CN109886641A - A kind of post portrait setting method, post portrait setting device and terminal device - Google Patents
A kind of post portrait setting method, post portrait setting device and terminal device Download PDFInfo
- Publication number
- CN109886641A CN109886641A CN201910068512.4A CN201910068512A CN109886641A CN 109886641 A CN109886641 A CN 109886641A CN 201910068512 A CN201910068512 A CN 201910068512A CN 109886641 A CN109886641 A CN 109886641A
- Authority
- CN
- China
- Prior art keywords
- portrait
- post
- target
- neural network
- network model
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
Abstract
This application provides a kind of post portrait setting method, post portrait setting device and terminal devices, which comprises obtains the corresponding first man portrait of each personnel held a post in target post；Each first man portrait is input in neural network model, so that the neural network model exports the post portrait of the target post；It calculates in each first man portrait, meets the ratio that the first man portrait that the post portrait requires accounts in all first mans portrait；Judge the ratio whether less than the first preset ratio；If being less than, the parameter of the neural network model is adjusted, and returns to execution second step；If being not less than, the post portrait that the neural network model is exported is drawn a portrait as final post.The application can be solved to a certain extent since post portrait setting is unreasonable, although and making recruitment side that can not recruit some the technical issues of being unsatisfactory for post portrait demand, capable of being actually competent at the personnel in post.
Description
Technical field
The application belongs to field of artificial intelligence more particularly to a kind of post portrait setting method, post portrait setting
Device, terminal device and computer readable storage medium.
Background technique
Recruitment side is needed when carrying out post recruitment for recruitment post setting post portrait (i.e. job position request), currently,
Setting for post portrait is typically all that recruiter is arranged according to recruitment experience.
Since post portrait is manually arranged, so will necessarily be influenced by the cognition of people, psychology etc., thus
The setting for causing post to be drawn a portrait is unreasonable, when post portrait setting is unreasonable, although it is some to miss recruitment side
It is unsatisfactory for post portrait demand, but can actually be competent at the personnel in post.
Summary of the invention
In view of this, this application provides a kind of post portrait setting method, post portrait setting device, terminal device and
Computer readable storage medium, can solving to draw a portrait due to post to a certain extent, it is unreasonable to be arranged, and makes the side's of recruitment nothing
Although method recruits some the technical issues of being unsatisfactory for post portrait demand, capable of being actually competent at the personnel in post.
The application first aspect provides a kind of post portrait setting method, comprising:
Obtain the corresponding first man portrait of each personnel held a post in target post；
Each first man portrait is input in neural network model, so that the neural network model is according to each the
One people, which draws a portrait, exports the post portrait of the target post；
It calculates in each first man portrait, meets first that the post portrait of above-mentioned neural network model output requires
People's portrait ratio shared in all first mans portrait；
Judge calculated ratio whether less than the first preset ratio；
If being less than above-mentioned first preset ratio, the parameter of above-mentioned neural network model is adjusted, and returns and executes above-mentioned incite somebody to action
Each first man portrait is input in neural network model, so that the neural network model is drawn a portrait according to each first man
The step of exporting the post portrait of the target post and its subsequent step；
If more than or equal to above-mentioned first preset ratio, then the post portrait exported above-mentioned neural network model is as institute
State the final post portrait of target post.
The application second aspect provides a kind of post portrait setting device, comprising:
First portrait obtains module, for obtaining the corresponding first man picture of each personnel in target post tenure
Picture；
Network inputs module, for each first man portrait to be input in neural network model, so that the nerve
Network model is drawn a portrait according to the post that each first man portrait exports the target post；
Ratio computing module meets the hilllock of above-mentioned neural network model output for calculating in each first man portrait
The first man portrait that position portrait requires ratio shared in all first mans portrait；
Ratio judgment module, for judging calculated ratio whether less than the first preset ratio；
Parameter adjustment module, if adjusting the parameter of above-mentioned neural network model for being less than above-mentioned first preset ratio,
And trigger above-mentioned network inputs module execute again by each first man portrait be input in neural network model so that should
Neural network model exports the operation of the post portrait of the target post according to each first man portrait；
Post portrait obtains module, is used for if more than or is equal to above-mentioned first preset ratio, then by above-mentioned neural network mould
The post portrait of type output is drawn a portrait as the final post of the target post.
The application third aspect provides a kind of terminal device, including memory, processor and is stored in above-mentioned storage
In device and the computer program that can run on above-mentioned processor, above-mentioned processor are realized as above when executing above-mentioned computer program
The step of stating first aspect method.
The application fourth aspect provides a kind of computer readable storage medium, above-mentioned computer-readable recording medium storage
There is computer program, realizes when above-mentioned computer program is executed by processor such as the step of above-mentioned first aspect method.
The 5th aspect of the application provides a kind of computer program product, and above-mentioned computer program product includes computer journey
Sequence is realized when above-mentioned computer program is executed by one or more processors such as the step of above-mentioned first aspect method.
Therefore this application provides a kind of post portrait setting method, acquisition first is held a post each in target post
The corresponding first man portrait of a personnel's difference, and each first man portrait is input in neural network model, it obtains
The post portrait of the above-mentioned target post of neural network model output；Secondly, calculating in each first man portrait, satisfaction is worked as
The first man portrait that the post portrait of preceding neural network model output requires ratio shared in all first mans portrait
Example, and the parameters of current neural network model are constantly adjusted, until calculated ratio reaches the first preset ratio and is
Only, final post is set by finally obtained post portrait to draw a portrait.It can be seen that in technical solution provided herein,
Meeting so that most of personnel in target post tenure can meet the requirement of finally obtained post portrait, that is to say it is above-mentioned most
Whole post portrait can include most of personnel that can be competent at target post, so that the application can be to a certain extent
Solve due to post portrait setting it is unreasonable, although and make recruitment side can not recruit it is some be unsatisfactory for post draw a portrait demand,
But the technical issues of capable of being actually competent at the personnel in post.
Detailed description of the invention
It in order to more clearly explain the technical solutions in the embodiments of the present application, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only some of the application
Embodiment for those of ordinary skill in the art without creative efforts, can also be attached according to these
Figure obtains other attached drawings.
