CN105894253A - Method and device for automatic pushing of job application demand - Google Patents
Method and device for automatic pushing of job application demand Download PDFInfo
- Publication number
- CN105894253A CN105894253A CN201610298635.3A CN201610298635A CN105894253A CN 105894253 A CN105894253 A CN 105894253A CN 201610298635 A CN201610298635 A CN 201610298635A CN 105894253 A CN105894253 A CN 105894253A
- Authority
- CN
- China
- Prior art keywords
- job
- job hunter
- hunter
- recruitment
- office
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
Abstract
The invention discloses a method and device for automatic pushing of a job application demand. The method is characterized in that whether a job hunter has left a job is monitored or whether the job hunter has a turnover intention is predicated; basic information of the job hunter is acquired when the method monitors that the job hunter has left the job or predicts that the job hunter has a turnover intention; resume information is generated according to the basic information; and the resume information is automatically sent to matched recruitment organizations. In this way, the technical problems that an existing method for job application demand pushing has complicated processes, operations are cumbersome and efficiency is not high can be solved; and when the method monitors that the job hunter has the turnover intention or has left the job, the resume information of the job hunter can be delivered to the proper recruitment organizations in time. The whole course does not require the job hunter to make any operation. The method is simple and reliable and has the advantages that the job application demand of the job hunter can be delivered to the proper recruitment organizations in time; delivery is quick and effective; and the efficiency of releasing the job hunter's job application demand to the recruitment organizations is greatly increased.
Description
Background technology
At present, increasing job hunter is looked for a job by the Internet, and the advertising unit carrying out online recruitment also gets more and more.Ask
Duty person carries out the process of the Internet job hunting after leaving office and is usually: first make resume, then send resume to recruitment website or
The position searching for coupling on recruitment website is delivered, and is to wait for interview notice or the Notice on Hiring of advertising unit with that.This
Model process is complicated, complex operation, and efficiency is the highest.
Summary of the invention
The invention provides and a kind of realize the method and device that job hunting demand pushes automatically, push solving existing realization job hunting demand
Flow process complicated, complex operation, and inefficient technical problem.
According to an aspect of the present invention, it is provided that a kind of realize the method that job hunting demand pushes automatically, including:
Whether monitoring job hunter leaves office or predicts whether job hunter has turnover intention, the most then ask for storage predefined
The data base of duty person's archives obtains the essential information of job hunter；
The biographic information corresponding with job hunter is generated according to essential information；
Obtain the advertising unit mated with the biographic information of job hunter, it is thus achieved that recruitment matching unit；
It is sent to biographic information recruit matching unit.
Further, whether monitoring job hunter leaves office and includes:
Monitoring job hunter whether have in the collaborative office system that it is residing leaving office operation, the most then judge job hunter from
Duty.
Further, it was predicted that whether job hunter has turnover intention to include:
Preset leaving office attributes entries；
Gather the user behavior data corresponding with leaving office attributes entries of training sample, wherein, training sample includes turnover intention person
With the training sample without turnover intention person；
Based on user behavior data, extract the characteristic vector of training sample；
Grader is trained, it is thus achieved that leaving office forecast model according to characteristic vector；
According to leaving office forecast model, determine whether job hunter has turnover intention.
Further, generate the biographic information corresponding with job hunter according to essential information to include:
Preset resume entry；
The information corresponding with resume entry is obtained, as biographic information from essential information.
Further, the advertising unit mated with the biographic information of job hunter is obtained, it is thus achieved that recruitment matching unit includes:
Web crawler is utilized to search for the recruitment requirement obtaining the advertising unit issuing recruitment needs on the internet；
According to default keyword extraction item, from biographic information, extract the first keyword sequence and from recruitment requires, extract second
Keyword sequence；
Calculate the similarity between the first keyword sequence and the second keyword sequence；
Choose the advertising unit corresponding more than the second keyword sequence corresponding to similarity presetting similarity threshold as with job hunter
Biographic information coupling advertising unit.
Further, biographic information is sent to recruit matching unit include:
Obtain recruitment matching unit for receiving the electronic receipt address of biographic information；
Biographic information is sent to electronic receipt address.
Further, name, contact method, work position, work industry.
According to a further aspect in the invention, it is provided that a kind of realize the device that job hunting demand pushes automatically, including:
Turnover intention acquisition device, is used for monitoring whether job hunter leaves office or predict whether job hunter has turnover intention, the most then
The essential information of job hunter is obtained in the predefined data base for storing job hunter's archives；
Biographic information generating means, for generating the biographic information corresponding with job hunter according to essential information；
Coalignment, for obtaining the advertising unit mated with the biographic information of job hunter, it is thus achieved that recruitment matching unit；
Dispensing device, for being sent to recruitment matching unit by biographic information.
Further, turnover intention acquisition device includes:
Monitoring device, for monitoring whether job hunter has leaving office operation in the collaborative office system that it is residing, the most then
Judge that job hunter leaves office.
Further, turnover intention acquisition device includes:
Preset device, be used for presetting leaving office attributes entries；
Harvester, for gathering the user behavior data corresponding with leaving office attributes entries of training sample, wherein, training sample bag
Include turnover intention person and the training sample without turnover intention person；
Extraction element, for based on user behavior data, extracting the characteristic vector of training sample；
Training devices, for training grader according to characteristic vector, it is thus achieved that leaving office forecast model；
Prediction means, for according to leaving office forecast model, determines whether job hunter has turnover intention.
The method have the advantages that
The present invention provide realize the method and device that job hunting demand pushes automatically, the method by monitoring job hunter whether leave office or
Whether prediction job hunter has turnover intention, and when monitoring job hunter and leaving office or predict that job hunter has turnover intention, obtains job hunting
The essential information of person, and generate biographic information according to essential information, and biographic information is automatically transmitted to the advertising unit mated,
Solve the flow process complexity that existing realization job hunting demand pushes, complex operation, and inefficient technical problem, it is achieved that at prison
Measure in the case of job hunter has turnover intention or leave office, in time the biographic information of job hunter be delivered to suitable advertising unit,
Whole process is without any operation of job hunter, simple and reliable, not only is delivered to suitably recruit by the job hunting demand of job hunter in time
Engage unit, and delivery process is quickly effective, is greatly improved the efficiency that the job hunting demand of job hunter is pushed to advertising unit.
