CN105159962B - Position recommends method and apparatus, resume to recommend method and apparatus, recruitment platform - Google Patents
Position recommends method and apparatus, resume to recommend method and apparatus, recruitment platform Download PDFInfo
- Publication number
- CN105159962B CN105159962B CN201510521072.5A CN201510521072A CN105159962B CN 105159962 B CN105159962 B CN 105159962B CN 201510521072 A CN201510521072 A CN 201510521072A CN 105159962 B CN105159962 B CN 105159962B
- Authority
- CN
- China
- Prior art keywords
- word
- information
- resume
- preset
- library
- 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.)
- Active
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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides position recommendation method and apparatus, resume recommendation method and apparatus, recruitment platform, wherein position recommendation method includes：Receive the biographic information from job hunter；It trains library to analyze biographic information according to preset biographic information, obtains the resume keyword of biographic information；Preset biographic information training library includes each word trained according to biographic information training sample, the corresponding weight of each word and relevance；The job information that selection matches with resume keyword in preset job information library, job hunter is recommended by the job information chosen；Preset job information library includes the position key term vector generated according to the job information of employing unit.Position in through the invention recommends method and apparatus, resume to recommend method and apparatus, recruitment platform, can accurately recommend the job information being consistent with its resume to job hunter, accurately recommend the biographic information being consistent with its position to employing unit.
Description
Technical field
The present invention relates to information matches and recruitment and application field, more particularly to position recommends method and apparatus, resume to recommend
Method and apparatus, recruitment platform.
Background technology
With the development of Internet technology, network application recruitment applies for work at job hunter, employing unit recruits employee
Main path.
The main operating mode of network application recruitment is that job hunter issues resume in the network platform, and employing unit exists
Job information is issued in the network platform.The network platform is after having a large amount of resume and job information, targetedly
Recommend job information to job hunter, recommends resume to employing unit, connected job hunter and employing unit with this, help
It helps job hunter to be quickly found the work for being suitble to its ability to work, employing unit is helped to be quickly found out the member for meeting job requirement
Work.
Inventor has found under study for action, existing network application recruitment mode exist the job information recommended to job hunter and
Not the problem of resume content of job hunter's publication is not inconsistent, such as the job hunter of " expert at software exploitation " is write in resume,
The positions such as Electronics Engineer or sale can be recommended.For this problem, there has been no good solutions at present.
Invention content
The present invention provides positions, and method and apparatus, resume to be recommended to recommend method and apparatus, recruitment platform, can be to job hunting
Person accurately recommends the job information being consistent with its resume, alleviates the job information recommended in the prior art to job hunter and job hunter
Not the problem of resume content of publication is not inconsistent.
In a first aspect, an embodiment of the present invention provides a kind of positions to recommend method, the method includes：
Receive the biographic information from job hunter；
It trains library to analyze the biographic information according to preset biographic information, obtains the resume of the biographic information
Keyword；The preset biographic information training library includes each word trained according to biographic information training sample, described each
The corresponding weight of a word and relevance；
The job information that selection matches with the resume keyword in preset job information library, by what is chosen
The job information recommends the job hunter；The preset job information library includes being given birth to according to the job information of employing unit
At position key term vector.
With reference to first aspect, the first possible embodiment an embodiment of the present invention provides first aspect, wherein described
It trains library to analyze the biographic information according to preset biographic information, obtains the resume keyword of the biographic information,
Including：
Word segmentation processing is carried out to the biographic information according to the preset biographic information training library, obtains resume word set
It closes；
The corresponding weight of word in the resume set of words and association are searched in the preset biographic information training library
Property；
According to the corresponding weight of word and relevance in the resume set of words found, the resume set of words is generated
In the corresponding synthesis result of word, according to the sequence of the synthesis result from high to low in the resume set of words word carry out
Sequence；
Determine resume keyword of the word as the biographic information of the first preset quantity in the sequence.
With reference to first aspect or first aspect the first possible embodiment, an embodiment of the present invention provides first party
The possible embodiment in second of face, wherein the selection in preset job information library and the resume keyword phase
The job information matched, including：
Corresponding resume key term vector is generated according to the resume keyword；
It calculates between the position key term vector in the resume key term vector and the preset job information library
Matching degree；
The position key term vector is ranked up according to the sequence of the matching degree from high to low；
The corresponding job information of position key term vector for selecting the second preset quantity in the sequence, as with the letter
Go through the job information that keyword matches.
Second aspect, a kind of resume of drawings of the embodiment of the present invention recommend method, the method includes：
Receive the job information from employing unit；
It trains library to analyze the job information according to preset job information, obtains the position of the job information
Keyword；The preset job information training library includes each word trained according to job information training sample, described each
The corresponding weight of a word and relevance；
The biographic information that selection matches with the position keyword in preset biographic information library, by what is chosen
The biographic information recommends the employing unit；The preset biographic information library includes being given birth to according to the biographic information of job hunter
At resume key term vector.
In conjunction with second aspect, the first possible embodiment an embodiment of the present invention provides second aspect, wherein described
It trains library to analyze the job information according to preset job information, obtains the position keyword of the job information,
Including：
Word segmentation processing is carried out to the job information according to the preset job information training library, get a duty word set
It closes；
The corresponding weight of word in the position set of words and association are searched in the preset job information training library
Property；
According to the corresponding weight of word and relevance in the position set of words found, the position set of words is generated
In the corresponding synthesis result of word, according to the sequence of the synthesis result from high to low in the position set of words word carry out
Sequence；
Determine position keyword of the word as the job information of third preset quantity in the sequence.
In conjunction with second aspect or second aspect the first possible embodiment, an embodiment of the present invention provides second party
The possible embodiment in second of face, wherein the selection in preset biographic information library and the position keyword phase
The biographic information matched, including：
Corresponding position key term vector is generated according to the position keyword；
It calculates between the resume key term vector in the position key term vector and the preset biographic information library
Matching degree；
The resume key term vector is ranked up according to the sequence of the matching degree from high to low；
The corresponding biographic information of resume key term vector for selecting the 4th preset quantity in the sequence, as with reported
The biographic information that position keyword matches.
The third aspect, an embodiment of the present invention provides a kind of position recommendation apparatus, described device includes：
Receiving module, for receiving the biographic information from job hunter；
Keyword determining module is obtained for training library to analyze the biographic information according to preset biographic information
To the resume keyword of the biographic information；The preset biographic information training library includes being instructed according to biographic information training sample
The each word practised, the corresponding weight of each word and relevance；
Recommending module is selected, for the position that selection matches with the resume keyword in preset job information library
The job information chosen is recommended the job hunter by information；The preset job information library include according to
The position key term vector that the job information of people's unit generates.