Fig. 1 is a kind of implementation process schematic diagram for post portrait setting method that the embodiment of the present application one provides；
Fig. 2 is the schematic diagram for acquired each first man portrait that the embodiment of the present application one provides；
Fig. 3 is the schematic diagram that post portrait is obtained using neural network model that the embodiment of the present application one provides；
Fig. 4 is the implementation process schematic diagram for another post portrait setting method that the embodiment of the present application two provides；
Fig. 5 is the mapping table schematic diagram for second people of target post-portrait that the embodiment of the present application two provides；
Fig. 6 is the implementation process schematic diagram for another post portrait setting method that the embodiment of the present application two provides；
Fig. 7 is the structural schematic diagram for the neural network model that the embodiment of the present application three provides；
Fig. 8 is the implementation process schematic diagram for another post portrait setting method that the embodiment of the present application three provides；
Fig. 9 is a kind of structural schematic diagram for post portrait setting device that the embodiment of the present application four provides；
Figure 10 is the structural schematic diagram for the terminal device that the embodiment of the present application five provides.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, so as to provide a thorough understanding of the present application embodiment.However, it will be clear to one skilled in the art that there is no these specific
The application also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, so as not to obscure the description of the present application with unnecessary details.
Portrait setting method in post provided by the embodiments of the present application is suitable for terminal device, illustratively, the terminal device
Including but not limited to: smart phone, tablet computer, notebook, desktop PC, intelligent wearable device etc..
It should be appreciated that ought use in this specification and in the appended claims, term " includes " instruction is described special
Sign, entirety, step, operation, the presence of element and/or component, but be not precluded one or more of the other feature, entirety, step,
Operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this present specification merely for the sake of description specific embodiment
And be not intended to limit the application.As present specification and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in present specification and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
In addition, term " first ", " second " etc. are only used for distinguishing description, and should not be understood as in the description of the present application
Indication or suggestion relative importance.
In order to illustrate technical solution described herein, the following is a description of specific embodiments.
Embodiment one
The post portrait setting method that the embodiment of the present application one provides is described below, please refers to attached drawing 1, the application
Embodiment one post portrait setting method include:
In step s101, the corresponding first man portrait of each personnel held a post in target post is obtained.
Each step in the embodiment of the present application one is applied to terminal device, and target post described in step S101 can be with
It is the post that user (for example, recruitment side) specifies in terminal device.For example, user can be manually entered in terminal device
" JAVA engineer " Lai Zhiding target post is JAVA engineer；Alternatively, user can be in each post that terminal device provides
It is middle to select a post as target post.
In addition, each personnel described in step S101 can be the personnel of the target post tenure, it is also possible to
Once in the personnel of target post tenure, the application is not construed as limiting this.In the embodiment of the present application, above-mentioned first man
Portrait may include educational background, degree, gender, career field, profession, the length of service, graduated school grade (such as, if be
Double First-class Universities) etc. information.
For example, by step S101, available post is if it is JAVA engineer that user, which specifies target post,
The corresponding first man portrait of each personnel of JAVA engineer, as shown in Fig. 2, being JAVA engineering for acquired post
The schematic diagram of the corresponding first man portrait of each personnel of teacher.
In addition, in the embodiment of the present application, step S101 may include steps of:
Step A, personal portrait search request is issued to predetermined server, is searched with indicating that the predetermined server executes in institute
State the operation of the corresponding first man portrait of each personnel of target post tenure；
Step B, the response message that above-mentioned predetermined server returns is received；
Step C, according to above-mentioned response message, each personnel corresponding first to hold a post in the target post are obtained
Individual's portrait.
I.e. through the above steps A~step C can obtain each first man portrait from predetermined server, in addition, on
Stating each first man portrait can also locally obtain from terminal device, and the application does not make the acquisition methods that first man is drawn a portrait
It limits.
In step s 102, each first man portrait is input in neural network model, so that the neural network
Model is drawn a portrait according to the post that each first man portrait exports above-mentioned target post.
It before terminal device executes step S102, needs to obtain a neural network model first, the neural network mould
Type is used to export corresponding post portrait according to each personal portrait for being input to the neural network model, wherein the nerve net
Network model can be stored in advance in terminal device local, and terminal device, can be first from local acquisition before executing step S102
Then the neural network model executes step S102, each first man portrait that step S101 is obtained is input to the nerve
In network model, and obtain the post portrait of neural network model output.
In step s 103, it calculates in each first man portrait, the post for meeting above-mentioned neural network model output is drawn
As desired first man portrait ratio shared in all first mans portrait.
In step S103, drawn a portrait using the post of neural network model output, acquired in judgment step S101
Whether each first man portrait meets the requirement of post portrait, and calculating meets the first man that post portrait requires and draws
As shared ratio in all personal portraits.
As shown in Figure 3, it is assumed that before step S102 execution, obtain neural network model 301, and assume step S101
Obtain each first man portrait be respectively as follows: " master, male, industry science, 211 ", " undergraduate course, male, industry science, 985 " and " master,
Female, industry science, 985 ".Above three first man portrait is input in neural network model 301, if the neural network model
301 output posies portrait for " master, male, literal arts, 985 ", then each first man portrait in search " degree master with
On, gender is male, and career field is literal arts, and graduated school grade is 985 or more " first man portrait, and calculate lookup
The ratio shared in all personal portraits of first man portrait out, in attached example shown in Fig. 3, it can be deduced that meeting should
The shared ratio of the first man portrait that post portrait requires is 0.
In addition, in attached example shown in Fig. 3, it is assumed that the post portrait that neural network model 301 exports is " master, work
Section, 211 ", since the post portrait of the neural network model 301 output at this time is not defined gender, then can recognize
Gender is not required for post portrait, therefore, it can be deduced that meet " master, industry science, 211 " desired first man portraits
Have: " master, male, industry science, 211 " and " master, female, industry science, 985 ", that is to say can be calculated ratio be 2/3.
In step S104, calculated ratio is judged whether less than the first preset ratio, if so, thening follow the steps
Otherwise S105 executes step S106.
In this step, judge whether current calculated ratio reaches above-mentioned first preset ratio, those skilled in the art
Member should be it is readily conceivable that guarantee that first man portraits more as far as possible can satisfy exported post portrait requirement, this
One preset ratio can be a biggish numerical value, for example be 90%.In addition, first preset ratio can also by user (such as
Recruitment side) customized setting, i.e., user can customized setting first preset ratio, obtain corresponding post portrait.
In step s105, the parameter of above-mentioned neural network model is adjusted, and returns to step S102.
If current calculated ratio is less than above-mentioned first preset ratio, the parameter of above-mentioned neural network model is adjusted,
Then, each first man portrait that step S101 is obtained is input in parameter neural network model adjusted, again
The post portrait that the neural network model adjusted that gets parms exports, and calculate meet parameter nerve adjusted again
Network model exports first man portrait that post portrait requires ratio shared in all first mans portrait, and sentences again
Whether the ratio of breaking reaches the first preset ratio.
In step s 106, the final hilllock that the post above-mentioned neural network model exported is drawn a portrait as above-mentioned target post
Position portrait.
If current calculated ratio is not less than above-mentioned first preset ratio, it may be considered that current neural network model
To train the neural network model completed, and the conduct that the post for the neural network model output that the training is completed can be drawn a portrait
Final post portrait.