In addition to objects, features and advantages described above, the present invention also has other objects, features and advantages.Below
Will be with reference to figure, the present invention is further detailed explanation.
Accompanying drawing explanation
The accompanying drawing of the part building the application is used for providing a further understanding of the present invention, the illustrative examples of the present invention and
Its explanation is used for explaining the present invention, does not build inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 be the preferred embodiment of the present invention realize the method flow diagram that job hunting demand pushes automatically；
Fig. 2 be the preferred embodiment of the present invention for first simplify embodiment realize the method flow diagram that job hunting demand pushes automatically；
Fig. 3 be the preferred embodiment of the present invention for second simplify embodiment realize the method flow diagram that job hunting demand pushes automatically；
Fig. 4 is the structured flowchart realizing the device that job hunting demand pushes automatically of the preferred embodiment of the present invention.
Description of reference numerals:
10, turnover intention acquisition device；20, biographic information generating means；30, coalignment；40, dispensing device.
Detailed description of the invention
Below in conjunction with accompanying drawing, embodiments of the invention are described in detail, but the present invention can be defined by the claims and cover
Multitude of different ways implement.
With reference to Fig. 1, the preferred embodiments of the present invention provide and a kind of realize the method that job hunting demand pushes automatically, including:
Step S101, whether monitoring job hunter leaves office or predicts whether job hunter has turnover intention, the most then predefined
The essential information of job hunter is obtained in the data base storing job hunter's archives；
Step S102, generates the biographic information corresponding with job hunter according to essential information；
Step S103, obtains the advertising unit mated with the biographic information of job hunter, it is thus achieved that recruitment matching unit；
Step S104, is sent to biographic information recruit matching unit.
Whether what the present invention provided realizes the method that job hunting demand pushes automatically, left office by monitoring job hunter or predicted that job hunter is
No have turnover intention, and when monitoring job hunter and leaving office or predict that job hunter has turnover intention, obtains the essential information of job hunter,
And generate biographic information according to essential information, and biographic information is automatically transmitted to the advertising unit mated, solve existing reality
The flow process that now job hunting demand pushes is complicated, complex operation, and inefficient technical problem, it is achieved that have monitoring job hunter
Turnover intention or in the case of leaving office, is delivered to suitable advertising unit in time by the biographic information of job hunter, whole process without
Need any operation of job hunter, simple and reliable, not only in time the job hunting demand of job hunter is delivered to suitable advertising unit, and
And delivery process is quickly effective, is greatly improved the efficiency that the job hunting demand of job hunter is pushed to advertising unit.
Specifically, the embodiment of the present invention not only solves the flow process complexity that existing realization job hunting demand pushes, complex operation, and effect
The technical problem that rate is the highest, and due to the present embodiment by monitor job hunter have leaving office or prediction job hunter have turnover intention
Time, the job hunting demand of job hunter is pushed to suitable advertising unit by the very first time, only also solves in prior art job hunter
Job hunting demand could be passed to advertising unit at recruitment Web realease or delivery resume, cause job hunting demand being transmitted in time
To the technical problem of advertising unit, it is achieved that when job hunter leaves office or has turnover intention, just can in time the job hunting of job hunter be needed
Ask and be delivered to suitable advertising unit, it is to avoid job hunter is in time at recruitment Web realease or deliver resume and miss suitable work
Make chance, avoid advertising unit because job hunter issues the most in time or delivers resume and misses outstanding personnel, it is achieved mode simultaneously
Simple and reliable, intelligence degree is high.
Alternatively, whether monitoring job hunter leaves office and includes:
Monitoring job hunter whether have in the collaborative office system that it is residing leaving office operation, the most then judge job hunter from
Duty.
Owing to existing collaborative office system the most all includes human resources's module, and human resources's module includes again occurrences in human life pipe
Reason module.Specifically, personnel management module mainly manage enterprise staff registration, become a full member, the work item such as leaving office.Therefore this reality
Execute example by monitoring job hunter whether have in the collaborative office system that it is residing leaving office operation judge job hunter whether from
Duty.It should be noted that the present embodiment is not limited to according to whether job hunter in collaborative office system has leaving office operation to judge
Whether it leaves office, for example, it is also possible to by judging whether the leading body at a higher level of this job hunter agrees to the things such as the leaving office application of this job hunter
Part monitors whether job hunter has leaving office operation in its residing enterprise collaborative office is.
The present embodiment utilizes the leaving office Action Events in collaborative office system as the triggering bar pushing job hunting demand relatively newly
Part, it is achieved that just its job hunting demand is automatically transmitted to when monitoring job hunter and leaving office the advertising unit being suitable for, not only facilitates
Job hunter is more rapid finds applicable work position, and is conducive to recruitment side to know the job hunting demand of job hunter earlier, thus carries
High job hunting or the efficiency of recruitment, it is achieved that job hunter is docked with the good of advertising unit, to alleviation social labor employment pressure also
Play positive role.
Alternatively, it was predicted that whether job hunter has turnover intention to include:
Preset leaving office attributes entries；
Gather the user behavior data corresponding with leaving office attributes entries of training sample, wherein, training sample includes turnover intention person
With the training sample without turnover intention person；
Based on user behavior data, extract the characteristic vector of training sample；
Grader is trained, it is thus achieved that leaving office forecast model according to characteristic vector；
According to leaving office forecast model, determine whether job hunter has turnover intention.
Owing to, in the middle of actual life, needing to issue job hunting demand and not only including that has left office asks to the main body of advertising unit
Duty person, also includes some on-job job hunters having turnover intention, therefore the present embodiment not only includes the job hunting that automatically pushes separation
Demand gives suitable advertising unit, also includes that the job hunting demand automatically pushing the job hunter of turnover intention is to suitable advertising unit.