Fourth aspect, an embodiment of the present invention provides a kind of resume recommendation apparatus, described device includes：
Receiving module, for receiving the job information from employing unit；
Keyword determining module is obtained for training library to analyze the job information according to preset job information
To the position keyword of the job information；The preset job information training library includes being instructed according to job information training sample
The each word practised, the corresponding weight of each word and relevance；
Recommending module is selected, for the resume that selection matches with the position keyword in preset biographic information library
The biographic information chosen is recommended the employing unit by information；The preset biographic information library includes basis
The resume key term vector that the biographic information of job hunter generates.
5th aspect, an embodiment of the present invention provides a kind of recruitment platforms, including the position described in the third aspect recommends dress
It sets and the resume recommendation apparatus described in fourth aspect.
In conjunction with the 5th aspect, an embodiment of the present invention provides the first possible embodiments in terms of the 5th, wherein described
Platform includes：
Biographic information trains library update module, for described preset according to the biographic information update from job hunter
Biographic information trains library；
Job information trains library update module, for described default according to the job information update from employing unit
Job information train library.
Position in through the embodiment of the present invention recommends method and apparatus, resume to recommend method and apparatus, recruitment platform, energy
Enough job informations for accurately recommending to be consistent with its resume to job hunter, accurately recommend the resume being consistent with its position to employing unit
Information, be not inconsistent to alleviate the resume content that the job information recommended in the prior art to job hunter is issued with job hunter,
Not the problem of job information that the biographic information recommended to employing unit is issued with employing unit is not inconsistent.
Description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows the structural schematic diagram for the network recruitment system that the embodiment of the present invention is provided；
Fig. 2 shows the flow diagrams that the position that the embodiment of the present invention is provided recommends method；
Fig. 3 shows that the resume that the embodiment of the present invention is provided recommends the flow diagram of method；
Fig. 4 shows the generation method schematic diagram in the biographic information training library that the embodiment of the present invention is provided；
Fig. 5 shows the structural schematic diagram for the position recommendation apparatus that the embodiment of the present invention is provided；
Fig. 6 shows the structural schematic diagram for the resume recommendation apparatus that the embodiment of the present invention is provided；
Fig. 7 shows the structural schematic diagram for the recruitment platform that the embodiment of the present invention is provided.
Specific implementation mode
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The present invention will be described in detail below with reference to the accompanying drawings and embodiments.
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction with attached in the embodiment of the present invention
Figure, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only this
Invention a part of the embodiment, instead of all the embodiments.Embodiments of the present invention, which are generally described and illustrated herein in the accompanying drawings
Component can arrange and design with a variety of different configurations.Therefore, the implementation to the present invention provided in the accompanying drawings below
The detailed description of example is not intended to limit the range of claimed invention, but is merely representative of the selected implementation of the present invention
Example.Based on the embodiment of the present invention, what those skilled in the art were obtained without making creative work is all
Other embodiment shall fall within the protection scope of the present invention.
For individual's letter of job information and job hunter's publication that existing network application recruitment mode is recommended to job hunter
The problem of content is not inconsistent is gone through, the present invention provides positions, and method and apparatus, resume to be recommended to recommend method and apparatus, recruitment platform,
It using word matching principle, can accurately recommend the job information being consistent with its resume to job hunter, alleviate in the prior art to asking
Not the problem of job information that duty person recommends and the resume content of job hunter's publication are not inconsistent.
In the embodiment of the present invention, it is between job hunter and use that position, which recommends method and resume to recommend the executive agent of method,
Third party's network recruitment system between people's unit, the network recruitment system recommend method that can recommend to job hunter by position
Suitable position recommends method that can recommend suitable resume to employing unit by resume.
With reference to the network recruitment system in the embodiment of the present invention as shown in Figure 1, the E-Recruit in the embodiment of the present invention
System 10 is previously provided with biographic information training library 11, job information training library 12, biographic information library 13 and job information library 14,
Wherein, biographic information training library 11 and job information train the generation method in library 12 identical, biographic information library 13 and job information
The generation method in library 14 is identical.
In Fig. 1, when network recruitment system 10 recommends method to recommend position to job hunter by position, need to use resume
Information trains library 11 and job information library 14；When network recruitment system 10 recommends method to recommend resume to employing unit by resume
When, it needs to use job information training library 12 and biographic information library 13.
Position provided in an embodiment of the present invention is described below and recommends method, recommends method with reference to position as shown in Figure 2, it should
The executive agent of method is network recruitment system, and this method includes：
Step 202, the biographic information from job hunter is received.Wherein, biographic information include job hunter resume text and
Job hunter sends the time of resume text.
Step 204, it trains library to analyze biographic information according to preset biographic information, obtains the resume of biographic information
Keyword；Preset biographic information training library includes each word trained according to biographic information training sample, and each word corresponds to
Weight and relevance.
Step 206, the job information that selection matches with resume keyword in preset job information library, will select
The job information come recommends job hunter；Preset job information library includes the position generated according to the job information of employing unit
Crucial term vector.
Position in through the embodiment of the present invention recommends method, can obtain the resume keyword of biographic information, and will be with
The job information that resume keyword matches recommends job hunter, to accurately recommend the position being consistent with its resume to job hunter
Information, what the resume content that the job information that alleviation is recommended to job hunter in the prior art is issued with job hunter was not inconsistent asks
Topic.
In step 204, trains library to analyze biographic information according to preset biographic information, obtain the letter of biographic information
Keyword is gone through, can be realized by following procedure：(1) library is trained to carry out at participle biographic information according to preset biographic information
Reason, obtains resume set of words；(2) the corresponding power of word in searching above-mentioned resume set of words during preset biographic information trains library
Weight and relevance；(3) according to the corresponding weight of word and relevance in the above-mentioned resume set of words found, above-mentioned resume is generated
The corresponding synthesis result of word in set of words, according to the sequence of the synthesis result from high to low to the word in above-mentioned resume set of words
It is ranked up；(4) resume keyword of the word as biographic information of the first preset quantity in the sequence is determined.
In the embodiment of the present invention, preset biographic information training library includes being trained according to biographic information training sample
Each word and the corresponding weight of each word and relevance.In process (1 |), train library can be to job hunting according to biographic information
The biographic information of person carries out word segmentation processing, obtains resume set of words.The method and process specifically segmented is those skilled in the art
Known, which is not described herein again.
