtain ranking results by terminal according to frequency descending;Terminal will be forward preset in ranking results
The keyword of number is determined as prediction label.
Wherein, the abstract classification a certain feature of certain a kind of special group or object carried out and summary, value (label
Value) have can classification.For example, " gender ", label value is according to enumerating analysis (mutually exclusive
Collectively exhaustive, MECE) principle can be divided into " male ", " female ", " unknown ";For label " age ", label
Value can be divided into " 0-18 ", " 18-35 ", " 35-60 ", " 60-100 " etc., specifically herein without limitation.
105, it is drawn a portrait according to the talent that prediction label generates the target talent.
Terminal is drawn a portrait according to the talent that prediction label generates the target talent.Specifically, terminal creates a target class, target
Class includes multiple attributes;Terminal determines each attribute in target class, the corresponding pre- mark of each attribute according to prediction label
Label;Terminal determines the output of target class as a result, output result includes multiple prediction labels;Terminal is according to each pre- in output result
The label value of mark label generates talent's portrait of the target talent.
The talent portrait can simply be understood as be mass data label, according to the difference of the target of user, behavior and viewpoint
It is different, they are divided into different types, characteristic feature is then extracted in each type, assigns name, photo, some populations
The description such as statistics element, scene, forms personage's prototype (personas).For example, in obtained target talent portrait
It may include age, gender, length of service, core skills, job hunting expectation etc..Specifically, for example, by being carried out to A resume
The talent's portrait obtained after refinement can be with are as follows: internet, married, top managers, booming income.Talent's portrait can also be other marks
Label, specifically herein without limitation.
It is understood that being defined according to characteristic value (i.e. prediction label) to the target talent, facilitate human resources
(Human Resource, HR) very clear characteristic for grasping the target talent, such as " being engaged in the work of many years computer development ",
" technology is really up to the mark " etc. can quickly recognize that the target talent is to be good at the work for being engaged in computer field, and thus HR can sentence
Whether disconnected be the talent that company needs.In another example such as " fashion intelligent ", HR can be associated quickly for this kind of people, fashion
Feel most important, i.e. the design sense of product, appearance etc., and two word of intelligent shows that such people does not pursue trend blindly, they
There are the aesthetic conceptions of oneself, and people at one's side can be influenced.HR can determine that the target talent is suitble to be engaged in the correlations such as fashion medium
Work.
Meanwhile a talent has multiple prediction labels, the coincidence of prediction label is also had between the different talents, at this time
The weight of prediction label reflects the core skills of the different talents.Such as in " fashion intelligent " and " scientific and technological pioneer " two class crowd all
There is women label, need to compare label weight of the women in the different talents at this time, the label interpreting any class people given determined
Group.In general, a good talent draws a portrait, the label registration between different crowd is smaller, only in the lesser mark of those weights
It signs and has a little coincidence.
In technical solution provided in an embodiment of the present invention, target resume is obtained;Resume data are extracted from target resume;Base
Resume data are cleaned in the text classification algorithm of natural language processing NLP, obtain target text, target text indicates mesh
Mark the core skills of the talent;It calls preset training pattern to analyze target text, generates prediction label, each pre- mark
Label all correspond to the core skills of the target talent;Talent's portrait of the target talent is generated according to prediction label.The present invention is implemented
Example, refines the core skills in resume, generates talent's portrait, checks convenient for recruiter, improves resume selection effect
Rate.
Referring to Fig. 2, another flow chart of the generation method of talent's portrait provided in an embodiment of the present invention, specific to wrap
It includes:
201, target resume is obtained.
Terminal obtains target resume.Wherein, terminal is selected from the resume of magnanimity and is met according to preset screening conditions
It is required that resume.Goal resume can be one, be also possible to multiple, and for ease of description, the present invention is with a mesh
It is illustrated for mark resume.
Specifically, terminal obtains the resume of magnanimity according to practical situation, and filter out the target letter for meeting basic demand
It goes through, wherein target resume can be different types of resume.Target resume can be directed to different groups, to the format of resume
It is adjusted.For example, if target resume is graduating student's resume, then may include: 1 in the target resume, personal basic
Information may include name, age, gender, nationality, telephone number, native place etc. in personal essential information;2, education background, religion
Educate in background may include secondary school education experience and university education experience, wherein secondary school education experience includes school's title and
Duration is practised, university education experience includes school's title, study duration, study profession;3, major courses, major courses may include
English, higher mathematics, linear algebra, College Physics etc., can also include Architectural Mechanics, the mechanics of materials, contract management etc. other
Course, specifically herein without limitation;4, self-assessment, self-assessment include hobby etc..