Specifically, the present embodiment by gather training sample the user behavior data corresponding with leaving office attributes entries set in advance,
And extract the characteristic vector of training sample based on the user behavior data obtained, and based on the eigen vector training extracted for pre-
Survey whether job hunter to be predicted has the leaving office forecast model of turnover intention.Namely whether prediction job hunter is had leaving office meaning by the present embodiment
To problem be converted to the classification problem in pattern recognition.In concrete implementation process, the present embodiment can be chosen and leave office
The training sample of person is as the training sample of the person that has turnover intention, and chooses the training sample of holder of an office as the person that do not has turnover intention
Training sample.It should be noted that in order to ensure to train the leaving office forecast model obtained to have of a relatively high precision of prediction,
The quantity of the training sample that the present embodiment obtains should be big as far as possible, and for having turnover intention and the training sample without turnover intention person
This quantity should be suitable.
Whether the leaving office forecast model prediction job hunter that the present embodiment proposes according to training relatively newly has turnover intention, and when logical
Cross leaving office forecast model and dope job hunter when having turnover intention, just the job hunting demand of job hunter is sent to the advertising unit being suitable for,
Not only facilitate that job hunter is more rapid finds applicable work position, and be conducive to recruitment side when job hunter has turnover intention just
Know the job hunting demand of job hunter, thus improve job hunting or the efficiency of recruitment, it is achieved that job hunter is the most right with advertising unit
Connect, also function to positive role to alleviating social labor employment pressure.
Additionally, the leaving office attributes entries that the present embodiment is preset can include history chat data, job performance, job tenure, receipts
Enter level, the last time promotes time interval, working distance (the most also includes that distance, traffic time cost, number of times of changing trains or buses become
Basis, expense cost etc.), one or more combinations of logging in recruitment and job hunting net frequency entries.Existing affect job hunter leave office because of
Element is more, and such as job performance, job tenure, income level, the last time promote time interval, working distance etc. factor,
Therefore the present embodiment goes out from demission or other user behavior datas (such as history chat data or login recruitment and job hunting network data)
Send out, gather the user behavior data corresponding for each leaving office attributes entries respectively, and enter according to the user behavior data gathered
Row subsequent analysis.Certainly, the leaving office attributes entries in the present embodiment be not limited to above-mentioned these, such as can also include enterprise development
Entry, industry development entry etc..The present embodiment is according to affecting factor or other user behaviors that job hunter leaves office in existing life
Data (such as history chat data or login recruitment and job hunting network data), arrange leaving office attributes entries, it is achieved thereby that tie up from each
Spending the user behavior data to training sample to be acquired, the accuracy and precision of prediction for improving forecast model provides important number
According to source base.
Alternatively, generate the biographic information corresponding with job hunter according to essential information to include:
Preset resume entry；
The information corresponding with resume entry is obtained, as biographic information from essential information.
Owing to the essential information in the present embodiment is to obtain based on the predefined data base for storing job hunter's archives, therefore
Essential information can be any information relevant to job hunter, such as job hunter's name, age, work position, the length of service,
Work industry, wage emolument etc., therefore the present embodiment can be fast based on the essential information obtained and resume entry set in advance
Fast-growing becomes the biographic information corresponding with job hunter.The resume entry that the present embodiment is preset at least includes name, contact method, work
Post, work industry, but be not limited to aforementioned four, such as can also include sex, the age, learning experiences, project experience,
Training experience etc..
The present embodiment is by default resume entry, and obtains the information corresponding with resume entry from essential information, believes as resume
Breath, it is possible to obtain the job hunting demand presented with biographic information form, facilitates advertising unit to check.Additionally, the present embodiment by from
Information corresponding to resume entry that obtains in essential information and preset and generate biographic information, it is not necessary to job hunter manually fills in resume,
Save the time manually filling in and delivering resume in a large number, improve job hunting efficiency.
Alternatively, the advertising unit mated with the biographic information of job hunter is obtained, it is thus achieved that recruitment matching unit includes:
Web crawler is utilized to search for the recruitment requirement obtaining the advertising unit issuing recruitment needs on the internet；
According to default keyword extraction item, from biographic information, extract the first keyword sequence and from recruitment requires, extract second
Keyword sequence；
Calculate the similarity between the first keyword sequence and the second keyword sequence；
Choose the advertising unit corresponding more than the second keyword sequence corresponding to similarity presetting similarity threshold as with job hunter
Biographic information coupling advertising unit.
The advertising unit mated for the biographic information obtained accurately with job hunter, and more accurately the resume of job hunter is believed
Breath be delivered to suitable advertising unit, the present embodiment first predetermined keyword extract item, then according to keyword extraction item respectively from
Extract the first keyword sequence and the second keyword sequence in biographic information and in recruitment requirement, calculate the two key word the most again
Similarity between sequence, and it is corresponding finally to choose second keyword sequence corresponding more than the similarity presetting similarity threshold
Advertising unit is as the advertising unit mated with the biographic information of job hunter.
The keyword extraction item that the present embodiment is preset can include one, it is also possible to includes multinomial.Such as, preset when the present embodiment
Keyword extraction item when including three, be work position, work industry, job site respectively, then can use regular expressions
The content corresponding with three keyword extraction items is extracted or matched to formula from biographic information and recruitment require.Assume the present embodiment
According to default keyword extraction item, the first keyword sequence extracted from biographic information is { cosmetologist, beauty treatment, Changsha }, and
According to default keyword extraction item, the second keyword sequence extracted from the recruitment of A advertising unit requires is { make up artist, U.S.
Holding, Changsha, the second keyword sequence extracted from the recruitment of B advertising unit requires is { mechanical engineer, machinery, Beijing },
It is readily seen and more mates with biographic information with the recruitment requirement in A advertising unit.
In actual implementation process, the present embodiment can quantitatively obtain the first keyword sequence by the method for Similarity Measure
And the similarity that second between keyword sequence.Specifically, first the first and second keyword sequences are converted to vector form,
Then the similarity between the first keyword sequence and the second keyword sequence is obtained by two vectorial included angle cosine values of calculating,
Concrete computing formula is:Wherein, X, Y represent vector X and vector Y respectively.Cos θ's
Span is [0,1], when cos θ is closer to 1, then it represents that the similarity between two vectors is the highest, otherwise, cos θ value
Closer to 0, then it represents that similarity is the lowest.