Assuming that resume set of words includes tetra- words of A, B, C and D, preset biographic information training contains A, B, C, D in library
With multiple words such as E.Process (2) concrete example is as follows.It is searched in preset biographic information trains library and obtains the corresponding weights of word A
A1 and relevance A2, word B corresponding weight B1 and relevance B2, word C corresponding weight C1 and relevance C2, the weight that word D is answered
D1 and relevance D2.The corresponding relevance of word refers to the relevance between current word and other words, and the corresponding relevance of word can
To be indicated with relevance sequence.For example, the corresponding relevance A2 of word A can be relevance sequence A2 (A21, A22, A23, A24,
A25 ... A2n), wherein A21 indicates that the relevance between word A and first word, A22 indicate between word A and second word
Relevance, A2n indicate the relevance between word A and n-th of word.
On the basis of process (2), process (3) concrete example is as follows.According to the corresponding weight A1 and A2 of word A, according to pre-
Fixed algorithm considers weight A1 and relevance A2, generates the corresponding synthesis result A3 of word A.In the same way, with this
Analogize, generates the corresponding synthesis result B3 of word B, the corresponding synthesis result C3 of word C, the corresponding synthesis result D3 of word D.According to synthesis
As a result sequence from high to low is ranked up word ABCD, it is assumed that obtained ranking results are CBAD, the wherein synthesis result of word C
The synthesis result of highest, word D is minimum.
On the basis of process (3), process (4) concrete example is as follows.Determine the word of the first preset quantity in sequence CBAD
The resume keyword of biographic information as job hunter.In a kind of preferred embodiment, the word of the first preset quantity is sequence
M word before middle ranking, such as ranking first two words C and B, using word C and word B as the resume keyword of the biographic information of job hunter.
In step 206, the job information that selection matches with resume keyword in preset job information library, Neng Goutong
Cross following procedure realization：(a) corresponding resume key term vector is generated according to resume keyword；(b) calculate resume keyword to
The matching degree between position key term vector in amount and preset job information library；(c) according to matching degree from high to low suitable
Ordered pair position key term vector is ranked up；(d) in selected and sorted the second preset quantity the corresponding duty of position key term vector
Position information, as the job information to match with resume keyword.
In the embodiment of the present invention, preset job information library includes being closed according to the position that the job information of employing unit generates
Keyword and corresponding position key term vector.In process (a), according to resume keyword generate corresponding resume keyword to
Amount, detailed process is known to those skilled in the art, and which is not described herein again.
A kind of preferred embodiment of process (b) is to be based on vector space model, calculates resume key term vector and position
Cosine angle between crucial term vector, between the cosine angle representative's curriculum vitae key term vector and position key term vector
With degree, the cosine angle is smaller, illustrates that the matching degree between resume key term vector and position key term vector is higher, i.e. resume
Crucial term vector is more matched with position key term vector.Cosine angle calcu-lation formula is
Wherein (x1, y1) indicate resume key term vector, (x2, y2) indicate position key term vector.Be able to know that, resume keyword to
It measures and is more than one in the case of usual s, preset job information library includes many position key term vectors, therefore in process
(b) it needs to calculate separately the matching degree between each resume key term vector and each position key term vector in.Such as, it counts respectively
Calculate the matching degree between each resume key term vector and position key term vector Q, W, E and R.
On the basis of process (b), process (c) concrete example is as follows.From high to low according to the matching degree calculated
Sequence position key term vector Q, W, E and R are ranked up, it is assumed that ranking results WERQ, wherein position key term vector W with
Matching degree highest between resume key term vector, the matching degree between position key term vector Q and resume key term vector is most
It is low.
On the basis of process (c), process (d) concrete example is as follows.Determine the duty of the second preset quantity in sequence WERQ
The corresponding job information of the crucial term vector in position, as the job information to match with resume keyword.A kind of preferred embodiment party
In formula, the position key term vector of the second preset quantity is ranking top n position key term vector in sequence, such as ranking the first two
Position key term vector W and E match the corresponding job information of position key term vector W and E as with resume keyword
Job information.Position key term vector W and E can be corresponded to a job information, can also correspond to different job informations.
In the method for web page interlinkage can include being shown in computer by the job information chosen in the embodiment of the present invention
On screen, the job information chosen can also be sent in a manner of the short breath of mobile phone in the mobile phone inbox of job hunter.
Resume provided in an embodiment of the present invention is described below and recommends method, recommends method with reference to resume as shown in Figure 3, it should
The executive agent of method is network recruitment system, and this method includes：
Step 302, the job information from employing unit is received.Wherein, job information includes the position letter of employing unit
Informative text and employing unit send the time of job information text.
Step 304, library is trained to analyze job information according to preset job information, the position for the information that gets a duty
Keyword；Preset job information training library includes each word trained according to job information training sample, each word pair
The weight and relevance answered.
Step 306, the biographic information that selection matches with position keyword in preset biographic information library, will select
The biographic information come recommends employing unit；Preset biographic information library includes the resume generated according to the biographic information of job hunter
Crucial term vector.
As it can be seen that the resume recommendation method in through the embodiment of the present invention, the position keyword for the information that can get a duty, and
The biographic information to match with position keyword is recommended into employing unit, to accurately recommend to employing unit and its position phase
The biographic information of symbol is alleviated in the job information that the biographic information recommended in the prior art to employing unit is issued with employing unit
Not the problem of appearance is not inconsistent.
In step 304, library is trained to analyze job information according to preset job information, the duty for the information that gets a duty
Position keyword, can be realized by following procedure：(1) library is trained to carry out at participle job information according to preset job information
Reason, get a duty set of words；(2) the corresponding power of word in searching above-mentioned position set of words during preset job information trains library
Weight and relevance；(3) according to the corresponding weight of word and relevance in the above-mentioned position set of words found, above-mentioned position is generated
The corresponding synthesis result of word in set of words, according to the sequence of the synthesis result from high to low to the word in above-mentioned position set of words
It is ranked up；(4) position keyword of the word of third preset quantity in sequence as job information is determined.
In the embodiment of the present invention, preset job information training library includes being trained according to job information training sample
Each word and the corresponding weight of each word and relevance.In process (1 |), train library can be to employment according to job information
The job information of unit carries out word segmentation processing, and get a duty set of words.The method and process specifically segmented is people in the art
Well known to member, which is not described herein again.