In addition, in the embodiment of the present application, it can be by above-mentioned final post portrait with the shape of text, picture and/or voice
Formula reminds user (such as recruitment side).
Optionally, in the embodiment of the present application one, each first man that can also be obtained according to step S101 is drawn a portrait, right
The information such as educational background, age, graduated school, career field in each first man portrait are for statistical analysis, and output phase is answered
Statistical result (such as histogram) so that user (such as recruitment side) is capable of the personal portrait of the direct feel target post
Distribution.
It can be seen that can make most of in target post tenure in technical solution provided by the embodiment of the present application one
Personnel can meet the requirement of finally obtained post portrait, that is to say that above-mentioned final post portrait can include most of energy
The personnel of enough competent target post, so that the application can avoid drawing a portrait to be arranged due to post not conforming to a certain extent
Reason, although and make recruitment side can not recruit it is some be unsatisfactory for post draw a portrait demand, can actually be competent at the personnel in post
The technical issues of.
Embodiment two
Another post portrait setting method that the embodiment of the present application two provides is described below, please refers to attached drawing 4,
The embodiment of the present application two post portrait setting method include:
In step S401, the corresponding first man portrait of each personnel held a post in target post is obtained, and obtain
Take the corresponding second people portrait of each personnel that can not be competent at the target post.
Step S401 is identical as the step S101 in embodiment one, needs to obtain each personnel in target post tenure
Corresponding first man portrait, related content can be found in the description of embodiment one, and details are not described herein again.
In addition, in step S401, it is also necessary to which each personnel that acquisition can not be competent at above-mentioned target post respectively correspond
Second people portrait.In the embodiment of the present application, it can locally be stored in advance and can not be competent in server or terminal device
Each second people of above-mentioned target post draws a portrait, as shown in figure 5, stored in server database JAVA engineer and
Second people's portrait corresponding to patent agency teacher.In addition, in the embodiment of the present application, it can also be by obtaining in other posies
The personal portrait of the personnel of (i.e. non-above-mentioned target post) tenure is drawn a portrait as above-mentioned second people, for example, if target post is
JAVA engineer, then the personal of the posies such as available cook, foreground or tour guide is drawn a portrait, and regard individual portrait as second
Individual's portrait.The acquisition modes that the application draws a portrait to second people are not construed as limiting.
In addition, ask those skilled in the art note that above-mentioned " obtain can not be competent at the target post each personnel it is right respectively
The step of second people portrait answered ", can execute before the step S406 described in the embodiment of the present application two, and the application is to the
The acquisition time of two people portrait is without limitation.
In step S402, each first man portrait is input in neural network model, so that the neural network
Model is drawn a portrait according to the post that each first man portrait exports above-mentioned target post.
It in step S403, calculates in each first man portrait, the post for meeting above-mentioned neural network model output is drawn
As desired first man portrait ratio shared in all first mans portrait.
In step s 404, whether judge calculated ratio less than the first preset ratio, if so, execute step S405,
Otherwise, step S406 is executed.
In step S405, the parameter of above-mentioned neural network model is adjusted, and returns to step S402.
Above-mentioned steps S402-S405 is identical with the step S102-S105 executive mode in embodiment one, can specifically join
See the description of embodiment one, details are not described herein again.
In step S406, judge in each second people draws a portrait, if having that meet above-mentioned neural network model defeated
Second people portrait that post portrait out requires, if so, S405 is returned to step, if it is not, executing step S407.
In the technical solution that the embodiment of the present application one provides, it is possible to draw a portrait to mesh in the final post that step S106 is obtained
The requirement for marking post is relatively low, so as to cause the personnel for enumerating the not competent target post in the final post portrait.Than
Such as, in the technical solution provided by embodiment one, it is assumed that it is each of JAVA engineer that step S101, which obtains target post,
First post portrait, is respectively as follows: " postgraduate ", " postgraduate ", " postgraduate " and " undergraduate course ", it is possible that step S106 is obtained
Requirement of the final post portrait taken for educational background is " senior middle school ", this is clearly not meet user (for example, recruitment side) demand
's.
So the requirement in order to avoid the finally obtained post portrait of appearance to target post is too low and does not meet user's need
The case where asking, the embodiment of the present application two improve the technical solution in embodiment one, increase step S406, it may be assumed that if
In each first man portrait, meet the first man portrait of post portrait requirement of Current Situation of Neural Network model output all
When shared ratio is not less than the first preset ratio in first man portrait, each the second of further judgment step S401 acquisition
In individual's portrait, if exist and meets second people portrait that the post portrait of current neural network model output requires, if
In the presence of the requirement for then illustrating that the post of current neural network model output is drawn a portrait to target post is too low, needs to continue to this
Neural network model is trained, and therefore, returns to step S405, adjusts the parameter of the neural network model, if step
The judging result of S406 is that there is no can then execute step S407, it is believed that the current neural network model is that training is completed
Neural network model, and the post portrait for the neural network model output that the training is completed is drawn a portrait as final post.
In step S 407, the final hilllock that the post above-mentioned neural network model exported is drawn a portrait as above-mentioned target post
Position portrait.
Step S407 is identical with the step S106 executive mode in embodiment one, and for details, reference can be made to embodiments one
Description, details are not described herein again.
From the above analysis it can be concluded that, technical solution provided by attached drawing 4 be in embodiment one technical solution into
One step is improved, and can avoid the occurrence of the finally obtained post portrait situation too low to target post requirement to a certain extent.
In addition, it is final to avoid the occurrence of also to can use attached technical solution shown in fig. 6 other than attached technical solution shown in Fig. 4
Obtained post portrait it is too low to target post requirement and the case where be unsatisfactory for user demand.
Attached drawing 6 is the implementation process schematic diagram for another post portrait setting method that the embodiment of the present application two provides, such as
Shown in Fig. 6, post portrait setting method includes step S601-S607.
In step s 601, the corresponding first man portrait of each personnel held a post in target post is obtained.
In step S602, each first man portrait is input in neural network model, so that the neural network
Model is drawn a portrait according to the post that each first man portrait exports above-mentioned target post.
It in step S603, calculates in each first man portrait, the post for meeting above-mentioned neural network model output is drawn
As desired first man portrait ratio shared in all first mans portrait.
In step s 604, whether judge calculated ratio less than the first preset ratio, if so, execute step S605,
Otherwise, step S606 is executed.
In step s 605, the parameter of above-mentioned neural network model is adjusted, and returns to step S602.
Above-mentioned steps S601-S605 is identical with the step S101-S105 executive mode in embodiment one, can specifically join
See the description of embodiment one, details are not described herein again.
In step S606, further judge whether calculated ratio is greater than the second preset ratio, the second default ratio
Example is greater than above-mentioned first preset ratio and less than 1, if so, S605 is returned to step, if it is not, thening follow the steps S607.