For example, if target resume is social personnel's resume, then may include: 1, personal basic letter in the target resume
It ceases, may include name, age, gender, nationality, telephone number, native place etc. in personal essential information;2, education background, education
It may include secondary school education experience and university education experience in background, wherein secondary school education experience includes school's title and study
Duration, university education experience include school's title, study duration, study profession;3, working experience, working experience may include work
Office's title, operating time, action and work unit's property etc.;4, self-assessment, self-assessment include hobby,
Working attitude etc..5, honor awards, honor awards include study awards, work awards and government's awards etc., specifically herein not
It limits.6, language is grasped, grasping language may include Chinese, English, French, Guangdong language etc., specifically herein without limitation.
It should be noted that the resume of different types, the group of adaptation is also different, in the resume for including in target resume
Hold also not identical.Resume can also be customized, simultaneously can include graduating student's resume and social personnel's resume in resume
In comprising some or all of content, specifically herein without limitation.
It is understood that the executing subject of the embodiment of the present invention can be the generating means of talent's portrait, can also be
Terminal or server, specifically herein without limitation.The present invention is illustrated so that terminal is executing subject as an example.
202, resume data are extracted from target resume.
Terminal extracts resume data from target resume.Specifically, terminal extracts resume data from target resume,
In, which includes the essential information and specialized information of the target talent, wherein essential information includes name, age, property
Not, contact method etc., specialized information include work unit, length of service, graduated school, graduation profession, the certificate obtained, profession
Technical ability, objective etc..
Wherein, resume data are the respective option for including in above-mentioned steps, for example, extracting for a copy of it resume
Resume data include name: Li Yan;Age: 18;Gender: female;Contact method: 151XXXXXX54 can also include other
Information, such as graduated school: Massachusetts science and engineering, specifically herein without limitation.
203, the text classification algorithm based on natural language processing NLP cleans resume data, obtains target text,
The core skills of the target text instruction target talent.
Terminal is based on the text classification algorithm pair of natural language processing (natural language processing, NLP)
Resume data are cleaned, and target text is obtained, and target text indicates the core skills of the target talent.Specifically, terminal is called
Convolutional neural networks CNN algorithm (TextCNN) or logistic regression (logistic regression, LR) algorithm are to resume data
Carry out text classification.It is understood that regardless of classification, it is most important that it is to be understood which is characterized in most reflecting this
The characteristics of a classification, that is, Feature Selection, the feature that text classification uses are exactly the word that can most represent this classification.For example,
Resume data can be divided into two classes, i.e. valid data and invalid data, wherein valid data may include work unit, surname
Name, age, gender etc., invalid data may include objective, length of service etc., specifically herein without limitation.
Wherein, the text classification algorithm of NLP is preset convolutional neural networks CNN algorithm or LR algorithm, according to practical need
It wants, after resume data classification, is screened, delete invalid data, retain valid data, have the target talent in the valid data
Core skills information valid data " good English-speaking " is used as target text for example, good English-speaking etc..
It should be noted that text classification can also be part-of-speech tagging, sentence segmentation, know in addition to can be document classification
Other conversation activity type and identification text contain, and specifically may refer to the prior art, details are not described herein again.
204, it calls preset training pattern to analyze target text, generates prediction label, each prediction label
The core skills of the corresponding target talent.
Terminal calls preset training pattern to analyze target text, generates prediction label, each prediction label
The core skills of the corresponding target talent.Specifically, terminal successively traverses every application information in target text, every is answered
Information is engaged all to correspond to the core skills of the target talent;Terminal divides every application information based on preset training pattern
Word obtains word segmentation result;Terminal is retrieved in business bag of words according to word segmentation result, and the business for obtaining every application information is closed
Keyword;Business keyword is arranged to obtain ranking results by terminal according to frequency descending;Terminal will be forward preset in ranking results
The keyword of number is determined as prediction label.
Wherein, the abstract classification a certain feature of certain a kind of special group or object carried out and summary, value (label
Value) have can classification.For example, " gender ", label value is according to enumerating analysis (mutually exclusive
Collectively exhaustive, MECE) principle can be divided into " male ", " female ", " unknown ";For label " age ", label
Value can be divided into " 0-18 ", " 18-35 ", " 35-60 ", " 60-100 " etc., specifically herein without limitation.
205, it is drawn a portrait according to the talent that prediction label generates the target talent.
Terminal is drawn a portrait according to the talent that prediction label generates the target talent.Specifically, terminal creates a target class, target
Class includes multiple attributes;Terminal determines each attribute in target class, the corresponding pre- mark of each attribute according to prediction label
Label;Terminal determines the output of target class as a result, output result includes multiple prediction labels;Terminal is according to each pre- in output result
The label value of mark label generates talent's portrait of the target talent.
The talent portrait can simply be understood as be mass data label, according to the difference of the target of user, behavior and viewpoint
It is different, they are divided into different types, characteristic feature is then extracted in each type, assigns name, photo, some populations
The description such as statistics element, scene, forms personage's prototype (personas).For example, in obtained target talent portrait
It may include age, gender, length of service, core skills, job hunting expectation etc..Specifically, for example, by being carried out to A resume
The talent's portrait obtained after refinement can be with are as follows: internet, married, top managers, booming income.Talent's portrait can also be other marks
Label, specifically herein without limitation.
