CN105159962A - Position recommendation method and apparatus, resume recommendation method and apparatus, and recruitment platform - Google Patents
Position recommendation method and apparatus, resume recommendation method and apparatus, and recruitment platform Download PDFInfo
- Publication number
- CN105159962A CN105159962A CN201510521072.5A CN201510521072A CN105159962A CN 105159962 A CN105159962 A CN 105159962A CN 201510521072 A CN201510521072 A CN 201510521072A CN 105159962 A CN105159962 A CN 105159962A
- Authority
- CN
- China
- Prior art keywords
- information
- resume
- word
- keyword
- job
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
Abstract
The present invention provides a position recommendation method and apparatus, a resume recommendation method and apparatus, and a recruitment platform. The position recommendation method comprises: receiving resume information from a job seeker; analyzing the resume information according to a preset resume information training library to obtain a resume keyword of the resume information, wherein the preset resume information training library comprises each word that is trained according to a resume information training sample and a weight and association corresponding to each word; and selecting position information matching the resume keyword from a preset position information library, and recommending the selected position information to the job seeker, wherein the preset position information library comprises a position keyword vector generated according to position information of an employer. By means of the position recommendation method and apparatus, the resume recommendation method and apparatus, and the recruitment platform provided by the present invention, position information that coincides with a resume of a job seeker can be accurately recommended to the job seeker, and resume information that coincides with a position of an employer can be accurately recommended to the employer.
Description
Technical field
The present invention relates to information matches and recruitment and application field, particularly position recommend method and device, resume recommend method and device, recruitment platform.
Background technology
Along with the development of Internet technology, the main path applying for work, employing unit recruitment employee into job hunter has been recruited in network application.
The main operating mode of network application recruitment is that job hunter issues resume in the network platform, and employing unit issues job information in the network platform.The network platform is after having a large amount of resumes and job information, job information is recommended targetedly to job hunter, resume is recommended to employing unit, with this, job hunter and employing unit are connected, help job hunter to find the work of its ability to work applicable rapidly, help employing unit to find the employee meeting job requirement fast.
Inventor finds under study for action, there is the problem that resume content that the job information recommended to job hunter and job hunter issue is not inconsistent in existing network application recruitment mode, such as, write the job hunter of " expert at software exploitation " in resume, can the position such as recommended Electronics Engineer or sale.For this problem, not yet there is good solution at present.
Summary of the invention
The invention provides position recommend method and device, resume recommend method and device, recruitment platform, can accurately recommend to job hunter the job information that conforms to its resume, alleviate the problem that resume content that the job information recommended to job hunter in prior art and job hunter issue is not inconsistent.
First aspect, embodiments provide a kind of position recommend method, described method comprises:
Receive the biographic information from job hunter;
Biographic information training storehouse according to presetting is analyzed described biographic information, obtains the resume keyword of described biographic information; Described default biographic information training storehouse comprises each word trained according to biographic information training sample, the weight that each word described is corresponding and relevance;
In the job information storehouse of presetting, select the job information matched with described resume keyword, the described job information chosen is recommended described job hunter; Described default job information storehouse comprises the position keyword vector generated according to the job information of employing unit.
In conjunction with first aspect, embodiments provide the first possible embodiment of first aspect, wherein, the biographic information training storehouse that described basis is preset is analyzed described biographic information, obtains the resume keyword of described biographic information, comprising:
According to described default biographic information training storehouse, word segmentation processing is carried out to described biographic information, obtain resume set of words;
The weight and relevance that the word searched in described resume set of words is corresponding is trained in storehouse at described default biographic information;
The weight corresponding according to the word in the described resume set of words found and relevance, generate the synthesis result that word in described resume set of words is corresponding, sort according to described synthesis result order from high to low to the word in described resume set of words;
Determine the resume keyword of the word of the first predetermined number in described sequence as described biographic information.
In conjunction with first aspect or the first possible embodiment of first aspect, embodiments provide the embodiment that first aspect the second is possible, wherein, selecting the job information matched with described resume keyword in the described job information storehouse presetting, comprising:
Corresponding resume keyword vector is generated according to described resume keyword;
Calculate the matching degree between the position keyword vector in described resume keyword vector and described default job information storehouse;
According to described matching degree order from high to low, described position keyword vector is sorted;
Select the job information that the position keyword of the second predetermined number in described sequence vector is corresponding, as the job information matched with described resume keyword.
Second aspect, a kind of resume recommend method of embodiment of the present invention drawings, described method comprises:
Receive the job information from employing unit;
Job information training storehouse according to presetting is analyzed described job information, obtains the position keyword of described job information; Described default job information training storehouse comprises each word trained according to job information training sample, the weight that each word described is corresponding and relevance;
In the biographic information storehouse of presetting, select the biographic information matched with described position keyword, the described biographic information chosen is recommended described employing unit; Described default biographic information storehouse comprises the resume keyword vector generated according to the biographic information of job hunter.
In conjunction with second aspect, embodiments provide the first possible embodiment of second aspect, wherein, the job information training storehouse that described basis is preset is analyzed described job information, obtains the position keyword of described job information, comprising:
Carry out word segmentation processing according to described default job information training storehouse to described job information, get a duty set of words;
The weight and relevance that the word searched in described position set of words is corresponding is trained in storehouse at described default job information;
The weight corresponding according to the word in the described position set of words found and relevance, generate the synthesis result that word in described position set of words is corresponding, sort according to described synthesis result order from high to low to the word in described position set of words;
Determine the position keyword of word as described job information of the 3rd predetermined number in described sequence.