In order to obtain the advertising unit more mated relative with the biographic information of job hunter, the present embodiment can calculate the first key
After similarity between word sequence and the second keyword sequence, choose second pass corresponding more than the similarity presetting similarity threshold
The advertising unit that keyword sequence pair is answered is as the advertising unit mated with the biographic information of job hunter.
It should be noted that in concrete implementation process, the present embodiment utilizes web crawler to search for acquisition on the internet
When the recruitment of the advertising unit issuing recruitment needs requires, can first obtain the work position in biographic information and/or work industry pair
The content answered, as search key word, then scans for further according to the search key word obtained on the internet, so can be big
The big speed improving search and efficiency；Further, the present embodiment can also be according to the search key word determined only in the trick of specialty
Engage and scan on platform website, such as the recruitment of intelligence connection, 51job etc., thus obtain more effective Search Results.
Alternatively, biographic information is sent to recruit matching unit include:
Obtain recruitment matching unit for receiving the electronic receipt address of biographic information；
Biographic information is sent to electronic receipt address.
Due to most advertising unit issue recruitment require time all can have for job hunter send job seeker resume for receiving resume
The electronic receipt address of information, the present embodiment can extract advertising unit by coupling or employing regular expression and be used for receiving resume
The electronic receipt address of information, is sent to electronic receipt address the most again by biographic information.Specifically, the electronics in the present embodiment
The form receiving address can be telephone number, E-mail address, instant messaging account etc..
Alternatively, resume entry at least includes: name, contact method, work position, work industry.
In order to allow advertising unit's job hunting demand compared with Overall Acquisition job hunter, the resume entry in the present embodiment at least includes name, connection
It is mode, work position, work industry message.But in concrete implementation process, it is not limited to only including above-mentioned resume entry,
Specifically can be by User Defined.
Simplify embodiment below for two and the present invention is realized the process of the automatic method for pushing of job hunting demand and principle more enters one
Step explanation.
Simplify embodiment one
With reference to Fig. 2, the present embodiment realizes the method that job hunting demand pushes automatically and includes:
Step S201, whether monitoring job hunter has leaving office operation in the collaborative office system that it is residing, the most then in advance
The essential information obtaining job hunter in the data base storing job hunter's archives first defined.
Specifically, present embodiment assumes that monitoring job hunter has leaving office operation in the collaborative office system that it is residing, then exist
The predefined data base for storing job hunter's archives obtains the essential information of job hunter.In actual implementation process,
The initiation monitored can be left office application operation as operation of leaving office by the present embodiment, it is also possible to application of the agreement monitored being left office
Operation as leave office operation, it is also possible to using monitor from initiate leave office application to agree to leaving office application process end operation as from
Duty operates.
Step S202, presets resume entry.
Specifically, valuable in order to obtain from the essential information of job hunter, for representing the information of job hunting demand, this enforcement
Example presets resume entry, and obtains biographic information according to resume entry.Specifically, the resume entry that the present embodiment is preset at least is wrapped
Include name, contact method, work position, work industry, job site.
Step S203, obtains the information corresponding with resume entry, as biographic information from essential information.
Specifically, present embodiment assumes that according to the resume entry preset, it is thus achieved that the biographic information of job hunter is: name: Zhang San；
Contact method: 133456789；Work position: cosmetologist；Work industry: beauty industry；Job site: Changsha.
Step S204, utilizes web crawler to search for the recruitment requirement obtaining the advertising unit issuing recruitment needs on the internet.
Specifically, present embodiment assumes that the advertising unit of search acquisition issue recruitment needs is two from the Internet, is respectively and recruits
Engage unit A and advertising unit B.It should be noted that in actual implementation process, from the Internet, search obtains to issue and recruits
The advertising unit engaging demand may run far deeper than two, additionally, the present embodiment is in order to reduce Search Results scope and get rid of uncorrelated
Search Results, can use relevant information in biographic information as search key word, such as with " cosmetologist " or " beauty treatment "
The advertising unit obtaining issue recruitment needs is searched on the internet Deng search key word.
Step S205, according to default keyword extraction item, extracts the first keyword sequence and from recruitment requirement from biographic information
Middle extraction the second keyword sequence.
Specifically, the keyword extraction item that the present embodiment is preset is assumed to be three, is work position, work industry, work respectively
Place, and assume from biographic information according to the first keyword sequence that obtains of keyword extraction item preset for cosmetologist, beauty treatment,
Changsha }, the second keyword sequence obtained according to the keyword extraction item preset from the recruitment of advertising unit A requires is { to make up
Teacher, beauty treatment, Changsha }, the second crucial word order obtained according to the keyword extraction item preset from the recruitment of advertising unit B requires
It is classified as { mechanical engineer, machinery, Beijing }.
Step S206, calculates the similarity between the first keyword sequence and the second keyword sequence.
Specifically, first the first keyword sequence and the second keyword sequence are converted to vector form by the present embodiment, then lead to
Cross two vectorial included angle cosine values of calculating and obtain the similarity between the first keyword sequence and the second keyword sequence, concrete
Computing formula is:Wherein, X, Y represent vector X and vector Y respectively.Specifically, this enforcement
Official holiday sets similarity that the recruitment of the biographic information of job hunter and advertising unit A requires as 0.7, the biographic information of job hunter and recruitment
The similarity that the recruitment of unit A requires is 0.2.
Step S207, chooses advertising unit's conduct that second keyword sequence corresponding more than the similarity presetting similarity threshold is corresponding
The advertising unit mated with the biographic information of job hunter.
Specifically, it is assumed that the similarity threshold preset is 0.5, then the present embodiment only chooses the similarity the second pass more than 0.5 correspondence
The advertising unit that keyword sequence pair is answered is as the advertising unit mated with the biographic information of job hunter, as recruitment matching unit, also
I.e. the present embodiment using advertising unit A as recruitment matching unit.
Step S208, is sent to biographic information recruit matching unit.
Specifically, the present embodiment first obtain recruitment matching unit for receiving the electronic receipt address of biographic information, then by letter
The information of going through is sent to electronic receipt address.