It is understood that being defined according to characteristic value (i.e. prediction label) to the target talent, facilitate human resources
(Human Resource, HR) very clear characteristic for grasping the target talent, such as " being engaged in the work of many years computer development ",
" technology is really up to the mark " etc. can quickly recognize that the target talent is to be good at the work for being engaged in computer field, and thus HR can sentence
Whether disconnected be the talent that company needs.In another example such as " fashion intelligent ", HR can be associated quickly for this kind of people, fashion
Feel most important, i.e. the design sense of product, appearance etc., and two word of intelligent shows that such people does not pursue trend blindly, they
There are the aesthetic conceptions of oneself, and people at one's side can be influenced.HR can determine that the target talent is suitble to be engaged in the correlations such as fashion medium
Work.
Meanwhile a talent has multiple prediction labels, the coincidence of prediction label is also had between the different talents, at this time
The weight of prediction label reflects the core skills of the different talents.Such as in " fashion intelligent " and " scientific and technological pioneer " two class crowd all
There is women label, need to compare label weight of the women in the different talents at this time, the label interpreting any class people given determined
Group.In general, a good talent draws a portrait, the label registration between different crowd is smaller, only in the lesser mark of those weights
It signs and has a little coincidence.
206, talent's portrait of the target talent is scored to obtain target score according to preset standard.
Terminal is scored to obtain target score according to preset standard to talent's portrait of the target talent.Specifically, terminal
According to preset standard, the weight and the corresponding score value of every information of every information in talent's portrait are determined, according to weight and score value
The target score of talent's portrait is calculated.For example, it is assumed that talent's portrait includes 2 information, operating time and working level, work
The weight for making duration and working level is all 0.5, preset standard are as follows: when operating when a length of 0-2, score value is 2 points, when work
When a length of 3-5, score value is 4 points, and when operating time is 5-8, score value is 6 points, when operating time is 9 years or more, score value 8
Point;When working level is common office worker, score value is 2 points, and when working level is middle-ranking officials, score value is 4 points, and working level is height
When layer cadre, score value is 6 points, when leading based on working level, and score value is 8 points.It works when in talent's portrait of the target talent
Shi Changwei 4 years, when working level is middle-ranking officials, 4*0.5+4*0.5=4 is calculated, obtained target score is 4 points.
207, judge whether the target score of talent's portrait of the target talent is greater than preset score value.
Terminal judges whether the target score of talent's portrait of the target talent is greater than preset score value.Specifically, preset
Score value is to be preset according to thing situation, for example, preset score value is 3 points, then the template score value in above-mentioned steps is 4 points
Target resume be greater than preset score value.If the target score that the talent of the target talent draws a portrait is greater than preset score value, execute
Step 208.If the target score that the talent of the target talent draws a portrait is less than or equal to preset score value, 209 are thened follow the steps.
If 208, the target score of talent's portrait of the target talent is greater than preset score value, it is determined that the talent of the target talent
Portrait is met the requirements, and the talent of target talent portrait is saved.
If the target score that the talent of the target talent draws a portrait is greater than preset score value, terminal determines the talent of the target talent
Portrait is met the requirements, and the talent of target talent portrait is saved.Terminal saves talent's portrait of meet demand,
So that transferring corresponding resume according to talent portrait when need to use.
If 209, the target score of talent's portrait of the target talent is less than or equal to preset score value, it is determined that the target talent
The talent portrait be unsatisfactory for requiring, and by the talent of the target talent portrait be marked.
If the target score that the talent of the target talent draws a portrait is less than or equal to preset score value, terminal determines the target talent
The talent portrait be unsatisfactory for requiring, and by the talent of the target talent portrait be marked.
Optionally, terminal can also generate prompt information wherein, and prompt information may be used also in addition to the score value including talent's portrait
To include the mark of talent's portrait, which is used to indicate whether talent's portrait meets the requirements, so that staff is receiving
When prompt, label pointedly is distinguished to the talent's portrait met the requirements.
In technical solution provided in an embodiment of the present invention, target resume is obtained;Resume data are extracted from target resume;Base
Resume data are cleaned in the text classification algorithm of natural language processing NLP, obtain target text, target text indicates mesh
Mark the core skills of the talent;It calls preset training pattern to analyze target text, generates prediction label, each pre- mark
Label all correspond to the core skills of the target talent;Talent's portrait of the target talent is generated according to prediction label.The present invention is implemented
Example, refines the core skills in resume, generates talent's portrait, checks convenient for recruiter, improves resume selection effect
Rate.