In attached technical solution shown in fig. 6, if meeting the output of Current Situation of Neural Network model in each first man portrait
When the first man portrait that post portrait requires accounts for the ratio of all first man portraits not less than the first preset ratio, further
Judge the ratio whether less than the second preset ratio (wherein, which is greater than and above-mentioned first preset ratio and is less than
1, which can be the customized setting of user), it is if be less than or equal to second preset ratio, this is current
Neural network model as training after the completion of neural network model, and by after the completion of the training neural network model export
Post portrait as final post draw a portrait, if the judging result of step S606 be greater than second preset ratio, continue to instruct
Practice the neural network model.
Under normal circumstances, if post requirement of the portrait to target post is too low, can make that step S601 obtains all the
One people's portrait all meets the requirement of post portrait, therefore, in attached technical solution shown in fig. 6, by making certain amount
First man portrait be unsatisfactory for the requirement of final post portrait, come the requirement for avoiding the final post from drawing a portrait to target post
It is low.
In step S607, final hilllock of the post portrait that above-mentioned neural network model is exported as above-mentioned target post
Position portrait.
Step S607 is identical with the step S106 executive mode in embodiment one, and for details, reference can be made to embodiments one
Description, details are not described herein again.
It can be seen that technical solution provided by the embodiment of the present application two be in embodiment one technical solution it is further
It improves, finally obtained post can be avoided the occurrence of to a certain extent and draw a portrait too low to target post requirement and be unsatisfactory for user
The case where demand (can be so that the setting of post portrait is more reasonable), in addition, the embodiment of the present application two and one phase of embodiment
Together, the setting that can also avoid drawing a portrait due to post to a certain extent is unreasonable, though and that recruitment side can not be recruited is some
The technical issues of being so unsatisfactory for post portrait demand, but capable of being actually competent at the personnel in post.
Embodiment three
Another post portrait setting method that the embodiment of the present application three provides is described below, the embodiment of the present application
Three is identical as embodiment one and embodiment two, needs to obtain post using neural network model and draw a portrait, however, the application is implemented
In example three neural network model output post portrait include each default dimension information (for example, include educational background, the age,
The information of graduated school grade and length of service etc.), also, the neural network model in the embodiment of the present application three includes more
A submodel, wherein the corresponding default dimension of each submodel, the post for exporting neural network model output are drawn
As the information in corresponding default dimension.
For example, as shown in fig. 7, neural network model 701 exported post portrait 702 include 3 default dimensions (i.e.
Length of service, degree and graduated school grade) information, include 3 submodels in the neural network model 701, it is respectively sub
Model 1, submodel 2 and submodel 3, the corresponding default dimension of submodel 1 are that length of service, the submodel 1 have been used to export
The information of length of service, the corresponding default dimension of submodel 2 are degree in post portrait 702, and the submodel 2 is for exporting hilllock
The information of degree in position portrait 702, the corresponding default dimension of submodel 3 are graduated school grade, and the submodel 3 is for exporting hilllock
The information of graduated school grade in position portrait 702.
Attached drawing 8 is please referred to, the post portrait setting method in the embodiment of the present application three includes the following steps:
In step S801, the corresponding first man portrait of each personnel held a post in target post is obtained, wherein
Each first man portrait includes the information of above-mentioned each default dimension.
Step S801 is identical as the step S101 in embodiment one, is both needed to obtain each personnel in target post tenure
Corresponding first man portrait, for details, reference can be made to the descriptions of embodiment one, and details are not described herein again.
In addition, what is different from the first embodiment is that including upper in each first man portrait acquired in step S801
State the information of each default dimension.It that is to say, if the post of the output of neural network model used in the embodiment of the present application three is drawn
It include the information of length of service, degree and graduated school grade in picture, then first each of acquired in step S801
It also should include the information of length of service, degree and graduated school grade in individual's portrait.As shown in fig. 7, neural network mould
It include the information of length of service, degree and graduated school grade in the post portrait that type 701 exports, then acquired the
It also include length of service, degree and to have finished in one people portrait 1, first man portrait 2 and first man portrait 3
The information of industry universities and colleges grade.
In step S802, a submodel is as target submodel in selection neural network model, wherein the target submodule
The corresponding default dimension of type is target dimension.
In step S802, the submodel in neural network model can be arbitrarily chosen as target submodel.Such as
Shown in Fig. 7, can choose submodel 1 be used as target submodel, then, in attached example shown in Fig. 7, " length of service " i.e.
For target dimension.
In step S803, by the information input of above-mentioned target dimension in each first man portrait to the target submodule
Type, so that the target submodel exports the information of above-mentioned target dimension in the portrait of post.
As shown in Figure 7, it is assumed that choose submodel 1 and draw first man then in step S803 as target submodel
As 2 years lengths of service, length of service 3 in 1 year length of service and first man portrait 3 in first man portrait 2 in 1
It year is input in submodel 1, so that the information of length of service is obtained in the post portrait of the submodel 1 output, such as Fig. 7 institute
Show, the information of length of service of the submodel 1 output is 3 years.
In step S804, in the information that calculates the target dimension of each first man portrait, meet above-mentioned target submodule
Ratio shared by the information of the above-mentioned target dimension of type output.
In attached example shown in Fig. 7, selection submodel 1 is target submodel, the length of service of the submodel 1 output
Information is 3 years, then in step S804, calculates information, the first man portrait 2 of the length of service of first man portrait 1
Length of service information and it is the first portrait 3 length of service information in, meet the length of service be 3 years shared by
Ratio, at this point it is possible to which being easy to calculate shared ratio is 1/3.
In step S805, judge whether the ratio calculated is less than the corresponding default submodel ratio of the target submodel,
If so, thening follow the steps S806, otherwise, step S807 is executed.
In attached example shown in Fig. 7, step S804 ratio calculated is 1/3, it is assumed that the corresponding default son of submodel 1
Model scale is 2/3, then in step S805, it can be determined that it is corresponding less than submodel 1 to go out the ratio that step S804 is calculated
Therefore default submodel ratio executes step S806.
In addition, the corresponding default submodel ratio of each submodel in the embodiment of the present application three can be customized by the user
Setting.
In step S806, the parameter of the target submodel is adjusted, and returns to step S803.
If the calculated ratio of step S804 is less than the corresponding default submodel ratio of above-mentioned target submodel, adjustment should
Then the parameter of target submodel returns to step S803 and its subsequent step.
In attached example shown in Fig. 7, it is assumed that after the parameter in adjustment submodel 1, when executing step S803, the submodule
The information of length of service that type 1 exports is 1.5 years, then, step S804 ratio calculated should be 2/3, and step S805's sentences
Disconnected result is therefore default submodel ratio corresponding not less than the submodel 1 can execute subsequent step S807.