The present embodiment utilizes the leaving office Action Events in collaborative office system as the triggering bar pushing job hunting demand relatively newly
Part, it is achieved that just its job hunting demand is automatically transmitted to when monitoring job hunter and leaving office the advertising unit being suitable for, not only facilitates
Job hunter is more rapid finds applicable work position, and is conducive to recruitment side to know the job hunting demand of job hunter earlier, thus carries
High job hunting or the efficiency of recruitment, it is achieved that job hunter is docked with the good of advertising unit, to alleviation social labor employment pressure also
Play positive role.
Simplify embodiment two
With reference to Fig. 3, the present embodiment realizes the method that job hunting demand pushes automatically and includes:
Step S301, presets leaving office attributes entries.
Specifically, present embodiment assumes that the leaving office attributes entries of setting includes 6, respectively history chat data entry, work
Performance entry, job tenure entry, income level entry, working distance entry, login recruitment and job hunting net frequency entries.
Step S302, gathers the user behavior data corresponding with leaving office attributes entries of training sample, and wherein, training sample includes
Turnover intention person and the training sample without turnover intention person.
Specifically, the present embodiment is by gathering SMS historical record and/or the instant messaging historical record of training sample, it is thus achieved that
The user behavior data corresponding with history chat data entry of training sample.And assume the present embodiment gather except history chat number
User behavior data corresponding to other 5 leaving office attributes entries outside according to entry is the most as shown in table 1.
Table 1
| Leaving office attributes entries | The user behavior data gathered |
| Job performance | Medium |
| Job tenure | 3 years |
| Income level | 6K |
| Working distance | 15 kilometers |
| Log in recruitment and job hunting net frequency | 6 times/month |
Step S303, based on user behavior data, extracts the characteristic vector of training sample.Specifically, the present embodiment is based on user's row
For data, the characteristic vector extracting training sample includes:
Step S3031, use word frequency against text algorithm obtain the feature of the user behavior data corresponding with history chat data entry to
Amount.
Specifically, the present embodiment uses word frequency to obtain the user behavior data corresponding with history chat data entry against text algorithm
Characteristic vector specifically includes that the character that first user behavior data corresponding with history chat data entry be converted into text formatting
String, it is thus achieved that history chat text.Specifically, the user behavior corresponding with history chat data entry gathered due to the present embodiment
Data potentially include various ways, such as text, picture, video, audio frequency, voice etc., therefore chat with history getting
After the user behavior data that number is corresponding, first convert thereof into the character string of text formatting, thus be that subsequent extracted is chatted with history
The characteristic vector of the user behavior data that Data Entry is corresponding lays the foundation.
Then history chat text is carried out participle, semantic disambiguation, removes stop words operation, it is thus achieved that participle text.Concrete
In implementation process, the present embodiment carries out pretreatment to history chat text, thus obtains participle text, be not limited to only including participle,
Semantic disambiguation, removal stop words operation, such as, can also include the operations such as part-of-speech tagging.And the present embodiment is to history chat text
The method carrying out participle can use the multiple segmenting method such as maximum forward matching method or maximum reverse matching method.
Word frequency is finally used to obtain the weight of the participle text mated in participle text with the leaving office Feature Words preset against text algorithm
Value, and using weighted value as the characteristic vector of the user behavior data corresponding with history chat data entry.
Specifically, present embodiment assumes that the leaving office Feature Words list that pre-sets for " changing jobs ", " job hunting ", " recruitment ", " look for
Work ", " leaving office ", " resignation ", use word frequency to obtain in participle text against text algorithm and default leaving office Feature Words the most again
The weighted value of participle text of coupling, and using weighted value as the feature of the user behavior data corresponding with history chat data entry
Vector.Namely the present embodiment add up respectively the participle text corresponding with history chat text comprises in leaving office Feature Words list from
The weighted value of duty Feature Words, for example, it is assumed that the present embodiment statistics and history chat text TjCorresponding participle text comprises leaving office
The computing formula of the weighted value of Feature Words (" changing jobs ") is:
w(tk,Tj)=tf (tk,Tj)idf(tk),
Wherein w (tk,Tj) it is history chat text TjIn with preset leaving office Feature Words (" changing jobs ") tkThe participle text of coupling
Weighted value, tf (tk,Tj) it is tkIn history chat text TjIn word frequency number, namely history chat text TjMiddle appearance leaving office feature
The word frequency number that word " changes jobs "；Represent tkInverse text frequency in training set, N is instruction
Practice history chat text total number in sample, NKLeaving office Feature Words (" changing jobs ") is comprised for the history chat text in training sample
tkCount mesh one by one.According to above-mentioned formula, it is not difficult to calculate in history chat text and each spy that leaves office in leaving office Feature Words list
Levy the weighted value that word is the most corresponding, it is assumed that the present embodiment gets history chat text TjIn with leaving office Feature Words list for { " to change work
Make ", " job hunting ", " recruitment ", " looking for a job ", " leaving office ", " resignation " in leaving office Feature Words respectively correspondence weighted value be
w(t1,Tj)～w (t6,Tj), then the present embodiment is by { w (t1,Tj)、w(t2,Tj)、w(t3,Tj)、w(t4,Tj)、w(t5,Tj)、
w(t6,Tj) as training sample TjThe characteristic vector of the user behavior data corresponding with history chat data entry.
Step S3032, according to predefined mark rule, to other leaving office attributes entries pair in addition to history chat data entry
The user behavior data answered carries out quantitative identifying, it is thus achieved that the characteristic vector of the user behavior data that other leaving office attributes entries are corresponding.
Specifically, the present embodiment is for user behavior data corresponding to other leaving office attributes entries in addition to history chat data entry
Carry out the mark rule of quantitative identifying by User Defined.In order to unify quantitative identifying scope, the present embodiment will be for user behavior
Data carry out the scope of quantitative identifying and are arranged between scope 0-100, referring in particular to table 2.
Table 2
According to table 2, present embodiment assumes that the user behavior data obtained for table 1 obtains after carrying out quantitative identifying chats except history
The ident value of the user behavior data that five leaving office attributes entries outside Data Entry are corresponding is respectively { 50,95,65,59,70}.Namely this
Embodiment get with in addition to history chat data entry five leaving office attributes entries (job performance entry, job tenure entry,
Income level entry, working distance entry, logging in recruitment and job hunting net frequency entries) ident value of corresponding user behavior data divides
Wei { 50,95,65,59,70}.