Assuming that position set of words includes tetra- words of A, B, C and D, preset job information training contains A, B, C, D in library
With multiple words such as E.Process (2) concrete example is as follows.It is searched in preset job information trains library and obtains the corresponding weights of word A
A1 and relevance A2, word B corresponding weight B1 and relevance B2, word C corresponding weight C1 and relevance C2, the weight that word D is answered
D1 and relevance D2.The corresponding relevance of word refers to the relevance between current word and other words, and the corresponding relevance of word can
To be indicated with relevance sequence.For example, the corresponding relevance A2 of word A can be relevance sequence A2 (A21, A22, A23, A24,
A25 ... A2n), wherein A21 indicates that the relevance between word A and first word, A22 indicate between word A and second word
Relevance, A2n indicate the relevance between word A and n-th of word.
On the basis of process (2), process (3) concrete example is as follows.According to the corresponding weight A1 and A2 of word A, according to rule
Fixed algorithm considers weight A1 and relevance A2, generates the corresponding synthesis result A3 of word A.In the same way, with this
Analogize, generates the corresponding synthesis result B3 of word B, the corresponding synthesis result C3 of word C, the corresponding synthesis result D3 of word D.According to synthesis
As a result sequence from high to low is ranked up word ABCD, it is assumed that obtained ranking results are CBAD, the wherein synthesis result of word C
The synthesis result of highest, word D is minimum.
On the basis of process (3), process (4) concrete example is as follows.Determine the word of third preset quantity in sequence CBAD
The position keyword of job information as employing unit.In a kind of preferred embodiment, the word of third preset quantity is row
M word before ranking in sequence, it is crucial using word C and word B as the position of the job information of employing unit such as ranking first two words C and B
Word.
Step 306, the biographic information that selection matches with position keyword in preset biographic information library, can pass through
Following procedure is realized：(a) corresponding position key term vector is generated according to position keyword；(b) position key term vector is calculated
With the matching degree between the resume key term vector in preset biographic information library；(c) sequence according to matching degree from high to low
Resume key term vector is ranked up；(d) in selected and sorted the 4th preset quantity the corresponding resume of resume key term vector
Information, as the biographic information to match with position keyword.
In the embodiment of the present invention, preset biographic information library includes the resume key generated according to the biographic information of job hunter
Word and corresponding resume key term vector.In process (a), corresponding position key term vector is generated according to position keyword,
Its detailed process is known to those skilled in the art, and which is not described herein again.
A kind of preferred embodiment of process (b) is to be based on vector space model, calculates position key term vector and resume
Cosine angle between crucial term vector, the cosine angle represent between position key term vector and resume key term vector
With degree, the cosine angle is smaller, illustrates that the matching degree between position key term vector and resume key term vector is higher, i.e. position
Crucial term vector is more matched with resume key term vector.It is able to know that, position keyword usually has multiple, preset biographic information
Library includes many resume key term vectors, thus need in process (b) to calculate separately each position key term vector with it is every
Matching degree between a resume key term vector.Such as, calculate separately each position key term vector and resume key term vector Q,
W, the matching degree between E and R.
On the basis of process (b), process (c) concrete example is as follows.From high to low according to the matching degree calculated
Sequence resume key term vector Q, W, E and R are ranked up, it is assumed that ranking results WERQ, wherein resume key term vector W with
Matching degree highest between position key term vector, the matching degree between resume key term vector Q and position key term vector is most
It is low.
On the basis of process (c), process (d) concrete example is as follows.Determine the letter of the 4th preset quantity in sequence WERQ
The corresponding biographic information of crucial term vector is gone through, as the biographic information to match with position keyword.A kind of preferred embodiment party
In formula, the resume key term vector of the 4th preset quantity is M resume key term vector before ranking in sequence, such as ranking the first two
Resume key term vector W and E match the corresponding biographic information of resume key term vector W and E as with position keyword
Biographic information.Resume key term vector W and E can be corresponded to a biographic information, can also correspond to different biographic informations.
In the method for web page interlinkage can include being shown in computer by the biographic information chosen in the embodiment of the present invention
On screen, the biographic information chosen can also be sent in a manner of the short breath of mobile phone in the mobile phone inbox of employing unit.
Train the generation method in library with reference to biographic information as shown in Figure 4, in the embodiment of the present invention, biographic information trains library
Generation method include：
Step 402, biographic information training sample is obtained.In a kind of preferred embodiment, answering for 1,000,000 parts of specifications is obtained
Engage resume as biographic information training sample.
Step 404, word segmentation processing is carried out to biographic information training sample according to Chinese word segmentation packet.A kind of preferred embodiment party
In formula, based on the Chinese word segmentation packet LibMMseq to increase income, the specialized dictionary of a large amount of recruitment industry is added, this reality is formed
Apply the Chinese word segmentation packet in example.
Step 406, weight calculation is carried out to the word obtained after participle.Assuming that n word has been obtained after participle, it is a kind of preferred
In embodiment, using random walk algorithm and TF-IDF (term frequency inverse document
Frequency, the reverse document-frequency of word frequency -) to this n word progress weight calculation, detailed process is algorithm：After participle
N obtained word builds the word network of a n*n, carries out weight calculation to this n word by random walk algorithm, then will be each
The weight that word is calculated is multiplied by the reverse document-frequency of each word, obtains the final weight of each word.
It is as follows that weight calculation concrete example is carried out to the word obtained after participle.Assuming that participle after obtain " full-time group, PHP,
Four words of engineer, recruitment ", this four word initial weights are all 1.To " full-time group, PHP, engineer, recruitment " four word structures
The word network for building 4*4 carries out weight calculation by random walk algorithm to this 4 words.Assuming that first time random walk result is：
Full-time group → engineer, full-time group → recruitment, engineer → PHP, recruitment → PHP, recruitment → engineer.It can be found that
The weight of " full-time group " is divided equally to " engineer " and " recruitment ", and the weight of " engineer " has all given " PHP ", " recruitment "
Weight is divided equally to " PHP " and " engineer ".Assuming that in calculating process, the weight of a word is equal to the initial power of the first predetermined multiplying power
Other words plus the second predetermined multiplying power are transmitted through the weight come again, wherein the first predetermined multiplying power and the second predetermined multiplying power can bases
It needs to select, the preferably first predetermined multiplying power and the second predetermined multiplying power are 0.5, then formula is expressed as weight=0.5* of a word
Other words of initial weight (being 1)+0.5* are transmitted through the weight come, then after first time iteration, weight=0.5*1+ of full-time group
0.5*0 (weight is transmitted to him by no word), engineer's weight=0.5*1+0.5* (recruit by the weight+1/2 of 1/2 full-time group
Weight), weight=0.5*1+0.5* (weight that the weight+1/2 of engineer is recruited) of PHP, weight=0.5*1+ of recruitment
The weight of the full-time groups of 0.5*1/2.After the repeatedly walking immediately of above procedure and calculating, each word has been obtained in document
Weight, then the weight that each word is calculated is multiplied by the reverse document-frequency of each word, obtain the final weight of each word.