In conjunction with second aspect or the first possible embodiment of second aspect, embodiments provide the embodiment that second aspect the second is possible, wherein, selecting the biographic information matched with described position keyword in the described biographic information storehouse presetting, comprising:
Corresponding position keyword vector is generated according to described position keyword;
Calculate the matching degree between the resume keyword vector in described position keyword vector and described default biographic information storehouse;
According to described matching degree order from high to low, described resume keyword vector is sorted;
Select the biographic information that the resume keyword of the 4th predetermined number in described sequence vector is corresponding, as the biographic information matched with described position keyword.
The third aspect, embodiments provide a kind of position recommendation apparatus, described device comprises:
Receiver module, for receiving the biographic information from job hunter;
Keyword determination module, for analyzing described biographic information according to the biographic information training storehouse of presetting, obtains the resume keyword of described biographic information; Described default biographic information training storehouse comprises each word trained according to biographic information training sample, the weight that each word described is corresponding and relevance;
Selecting recommending module, for selecting the job information matched with described resume keyword in the job information storehouse of presetting, the described job information chosen being recommended described job hunter; Described default job information storehouse comprises the position keyword vector generated according to the job information of employing unit.
Fourth aspect, embodiments provide a kind of resume recommendation apparatus, described device comprises:
Receiver module, for receiving the job information from employing unit;
Keyword determination module, for analyzing described job information according to the job information training storehouse of presetting, obtains the position keyword of described job information; Described default job information training storehouse comprises each word trained according to job information training sample, the weight that each word described is corresponding and relevance;
Selecting recommending module, for selecting the biographic information matched with described position keyword in the biographic information storehouse of presetting, the described biographic information chosen being recommended described employing unit; Described default biographic information storehouse comprises the resume keyword vector generated according to the biographic information of job hunter.
5th aspect, embodiments provides a kind of recruitment platform, comprises the position recommendation apparatus described in the third aspect and the resume recommendation apparatus described in fourth aspect.
In conjunction with the 5th aspect, embodiments provide the first possible embodiment of the 5th aspect, wherein, described platform comprises:
Biographic information training storehouse update module, for upgrading described default biographic information training storehouse according to the described biographic information from job hunter;
Job information training storehouse update module, for upgrading described default job information training storehouse according to the described job information from employing unit.
By the position recommend method in the embodiment of the present invention and device, resume recommend method and device, recruitment platform, the job information that conforms to its resume can be accurately recommended to job hunter, accurately recommend the biographic information conformed to its position to employing unit, thus alleviate that the resume content that the job information recommended to job hunter in prior art and job hunter issue is not inconsistent, problem that job information that the biographic information recommended to employing unit and employing unit issue is not inconsistent.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme of the embodiment of the present invention, be briefly described to the accompanying drawing used required in embodiment below, be to be understood that, the following drawings illustrate only some embodiment of the present invention, therefore the restriction to scope should be counted as, for those of ordinary skill in the art, under the prerequisite not paying creative work, other relevant accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 shows the structural representation of the network recruitment system that the embodiment of the present invention provides;
Fig. 2 shows the schematic flow sheet of the position recommend method that the embodiment of the present invention provides;
Fig. 3 shows the schematic flow sheet of the resume recommend method that the embodiment of the present invention provides;
Fig. 4 shows the generation method schematic diagram in the biographic information training storehouse that the embodiment of the present invention provides;
Fig. 5 shows the structural representation of the position recommendation apparatus that the embodiment of the present invention provides;
Fig. 6 shows the structural representation of the resume recommendation apparatus that the embodiment of the present invention provides;
Fig. 7 shows the structural representation of the recruitment platform that the embodiment of the present invention provides.
Embodiment
It should be noted that, when not conflicting, the embodiment in the application and the feature in embodiment can combine mutually.Below with reference to the accompanying drawings and describe the present invention in detail in conjunction with the embodiments.
The present invention program is understood better in order to make those skilled in the art person, below in conjunction with accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.The assembly of the embodiment of the present invention describing and illustrate in usual accompanying drawing herein can be arranged with various different configuration and design.Therefore, below to the detailed description of the embodiments of the invention provided in the accompanying drawings and the claimed scope of the present invention of not intended to be limiting, but selected embodiment of the present invention is only represented.Based on embodiments of the invention, the every other embodiment that those skilled in the art obtain under the prerequisite not making creative work, all belongs to the scope of protection of the invention.
The problem that the resume content that the job information recommended to job hunter for existing network application recruitment mode and job hunter issue is not inconsistent, the invention provides position recommend method and device, resume recommend method and device, recruitment platform, utilize word matching principle, can accurately recommend to job hunter the job information that conforms to its resume, alleviate the problem that resume content that the job information recommended to job hunter in prior art and job hunter issue is not inconsistent.
In the embodiment of the present invention, the executive agent of position recommend method and resume recommend method is all the third party's network recruitment systems between job hunter and employing unit, this network recruitment system can recommend suitable position to job hunter by position recommend method, can recommend suitable resume by resume recommend method to employing unit.
With reference to the network recruitment system in the embodiment of the present invention as shown in Figure 1, network recruitment system 10 in the embodiment of the present invention is previously provided with biographic information training storehouse 11, job information training storehouse 12, biographic information storehouse 13 and job information storehouse 14, wherein, biographic information training storehouse 11 is identical with the generation method in job information training storehouse 12, and biographic information storehouse 13 is identical with the generation method in job information storehouse 14.
In Fig. 1, when network recruitment system 10 recommends position by position recommend method to job hunter, need to use biographic information training storehouse 11 and job information storehouse 14; When network recruitment system 10 recommends resume by resume recommend method to employing unit, need to use job information training storehouse 12 and biographic information storehouse 13.
Introduce the position recommend method that the embodiment of the present invention provides below, with reference to position recommend method as shown in Figure 2, the executive agent of the method is network recruitment system, and the method comprises:
Step 202, receives the biographic information from job hunter.Wherein, biographic information comprises the time that the resume text of job hunter and job hunter send resume text.