In step S807, the post that is exported as above-mentioned neural network model of information that above-mentioned target submodel is exported
The information of above-mentioned target dimension in portrait.
In the example shown in step S804, it can be deduced that work in the post portrait 702 that neural network model 700 exports
The information for making the time limit is 1.5 years.
In step S808, remaining submodel in above-mentioned neural network model is traversed, obtains each submodel output
The post portrait of above-mentioned neural network model output is exported in the information of corresponding default dimension to obtain the neural network model
Post portrait.
In attached example shown in Fig. 7, obtain submodel 1 output post portrait in the length of service information it
Afterwards, submodel 2 can be chosen respectively again and submodel 3 is used as target submodel, step S802-S807 is executed again, obtain
Post portrait in degree information and post portrait in graduated school grade information.
It in step S809, calculates in each first man portrait, the post for meeting above-mentioned neural network model output is drawn
As desired first man portrait ratio shared in all first mans portrait.
In step S810, calculated ratio is judged whether less than the first preset ratio, if so, thening follow the steps
Otherwise S811 executes step S812.
In step S811, the parameter of above-mentioned neural network model is adjusted, and returns to step S802.
In step S812, final hilllock of the post portrait that above-mentioned neural network model is exported as above-mentioned target post
Position portrait.
Step S809-S812 is identical with step S103-S106 executive mode in embodiment one, and for details, reference can be made to realities
The description of example one is applied, details are not described herein again.
In addition, in the embodiment of the present application three, described in step S811 " parameter of above-mentioned neural network model is adjusted, and
Returning to step S802 " can be " to adjust the parameter of one or more submodels in above-mentioned neural network model, and return and hold
Row step S802 "；Or, or: it improves in above-mentioned neural network model and is preset corresponding to one or more submodels
Submodel ratio, and return to step S802 and (it should be readily apparent to one skilled in the art that in the embodiment of the present application three, improve
Default submodel ratio, will necessarily adjust the parameter in corresponding target submodel).
Optionally, in the embodiment of the present application three, the step in similar attached drawing 4 can also be increased before step S807
The step of step S606 in S406 or attached drawing 6.Specifically can be with the description of reference implementation example two, details are not described herein again.
The embodiment of the present application three has carried out specific restriction to the structure of neural network model described in embodiment one.This Shen
Please in technical solution provided by embodiment one, can not draw a portrait to post in each dimension (i.e. educational background, age etc.) control
System, and technical solution provided by the embodiment of the present application three can control each dimension in the portrait of post, therefore,
Technical solution in the embodiment of the present application three has stronger flexibility compared to embodiment one.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above method embodiment, respectively
The execution sequence of process should be determined by its function and internal logic, and the implementation process without coping with the embodiment of the present application constitutes any
It limits.
Example IV
The embodiment of the present application four provides a kind of post portrait setting device, for ease of description, only shows and the application
Relevant part, as shown in figure 9, post portrait setting device 900 includes:
First portrait obtains module 901, first corresponding for obtaining each personnel to hold a post in target post
People's portrait；
Network inputs module 902, for each first man portrait to be input in neural network model, so that the mind
It is drawn a portrait through network model according to the post that each first man portrait exports the target post；
Ratio computing module 903 meets above-mentioned neural network model output for calculating in each first man portrait
The first man portrait that post portrait requires ratio shared in all first mans portrait；
Ratio judgment module 904, for judging calculated ratio whether less than the first preset ratio；
Parameter adjustment module 905, if adjusting the ginseng of above-mentioned neural network model for being less than above-mentioned first preset ratio
Number, and trigger above-mentioned network inputs module 902 execute again by each first man portrait be input in neural network model, with
So that the operation that the neural network model is drawn a portrait according to the post that each first man portrait exports the target post；
Post portrait obtains module 906, is used for if more than or is equal to above-mentioned first preset ratio, then by above-mentioned neural network
The post portrait of model output is drawn a portrait as the final post of the target post.
Optionally, above-mentioned post portrait setting device 900 further include:
Second portrait obtains module, for obtaining each personnel corresponding second that can not be competent at above-mentioned target post
Individual's portrait；
Correspondingly, the post portrait acquisition module 906 includes:
Portrait judging unit is used for if more than or is equal to above-mentioned first preset ratio, then judges to draw in each second people
As in, if exist and meet second people portrait that the post portrait of above-mentioned neural network model output requires；
First acquisition unit, if the judging result for above-mentioned portrait judging unit is that there is no by above-mentioned nerve net
The post portrait of network model output is drawn a portrait as the final post of above-mentioned target post.
Optionally, above-mentioned post portrait acquisition module 906 includes:
Ratio judging unit again, for if more than or be equal to above-mentioned first preset ratio, then further judgement calculates
Ratio whether be greater than the second preset ratio, which is greater than above-mentioned first preset ratio and less than 1；
Second acquisition unit, if for being less than or equal to above-mentioned second preset ratio, above-mentioned neural network model is defeated
Post portrait out is drawn a portrait as the final post of above-mentioned target post.
Optionally, the post portrait of the above-mentioned target post of above-mentioned neural network model output includes each default dimension
Information, wherein the information of each default dimension is used to indicate above-mentioned target post and presets the requirement of dimension at this；Above-mentioned nerve net
Network model includes multiple submodels, wherein the corresponding default dimension of each submodel, for exporting above-mentioned neural network model
Information of the post portrait of output in corresponding default dimension；
Correspondingly, above-mentioned first portrait obtains module 901, comprising:
Obtain the corresponding first man portrait of each personnel held a post in target post, wherein each first man
Portrait includes the information of above-mentioned each default dimension；
Correspondingly, above-mentioned network inputs module 902, comprising:
Submodel selection unit, for choosing in above-mentioned neural network model a submodel as target submodel, wherein
The corresponding default dimension of the target submodel is target dimension；
Dimension input unit, for by the information input of above-mentioned target dimension in each first man portrait to above-mentioned target
Submodel, so that the target submodel exports the information of above-mentioned target dimension in the portrait of post；
Ratio computing unit in the information of the target dimension for calculating each first man portrait, meets above-mentioned target
Ratio shared by the information of the above-mentioned target dimension of submodel output；
Ratio judging unit, for judging whether the ratio calculated is less than the corresponding default submodel of above-mentioned target submodel
Ratio；
Parameter adjustment unit, if being adjusted above-mentioned for being less than the corresponding default submodel ratio of above-mentioned target submodel
The parameter of target submodel, and trigger above-mentioned dimension input unit and executed again by target dimension above-mentioned in each first man portrait
The information input of degree is to above-mentioned target submodel, so that the target submodel exports the letter of above-mentioned target dimension in the portrait of post
The operation of breath；
Dimension acquiring unit is used for if more than or is equal to the corresponding default submodel ratio of above-mentioned target submodel, then will
The letter of above-mentioned target dimension in the post portrait that the information of above-mentioned target submodel output is exported as above-mentioned neural network model
Breath.