Step 408, the being associated property of word for calculating weight is analyzed.The relevance of word indicates the association journey of two words
Degree.In a preferred embodiment, word association analysis is carried out using mutual information algorithm, obtains each word and other words
Between relevance, such as the association between relevance, first word and third word between first word and second word
Relevance of the property ... between first word and k-th word, relevance, second word between second word and first word and
Second word of relevance ... between third word and the relevance between k-th word, remaining word are analogized with this rule.
Step 410, the relevance being calculated in the weight and step 408 that are calculated in step 406 is carried out artificial
Intervention and amendment, corrected Calculation slip up the case where.
Step 412, the word obtained by step 402 to step 410 and its corresponding weight and relevance are stored,
It forms biographic information and trains library.
In the embodiment of the present invention, job information trains the generation method phase of the generation method and biographic information training library in library
Together, which is not described herein again.In a kind of preferred embodiment, the job description text of 500,000 parts of specifications is obtained as job information
The job information training sample in training library.
In the embodiment of the present invention, the generation method in preset biographic information library is：It, will when job hunter provides biographic information
The biographic information of job hunter is input to biographic information training library, is analyzed biographic information, is obtained using biographic information training library
To the resume keyword of biographic information, and calculate the corresponding resume key term vector of resume keyword.A large amount of resume keyword
And resume key term vector collectively constitutes biographic information library.Wherein, biographic information is divided using biographic information training library
The detailed process for analysing the resume keyword for obtaining biographic information is identical with the process in position recommendation method above-mentioned.
In the embodiment of the present invention, the generation method in preset job information library is：When employing unit provides job information,
The job information of employing unit is input to job information and trains library, job information is divided using job information training library
Analysis, the position keyword for the information that gets a duty, and calculate the corresponding position key term vector of position keyword.A large amount of position is closed
Keyword and position key term vector collectively constitute job information library.Wherein, using job information train library to job information into
The detailed process that row analyzes the position keyword for the information that gets a duty is identical with the process in resume recommendation method above-mentioned.
Position in corresponding diagram 2 recommends method, as shown in figure 5, the embodiment of the present invention also provides a kind of position recommendation apparatus
50, which is set in network recruitment system, which includes：
Receiving module 51, for receiving the biographic information from job hunter.
Keyword determining module 52 is obtained for training library to analyze biographic information according to preset biographic information
The resume keyword of biographic information；Preset biographic information training library include trained according to biographic information training sample it is each
A word, the corresponding weight of each word and relevance.
Recommending module 53 is selected, for the position letter that selection matches with resume keyword in preset job information library
Breath, job hunter is recommended by the job information chosen；Preset job information library includes being believed according to the position of employing unit
Cease the position key term vector generated.
Position recommendation apparatus in through the embodiment of the present invention, can obtain the resume keyword of biographic information, and will be with
The job information that resume keyword matches recommends job hunter, to accurately recommend the position being consistent with its resume to job hunter
Information, what the resume content that the job information that alleviation is recommended to job hunter in the prior art is issued with job hunter was not inconsistent asks
Topic.
Resume in corresponding diagram 3 recommends method, as shown in fig. 6, the embodiment of the present invention also provides a kind of resume recommendation apparatus
60, which is set in network recruitment system, which includes：
Receiving module 61, for receiving the job information from employing unit.
Keyword determining module 62 is obtained for training library to analyze job information according to preset job information
The position keyword of job information；Preset job information training library include trained according to job information training sample it is each
A word, the corresponding weight of each word and relevance.
Recommending module 63 is selected, for the resume letter that selection matches with position keyword in preset biographic information library
Breath, employing unit is recommended by the biographic information chosen；Preset biographic information library includes being believed according to the resume of job hunter
Cease the resume key term vector generated.
Resume recommendation apparatus in through the embodiment of the present invention, the position keyword for the information that can get a duty, and will be with
The biographic information that position keyword matches recommends employing unit, to accurately recommend to be consistent with its position to employing unit
Biographic information alleviates the job information content issued in the prior art to the biographic information of employing unit's recommendation with employing unit not
The problem of symbol.
As shown in fig. 7, the embodiment of the present invention additionally provides a kind of recruitment platform 70, including position as shown in Figure 5 is recommended
Device 50 and resume recommendation apparatus 60 as shown in FIG. 6.
In the embodiment of the present invention, recruitment platform 70 includes that biographic information trains library update module, biographic information to train library more
New module, which is used to update preset biographic information according to the biographic information from job hunter, trains library.Specifically, when from job hunting
When in the biographic information of person comprising the word not having in biographic information training library, train library update module can by biographic information
These biographic informations are trained the word not having in library arrange to together, the word not having in library is trained using these biographic informations
It updates biographic information and trains library.
Recruitment platform 70 includes that job information trains library update module, job information that library update module is trained to come for basis
Preset job information, which is updated, from the job information of employing unit trains library.Specifically, when the job information from employing unit
In comprising job information training library in do not have word when, by job information train library update module these positions can be believed
The word not having in breath training library is arranged to together, trains the word not having in library to update job information using these job informations
Training library.
Recruitment platform in through the embodiment of the present invention can either recommend matched position, additionally it is possible to Xiang Yong to job hunter
People's unit recommends matched resume, to facilitate job hunter's job search, facilitates and employs employee between employing unit.
Position in through the embodiment of the present invention recommends method and apparatus, resume to recommend method and apparatus, recruitment platform, energy
Enough job informations for accurately recommending to be consistent with its resume to job hunter, accurately recommend the resume being consistent with its position to employing unit
Information, be not inconsistent to alleviate the resume content that the job information recommended in the prior art to job hunter is issued with job hunter,
Not the problem of job information that the biographic information recommended to employing unit is issued with employing unit is not inconsistent.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. a kind of position recommends method, which is characterized in that the method includes：
Receive the biographic information from job hunter；
Library is trained to analyze the biographic information according to preset biographic information, the resume for obtaining the biographic information is crucial
Word specifically includes：Word segmentation processing is carried out to the biographic information according to the preset biographic information training library, obtains resume word
Set；The corresponding weight of word and relevance in searching the resume set of words in the preset biographic information training library；
According to the corresponding weight of word and relevance in the resume set of words found, the word pair in the resume set of words is generated
The synthesis result answered is ranked up the word in the resume set of words according to the sequence of the synthesis result from high to low；Really
Resume keyword of the word of first preset quantity as the biographic information in the fixed sequence；The preset biographic information instruction
It includes each word trained according to biographic information training sample to practice library, the corresponding weight of each word and relevance；
The job information that selection matches with the resume keyword in preset job information library, described in choosing
Job information recommends the job hunter；The preset job information library includes being generated according to the job information of employing unit
Position key term vector.