Step 204, the biographic information training storehouse according to presetting is analyzed biographic information, obtains the resume keyword of biographic information; The biographic information training storehouse of presetting comprises each word trained according to biographic information training sample, the weight that each word is corresponding and relevance.
Step 206, selects the job information matched with resume keyword, the job information chosen is recommended job hunter in the job information storehouse of presetting; The job information storehouse of presetting comprises the position keyword vector generated according to the job information of employing unit.
By the position recommend method in the embodiment of the present invention, the resume keyword of biographic information can be obtained, and the job information matched with resume keyword is recommended job hunter, thus the job information that conforms to its resume is accurately recommended to job hunter, alleviate the problem that resume content that the job information recommended to job hunter in prior art and job hunter issue is not inconsistent.
In step 204, biographic information training storehouse according to presetting is analyzed biographic information, obtain the resume keyword of biographic information, can by following process implementation: (1) carries out word segmentation processing according to the biographic information training storehouse of presetting to biographic information, obtains resume set of words; (2) train in storehouse at the biographic information preset the weight and relevance that the word searched in above-mentioned resume set of words is corresponding; (3) according to weight corresponding to the word in the above-mentioned resume set of words that finds and relevance, generate the synthesis result that word in above-mentioned resume set of words is corresponding, according to this synthesis result order from high to low, the word in above-mentioned resume set of words is sorted; (4) the resume keyword of the word of the first predetermined number in this sequence as biographic information is determined.
In the embodiment of the present invention, the biographic information training storehouse of presetting comprises each word trained according to biographic information training sample, and weight corresponding to each word and relevance.In process (1|), word segmentation processing can be carried out to the biographic information of job hunter according to biographic information training storehouse, obtain resume set of words.The method of concrete participle and process are known in those skilled in the art, repeat no more here.
Suppose that resume set of words comprises A, B, C and D tetra-words, containing multiple word such as A, B, C, D and E in default biographic information training storehouse.Process (2) concrete example is as follows.Search in the biographic information training storehouse of presetting and obtain word A corresponding weight A1 and relevance A2, the weight B1 that word B is corresponding and relevance B2, the weight C1 that word C is corresponding and relevance C2, the weight D1 that word D answers and relevance D2.The relevance that word is corresponding refers to the relevance between current word and other words, and the relevance that word is corresponding can represent by relevance sequence.Such as, the relevance A2 that word A is corresponding can be relevance sequence A 2 (A21, A22, A23, A24, A25 ... A2n), wherein, A21 represents the relevance between word A and first word, A22 represents the relevance between word A and second word, and A2n represents the relevance between word A and the n-th word.
On the basis of process (2), process (3) concrete example is as follows.The weight A1 corresponding according to word A and A2, according to predetermined algorithm, considers weight A1 and relevance A2, generates the synthesis result A3 that word A is corresponding.In the same way, by that analogy, synthesis result B3 corresponding to word B, synthesis result C3 that word C is corresponding, synthesis result D3 that word D is corresponding is generated.Sort to word ABCD according to synthesis result order from high to low, suppose that the ranking results obtained is CBAD, wherein the synthesis result of word C is the highest, and the synthesis result of word D is minimum.
On the basis of process (3), process (4) concrete example is as follows.Determine the resume keyword of word as the biographic information of job hunter of the first predetermined number in sequence CBAD.One preferred embodiment in, the word of the first predetermined number is M word before rank in sequence, as rank first two words C and B, using the resume keyword of word C and word B as the biographic information of job hunter.
In step 206, in the job information storehouse of presetting, select the job information matched with resume keyword, can following process implementation be passed through: (a) generates corresponding resume keyword vector according to resume keyword; B () calculates the matching degree between the position keyword vector in resume keyword vector and default job information storehouse; C () is sorted to position keyword vector according to matching degree order from high to low; D job information that in () selected and sorted, the position keyword vector of the second predetermined number is corresponding, as the job information matched with resume keyword.
In the embodiment of the present invention, the job information storehouse of presetting comprises the position keyword and corresponding position keyword vector that generate according to the job information of employing unit.In process (a), generate corresponding resume keyword vector according to resume keyword, its detailed process is known in those skilled in the art, repeats no more here.
Process (b) one is preferred embodiment, based on vector space model, calculate the cosine angle between resume keyword vector and position keyword vector, matching degree between this cosine angle representative's curriculum vitae keyword vector and position keyword vector, this cosine angle is less, illustrate that the matching degree between resume keyword vector and position keyword vector is higher, namely resume keyword vector more mates with position keyword vector.Cosine angle calcu-lation formula is
wherein (x
1, y
1) represent resume keyword vector, (x
2, y
2) represent position keyword vector.Can know, more than one in the usual s situation of resume keyword vector, the job information storehouse of presetting comprises a lot of position keyword vectors, therefore needs to calculate the matching degree between each resume keyword vector and each position keyword vector respectively in process (b).As, calculate each resume keyword vector and the matching degree of position keyword vector between Q, W, E and R respectively.
On the basis of process (b), process (c) concrete example is as follows.According to the matching degree calculated order from high to low, position keyword vector Q, W, E and R are sorted, suppose that ranking results is WERQ, matching degree wherein between position keyword vector W and resume keyword vector is the highest, and the matching degree between position keyword vector Q and resume keyword vector is minimum.
On the basis of process (c), process (d) concrete example is as follows.To determine to sort the job information that the position keyword vector of the second predetermined number is corresponding in WERQ, as the job information matched with resume keyword.One preferred embodiment in, the position keyword vector of the second predetermined number is rank top n position keyword vector in sequence, as rank the first two position keyword vector W and E, by job information corresponding to position keyword vector W and E, as the job information matched with resume keyword.Position keyword vector W and E can be corresponding to a job information, job information that also can be corresponding different.