It is defeated to obtain each submodel difference for traversing remaining submodel in above-mentioned neural network model for Traversal Unit
The post portrait of above-mentioned neural network model output out is in the corresponding information for presetting dimension, to obtain the neural network model
It draws a portrait in the post of output.
Correspondingly, above-mentioned parameter adjustment module 905 is specifically used for: if being less than above-mentioned first preset ratio, improving above-mentioned
Default submodel ratio corresponding to one or more submodels in neural network model, and trigger above-mentioned submodel selection unit
It executes and chooses operation of the submodel as target submodel in above-mentioned neural network model.
Optionally, above-mentioned first portrait obtains module 901, comprising:
Transmission unit, for issuing personal portrait search request to predetermined server, to indicate that the predetermined server executes
Search the operation for the corresponding first man portrait of each personnel held a post in above-mentioned target post；
Receiving unit, the response message returned for receiving above-mentioned predetermined server；
First portrait acquiring unit, for obtaining each individual to hold a post in above-mentioned target post according to above-mentioned response message
The corresponding first man portrait of member.
It should be noted that the contents such as information exchange, implementation procedure between above-mentioned apparatus/unit, due to the application
Embodiment of the method is based on same design, concrete function and bring technical effect, for details, reference can be made to embodiment of the method part, this
Place repeats no more.
Embodiment five
Figure 10 is the schematic diagram for the terminal device that the embodiment of the present application five provides.As shown in Figure 10, the terminal of the embodiment
Equipment 100 includes: processor 101, memory 102 and is stored in above-mentioned memory 102 and can be on above-mentioned processor 101
The computer program 103 of operation.Above-mentioned processor 101 realizes that above-mentioned each method is implemented when executing above-mentioned computer program 103
Step in example, such as step S101 to S106 shown in FIG. 1.Alternatively, above-mentioned processor 101 executes above-mentioned computer program
The function of each module/unit in above-mentioned each Installation practice, such as the function of module 901 to 906 shown in Fig. 9 are realized when 103.
Illustratively, above-mentioned computer program 103 can be divided into one or more module/units, said one or
Multiple module/the units of person are stored in above-mentioned memory 102, and are executed by above-mentioned processor 101, to complete the application.On
Stating one or more module/units can be the series of computation machine program instruction section that can complete specific function, the instruction segment
For describing implementation procedure of the above-mentioned computer program 103 in above-mentioned terminal device 100.For example, above-mentioned computer program 103
The first portrait can be divided into and obtain module, network inputs module, ratio computing module, ratio judgment module, parameter adjustment
Module and post portrait obtain module, and each module concrete function is as follows:
Obtain the corresponding first man portrait of each personnel held a post in target post；
Each first man portrait is input in neural network model, so that the neural network model is according to each the
One people, which draws a portrait, exports the post portrait of the target post；
It calculates in each first man portrait, meets first that the post portrait of above-mentioned neural network model output requires
People's portrait ratio shared in all first mans portrait；
Judge calculated ratio whether less than the first preset ratio；
If being less than above-mentioned first preset ratio, the parameter of above-mentioned neural network model is adjusted, and returns and executes above-mentioned incite somebody to action
Each first man portrait is input in neural network model, so that the neural network model is drawn a portrait according to each first man
The step of exporting the post portrait of the target post and its subsequent step；
If more than or equal to above-mentioned first preset ratio, then the post portrait exported above-mentioned neural network model is as institute
State the final post portrait of target post.
Above-mentioned terminal device may include, but be not limited only to, processor 101, memory 102.Those skilled in the art can be with
Understand, Figure 10 is only the example of terminal device 100, does not constitute the restriction to terminal device 100, may include than illustrating more
More or less component perhaps combines certain components or different components, such as above-mentioned terminal device can also include input
Output equipment, network access equipment, bus etc..
Alleged processor 101 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
Above-mentioned memory 102 can be the internal storage unit of above-mentioned terminal device 100, such as terminal device 100 is hard
Disk or memory.Above-mentioned memory 102 is also possible to the External memory equipment of above-mentioned terminal device 100, such as above-mentioned terminal device
The plug-in type hard disk being equipped on 100, intelligent memory card (Smart Media Card, SMC), secure digital (Secure
Digital, SD) card, flash card (Flash Card) etc..Further, above-mentioned memory 102 can also both include above-mentioned terminal
The internal storage unit of equipment 100 also includes External memory equipment.Above-mentioned memory 102 for store above-mentioned computer program with
And other programs and data needed for above-mentioned terminal device.Above-mentioned memory 102, which can be also used for temporarily storing, have been exported
Or the data that will be exported.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of above-mentioned apparatus is divided into different functional unit or module, more than completing
The all or part of function of description.Each functional unit in embodiment, module can integrate in one processing unit, can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units, it is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.In addition, each function list
Member, the specific name of module are also only for convenience of distinguishing each other, the protection scope being not intended to limit this application.Above system
The specific work process of middle unit, module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
Scope of the present application.
In embodiment provided herein, it should be understood that disclosed device/terminal device and method, it can be with
It realizes by another way.For example, device described above/terminal device embodiment is only schematical, for example, on
The division of module or unit is stated, only a kind of logical function partition, there may be another division manner in actual implementation, such as
Multiple units or components can be combined or can be integrated into another system, or some features can be ignored or not executed.
Above-mentioned 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.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If above-mentioned integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the application realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, above-mentioned meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, above-mentioned computer program includes computer program code, above-mentioned computer program generation
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..Above-mentioned computer-readable medium
It may include: any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic that can carry above-mentioned computer program code
Dish, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that above-mentioned
The content that computer-readable medium includes can carry out increasing appropriate according to the requirement made laws in jurisdiction with patent practice
Subtract, such as does not include electric carrier signal and electricity according to legislation and patent practice, computer-readable medium in certain jurisdictions
Believe signal.
Above above-described embodiment is only to illustrate the technical solution of the application, rather than its limitations；Although referring to aforementioned reality
Example is applied the application is described in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope of each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution should all
Comprising within the scope of protection of this application.
Claims (10)
- The setting method 1. a kind of post is drawn a portrait characterized by comprisingObtain the corresponding first man portrait of each personnel held a post in target post；Each first man portrait is input in neural network model, so that the neural network model is according to each first People, which draws a portrait, exports the post portrait of the target post；It calculates in each first man portrait, meets the first man picture that the post portrait of the neural network model output requires As shared ratio in all first mans portrait；Judge calculated ratio whether less than the first preset ratio；If be less than first preset ratio, adjust the parameter of the neural network model, and return execute it is described will be each First man portrait is input in neural network model, is exported so that the neural network model is drawn a portrait according to each first man The step of post portrait of the target post and its subsequent step；If more than or equal to first preset ratio, then the post portrait exported the neural network model is as the mesh Mark the final post portrait in post.