Step S3033, according to characteristic vector and other leaving office attributes of the user behavior data corresponding with history chat data entry
The characteristic vector of the user behavior data that entry is corresponding, it is thus achieved that the characteristic vector of training sample.
According to step S3031, the characteristic vector of the user behavior data that the present embodiment obtains for history chat data entry
For W={w (t1,Tj)、w(t2,Tj)、w(t3,Tj)、w(t4,Tj)、w(t5,Tj)、w(t6,Tj), and for job performance bar
User's row that mesh, job tenure entry, income level entry, working distance entry, login recruitment and job hunting net frequency entries obtain
Characteristic vector for data is respectively { 50}, { 95}, { 65}, { 59}, { 70}.Therefore the present embodiment uses the side that " 0 " fills
Method will be for job performance entry, job tenure entry, income level entry, working distance entry, login recruitment and job hunting net frequency
The dimension of the characteristic vector of the user behavior data that rate entry obtains extends to the user obtained for history chat data entry respectively
The dimension of the characteristic vector of behavioral data, namely will be less than the characteristic vector of 6 DOF, the method all using " 0 " to fill is expanded
To 6 DOF, thus the characteristic vector that finally can obtain training sample is 6*6 dimension.
Step S304, trains grader according to characteristic vector, it is thus achieved that leaving office forecast model.
Specifically, it is assumed that the training sample sum of the present embodiment is N, the most respectively by the characteristic vector input point of each training sample
Class device is trained, thus obtains leaving office forecast model, it should be noted that in order to obtain of a relatively high classification accuracy and prediction
Precision, the quantity of the training sample that the present embodiment is chosen should be tried one's best greatly.
Step S305, according to leaving office forecast model, determines whether job hunter has turnover intention, the most then predefined for
The data base of storage job hunter's archives obtains the essential information of job hunter.
Specifically, present embodiment assumes that according to leaving office forecast model, it was predicted that going out job hunter has turnover intention, then in predefined use
The essential information of job hunter is obtained in the data base of storage job hunter's archives.
Step S306, generates the biographic information corresponding with job hunter according to essential information.
Specifically, first the present embodiment presets resume entry, then obtains the information corresponding with resume entry from essential information, makees
For biographic information.The biographic information assuming the job hunter that the present embodiment obtains is: name: Zhang San；Contact method: 133456789；
Work position: cosmetologist；Work industry: beauty industry；Job site: Changsha.
Step S307, obtains the advertising unit mated with the biographic information of job hunter, it is thus achieved that recruitment matching unit.
Specifically, the present embodiment can use the method for Similarity Measure or take the advertising unit that the biographic information with job hunter mates,
Specifically can refer to simplify the computational methods in embodiment one.
Step S308, is sent to biographic information recruit matching unit.
Whether the present embodiment has turnover intention by the leaving office forecast model prediction job hunter trained, and when by prediction mould of leaving office
Type dopes job hunter when having turnover intention, the job hunting demand of job hunter is just sent to the advertising unit being suitable for, not only facilitates
Job hunter is more rapid finds applicable work position, and is conducive to recruitment side just to know job hunter when job hunter has turnover intention
Job hunting demand, thus improve job hunting or the efficiency of recruitment, it is achieved that well docking, to alleviation of job hunter and advertising unit
Social labor employment pressure also functions to positive role.
With reference to Fig. 4, what the preferred embodiments of the present invention provided realizes the device that job hunting demand pushes automatically, including:
Turnover intention acquisition device 10, is used for monitoring whether job hunter leaves office or predict whether job hunter has turnover intention, if so,
In the predefined data base for storing job hunter's archives, then obtain the essential information of job hunter；
Biographic information generating means 20, for generating the biographic information corresponding with job hunter according to essential information；
Coalignment 30, for obtaining the advertising unit mated with the biographic information of job hunter, it is thus achieved that recruitment matching unit；
Dispensing device 40, for being sent to recruitment matching unit by biographic information.
Alternatively, turnover intention acquisition device 10 includes:
Monitoring device, for monitoring whether job hunter has leaving office operation in the collaborative office system that it is residing, the most then
Judge that job hunter leaves office.
Alternatively, turnover intention acquisition device 10 includes:
Preset device, be used for presetting leaving office attributes entries；
Harvester, for gathering the user behavior data corresponding with leaving office attributes entries of training sample, wherein, training sample bag
Include turnover intention person and the training sample without turnover intention person；
Extraction element, for based on user behavior data, extracting the characteristic vector of training sample；
Training devices, for training grader according to characteristic vector, it is thus achieved that leaving office forecast model；
Prediction means, for according to leaving office forecast model, determines whether job hunter has turnover intention.
The present embodiment realizes the specific works process of the device that job hunting demand pushes automatically and operation principle can refer to the reality of the present embodiment
The work process of the method that demand of now hunting for a job pushes automatically and operation principle.
These are only the preferred embodiments of the present invention, be not limited to the present invention, for a person skilled in the art,
The present invention can have various modifications and variations.All within the spirit and principles in the present invention, any amendment of being made, equivalent,
Improve, should be included within the scope of the present invention.
Claims (10)
1. one kind realizes the method that job hunting demand pushes automatically, it is characterised in that including:
Whether monitoring job hunter leaves office or predicts whether described job hunter has turnover intention, the most then obtain the essential information of described job hunter in the predefined data base for storing described job hunter's archives；
The biographic information corresponding with described job hunter is generated according to described essential information；
Obtain the advertising unit mated with the biographic information of described job hunter, it is thus achieved that recruitment matching unit；
Described biographic information is sent to described recruitment matching unit.
The method that realization job hunting demand the most according to claim 1 pushes automatically, it is characterised in that whether monitoring job hunter leaves office and include:
Monitor whether described job hunter has leaving office operation in the collaborative office system that it is residing, the most then judge that described job hunter leaves office.