In the embodiment of the present invention, can the job information chosen be presented on computer display screen with the method for web page interlinkage, the job information chosen can also be sent in the mobile phone inbox of job hunter in the mode of the short breath of mobile phone.
Introduce the resume recommend method that the embodiment of the present invention provides below, with reference to resume recommend method as shown in Figure 3, the executive agent of the method is network recruitment system, and the method comprises:
Step 302, receives the job information from employing unit.Wherein, job information comprises the job information text of employing unit and the time of employing unit's transmission job information text.
Step 304, the job information training storehouse according to presetting is analyzed job information, the position keyword of the information that gets a duty; The job information training storehouse of presetting comprises each word trained according to job information training sample, the weight that each word is corresponding and relevance.
Step 306, selects the biographic information matched with position keyword, the biographic information chosen is recommended employing unit in the biographic information storehouse of presetting; The biographic information storehouse of presetting comprises the resume keyword vector generated according to the biographic information of job hunter.
Visible, by the resume recommend method in the embodiment of the present invention, the position keyword of the information that can get a duty, and the biographic information matched with position keyword is recommended employing unit, thus the biographic information that conforms to its position is accurately recommended to employing unit, alleviate the problem that job information content that the biographic information recommended to employing unit in prior art and employing unit issue is not inconsistent.
In step 304, job information training storehouse according to presetting is analyzed job information, the position keyword of the information that gets a duty, can by following process implementation: (1) carries out word segmentation processing according to the job information training storehouse of presetting to job information, and get a duty set of words; (2) train in storehouse at the job information preset the weight and relevance that the word searched in above-mentioned position set of words is corresponding; (3) according to weight corresponding to the word in the above-mentioned position set of words that finds and relevance, generate the synthesis result that word in above-mentioned position set of words is corresponding, according to this synthesis result order from high to low, the word in above-mentioned position set of words is sorted; (4) the position keyword of word as job information of the 3rd predetermined number in sequence is determined.
In the embodiment of the present invention, the job information training storehouse of presetting comprises each word trained according to job information training sample, and weight corresponding to each word and relevance.In process (1|), can carry out word segmentation processing to the job information of employing unit according to job information training storehouse, get a duty set of words.The method of concrete participle and process are known in those skilled in the art, repeat no more here.
Suppose that position set of words comprises A, B, C and D tetra-words, containing multiple word such as A, B, C, D and E in default job information training storehouse.Process (2) concrete example is as follows.Search in the job information training storehouse of presetting and obtain word A corresponding weight A1 and relevance A2, the weight B1 that word B is corresponding and relevance B2, the weight C1 that word C is corresponding and relevance C2, the weight D1 that word D answers and relevance D2.The relevance that word is corresponding refers to the relevance between current word and other words, and the relevance that word is corresponding can represent by relevance sequence.Such as, the relevance A2 that word A is corresponding can be relevance sequence A 2 (A21, A22, A23, A24, A25 ... A2n), wherein, A21 represents the relevance between word A and first word, A22 represents the relevance between word A and second word, and A2n represents the relevance between word A and the n-th word.
On the basis of process (2), process (3) concrete example is as follows.The weight A1 corresponding according to word A and A2, according to the algorithm of regulation, considers weight A1 and relevance A2, generates the synthesis result A3 that word A is corresponding.In the same way, by that analogy, synthesis result B3 corresponding to word B, synthesis result C3 that word C is corresponding, synthesis result D3 that word D is corresponding is generated.Sort to word ABCD according to synthesis result order from high to low, suppose that the ranking results obtained is CBAD, wherein the synthesis result of word C is the highest, and the synthesis result of word D is minimum.
On the basis of process (3), process (4) concrete example is as follows.Determine the position keyword of word as the job information of employing unit of the 3rd predetermined number in sequence CBAD.One preferred embodiment in, the word of the 3rd predetermined number is M word before rank in sequence, as rank first two words C and B, using the position keyword of word C and word B as the job information of employing unit.
Step 306, selects the biographic information matched with position keyword in the biographic information storehouse of presetting, can by following process implementation: it is vectorial that (a) generates corresponding position keyword according to position keyword; B () calculates the matching degree between the resume keyword vector in position keyword vector and default biographic information storehouse; C () is sorted to resume keyword vector according to matching degree order from high to low; D biographic information that in () selected and sorted, the resume keyword vector of the 4th predetermined number is corresponding, as the biographic information matched with position keyword.
In the embodiment of the present invention, the biographic information storehouse of presetting comprises the resume keyword and corresponding resume keyword vector that generate according to the biographic information of job hunter.In process (a), generate corresponding position keyword vector according to position keyword, its detailed process is known in those skilled in the art, repeats no more here.
Process (b) one is preferred embodiment, based on vector space model, calculate the cosine angle between position keyword vector and resume keyword vector, this cosine angle represents the matching degree between position keyword vector and resume keyword vector, this cosine angle is less, illustrate that the matching degree between position keyword vector and resume keyword vector is higher, namely position keyword vector more mates with resume keyword vector.Can know, position keyword has multiple usually, and the biographic information storehouse of presetting comprises a lot of resume keyword vectors, therefore needs to calculate the matching degree between each position keyword vector and each resume keyword vector respectively in process (b).As, calculate each position keyword vector and the matching degree of resume keyword vector between Q, W, E and R respectively.
On the basis of process (b), process (c) concrete example is as follows.According to the matching degree calculated order from high to low, resume keyword vector Q, W, E and R are sorted, suppose that ranking results is WERQ, matching degree wherein between resume keyword vector W and position keyword vector is the highest, and the matching degree between resume keyword vector Q and position keyword vector is minimum.