The generation method drawn a portrait above to the talent in the embodiment of the present invention is described, below in the embodiment of the present invention
The generating means of talent's portrait are described, referring to Fig. 3, a reality of the generating means that the talent draws a portrait in the embodiment of the present invention
Applying example includes:
Acquiring unit 301, for obtaining target resume;
Extraction unit 302, for extracting resume data from the target resume;
Cleaning unit 303 carries out the resume data for the text classification algorithm based on natural language processing NLP clear
It washes, obtains target text, the core skills of the target text instruction target talent;
First generation unit 304 generates prediction for calling preset training pattern to analyze the target text
Label, each prediction label correspond to the core skills of the target talent;
Second generation unit 305, the talent for generating the target talent according to the prediction label draw a portrait.
In the embodiment of the present invention, target resume is obtained;Resume data are extracted from target resume;Based on natural language processing
The text classification algorithm of NLP cleans resume data, obtains target text, and target text indicates the core skill of the target talent
Energy;It calls preset training pattern to analyze target text, generates prediction label, each prediction label corresponds to target person
One core skills of;Talent's portrait of the target talent is generated according to prediction label.The embodiment of the present invention, to the core in resume
Heart technical ability is refined, and is generated talent's portrait, is checked convenient for recruiter, improve resume selection efficiency.
Referring to Fig. 4, another embodiment for the generating means that the talent draws a portrait in the embodiment of the present invention includes:
Acquiring unit 301, for obtaining target resume;
Extraction unit 302, for extracting resume data from the target resume;
Cleaning unit 303 carries out the resume data for the text classification algorithm based on natural language processing NLP clear
It washes, obtains target text, the core skills of the target text instruction target talent;
First generation unit 304 generates prediction for calling preset training pattern to analyze the target text
Label, each prediction label correspond to the core skills of the target talent;
Second generation unit 305, the talent for generating the target talent according to the prediction label draw a portrait.
Optionally, the first generation unit 304 is specifically used for:
Every application information in the target text is successively traversed, every application information all corresponds to the target talent's
One core skills;Every application information is segmented based on preset training pattern, obtains word segmentation result;According to described point
Word result is retrieved in business bag of words, obtains the business keyword of every application information;By the business keyword according to
Frequency descending arranges to obtain ranking results;The keyword of preset number forward in the ranking results is determined as pre- mark
Label.
Optionally, the second generation unit 305 is specifically used for:
A target class is created, the target class includes multiple attributes;The target class is determined according to the prediction label
In each attribute, the corresponding prediction label of each attribute;The output of the target class is determined as a result, the output is tied
Fruit includes multiple prediction labels;The target talent is generated according to the label value of each prediction label in the output result
The talent portrait.
Optionally, the generating means of talent's portrait further include:
Third generation unit 306, for generating preset training pattern, the preset training pattern is used for according to text
Data generate prediction label.
Optionally, third generation unit 306 includes:
Module 3061 is obtained, for obtaining the resume data of preset quantity;
Cleaning module 3062 cleans for the resume data to the preset quantity, obtains valid data;
First determining module 3063 obtains corpus for determining corresponding label for each valid data;
Input module 3064, for the corpus to be input in text training pattern;
Generation module 3065 is adjusted, for carrying out parameter adjustment to the text training pattern, generates preset training mould
Type, the preset training pattern are used to generate prediction label according to text data.
Optionally, third generation unit 306 further include:
Second determining module 3066, for determining the accurate rate P and recall rate R of the preset training pattern;
Generation module 3067, for generating the preset training pattern according to the accurate rate P and the recall rate R
F α value, the F α value meet formula: F α=(α2+1)PR/(α2P+R), wherein the α is greater than or equal to 1;
Judgment module 3068, for whether being greater than preset threshold value according to the accuracy of the F α value training of judgement model;
Third determining module 3069, if the accuracy of the training pattern is greater than preset threshold value, described in determining
Preset training pattern meets production requirement.
Optionally, the generating means of talent's portrait further include:
Score unit 307, is scored to obtain target according to preset standard for talent's portrait to the target talent
Score value;
Whether judging unit 308, the target score for judging that the talent of the target talent draws a portrait are greater than preset point
Value;
Storage unit 309, if the target score that the talent of the target talent draws a portrait is greater than preset score value, for true
Talent's portrait of the fixed target talent is met the requirements, and the talent of target talent portrait is saved;
Marking unit 310, if the target score that the talent of the target talent draws a portrait is less than or equal to described preset point
Value then for determining that talent's portrait of the target talent is unsatisfactory for requiring, and the talent of the target talent is drawn a portrait and is carried out
Label.
In the embodiment of the present invention, target resume is obtained;Resume data are extracted from target resume;Based on natural language processing
The text classification algorithm of NLP cleans resume data, obtains target text, and target text indicates the core skill of the target talent
Energy;It calls preset training pattern to analyze target text, generates prediction label, each prediction label corresponds to target person
One core skills of;Talent's portrait of the target talent is generated according to prediction label.The embodiment of the present invention, to the core in resume
Heart technical ability is refined, and is generated talent's portrait, is checked convenient for recruiter, improve resume selection efficiency.