The method that realization job hunting demand the most according to claim 1 pushes automatically, it is characterised in that predict whether described job hunter has turnover intention to include:
Preset leaving office attributes entries；
Gather the user behavior data corresponding with described leaving office attributes entries of training sample, wherein, described training sample includes turnover intention person and the training sample without turnover intention person;
Based on described user behavior data, extract the characteristic vector of described training sample；
Grader is trained, it is thus achieved that leaving office forecast model according to described characteristic vector；
According to described leaving office forecast model, determine whether described job hunter has turnover intention.
The method that realization job hunting demand the most according to claim 3 pushes automatically, it is characterised in that generate the biographic information corresponding with described job hunter according to described essential information and include:
Preset resume entry；
The information corresponding with described resume entry is obtained, as biographic information from described essential information.
The method that realization job hunting demand the most according to claim 4 pushes automatically, it is characterised in that obtain the advertising unit mated with the biographic information of described job hunter, it is thus achieved that recruitment matching unit includes:
Web crawler is utilized to search for the recruitment requirement obtaining the advertising unit issuing recruitment needs on the internet；
According to default keyword extraction item, from described biographic information, extract the first keyword sequence and extract the second keyword sequence from described recruitment requires；
Calculate the similarity between described first keyword sequence and described second keyword sequence；
Choose advertising unit corresponding to second keyword sequence corresponding more than the described similarity presetting similarity threshold as the advertising unit mated with the biographic information of described job hunter.
The method that realization job hunting demand the most according to claim 5 pushes automatically, it is characterised in that described biographic information is sent to described recruitment matching unit and includes:
Obtain described recruitment matching unit for receiving the electronic receipt address of described biographic information；
Described biographic information is sent to described electronic receipt address.
The method that realization job hunting demand the most according to claim 6 pushes automatically, it is characterised in that described resume entry at least includes:
Name, contact method, work position, work industry.
8. one kind realizes the device that job hunting demand pushes automatically, it is characterised in that
Turnover intention acquisition device, is used for monitoring whether job hunter leaves office or predict whether described job hunter has turnover intention, the most then obtain the essential information of described job hunter in the predefined data base for storing described job hunter's archives；
Biographic information generating means, for generating the biographic information corresponding with described job hunter according to described essential information；
Coalignment, for obtaining the advertising unit mated with the biographic information of described job hunter, it is thus achieved that recruitment matching unit；
Dispensing device, for being sent to described recruitment matching unit by described biographic information.
The device that realization job hunting demand the most according to claim 8 pushes automatically, it is characterised in that described turnover intention acquisition device includes:
Monitoring device, for monitoring whether described job hunter has leaving office operation in the collaborative office system that it is residing, the most then judges that described job hunter leaves office.
The device that realization job hunting demand the most according to claim 8 pushes automatically, it is characterised in that described turnover intention acquisition device includes:
Preset device, be used for presetting leaving office attributes entries；
Harvester, for gathering the user behavior data corresponding with described leaving office attributes entries of training sample, wherein, described training sample includes turnover intention person and the training sample without turnover intention person;
Extraction element, for based on described user behavior data, extracts the characteristic vector of described training sample；
Training devices, for training grader according to described characteristic vector, it is thus achieved that leaving office forecast model；
Prediction means, for according to described leaving office forecast model, determines whether described job hunter has turnover intention.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610298635.3A CN105894253A (en) | 2016-05-09 | 2016-05-09 | Method and device for automatic pushing of job application demand |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610298635.3A CN105894253A (en) | 2016-05-09 | 2016-05-09 | Method and device for automatic pushing of job application demand |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105894253A true CN105894253A (en) | 2016-08-24 |
Family
ID=56702456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610298635.3A Pending CN105894253A (en) | 2016-05-09 | 2016-05-09 | Method and device for automatic pushing of job application demand |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105894253A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022709A (en) * | 2016-05-09 | 2016-10-12 | 陈包容 | Method and apparatus for pushing job demands on the basis of enterprise cooperative office system |
| CN106205288A (en) * | 2016-09-23 | 2016-12-07 | 长沙军鸽软件有限公司 | A kind of implementation method training robot |
| CN106570683A (en) * | 2016-11-10 | 2017-04-19 | 刘勇 | Online recruitment system capable of pushing matched data bidirectionally for blue collar mainly |
| CN107562916A (en) * | 2017-09-12 | 2018-01-09 | 如皋福大工程技术研究院有限公司 | Information matching method and device |
| CN107656909A (en) * | 2017-10-30 | 2018-02-02 | 北京明朝万达科技股份有限公司 | A kind of Documents Similarity decision method and device based on document composite character |
| CN108055295A (en) * | 2017-11-29 | 2018-05-18 | 政和科技股份有限公司 | A kind of information-pushing method and equipment |
| CN108427758A (en) * | 2018-03-19 | 2018-08-21 | 深信服科技股份有限公司 | A kind of leaving office trend analysis method, apparatus, equipment and storage medium |
| CN108428096A (en) * | 2017-09-25 | 2018-08-21 | 平安科技（深圳）有限公司 | Electronic device, personnel to be released recommend method and computer readable storage medium |
| CN108805523A (en) * | 2018-05-24 | 2018-11-13 | 佛山市轻遣网络有限公司 | It is a kind of can Auto-matching work network recruitment system and method |