On the basis of process (c), process (d) concrete example is as follows.To determine to sort the biographic information that the resume keyword vector of the 4th predetermined number is corresponding in WERQ, as the biographic information matched with position keyword.One preferred embodiment in, the resume keyword vector of the 4th predetermined number is that in sequence, before rank, M resume keyword is vectorial, as rank the first two resume keyword vector W and E, by biographic information corresponding to resume keyword vector W and E, as the biographic information matched with position keyword.Resume keyword vector W and E can be corresponding to a biographic information, biographic information that also can be corresponding different.
In the embodiment of the present invention, can the biographic information chosen be presented on computer display screen with the method for web page interlinkage, the biographic information chosen can also be sent in the mobile phone inbox of employing unit in the mode of the short breath of mobile phone.
With reference to the generation method in biographic information training storehouse as shown in Figure 4, in the embodiment of the present invention, the generation method in biographic information training storehouse comprises:
Step 402, obtains biographic information training sample.One preferred embodiment in, obtain the application resume of 1,000,000 parts of specifications as biographic information training sample.
Step 404, carries out word segmentation processing according to Chinese word segmentation bag to biographic information training sample.One preferred embodiment in, based on the Chinese word segmentation bag LibMMseq increased income, then add the specialized dictionary of a large amount of recruitment industries, form the Chinese word segmentation bag in the present embodiment.
Step 406, carries out weight calculation to the word obtained after participle.N word is obtained after supposing participle, one preferred embodiment in, adopt random walk algorithm and TF-IDF (termfrequencyinversedocumentfrequency, word frequency-reverse document-frequency) algorithm carries out weight calculation to this n word, its detailed process is: the word network building a n*n for n the word obtained after participle, by random walk algorithm, weight calculation is carried out to this n word, again the weight that each word calculates is multiplied by the reverse document-frequency of each word, obtains the final weight of each word.
Weight calculation concrete example carries out to the word obtained after participle as follows.Obtain " full-time group, PHP, slip-stick artist, recruitment " four words after supposing participle, these four word initial weights are all 1." full-time group, PHP, slip-stick artist, recruitment " four words are built to the word network of 4*4, by random walk algorithm, weight calculation is carried out to these 4 words.Suppose that random walk result is for the first time: full-time group → slip-stick artist, full-time group → recruitment, slip-stick artist → PHP, recruitment → PHP, recruitment → slip-stick artist.Can find, the weight of " full-time group " is divided equally and is given " slip-stick artist " and " recruitment ", and the weight of " slip-stick artist " all gives " PHP ", and the weight of " recruitment " is divided equally to " PHP " and " slip-stick artist ".Suppose in computation process, the initial weight that the weight of a word equals the first predetermined multiplying power adds that other words of the second predetermined multiplying power pass the weight of coming, wherein the first predetermined multiplying power and the second predetermined multiplying power can be selected as required, preferably the first predetermined multiplying power and the second predetermined multiplying power are 0.5, then equation expression is that weight=other words of 0.5* initial weight (being 1)+0.5* of a word pass the weight of coming, then after first time iteration, weight=the 0.5*1+0.5*0 (not having word that weight is passed to him) of full-time group, slip-stick artist weight=0.5*1+0.5* (weight of weight+1/2 recruitment of 1/2 full-time group), weight=the 0.5*1+0.5* (weight of weight+1/2 recruitment of slip-stick artist) of PHP, the weight of the full-time group of weight=0.5*1+0.5*1/2 of recruitment.After repeatedly the walking immediately and calculate of above process, obtain the weight of each word at document, then the weight that each word calculates is multiplied by the reverse document-frequency of each word, obtain the final weight of each word.
Step 408, carries out correlation analysis to the word of calculated weight.The relevance of word represents the correlation degree of two words.In a preferred embodiment, point mutual information algorithm is adopted to carry out word association analysis, obtain the relevance between each word and other words, as the relevance between first word and second word, relevance between first word and the 3rd word ... relevance between first word and K word, relevance between second word and first word, relevance between second word and the 3rd word ... relevance between second word and K word, remaining word is analogized with this rule.
Correlation analysis concrete example carries out to the word of calculated weight as follows.Pass through formula
Calculate the relevance of word x word y, wherein, the probability that p (x) occurs separately for word x, the probability that p (y) occurs separately for word y, the probability that p (x, y) occurs jointly for word x, y.
Step 410, carries out artificial intervention and correction to the relevance calculated in the weight calculated in step 406 and step 408, the situation of corrected Calculation error.
Step 412, is stored the weight of the word obtained by step 402 to step 410 and correspondence thereof and relevance, forms biographic information training storehouse.
In the embodiment of the present invention, the generation method in job information training storehouse is identical with the generation method in biographic information training storehouse, repeats no more here.One preferred embodiment in, obtain 500,000 parts of specifications job description text as job information training storehouse job information training sample.
In the embodiment of the present invention, the generation method in the biographic information storehouse of presetting is: when job hunter provides biographic information, the biographic information of job hunter is inputed to biographic information training storehouse, biographic information is utilized to train storehouse to analyze biographic information, obtain the resume keyword of biographic information, and calculate resume keyword vector corresponding to resume keyword.A large amount of resume keywords and resume keyword vector common composition biographic information storehouse.Wherein, biographic information is utilized to train storehouse biographic information analysis to be obtained to the detailed process of the resume keyword of biographic information identical with the process in aforesaid position recommend method.
In the embodiment of the present invention, the generation method in the job information storehouse of presetting is: when employing unit provides job information, the job information of employing unit is inputed to job information training storehouse, job information is utilized to train storehouse to analyze job information, the position keyword of the information that gets a duty, and calculate position keyword vector corresponding to position keyword.A large amount of position keywords and position keyword vector common composition job information storehouse.Wherein, job information is utilized to train storehouse identical with the process in aforesaid resume recommend method to the get a duty detailed process of position keyword of information of job information analysis.