Angle of the above figure 3 to Fig. 4 from modular functionality entity fills the generation of talent's portrait in the embodiment of the present invention
It sets and is described in detail, the generating device that the talent in the embodiment of the present invention draws a portrait is carried out from the angle of hardware handles below detailed
Description.
Fig. 5 is a kind of structural schematic diagram of the generating device of talent's portrait provided in an embodiment of the present invention, talent portrait
Generating device 500 can generate bigger difference because configuration or performance are different, may include one or more processing
Device (central processing units, CPU) 501 (for example, one or more processors) and memory 509, one
(such as one or more mass memories of storage medium 508 of a or more than one storage application program 507 or data 506
Equipment).Wherein, memory 509 and storage medium 508 can be of short duration storage or persistent storage.It is stored in storage medium 508
Program may include one or more modules (diagram does not mark), and each module may include setting to the generation of talent's portrait
Series of instructions operation in standby.Further, processor 501 can be set to communicate with storage medium 508, draw in the talent
The series of instructions operation in storage medium 508 is executed in the generating device 500 of picture.
The generating device 500 of talent's portrait can also include one or more power supplys 502, one or more have
Line or radio network interface 503, one or more input/output interfaces 504, and/or, one or more operation systems
System 505, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD etc..Those skilled in the art can manage
It solves, the generating device structure of the portrait of the talent shown in Fig. 5 does not constitute the restriction of the generating device to talent's portrait, can wrap
It includes than illustrating more or fewer components, perhaps combines certain components or different component layouts.Processor 501 can be held
Acquiring unit 301, extraction unit 302, cleaning unit 303, the first generation unit 304, second generate single in row above-described embodiment
Member 305, third generation unit 306, the function of scoring unit 307, judging unit 308 and marking unit 310.
It is specifically introduced below with reference to each component parts of the Fig. 5 to the generating device that the talent draws a portrait:
Processor 501 is the control centre of the generating device of talent's portrait, the generation that can be drawn a portrait according to the talent of setting
Method is handled.The various pieces for the generating device that processor 501 is drawn a portrait using various interfaces and the entire talent of connection,
By running or execute the software program and/or module that are stored in memory 509, and calls and be stored in memory 509
Data, execute the talent portrait generating device various functions and processing data, the core skills in resume is refined,
Talent's portrait is generated, is checked convenient for recruiter, improves resume selection efficiency.Storage medium 508 and memory 509 are all deposited
The carrier for storing up data, in the embodiment of the present invention, storage medium 508 can refer to that storage volume is smaller, but fireballing interior storage
Device, and memory 509 can be that storage volume is big, but the external memory that storage speed is slow.
Memory 509 can be used for storing software program and module, and processor 501 is stored in memory 509 by operation
Software program and module, thereby executing the talent portrait generating device 500 various function application and data processing.It deposits
Reservoir 509 can mainly include storing program area and storage data area, wherein storing program area can storage program area, at least one
Application program needed for a function (for example resume data are extracted from target resume) etc.;Storage data area can be stored according to the talent
The generating device of portrait uses created data (such as prediction label etc.) etc..In addition, memory 509 may include high speed
Random access memory, can also include nonvolatile memory, a for example, at least disk memory, flush memory device or
Other volatile solid-state parts.It the generation method program of the talent's portrait provided in embodiments of the present invention and receives
Data flow stores in memory, and when it is desired to be used, processor 501 is called from memory 509.
When loading on computers and executing the computer program instructions, entirely or partly generate according to of the invention real
Apply process described in example or function.The computer can be general purpose computer, special purpose computer, computer network or its
His programmable device.The computer instruction may be stored in a computer readable storage medium, or can from a computer
Read storage medium transmitted to another computer readable storage medium, for example, the computer instruction can from a web-site,
Computer, server or data center pass through wired (such as coaxial cable, optical fiber, twisted pair) or wireless (such as infrared, nothing
Line, microwave etc.) mode transmitted to another web-site, computer, server or data center.It is described computer-readable
Storage medium can be any usable medium that computer can store or include that one or more usable mediums are integrated
The data storage devices such as server, data center.The usable medium can be magnetic medium, (for example, floppy disk, hard disk, magnetic
Band), optical medium (for example, CD) or semiconductor medium (such as solid state hard disk (solid state disk, SSD)) etc..
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided by the present invention, it should be understood that disclosed system, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, the indirect coupling of device or unit
It closes or communicates to connect, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in embodiments of the present invention can integrate in one processing unit, it is also possible to each
A unit physically exists alone, and can also be integrated in one unit with two or more units.Above-mentioned integrated unit was both
It can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or the network equipment etc.) executes the complete of each embodiment the method for the present invention
Portion or part steps.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (read-only memory,
ROM), random access memory (random access memory, RAM), magnetic or disk etc. are various can store program
The medium of code.