- The setting method 2. post as described in claim 1 is drawn a portrait, which is characterized in that the post portrait setting method is also wrapped It includes:Obtain the corresponding second people portrait of each personnel that can not be competent at the target post；Correspondingly, it is described if more than or be equal to first preset ratio, then the post exported the neural network model is drawn As the final post as the target post is drawn a portrait, comprising:If more than or be equal to first preset ratio, then:Judge in each second people draws a portrait, if there is the post portrait requirement for meeting the neural network model output Second people's portrait；If it does not exist, then the post portrait exported the neural network model is drawn as the final post of the target post Picture.
- The setting method 3. post as described in claim 1 is drawn a portrait, which is characterized in that it is described if more than or to be equal to described first pre- If ratio, then the post portrait exported the neural network model is drawn a portrait as the final post of the target post, comprising:If more than or be equal to first preset ratio, then:Further judge whether calculated ratio is greater than the second preset ratio, it is pre- that second preset ratio is greater than described first If ratio and less than 1；If being less than or equal to second preset ratio, the post portrait that the neural network model is exported is used as the mesh Mark the final post portrait in post.
- The setting method 4. post as described in claim 1 is drawn a portrait, which is characterized in that the neural network model exports described The post portrait of target post includes the information of each default dimension, wherein the information of each default dimension is used to indicate described Target post presets the requirement of dimension at this；The neural network model includes multiple submodels, wherein each submodel is corresponding One default dimension, for exporting information of the post portrait in corresponding default dimension of the neural network model output；It is correspondingly, described to obtain the corresponding first man portrait of each personnel held a post in target post, comprising:Obtain the corresponding first man portrait of each personnel held a post in target post, wherein each first man portrait It include the information of each default dimension；Correspondingly, described that each first man portrait is input in neural network model, so that the neural network model root The post portrait of the target post is exported according to each first man portrait, comprising:A submodel is chosen in the neural network model as target submodel, wherein the target submodel is corresponding pre- If dimension is target dimension；By the information input of target dimension described in each first man portrait to the target submodel, so that the target Submodel exports the information of target dimension described in the portrait of post；In the information for calculating the target dimension of each first man portrait, meet the target dimension of the target submodel output Ratio shared by the information of degree；Judge whether the ratio calculated is less than the corresponding default submodel ratio of the target submodel；If being less than the corresponding default submodel ratio of the target submodel, the parameter of the target submodel is adjusted, and return By the information input of target dimension in each first man portrait to the target submodel described in receipt row, so that the mesh The step of marking the information of target dimension described in the portrait of submodel output post and its subsequent step；If more than or be equal to the corresponding default submodel ratio of the target submodel, then by the target submodel export letter Cease the information of target dimension described in the post portrait exported as the neural network model.Remaining submodel in the neural network model is traversed, the neural network mould that each submodel exports respectively is obtained The post portrait of type output is in the corresponding information for presetting dimension, to obtain the post portrait of the neural network model output.
- The setting method 5. post as claimed in claim 4 is drawn a portrait, which is characterized in that if described be less than the described first default ratio Example, then adjust the parameter of the neural network model, and returns to described each first man is drawn a portrait of execution and be input to nerve net In network model, so that the neural network model was drawn a portrait according to the post that each first man portrait exports the target post Step and its subsequent step, comprising:If being less than first preset ratio, improve pre- corresponding to one or more submodels in the neural network model If submodel ratio, and return and execute a step of submodel is as target submodel in the selection neural network model And its subsequent step.
- The setting method 6. post as described in any one of claims 1 to 5 is drawn a portrait, which is characterized in that the acquisition is in target The corresponding first man portrait of each personnel of post tenure, comprising:Personal portrait search request is issued to predetermined server, is searched with indicating that the predetermined server executes on the target hilllock The operation of the corresponding first man portrait of each personnel of position tenure；Receive the response message that the predetermined server returns；According to the response message, the corresponding first man portrait of each personnel held a post in the target post is obtained.
- 7. a kind of post portrait setting device characterized by comprisingFirst portrait obtains module, for obtaining the corresponding first man portrait of each personnel in target post tenure；Network inputs module, for each first man portrait to be input in neural network model, so that the neural network Model is drawn a portrait according to the post that each first man portrait exports the target post；Ratio computing module, for calculating in each first man portrait, the post for meeting the neural network model output is drawn As desired first man portrait ratio shared in all first mans portrait；Ratio judgment module, for judging calculated ratio whether less than the first preset ratio；Parameter adjustment module, if adjusting the parameter of the neural network model, and touch for being less than first preset ratio It sends out network inputs module described and executes again and each first man portrait is input in neural network model, so that the nerve Network model exports the operation of the post portrait of the target post according to each first man portrait；Post portrait obtains module, is used for if more than or is equal to first preset ratio, then the neural network model is defeated Post portrait out is drawn a portrait as the final post of the target post.
- 8. portrait setting device in post as claimed in claim 7, which is characterized in that the post portrait setting device also wraps It includes:Second portrait obtains module, for obtaining corresponding second people of each personnel that can not be competent at the target post Portrait；Correspondingly, the post portrait acquisition module includes:Portrait judging unit is used for if more than or is equal to first preset ratio, then judges in each second people draws a portrait, The second people portrait required with the presence or absence of the post portrait for meeting the neural network model output；First acquisition unit, if the judging result for the portrait judging unit is that there is no by the neural network mould The post portrait of type output is drawn a portrait as the final post of the target post.
- 9. a kind of terminal device, including memory, processor and storage are in the memory and can be on the processor The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 6 when executing the computer program The step of any one the method.