Position recommend method in corresponding diagram 2, as shown in Figure 5, the embodiment of the present invention also provides a kind of position recommendation apparatus 50, and this device is arranged in network recruitment system, and this device comprises:
Receiver module 51, for receiving the biographic information from job hunter.
Keyword determination module 52, for analyzing biographic information according to the biographic information training storehouse of presetting, obtains the resume keyword of biographic information; The biographic information training storehouse of presetting comprises each word trained according to biographic information training sample, the weight that each word is corresponding and relevance.
Selecting recommending module 53, for selecting the job information matched with resume keyword in the job information storehouse of presetting, the job information chosen being recommended job hunter; The job information storehouse of presetting comprises the position keyword vector generated according to the job information of employing unit.
By the position recommendation apparatus in the embodiment of the present invention, the resume keyword of biographic information can be obtained, and the job information matched with resume keyword is recommended job hunter, thus the job information that conforms to its resume is accurately recommended to job hunter, alleviate the problem that resume content that the job information recommended to job hunter in prior art and job hunter issue is not inconsistent.
Resume recommend method in corresponding diagram 3, as shown in Figure 6, the embodiment of the present invention also provides a kind of resume recommendation apparatus 60, and this device is arranged in network recruitment system, and this device comprises:
Receiver module 61, for receiving the job information from employing unit.
Keyword determination module 62, for analyzing job information according to the job information training storehouse of presetting, the position keyword of the information that gets a duty; The job information training storehouse of presetting comprises each word trained according to job information training sample, the weight that each word is corresponding and relevance.
Selecting recommending module 63, for selecting the biographic information matched with position keyword in the biographic information storehouse of presetting, the biographic information chosen being recommended employing unit; The biographic information storehouse of presetting comprises the resume keyword vector generated according to the biographic information of job hunter.
By the resume recommendation apparatus in the embodiment of the present invention, the position keyword of the information that can get a duty, and the biographic information matched with position keyword is recommended employing unit, thus the biographic information that conforms to its position is accurately recommended to employing unit, alleviate the problem that job information content that the biographic information recommended to employing unit in prior art and employing unit issue is not inconsistent.
As shown in Figure 7, the embodiment of the present invention additionally provides a kind of recruitment platform 70, comprises position recommendation apparatus 50 as shown in Figure 5 and resume recommendation apparatus 60 as shown in Figure 6.
In the embodiment of the present invention, recruitment platform 70 comprises biographic information training storehouse update module, and biographic information training storehouse update module is used for upgrading the biographic information training storehouse of presetting according to the biographic information from job hunter.Particularly, when comprising the word do not had in biographic information training storehouse in from the biographic information of job hunter, can arrange together by the word do not had in these biographic information training storehouse by biographic information training storehouse update module, the word that utilizing these biographic information to train does not have in storehouse upgrades biographic information training storehouse.
Recruitment platform 70 comprises job information training storehouse update module, and job information training storehouse update module is used for upgrading the job information training storehouse of presetting according to the job information from employing unit.Particularly, when comprising the word do not had in job information training storehouse in from the job information of employing unit, can arrange together by the word do not had in these job information training storehouse by job information training storehouse update module, the word that utilizing these job information to train does not have in storehouse upgrades job information training storehouse.
By the recruitment platform in the embodiment of the present invention, the position of coupling can either be recommended to job hunter, the resume of coupling can also be recommended to employing unit, thus facilitate job hunter's job search, facilitate between employing unit and employ employee.
By the position recommend method in the embodiment of the present invention and device, resume recommend method and device, recruitment platform, the job information that conforms to its resume can be accurately recommended to job hunter, accurately recommend the biographic information conformed to its position to employing unit, thus alleviate that the resume content that the job information recommended to job hunter in prior art and job hunter issue is not inconsistent, problem that job information that the biographic information recommended to employing unit and employing unit issue is not inconsistent.
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should described be as the criterion with the protection domain of claim.
Claims (10)
1. a position recommend method, is characterized in that, described method comprises:
Receive the biographic information from job hunter;
Biographic information training storehouse according to presetting is analyzed described biographic information, obtains the resume keyword of described biographic information; Described default biographic information training storehouse comprises each word trained according to biographic information training sample, the weight that each word described is corresponding and relevance;
In the job information storehouse of presetting, select the job information matched with described resume keyword, the described job information chosen is recommended described job hunter; Described default job information storehouse comprises the position keyword vector generated according to the job information of employing unit.
2. method according to claim 1, is characterized in that, the biographic information training storehouse that described basis is preset is analyzed described biographic information, obtains the resume keyword of described biographic information, comprising:
According to described default biographic information training storehouse, word segmentation processing is carried out to described biographic information, obtain resume set of words;
The weight and relevance that the word searched in described resume set of words is corresponding is trained in storehouse at described default biographic information;
The weight corresponding according to the word in the described resume set of words found and relevance, generate the synthesis result that word in described resume set of words is corresponding, sort according to described synthesis result order from high to low to the word in described resume set of words;
Determine the resume keyword of the word of the first predetermined number in described sequence as described biographic information.
3. method according to claim 1 and 2, is characterized in that, selecting the job information matched with described resume keyword, comprising in the described job information storehouse presetting:
Corresponding resume keyword vector is generated according to described resume keyword;
Calculate the matching degree between the position keyword vector in described resume keyword vector and described default job information storehouse;
According to described matching degree order from high to low, described position keyword vector is sorted;
Select the job information that the position keyword of the second predetermined number in described sequence vector is corresponding, as the job information matched with described resume keyword.
4. a resume recommend method, is characterized in that, described method comprises:
Receive the job information from employing unit;
Job information training storehouse according to presetting is analyzed described job information, obtains the position keyword of described job information; Described default job information training storehouse comprises each word trained according to job information training sample, the weight that each word described is corresponding and relevance;
In the biographic information storehouse of presetting, select the biographic information matched with described position keyword, the described biographic information chosen is recommended described employing unit; Described default biographic information storehouse comprises the resume keyword vector generated according to the biographic information of job hunter.