The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although referring to before
Stating embodiment, invention is explained in detail, those skilled in the art should understand that: it still can be to preceding
Technical solution documented by each embodiment is stated to modify or equivalent replacement of some of the technical features;And these
It modifies or replaces, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. a kind of generation method of talent's portrait characterized by comprising
Obtain target resume;
Resume data are extracted from the target resume;
Text classification algorithm based on natural language processing NLP cleans the resume data, obtains target text, described
The core skills of the target text instruction target talent;
It calls preset training pattern to analyze the target text, generates prediction label, each prediction label is corresponding
The core skills of the target talent;
Talent's portrait of the target talent is generated according to the prediction label.
2. the generation method of talent's portrait according to claim 1, which is characterized in that described to call preset training pattern
The target text is analyzed, prediction label is generated, each prediction label corresponds to the core of the target talent
Technical ability includes:
Every application information in the target text is successively traversed, every application information all corresponds to one of the target talent
Core skills;
Every application information is segmented based on preset training pattern, obtains word segmentation result;
It is retrieved in business bag of words according to the word segmentation result, obtains the business keyword of every application information;
The business keyword is arranged to obtain ranking results according to frequency descending;
The keyword of preset number forward in the ranking results is determined as prediction label.
3. the generation method of talent's portrait according to claim 1, which is characterized in that described raw according to the prediction label
Include: at talent's portrait of the target talent
A target class is created, the target class includes multiple attributes;
Each attribute in the target class, the corresponding prediction label of each attribute are determined according to the prediction label;
The output of the target class is determined as a result, the output result includes multiple prediction labels;
Talent's portrait of the target talent is generated according to the label value of each prediction label in the output result.
4. the generation method of talent's portrait according to claim 1, which is characterized in that described to be based on natural language processing
The text classification algorithm of NLP cleans the resume data, obtains target text, and the target text indicates the target talent
Core skills after, it is described that preset training pattern is called to analyze the target text, generate prediction label, each
Before prediction label all corresponds to the core skills of the target talent, the method also includes:
Preset training pattern is generated, the preset training pattern is used to generate prediction label according to text data.
5. the generation method of talent's portrait according to claim 4, which is characterized in that described to generate preset training mould
Type, the preset training pattern, which is used to generate prediction label according to text data, includes:
Obtain the resume data of preset quantity;
The resume data of the preset quantity are cleaned, valid data are obtained;
Corresponding label is determined for each valid data, obtains corpus;
The corpus is input in text training pattern;
Parameter adjustment is carried out to the text training pattern, generates preset training pattern, the preset training pattern is used for
Prediction label is generated according to text data.
6. the generation method of talent's portrait according to claim 5, which is characterized in that described to the text training pattern
Parameter adjustment is carried out, preset training pattern is generated, the preset training pattern is used to generate pre- mark according to text data
After label, the method also includes:
Determine the accurate rate P and recall rate R of the preset training pattern;
The F α value of the preset training pattern is generated according to the accurate rate P and the recall rate R, the F α value meets public
Formula:
F α=(α2+1)PR/(α2P+R), wherein the α is greater than or equal to 1;
Whether it is greater than preset threshold value according to the accuracy of the F α value training of judgement model;
If the accuracy of the training pattern is greater than preset threshold value, it is determined that the preset training pattern meets production need
It asks.
7. according to claim 1 in -6 any talent's portrait generation method, which is characterized in that it is described according to described pre-
After mark label generate talent's portrait of the target talent, the method also includes:
Talent's portrait of the target talent is scored to obtain target score according to preset standard;
Judge whether the target score of talent's portrait of the target talent is greater than preset score value;
If the target score that the talent of the target talent draws a portrait is greater than preset score value, it is determined that the talent of the target talent
Portrait is met the requirements, and the talent of target talent portrait is saved;
If the target score that the talent of the target talent draws a portrait is less than or equal to the preset score value, it is determined that the target
Talent's portrait of the talent is unsatisfactory for requiring, and the talent of target talent portrait is marked.
8. a kind of generating means of talent's portrait characterized by comprising
Acquiring unit, for obtaining target resume;
Extraction unit, for extracting resume data from the target resume;
Cleaning unit cleans the resume data for the text classification algorithm based on natural language processing NLP, obtains
Target text, the core skills of the target text instruction target talent;
First generation unit generates prediction label, often for calling preset training pattern to analyze the target text
A prediction label all corresponds to the core skills of the target talent;
Second generation unit, the talent for generating the target talent according to the prediction label draw a portrait.
9. a kind of generating device of talent's portrait, which is characterized in that including memory, processor and be stored on the memory
And the computer program that can be run on the processor, it is realized when the processor executes the computer program as right is wanted
The generation method for asking the talent described in any one of 1-7 to draw a portrait.