- 10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists In when the computer program is executed by processor the step of any one of such as claim 1 to 6 of realization the method.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910068512.4A CN109886641A (en) | 2019-01-24 | 2019-01-24 | A kind of post portrait setting method, post portrait setting device and terminal device |
| PCT/CN2019/091544 WO2020151170A1 (en) | 2019-01-24 | 2019-06-17 | Position describing method, position describing apparatus, and terminal device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910068512.4A CN109886641A (en) | 2019-01-24 | 2019-01-24 | A kind of post portrait setting method, post portrait setting device and terminal device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109886641A true CN109886641A (en) | 2019-06-14 |
Family
ID=66926754
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910068512.4A Pending CN109886641A (en) | 2019-01-24 | 2019-01-24 | A kind of post portrait setting method, post portrait setting device and terminal device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109886641A (en) |
| WO (1) | WO2020151170A1 (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110377804A (en) * | 2019-06-20 | 2019-10-25 | 平安科技（深圳）有限公司 | Method for pushing, device, system and the storage medium of training course data |
| CN110378563A (en) * | 2019-06-18 | 2019-10-25 | 平安普惠企业管理有限公司 | Information processing method, device, computer equipment and storage medium |
| CN110619506A (en) * | 2019-08-13 | 2019-12-27 | 平安科技（深圳）有限公司 | Post portrait generation method, post portrait generation device and electronic equipment |
| CN111105138A (en) * | 2019-11-20 | 2020-05-05 | 北京鳄梨科技有限公司 | Human resource analysis and evaluation system based on task completion data |
| WO2020151170A1 (en) * | 2019-01-24 | 2020-07-30 | 平安科技（深圳）有限公司 | Position describing method, position describing apparatus, and terminal device |
| CN113627135A (en) * | 2020-05-08 | 2021-11-09 | 百度在线网络技术（北京）有限公司 | Method, device, equipment and medium for generating recruitment post description text |
| CN116993312A (en) * | 2023-06-02 | 2023-11-03 | 广州红海云计算股份有限公司 | Human resource management method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140279635A1 (en) * | 2013-03-13 | 2014-09-18 | Profiles International, Inc. | System and method for utilizing assessments |
| CN109214446A (en) * | 2018-08-27 | 2019-01-15 | 平安科技（深圳）有限公司 | Potentiality good performance personnel kind identification method, system, terminal and computer readable storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120290365A1 (en) * | 2011-05-13 | 2012-11-15 | Profiles International, Inc. | System for selecting employment candidates |
| AU2016228539A1 (en) * | 2015-03-12 | 2017-10-19 | Kaplan, Inc. | Course skill matching system and method thereof |
| CN107784426A (en) * | 2017-08-03 | 2018-03-09 | 平安科技（深圳）有限公司 | Post distribution method, device and the equipment of a kind of employee |
| CN109886641A (en) * | 2019-01-24 | 2019-06-14 | 平安科技（深圳）有限公司 | A kind of post portrait setting method, post portrait setting device and terminal device |
-
2019
- 2019-01-24 CN CN201910068512.4A patent/CN109886641A/en active Pending
- 2019-06-17 WO PCT/CN2019/091544 patent/WO2020151170A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140279635A1 (en) * | 2013-03-13 | 2014-09-18 | Profiles International, Inc. | System and method for utilizing assessments |
| CN109214446A (en) * | 2018-08-27 | 2019-01-15 | 平安科技（深圳）有限公司 | Potentiality good performance personnel kind identification method, system, terminal and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 王庆 等: "基于BP神经网络的知识员工―岗位匹配测评研究", 科技管理研究, no. 10, pages 294 - 295 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020151170A1 (en) * | 2019-01-24 | 2020-07-30 | 平安科技（深圳）有限公司 | Position describing method, position describing apparatus, and terminal device |
| CN110378563A (en) * | 2019-06-18 | 2019-10-25 | 平安普惠企业管理有限公司 | Information processing method, device, computer equipment and storage medium |
| CN110377804A (en) * | 2019-06-20 | 2019-10-25 | 平安科技（深圳）有限公司 | Method for pushing, device, system and the storage medium of training course data |
| CN110377804B (en) * | 2019-06-20 | 2024-03-15 | 平安科技（深圳）有限公司 | Training course data pushing method, device and system and storage medium |
| CN110619506A (en) * | 2019-08-13 | 2019-12-27 | 平安科技（深圳）有限公司 | Post portrait generation method, post portrait generation device and electronic equipment |
| CN110619506B (en) * | 2019-08-13 | 2023-05-26 | 平安科技（深圳）有限公司 | Post image generation method, post image generation device and electronic equipment |
| CN111105138A (en) * | 2019-11-20 | 2020-05-05 | 北京鳄梨科技有限公司 | Human resource analysis and evaluation system based on task completion data |
| CN113627135A (en) * | 2020-05-08 | 2021-11-09 | 百度在线网络技术（北京）有限公司 | Method, device, equipment and medium for generating recruitment post description text |
| CN113627135B (en) * | 2020-05-08 | 2023-09-29 | 百度在线网络技术（北京）有限公司 | Recruitment post description text generation method, device, equipment and medium |
| CN116993312A (en) * | 2023-06-02 | 2023-11-03 | 广州红海云计算股份有限公司 | Human resource management method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020151170A1 (en) | 2020-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109886641A (en) | A kind of post portrait setting method, post portrait setting device and terminal device | |
| Nanduri et al. | A reinforcement learning model to assess market power under auction-based energy pricing | |
| Vickers | Economics and the antagonism of time: time, uncertainty, and choice in economic theory | |
| Lindberg | The European Community as a political system: notes toward the construction of a model | |
| Bairagi et al. | Selection of robot for automated foundry operations using fuzzy multi-criteria decision making approaches | |
| Wang et al. | Case-based reasoning for product style construction and fuzzy analytic hierarchy process evaluation modeling using consumers linguistic variables | |
| Tapia García et al. | A consensus model for group decision-making problems with interval fuzzy preference relations | |
| CN108629698A (en) | A kind of pricing method of insurance products, device, terminal device and storage medium | |
| CN100565395C (en) | The autonomy field system of reconfigurable digital controller | |
| CN109918574A (en) | Item recommendation method, device, equipment and storage medium | |
| Liu et al. | Optimization of brand marketing strategy of intelligent technology under the background of artificial intelligence | |
| Wang et al. | A measure of mental workload during multitasking: Using performance-based Timed Petri Nets | |
| CN109636653A (en) | Monitoring method, monitoring service end and the storage medium of medical expense exception | |
| Hinojosa et al. | Nash decomposition for process efficiency in multistage production systems | |
| CN108648087A (en) | Risk analysis method, device and equipment about fund product-specific investments management | |
| Buchanan | Can machine learning offer anything to expert systems? | |
| CN113077147B (en) | Intelligent student course pushing method and system and terminal equipment | |
| CN104504041B (en) | data analysis system, method and device | |
| Oldfield | Talking quality, meaning control: McDonalds, the market and the probation service | |
| Akay et al. | A neuro-fuzzy based approach to affective design | |
| CN116151868A (en) | Intelligent price checking method, intelligent price checking device, computer equipment and storage medium | |
| Mathiasen | Multilateral technical assistance | |
| Kopka et al. | The system ergonomics and usability as measurement of the software agent impact to the organization | |
| CN110473636A (en) | Intelligent doctor's advice recommended method and system based on deep learning | |
| CN112200411A (en) | Nursing human resource scheduling system giving consideration to patient and caregiver appeal |
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 |