5. method according to claim 4, is characterized in that, the job information training storehouse that described basis is preset is analyzed described job information, obtains the position keyword of described job information, comprising:
Carry out word segmentation processing according to described default job information training storehouse to described job information, get a duty set of words;
The weight and relevance that the word searched in described position set of words is corresponding is trained in storehouse at described default job information;
The weight corresponding according to the word in the described position set of words found and relevance, generate the synthesis result that word in described position set of words is corresponding, sort according to described synthesis result order from high to low to the word in described position set of words;
Determine the position keyword of word as described job information of the 3rd predetermined number in described sequence.
6. the method according to claim 4 or 5, is characterized in that, selecting the biographic information matched with described position keyword, comprising in the described biographic information storehouse presetting:
Corresponding position keyword vector is generated according to described position keyword;
Calculate the matching degree between the resume keyword vector in described position keyword vector and described default biographic information storehouse;
According to described matching degree order from high to low, described resume keyword vector is sorted;
Select the biographic information that the resume keyword of the 4th predetermined number in described sequence vector is corresponding, as the biographic information matched with described position keyword.
7. a position recommendation apparatus, is characterized in that, described device comprises:
Receiver module, for receiving the biographic information from job hunter;
Keyword determination module, for analyzing described biographic information according to the biographic information training storehouse of presetting, obtains the resume keyword of described biographic information; Described default biographic information training storehouse comprises each word trained according to biographic information training sample, the weight that each word described is corresponding and relevance;
Selecting recommending module, for selecting the job information matched with described resume keyword in the job information storehouse of presetting, the described job information chosen being recommended described job hunter; Described default job information storehouse comprises the position keyword vector generated according to the job information of employing unit.
8. a resume recommendation apparatus, is characterized in that, described device comprises:
Receiver module, for receiving the job information from employing unit;
Keyword determination module, for analyzing described job information according to the job information training storehouse of presetting, obtains the position keyword of described job information; Described default job information training storehouse comprises each word trained according to job information training sample, the weight that each word described is corresponding and relevance;
Selecting recommending module, for selecting the biographic information matched with described position keyword in the biographic information storehouse of presetting, the described biographic information chosen being recommended described employing unit; Described default biographic information storehouse comprises the resume keyword vector generated according to the biographic information of job hunter.
9. a recruitment platform, is characterized in that, comprises position recommendation apparatus according to claim 7 and resume recommendation apparatus according to claim 8.
10. platform according to claim 9, is characterized in that, described platform comprises:
Biographic information training storehouse update module, for upgrading described default biographic information training storehouse according to the described biographic information from job hunter;
Job information training storehouse update module, for upgrading described default job information training storehouse according to the described job information from employing unit.
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 true CN105159962A (en) | 2015-12-16 |
| CN105159962B 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) |
Cited By (61)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN105741077A (en) * | 2016-01-26 | 2016-07-06 | 南华大学 | Occupational information providing method and system |
| CN105893641A (en) * | 2016-07-01 | 2016-08-24 | 中国传媒大学 | Job recommending method |
| 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 |
| CN106228311A (en) * | 2016-07-28 | 2016-12-14 | 五八同城信息技术有限公司 | Post processing method and processing device |
| CN106327107A (en) * | 2016-09-23 | 2017-01-11 | 深圳市讯方技术股份有限公司 | Position information matching method and device |
| 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 |
| 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 |
| CN106408262A (en) * | 2016-09-27 | 2017-02-15 | 吉林码帝科技有限公司 | Recruitment and application matching method |
| CN106447285A (en) * | 2016-09-12 | 2017-02-22 | 北京大学 | Multidimensional field key knowledge-based recruitment information matching method |
| CN106446089A (en) * | 2016-09-12 | 2017-02-22 | 北京大学 | Method for extracting and storing multidimensional field key knowledge |
| CN106600213A (en) * | 2016-11-15 | 2017-04-26 | 广东家易科技有限公司 | Intelligent resume management system and method |
| 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 |
| CN106844771A (en) * | 2017-02-28 | 2017-06-13 | 海南职业技术学院 | A kind of information processing method and device based on text matches |
| 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 |
| 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 |
| 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 |
| 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 |
| WO2017167069A1 (en) * | 2016-03-30 | 2017-10-05 | 阿里巴巴集团控股有限公司 | Resume assessment method and apparatus |
| 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 |
| 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 |
| 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 |
| 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 |
| CN107688609A (en) * | 2017-07-31 | 2018-02-13 | 北京拉勾科技有限公司 | A kind of position label recommendation method and computing device |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| CN109754233A (en) * | 2019-01-29 | 2019-05-14 | 上海嘉道信息技术有限公司 | A kind of method and system of intelligent recommendation job information |
| 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 |
| WO2019137493A1 (en) * | 2018-01-12 | 2019-07-18 | 刘伟 | Machine learning system for matching resume of job applicant with job requirements |
| 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 | A kind of resume selection method, apparatus, server and medium |