10. a kind of computer readable storage medium, which is characterized in that including instruction, when described instruction is run on computers,
So that computer executes the generation method of talent's portrait as described in any one of claim 1-7.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910524634.XA CN110399476A (en) | 2019-06-18 | 2019-06-18 | Generation method, device, equipment and the storage medium of talent's portrait |
PCT/CN2020/093409 WO2020253503A1 (en) | 2019-06-18 | 2020-05-29 | Talent portrait generation method, apparatus and device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910524634.XA CN110399476A (en) | 2019-06-18 | 2019-06-18 | Generation method, device, equipment and the storage medium of talent's portrait |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110399476A true CN110399476A (en) | 2019-11-01 |
Family
ID=68323184
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910524634.XA Pending CN110399476A (en) | 2019-06-18 | 2019-06-18 | Generation method, device, equipment and the storage medium of talent's portrait |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110399476A (en) |
WO (1) | WO2020253503A1 (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111143517A (en) * | 2019-12-30 | 2020-05-12 | 浙江阿尔法人力资源有限公司 | Method, device, equipment and storage medium for predicting human-selected label |
CN111160850A (en) * | 2019-12-11 | 2020-05-15 | 浙江微元智能科技股份有限公司 | Matching system and matching method suitable for person discrimination |
CN111738586A (en) * | 2020-06-17 | 2020-10-02 | 中国银行股份有限公司 | Talent assessment method and device |
CN111754109A (en) * | 2020-06-23 | 2020-10-09 | 重庆电子工程职业学院 | Graduate employment management system |
CN111813842A (en) * | 2020-09-10 | 2020-10-23 | 杭州城市大数据运营有限公司 | Data processing method, device, system, equipment and storage medium |
WO2020253503A1 (en) * | 2019-06-18 | 2020-12-24 | 平安科技(深圳)有限公司 | Talent portrait generation method, apparatus and device, and storage medium |
CN112434504A (en) * | 2020-11-23 | 2021-03-02 | 京东数字科技控股股份有限公司 | Method and device for generating file information, electronic equipment and computer readable medium |
CN113010727A (en) * | 2021-03-22 | 2021-06-22 | 平安科技(深圳)有限公司 | Live broadcast platform portrait construction method, device, equipment and storage medium |
CN113032441A (en) * | 2021-03-24 | 2021-06-25 | 宁波莱博网络科技有限公司 | User portrait analysis system based on big data technology |
CN113360733A (en) * | 2021-06-17 | 2021-09-07 | 林宏佳 | Talent data tag classification method and system based on artificial intelligence and cloud platform |
CN114943037A (en) * | 2022-07-20 | 2022-08-26 | 平安银行股份有限公司 | System method, computer equipment and storage medium for talent portrayal |
CN115001856A (en) * | 2022-07-18 | 2022-09-02 | 国网浙江省电力有限公司杭州供电公司 | Network security portrait and attack prediction method based on data processing |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105159962A (en) * | 2015-08-21 | 2015-12-16 | 北京全聘致远科技有限公司 | Position recommendation method and apparatus, resume recommendation method and apparatus, and recruitment platform |
US20160004990A1 (en) * | 2014-07-01 | 2016-01-07 | Piazza Technologies, Inc. | Computer systems and user interfaces for learning, talent discovery, relationship management, and campaign development |
CN109492164A (en) * | 2018-11-26 | 2019-03-19 | 北京网聘咨询有限公司 | A kind of recommended method of resume, device, electronic equipment and storage medium |
CN109766438A (en) * | 2018-12-12 | 2019-05-17 | 平安科技(深圳)有限公司 | Biographic information extracting method, device, computer equipment and storage medium |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2015177491A (en) * | 2014-03-18 | 2015-10-05 | 株式会社リコー | Information processing apparatus, information processing system, information processing method and program |
CN108764835A (en) * | 2018-05-24 | 2018-11-06 | 广州合摩计算机科技有限公司 | Reverse talent's pushed information method and apparatus |
CN109636337A (en) * | 2018-12-12 | 2019-04-16 | 北京唐冠天朗科技开发有限公司 | A kind of talent's base construction method and electronic equipment based on big data |
CN110399476A (en) * | 2019-06-18 | 2019-11-01 | 平安科技(深圳)有限公司 | Generation method, device, equipment and the storage medium of talent's portrait |
-
2019
- 2019-06-18 CN CN201910524634.XA patent/CN110399476A/en active Pending
-
2020
- 2020-05-29 WO PCT/CN2020/093409 patent/WO2020253503A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160004990A1 (en) * | 2014-07-01 | 2016-01-07 | Piazza Technologies, Inc. | Computer systems and user interfaces for learning, talent discovery, relationship management, and campaign development |
CN105159962A (en) * | 2015-08-21 | 2015-12-16 | 北京全聘致远科技有限公司 | Position recommendation method and apparatus, resume recommendation method and apparatus, and recruitment platform |
CN109492164A (en) * | 2018-11-26 | 2019-03-19 | 北京网聘咨询有限公司 | A kind of recommended method of resume, device, electronic equipment and storage medium |