2. according to the method described in claim 1, it is characterized in that, the selection in preset job information library and the letter
The job information that keyword matches is gone through, including：
Corresponding resume key term vector is generated according to the resume keyword；
Calculate the matching between the position key term vector in the resume key term vector and the preset job information library
Degree；
The position key term vector is ranked up according to the sequence of the matching degree from high to low；
The corresponding job information of position key term vector for selecting the second preset quantity in the sequence is closed as with the resume
The job information that keyword matches.
3. a kind of resume recommends method, which is characterized in that the method includes：
Receive the job information from employing unit；
Library is trained to analyze the job information according to preset job information, the position for obtaining the job information is crucial
Word specifically includes：Word segmentation processing is carried out to the job information according to the preset job information training library, get a duty word
Set；The corresponding weight of word and relevance in searching the position set of words in the preset job information training library；
According to the corresponding weight of word and relevance in the position set of words found, the word pair in the position set of words is generated
The synthesis result answered is ranked up the word in the position set of words according to the sequence of the synthesis result from high to low；Really
Position keyword of the word of third preset quantity as the job information in the fixed sequence；The preset job information instruction
It includes each word trained according to job information training sample to practice library, the corresponding weight of each word and relevance；
The biographic information that selection matches with the position keyword in preset biographic information library, described in choosing
Biographic information recommends the employing unit；The preset biographic information library includes being generated according to the biographic information of job hunter
Resume key term vector.
4. according to the method described in claim 3, it is characterized in that, described select and reported in preset biographic information library
The biographic information that position keyword matches, including：
Corresponding position key term vector is generated according to the position keyword；
Calculate the matching between the resume key term vector in the position key term vector and the preset biographic information library
Degree；
The resume key term vector is ranked up according to the sequence of the matching degree from high to low；
The corresponding biographic information of resume key term vector for selecting the 4th preset quantity in the sequence is closed as with the position
The biographic information that keyword matches.
5. a kind of position recommendation apparatus, which is characterized in that described device includes：
Receiving module, for receiving the biographic information from job hunter；
Keyword determining module obtains institute for training library to analyze the biographic information according to preset biographic information
The resume keyword for stating biographic information, specifically includes：According to the preset biographic information training library to the biographic information into
Row word segmentation processing obtains resume set of words；It is searched in the preset biographic information training library in the resume set of words
The corresponding weight of word and relevance；According to the corresponding weight of word and relevance in the resume set of words found, generate
The corresponding synthesis result of word in the resume set of words, according to the sequence of the synthesis result from high to low to the resume word
Word in set is ranked up；Determine that the word of the first preset quantity in the sequence is crucial as the resume of the biographic information
Word；The preset biographic information training library includes each word trained according to biographic information training sample, each word
Corresponding weight and relevance；
Recommending module is selected, for the position letter that selection matches with the resume keyword in preset job information library
Breath, the job hunter is recommended by the job information chosen；The preset job information library includes according to employment
The position key term vector that the job information of unit generates.
6. a kind of resume recommendation apparatus, which is characterized in that described device includes：
Receiving module, for receiving the job information from employing unit；
Keyword determining module obtains institute for training library to analyze the job information according to preset job information
The position keyword for stating job information, specifically includes：According to the preset job information training library to the job information into
Row word segmentation processing, get a duty set of words；It is searched in the preset job information training library in the position set of words
The corresponding weight of word and relevance；According to the corresponding weight of word and relevance in the position set of words found, generate
The corresponding synthesis result of word in the position set of words, according to the sequence of the synthesis result from high to low to the position word
Word in set is ranked up；Determine that the word of third preset quantity in the sequence is crucial as the position of the job information
Word；The preset job information training library includes each word trained according to job information training sample, each word
Corresponding weight and relevance；
Recommending module is selected, for the resume letter that selection matches with the position keyword in preset biographic information library
Breath, the employing unit is recommended by the biographic information chosen；The preset biographic information library includes that basis is asked
The resume key term vector that the biographic information of duty person generates.
7. a kind of recruitment platform, which is characterized in that including described in claim 5 position recommendation apparatus and claim 6 described in
Resume recommendation apparatus.