| CN109559093A (en) * | 2018-11-16 | 2019-04-02 | 合肥风聘网络科技有限公司 | An a kind of key delivery system that integrating multi-platform recruitment information convenient for hunter |
| 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 |
| CN110298622A (en) * | 2018-03-23 | 2019-10-01 | 周元如 | Function selects ability method and system |
| CN110414910A (en) * | 2019-06-06 | 2019-11-05 | 万马奔腾(上海)数据有限公司 | Based on big data artificial intelligence analysis, recruitment and job hunting system |
| CN110533562A (en) * | 2019-09-04 | 2019-12-03 | 胡帮贵 | Talent's channel and internet data shared system |
| CN111798059A (en) * | 2020-07-10 | 2020-10-20 | 河北冀联人力资源服务集团有限公司 | System and method for predicting job leaving |
| CN112257777A (en) * | 2020-10-21 | 2021-01-22 | 平安科技（深圳）有限公司 | Off-job prediction method based on hidden Markov model and related device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070088640A1 (en) * | 2002-04-05 | 2007-04-19 | Shogo Hyakutake | System, computer program product and method for managing documents |
| CN104573998A (en) * | 2015-01-30 | 2015-04-29 | 薛晔伟 | Application data processing method and device |
| CN105117863A (en) * | 2015-09-28 | 2015-12-02 | 北京橙鑫数据科技有限公司 | Resume position matching method and device |
-
2016
- 2016-05-09 CN CN201610298635.3A patent/CN105894253A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070088640A1 (en) * | 2002-04-05 | 2007-04-19 | Shogo Hyakutake | System, computer program product and method for managing documents |
| CN104573998A (en) * | 2015-01-30 | 2015-04-29 | 薛晔伟 | Application data processing method and device |
| CN105117863A (en) * | 2015-09-28 | 2015-12-02 | 北京橙鑫数据科技有限公司 | Resume position matching method and device |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022709A (en) * | 2016-05-09 | 2016-10-12 | 陈包容 | Method and apparatus for pushing job demands on the basis of enterprise cooperative office system |
| CN106205288A (en) * | 2016-09-23 | 2016-12-07 | 长沙军鸽软件有限公司 | A kind of implementation method training robot |
| CN106570683A (en) * | 2016-11-10 | 2017-04-19 | 刘勇 | Online recruitment system capable of pushing matched data bidirectionally for blue collar mainly |
| CN107562916A (en) * | 2017-09-12 | 2018-01-09 | 如皋福大工程技术研究院有限公司 | Information matching method and device |
| WO2019056708A1 (en) * | 2017-09-25 | 2019-03-28 | 平安科技（深圳）有限公司 | Electronic device, method for recommending re-use of previously contracted personnel, and computer readable storage medium |
| CN108428096A (en) * | 2017-09-25 | 2018-08-21 | 平安科技（深圳）有限公司 | Electronic device, personnel to be released recommend method and computer readable storage medium |
| CN107656909A (en) * | 2017-10-30 | 2018-02-02 | 北京明朝万达科技股份有限公司 | A kind of Documents Similarity decision method and device based on document composite character |
| CN108055295A (en) * | 2017-11-29 | 2018-05-18 | 政和科技股份有限公司 | A kind of information-pushing method and equipment |
| CN108427758A (en) * | 2018-03-19 | 2018-08-21 | 深信服科技股份有限公司 | A kind of leaving office trend analysis method, apparatus, equipment and storage medium |
| CN110298622A (en) * | 2018-03-23 | 2019-10-01 | 周元如 | Function selects ability method and system |
| CN108805523A (en) * | 2018-05-24 | 2018-11-13 | 佛山市轻遣网络有限公司 | It is a kind of can Auto-matching work network recruitment system and method |
| CN109559093A (en) * | 2018-11-16 | 2019-04-02 | 合肥风聘网络科技有限公司 | An a kind of key delivery system that integrating multi-platform recruitment information convenient for hunter |
| 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 |
| CN110414910A (en) * | 2019-06-06 | 2019-11-05 | 万马奔腾(上海)数据有限公司 | Based on big data artificial intelligence analysis, recruitment and job hunting system |
| CN110533562A (en) * | 2019-09-04 | 2019-12-03 | 胡帮贵 | Talent's channel and internet data shared system |
| CN111798059A (en) * | 2020-07-10 | 2020-10-20 | 河北冀联人力资源服务集团有限公司 | System and method for predicting job leaving |
| CN111798059B (en) * | 2020-07-10 | 2023-11-24 | 河北冀联人力资源服务集团有限公司 | Off-duty prediction system and method |
| CN112257777A (en) * | 2020-10-21 | 2021-01-22 | 平安科技（深圳）有限公司 | Off-job prediction method based on hidden Markov model and related device |
| CN112257777B (en) * | 2020-10-21 | 2023-09-05 | 平安科技（深圳）有限公司 | Off-duty prediction method and related device based on hidden Markov model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105894253A (en) | Method and device for automatic pushing of job application demand | |
| CN105488092B (en) | A kind of time-sensitive and adaptive sub-topic online test method and system | |
| CN104951539B (en) | Internet data center's harmful information monitoring system | |
| CN105138670B (en) | Audio file label generating method and system | |
| Kherwa et al. | An approach towards comprehensive sentimental data analysis and opinion mining | |
| CN108776671A (en) | A kind of network public sentiment monitoring system and method | |
| CN104899324B (en) | One kind monitoring systematic sample training system based on IDC harmful informations | |
| Joho et al. | Overview of NTCIR-11 Temporal Information Access (Temporalia) Task. | |
| CN102117323A (en) | Job seeker resume recommendation processing method and system | |
| US20180060426A1 (en) | Systems and methods for issue management | |
| CN102270212A (en) | User interest feature extraction method based on hidden semi-Markov model | |
| CN106155817A (en) | Business information processing method, server and system | |
| CN109978020A (en) | A kind of social networks account vest identity identification method based on multidimensional characteristic | |
| CN105893484A (en) | Microblog Spammer recognition method based on text characteristics and behavior characteristics | |
| Chamberlain | Groupsourcing: Distributed problem solving using social networks | |
| CN107918644A (en) | News subject under discussion analysis method and implementation system in reputation Governance framework | |
| WO2021210992A9 (en) | Systems and methods for determining entity attribute representations | |
| CN106022709A (en) | Method and apparatus for pushing job demands on the basis of enterprise cooperative office system | |
| CN110019703A (en) | Data markers method and device, intelligent answer method and system | |
| CN107085568A (en) | A kind of text similarity method of discrimination and device | |
| CN105589916B (en) | Method for extracting explicit and implicit interest knowledge | |
| CN110084373A (en) | Information processing method, device, computer readable storage medium and computer equipment | |
| CN105279191A (en) | Potential user mining method based on network data analysis | |
| Wu et al. | Sub-event discovery and retrieval during natural hazards on social media data | |
| CN106777124B (en) | Semantic knowledge method, apparatus and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160824 |
|
| RJ01 | Rejection of invention patent application after publication |