| CN110210765A (en) * | 2019-06-06 | 2019-09-06 | 中国传媒大学 | A kind of the resources of movie & TV matching process and system |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| CN111105209A (en) * | 2019-12-17 | 2020-05-05 | 上海沃锐企业发展有限公司 | Job resume matching method and device suitable for 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 |
| 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 |
| CN111353014A (en) * | 2018-12-20 | 2020-06-30 | 阿里巴巴集团控股有限公司 | Method and device for extracting job keywords and updating post requirements |
| CN111598462A (en) * | 2020-05-19 | 2020-08-28 | 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 |
| WO2020252919A1 (en) * | 2019-06-20 | 2020-12-24 | 平安科技（深圳）有限公司 | Resume identification method and apparatus, and computer device and storage medium |
| CN112199602A (en) * | 2020-12-03 | 2021-01-08 | 中电科新型智慧城市研究院有限公司 | Post recommendation method, recommendation platform and server |
| 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 |
| 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 |
| CN116340460A (en) * | 2023-03-17 | 2023-06-27 | 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 |
|---|
| 刘欢: "职位匹配系统的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 孟凡连: "基于混合式推荐算法的人力资源推荐引擎的应用研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (69)
| 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 |
| CN105741077A (en) * | 2016-01-26 | 2016-07-06 | 南华大学 | Occupational information providing 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 |
| 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 |
| WO2017167069A1 (en) * | 2016-03-30 | 2017-10-05 | 阿里巴巴集团控股有限公司 | Resume assessment method and apparatus |
| 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 |
| CN105893641A (en) * | 2016-07-01 | 2016-08-24 | 中国传媒大学 | Job recommending method |
| CN105893641B (en) * | 2016-07-01 | 2019-02-26 | 中国传媒大学 | A kind of position recommended method |
| CN106228311A (en) * | 2016-07-28 | 2016-12-14 | 五八同城信息技术有限公司 | Post processing method and processing device |
| CN106446089A (en) * | 2016-09-12 | 2017-02-22 | 北京大学 | Method for extracting and storing multidimensional field key knowledge |
| CN106447285A (en) * | 2016-09-12 | 2017-02-22 | 北京大学 | Multidimensional field key knowledge-based recruitment information matching method |
| 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 |
| CN106327107A (en) * | 2016-09-23 | 2017-01-11 | 深圳市讯方技术股份有限公司 | Position 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 |
| CN106600213A (en) * | 2016-11-15 | 2017-04-26 | 广东家易科技有限公司 | Intelligent resume management system and method |
| 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 |
| CN106844771A (en) * | 2017-02-28 | 2017-06-13 | 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 |
| CN107688609A (en) * | 2017-07-31 | 2018-02-13 | 北京拉勾科技有限公司 | A kind of position 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 |
| WO2019137493A1 (en) * | 2018-01-12 | 2019-07-18 | 刘伟 | Machine learning system for matching resume of job applicant 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 |
| US11238381B2 (en) | 2018-04-12 | 2022-02-01 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for talent-post matching 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 |
| CN111353014A (en) * | 2018-12-20 | 2020-06-30 | 阿里巴巴集团控股有限公司 | Method and device for extracting job keywords and updating post requirements |
| CN109754233A (en) * | 2019-01-29 | 2019-05-14 | 上海嘉道信息技术有限公司 | A kind of method and system of intelligent recommendation job 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 | A kind of resume selection method, apparatus, 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 |
| CN110210765A (en) * | 2019-06-06 | 2019-09-06 | 中国传媒大学 | A kind of the resources of movie & TV matching process and system |
| 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 |
| 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 |
| WO2020252919A1 (en) * | 2019-06-20 | 2020-12-24 | 平安科技（深圳）有限公司 | Resume identification method and apparatus, and computer device 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 |
| CN111105209A (en) * | 2019-12-17 | 2020-05-05 | 上海沃锐企业发展有限公司 | Job resume matching method and device suitable for 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 |
| CN111598462A (en) * | 2020-05-19 | 2020-08-28 | 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 |
| CN112199602A (en) * | 2020-12-03 | 2021-01-08 | 中电科新型智慧城市研究院有限公司 | Post recommendation method, recommendation platform and server |
| 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 |
| CN116340460A (en) * | 2023-03-17 | 2023-06-27 | 杭州东方网升科技股份有限公司 | Position recommendation method, system 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105159962B (en) | 2018-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105159962A (en) | Position recommendation method and apparatus, resume recommendation method and apparatus, and recruitment platform | |
| CN108776684B (en) | Optimization method, device, medium, equipment and system for edge weight in knowledge graph | |
| US20210056378A1 (en) | Resource constrained neural network architecture search | |
| CN104766606B (en) | Method, apparatus and its navigation application by natural language translation into instruction | |
| Högnäs et al. | Probability measures on semigroups: convolution products, random walks, and random matrices | |
| van De Sande | Properties Of The Bayesian Knowledge Tracing Model. | |
| CN107729532A (en) | A kind of resume matching process and computing device | |
| CN109800307B (en) | Product evaluation analysis method and device, computer equipment and storage medium | |
| US20180276535A1 (en) | Input-output example encoding | |
| CN105404698A (en) | Education video recommendation method and device | |
| CN111859140B (en) | Knowledge recommendation method and device, recommendation equipment and readable storage medium | |
| CN103389979A (en) | System, device and method for recommending classification lexicon in input method | |
| Zheng et al. | Integrating context similarity with sparse linear recommendation model | |
| CN105069103A (en) | Method and system for APP search engine to utilize client comment | |
| CN111461301A (en) | Serialized data processing method and device, and text processing method and device | |
| CN103631889B (en) | Image recognizing method and device | |
| CN105893362A (en) | A method for acquiring knowledge point semantic vectors and a method and a system for determining correlative knowledge points | |
| CN104915444A (en) | Information recommending method and device | |
| CN114862340A (en) | Personnel and post matching method, device, equipment and readable storage medium | |
| Kim et al. | Improving a recommender system by collective matrix factorization with tag information | |
| CN108776864A (en) | The appraisal procedure and device of user comment value | |
| CN103577547A (en) | Webpage type identification method and device | |
| Konstantinov et al. | AGBoost: Attention-based modification of gradient boosting machine | |
| Sachdeva et al. | Empirical analysis of machine learning techniques for context aware recommender systems in the environment of IoT | |
| Xiao et al. | Positivity and stability of coupled differential–difference equations with time-varying delay on time scales |
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 |