8. platform according to claim 7, which is characterized in that the platform includes：
Biographic information trains library update module, for updating the preset resume according to the biographic information from job hunter
Information trains library；
Job information trains library update module, for updating the preset duty according to the job information from employing unit
Position information trains library.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510521072.5A CN105159962B (en) | 2015-08-21 | 2015-08-21 | Position recommends method and apparatus, resume to recommend method and apparatus, recruitment platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510521072.5A CN105159962B (en) | 2015-08-21 | 2015-08-21 | Position recommends method and apparatus, resume to recommend method and apparatus, recruitment platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105159962A CN105159962A (en) | 2015-12-16 |
| CN105159962B true CN105159962B (en) | 2018-08-17 |
Family
ID=54800818
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510521072.5A Active CN105159962B (en) | 2015-08-21 | 2015-08-21 | Position recommends method and apparatus, resume to recommend method and apparatus, recruitment platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105159962B (en) |
Families Citing this family (62)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106933821A (en) * | 2015-12-29 | 2017-07-07 | 中国电信股份有限公司 | A kind of personalized position based on Similarity Measure recommends method and system |
| CN106997336A (en) * | 2016-01-26 | 2017-08-01 | 上海乔布堂信息科技有限公司 | A kind of intelligent resume making method |
| CN105741077A (en) * | 2016-01-26 | 2016-07-06 | 南华大学 | Occupational information providing method and system |
| CN105550855A (en) * | 2016-01-28 | 2016-05-04 | 华南理工大学 | Undergraduate-oriented campus project and applicant mutual-matching system and method |
| CN107291715A (en) * | 2016-03-30 | 2017-10-24 | 阿里巴巴集团控股有限公司 | Resume appraisal procedure and device |
| CN106022722A (en) * | 2016-05-18 | 2016-10-12 | 广东源恒软件科技有限公司 | Talent recommendation platform |
| CN106022728A (en) * | 2016-05-26 | 2016-10-12 | 深圳峰创智诚科技有限公司 | User evaluation method and device |
| CN105893641B (en) * | 2016-07-01 | 2019-02-26 | 中国传媒大学 | A kind of position recommended method |
| CN106228311B (en) * | 2016-07-28 | 2021-04-13 | 五八同城信息技术有限公司 | Post processing method and device |
| CN106447285B (en) * | 2016-09-12 | 2020-06-12 | 北京大学 | Recruitment information matching method based on multi-dimensional domain key knowledge |
| CN106446089B (en) * | 2016-09-12 | 2019-08-16 | 北京大学 | The extraction and storage method of a kind of various dimensions field all critical learning |
| CN106372858A (en) * | 2016-09-12 | 2017-02-01 | 成都集致生活科技有限公司 | Recruitment system of building industry, and application method thereof |
| CN106327107B (en) * | 2016-09-23 | 2020-06-12 | 深圳市讯方技术股份有限公司 | Job information matching method and device |
| CN106408262A (en) * | 2016-09-27 | 2017-02-15 | 吉林码帝科技有限公司 | Recruitment and application matching method |
| CN106384230A (en) * | 2016-10-21 | 2017-02-08 | 北京搜前途科技有限公司 | Method of matching work experience in resume with recruitment job and method of matching resume with recruitment information |
| CN106600213B (en) * | 2016-11-15 | 2021-03-05 | 惠州匠韵智能科技有限公司 | Intelligent management system and method for personal resume |
| CN106649885A (en) * | 2017-01-13 | 2017-05-10 | 深圳爱拼信息科技有限公司 | Professional category and standard professional name matching method and system |
| CN106844771B (en) * | 2017-02-28 | 2018-05-11 | 海南职业技术学院 | A kind of information processing method and device based on text matches |
| CN106980961A (en) * | 2017-03-02 | 2017-07-25 | 中科天地互联网科技（苏州）有限公司 | A kind of resume selection matching process and system |
| CN107220234A (en) * | 2017-05-17 | 2017-09-29 | 东莞市华睿电子科技有限公司 | A kind of screening technique of electronics resume |
| CN107316181A (en) * | 2017-06-26 | 2017-11-03 | 上海易路软件有限公司 | Obtain the method, device and mobile terminal of position market emolument |
| CN107688609B (en) * | 2017-07-31 | 2020-11-06 | 北京拉勾科技有限公司 | Job label recommendation method and computing device |
| CN107562870A (en) * | 2017-08-30 | 2018-01-09 | 国信优易数据有限公司 | A kind of user recommends method and apparatus |
| CN107516194A (en) * | 2017-09-14 | 2017-12-26 | 台州市黄岩宏福人力资源开发有限公司 | A kind of job hunting operated on cell phone platform, recruitment service system |
| CN107818134A (en) * | 2017-09-26 | 2018-03-20 | 北京纳人网络科技有限公司 | A kind of position similarity calculating method, client and server |
| CN107679737A (en) * | 2017-09-29 | 2018-02-09 | 广东掌中万维电子有限公司 | The method and device of project recommendation |
| CN108038655A (en) * | 2017-11-01 | 2018-05-15 | 平安科技（深圳）有限公司 | Recommendation method, application server and the computer-readable recording medium of department's demand |
| CN108021673A (en) * | 2017-12-06 | 2018-05-11 | 北京拉勾科技有限公司 | A kind of user interest model generation method, position recommend method and computing device |
| CN108133357A (en) * | 2017-12-22 | 2018-06-08 | 北京拉勾科技有限公司 | A kind of talent recommendation method and computing device |
| US20190220824A1 (en) * | 2018-01-12 | 2019-07-18 | Wei Liu | Machine learning systems for matching job candidate resumes with job requirements |
| CN108229924A (en) * | 2018-01-31 | 2018-06-29 | 广州市全周至程软件技术有限公司 | Recruitment information matching process, device and computer readable storage medium |
| CN110378544A (en) * | 2018-04-12 | 2019-10-25 | 百度在线网络技术（北京）有限公司 | A kind of personnel and post matching analysis method, device, equipment and medium |
| CN108664587A (en) * | 2018-05-07 | 2018-10-16 | 嘉善在线信息科技有限公司 | Based on keyword combination producing, perfect, search resume method and system |
| CN108665242A (en) * | 2018-05-09 | 2018-10-16 | 北京邦邦共赢网络科技有限公司 | A kind of resume matching process and device |
| CN108874901A (en) * | 2018-05-24 | 2018-11-23 | 佛山市轻遣网络有限公司 | A kind of hunter's recruitment information acquisition methods and system |
| CN108829676A (en) * | 2018-06-11 | 2018-11-16 | 安徽引航科技有限公司 | Talent's professional ability appraisal procedure based on text analysis technique |
| CN108984507A (en) * | 2018-08-03 | 2018-12-11 | 四川民工加网络科技有限公司 | The resume generation method and device of mobility worker |
| CN110874714A (en) * | 2018-08-31 | 2020-03-10 | 阿里巴巴集团控股有限公司 | Data matching method and device |
| CN109740046A (en) * | 2018-11-22 | 2019-05-10 | 北京网聘咨询有限公司 | Aerial double choosings based on internet recruitment can 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 |
| CN109840468A (en) * | 2018-12-14 | 2019-06-04 | 深圳壹账通智能科技有限公司 | A kind of generation method and equipment of customer analysis report |
| CN109710839A (en) * | 2018-12-14 | 2019-05-03 | 泰康保险集团股份有限公司 | Post method for pushing, device and equipment |