CN109766438A (en) * | 2018-12-12 | 2019-05-17 | 平安科技(深圳)有限公司 | Biographic information extracting method, device, computer equipment and storage medium |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020253503A1 (en) * | 2019-06-18 | 2020-12-24 | 平安科技(深圳)有限公司 | Talent portrait generation method, apparatus and device, and storage medium |
CN111160850A (en) * | 2019-12-11 | 2020-05-15 | 浙江微元智能科技股份有限公司 | Matching system and matching method suitable for person discrimination |
CN111143517B (en) * | 2019-12-30 | 2023-09-05 | 浙江阿尔法人力资源有限公司 | Human selection label prediction method, device, equipment and storage medium |
CN111143517A (en) * | 2019-12-30 | 2020-05-12 | 浙江阿尔法人力资源有限公司 | Method, device, equipment and storage medium for predicting human-selected label |
CN111738586A (en) * | 2020-06-17 | 2020-10-02 | 中国银行股份有限公司 | Talent assessment method and device |
CN111738586B (en) * | 2020-06-17 | 2024-04-23 | 中国银行股份有限公司 | Talent assessment method and device |
CN111754109A (en) * | 2020-06-23 | 2020-10-09 | 重庆电子工程职业学院 | Graduate employment management system |
CN111813842A (en) * | 2020-09-10 | 2020-10-23 | 杭州城市大数据运营有限公司 | Data processing method, device, system, equipment and storage medium |
CN112434504A (en) * | 2020-11-23 | 2021-03-02 | 京东数字科技控股股份有限公司 | Method and device for generating file information, electronic equipment and computer readable medium |
CN113010727B (en) * | 2021-03-22 | 2024-02-02 | 平安科技(深圳)有限公司 | Live platform portrait construction method, device, equipment and storage medium |
CN113010727A (en) * | 2021-03-22 | 2021-06-22 | 平安科技(深圳)有限公司 | Live broadcast platform portrait construction method, device, equipment and storage medium |
CN113032441A (en) * | 2021-03-24 | 2021-06-25 | 宁波莱博网络科技有限公司 | User portrait analysis system based on big data technology |
CN113360733A (en) * | 2021-06-17 | 2021-09-07 | 林宏佳 | Talent data tag classification method and system based on artificial intelligence and cloud platform |
CN115001856A (en) * | 2022-07-18 | 2022-09-02 | 国网浙江省电力有限公司杭州供电公司 | Network security portrait and attack prediction method based on data processing |
CN114943037A (en) * | 2022-07-20 | 2022-08-26 | 平安银行股份有限公司 | System method, computer equipment and storage medium for talent portrayal |
Also Published As
Publication number | Publication date |
---|---|
WO2020253503A1 (en) | 2020-12-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110399476A (en) | Generation method, device, equipment and the storage medium of talent's portrait | |
CN112632385B (en) | Course recommendation method, course recommendation device, computer equipment and medium | |
CN109165249B (en) | Data processing model construction method and device, server and user side | |
CN110399475A (en) | Resume matching process, device, equipment and storage medium based on artificial intelligence | |
CN110472060B (en) | Topic pushing method and device, computer equipment and storage medium | |
CN109902708A (en) | A kind of recommended models training method and relevant apparatus | |
KR102179890B1 (en) | Systems for data collection and analysis | |
CN107436875A (en) | File classification method and device | |
CN111177473B (en) | Personnel relationship analysis method, device and readable storage medium | |
CN105264528A (en) | Client intent in integrated search environment | |
CN111507768A (en) | Determination method of potential user, model training method and related device | |
AU2019201382A1 (en) | Determining optimal workforce types to fulfill occupational roles in an organization based on occupational attributes | |
CN110032647A (en) | Method, apparatus and storage medium based on industrial circle building knowledge mapping | |
US20220172260A1 (en) | Method, apparatus, storage medium, and device for generating user profile | |
CN110489545A (en) | File classification method and device, storage medium, computer equipment | |
CN110598869B (en) | Classification method and device based on sequence model and electronic equipment | |
CN111667056A (en) | Method and apparatus for searching model structure | |
KR20170027576A (en) | Apparatus and method of researcher rcommendation based on matching studying career | |
CN112785005A (en) | Multi-target task assistant decision-making method and device, computer equipment and medium | |
CN111539209A (en) | Method and apparatus for entity classification | |
CN112632239A (en) | Brain-like question-answering system based on artificial intelligence technology | |
CN112417121A (en) | Client intention recognition method and device, computer equipment and storage medium | |
CN113569018A (en) | Question and answer pair mining method and device | |
CN112269928A (en) | User recommendation method and device, electronic equipment and computer readable medium | |
CN111931034A (en) | Data searching method, device, equipment and storage medium |
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 |