| CN111353014B (en) * | 2018-12-20 | 2023-05-02 | 阿里巴巴集团控股有限公司 | Position keyword extraction and position demand updating method and device |
| CN109754233B (en) * | 2019-01-29 | 2024-05-07 | 上海嘉道信息技术有限公司 | Method and system for intelligently recommending position information |
| CN110059162A (en) * | 2019-04-28 | 2019-07-26 | 苏州创汇智信息技术有限公司 | A kind of matching process and device of job seeker resume and position vacant |
| CN110084571A (en) * | 2019-05-08 | 2019-08-02 | 软通智慧科技有限公司 | Resume screening method, device, server and medium |
| CN110210765B (en) * | 2019-06-06 | 2021-06-11 | 中国传媒大学 | Movie and television resource matching method and system |
| 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 |
| CN110399475A (en) * | 2019-06-18 | 2019-11-01 | 平安科技（深圳）有限公司 | Resume matching process, device, equipment and storage medium based on artificial intelligence |
| CN110442841B (en) * | 2019-06-20 | 2024-02-02 | 平安科技（深圳）有限公司 | Resume identification method and device, computer equipment and storage medium |
| CN110378669A (en) * | 2019-06-28 | 2019-10-25 | 深圳市元征科技股份有限公司 | A kind of talent recommendation method and relevant apparatus |
| CN110781405B (en) * | 2019-10-12 | 2020-05-29 | 山东师范大学 | Document context perception recommendation method and system based on joint convolution matrix decomposition |
| CN110929169A (en) * | 2019-11-22 | 2020-03-27 | 北京网聘咨询有限公司 | Position recommendation method based on improved Canopy clustering collaborative filtering algorithm |
| CN111105209B (en) * | 2019-12-17 | 2023-07-21 | 上海沃锐企业发展有限公司 | Job resume matching method and device suitable for person post matching recommendation system |
| CN111125494A (en) * | 2019-12-24 | 2020-05-08 | 珠海大横琴科技发展有限公司 | Method and device for displaying personalized access page, electronic equipment and storage medium |
| CN111598462B (en) * | 2020-05-19 | 2022-07-12 | 厦门大学 | Resume screening method for campus recruitment |
| CN111861268A (en) * | 2020-07-31 | 2020-10-30 | 平安金融管理学院(中国·深圳) | Candidate recommending method and device, electronic equipment and storage medium |
| CN112287215A (en) * | 2020-10-23 | 2021-01-29 | 山大地纬软件股份有限公司 | Intelligent employment recommendation method and device |
| CN112199602B (en) * | 2020-12-03 | 2021-05-11 | 中电科新型智慧城市研究院有限公司 | Post recommendation method, recommendation platform and server |
| CN114691965A (en) * | 2020-12-29 | 2022-07-01 | 北京达佳互联信息技术有限公司 | Resume recommendation method, post recommendation method and electronic equipment |
| CN116228178A (en) * | 2023-03-09 | 2023-06-06 | 贵州迦太利华信息科技有限公司 | User behavior analysis method and device based on big data and storage medium |
| CN116340460B (en) * | 2023-03-17 | 2023-09-01 | 杭州东方网升科技股份有限公司 | Position recommendation method, system and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102708525A (en) * | 2012-05-22 | 2012-10-03 | 华南理工大学 | Vacant position intelligent recommendation method based on GPU (graphics processing unit) acceleration |
| CN103294816A (en) * | 2013-06-09 | 2013-09-11 | 广东倍智人才管理咨询有限公司 | Method and system for recommending positions for job seeker |
| CN103870575A (en) * | 2014-03-19 | 2014-06-18 | 北京百度网讯科技有限公司 | Method and device for extracting domain keywords |
| CN104731906A (en) * | 2015-03-24 | 2015-06-24 | 浪潮集团有限公司 | Automatic recruiting website resume pushing method |
| CN104834668A (en) * | 2015-03-13 | 2015-08-12 | 浙江奇道网络科技有限公司 | Position recommendation system based on knowledge base |
-
2015
- 2015-08-21 CN CN201510521072.5A patent/CN105159962B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102708525A (en) * | 2012-05-22 | 2012-10-03 | 华南理工大学 | Vacant position intelligent recommendation method based on GPU (graphics processing unit) acceleration |
| CN103294816A (en) * | 2013-06-09 | 2013-09-11 | 广东倍智人才管理咨询有限公司 | Method and system for recommending positions for job seeker |
| CN103870575A (en) * | 2014-03-19 | 2014-06-18 | 北京百度网讯科技有限公司 | Method and device for extracting domain keywords |
| CN104834668A (en) * | 2015-03-13 | 2015-08-12 | 浙江奇道网络科技有限公司 | Position recommendation system based on knowledge base |
| CN104731906A (en) * | 2015-03-24 | 2015-06-24 | 浪潮集团有限公司 | Automatic recruiting website resume pushing method |
Non-Patent Citations (2)
| Title |
|---|
| 基于混合式推荐算法的人力资源推荐引擎的应用研究;孟凡连;《中国优秀硕士学位论文全文数据库 信息科技辑》;20150315;第I138-2792页 * |
| 职位匹配系统的设计与实现;刘欢;《中国优秀硕士学位论文全文数据库 信息科技辑》;20111015;第I138-880页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105159962A (en) | 2015-12-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105159962B (en) | Position recommends method and apparatus, resume to recommend method and apparatus, recruitment platform | |
| Penha et al. | Curriculum learning strategies for IR: An empirical study on conversation response ranking | |
| CN102810117B (en) | A kind of for providing the method and apparatus of Search Results | |
| CN104598611B (en) | The method and system being ranked up to search entry | |
| CN108255921A (en) | The system for determining and showing the relevant explanation of recommendation | |
| CN107491547A (en) | Searching method and device based on artificial intelligence | |
| CN107463704A (en) | Searching method and device based on artificial intelligence | |
| CN108287864A (en) | A kind of interest group division methods, device, medium and computing device | |
| US10521489B2 (en) | Machine learning to predict numerical outcomes in a matrix-defined problem space | |
| US20170103337A1 (en) | System and method to discover meaningful paths from linked open data | |
| US11429915B2 (en) | Predicting feature values in a matrix | |
| CN105070124A (en) | Interactive commercial law basic teaching system | |
| CN109800307A (en) | Analysis method, device, computer equipment and the storage medium of product evaluation | |
| CN108121800A (en) | Information generating method and device based on artificial intelligence | |
| US11010688B2 (en) | Negative sampling | |
| US10679188B2 (en) | Ranking job candidate search results | |
| CN107292785A (en) | One kind is set a question method and system | |
| CN109241268A (en) | A kind of analog information recommended method, device, equipment and storage medium | |
| CN110462638A (en) | Training neural network is sharpened using posteriority | |
| CN106407381A (en) | Method and device for pushing information based on artificial intelligence | |
| CN116401464B (en) | Professional user portrait construction method, device, equipment and storage medium | |
| CN108874935A (en) | Review content recommendation method based on voice search and electronic equipment | |
| JP2022169743A (en) | Information extraction method and device, electronic equipment, and storage medium | |
| CN114862340A (en) | Personnel and post matching method, device, equipment and readable storage medium | |
| CN113961679A (en) | Intelligent question and answer processing method and system, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |