CN110032637A - A kind of resume intelligent recommendation algorithm based on natural semantic analysis technology - Google Patents
A kind of resume intelligent recommendation algorithm based on natural semantic analysis technology Download PDFInfo
- Publication number
- CN110032637A CN110032637A CN201910302296.5A CN201910302296A CN110032637A CN 110032637 A CN110032637 A CN 110032637A CN 201910302296 A CN201910302296 A CN 201910302296A CN 110032637 A CN110032637 A CN 110032637A
- Authority
- CN
- China
- Prior art keywords
- resume
- information
- data
- job
- recommendation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of resume intelligent recommendation algorithm based on natural semantic analysis technology, the present invention is based on the delivery of cloud recruitment platform magnanimity, screening, interviews, enters official rank user behavior data, design the matching proposed algorithm of resume, position, it can recommend suitable resume or position automatically according to the algorithm for recruitment side and job hunter, to improve the efficiency of E-Recruit, job hunting；Traditional proposed algorithm, it is based on commending contents, recommended based on hobby, and the underlying factors such as some industries, company are added based on the combination that the two cooperates in algorithm of the invention simultaneously, make every effort to accurate, quick recommendation, it is advantageous that being based on cloud recruitment platform, platform has precipitated the recruitment behavioral data of several hundred million meters, proposed algorithm is based not only on the matching degree in post itself, also based on the preference of user behavior, after recommendation, according to the processing result of user, recommender system is fed back to, recommender system learns data model again, so that accuracy is higher and higher.
Description
Technical field
The present invention relates to the related fields of biographic information retrieval, specially a kind of resumes based on natural semantic analysis technology
Intelligent recommendation algorithm.
Background technique
How with the continuous aggravation of talent competition between enterprise, in reasonable budget limitations the talent is found faster more quasi-ly,
The subject under discussion that enterprise more pays close attention to and the significant challenge that drainage of human resources department (HR) faces are had become, in these challenges,
Comparing significant pain spot includes: a. the understanding to recruitment needs: for enterprise HR, promoting recruitment performance, primary task
Seek to the recruitment needs of energy profound understanding employment department, the HR of different background, different experiences, often in the understanding of recruitment needs
On have differences, and if demand understands not in place, not only waste the resume selection time of HR, while can also waste employment department
The interview time, and then reduce employment department to the recruitment satisfaction of HR.B. resume selection consumes the HR plenty of time: recruiting
Cheng Zhong, the HR a large amount of time are all flowers in resume selection, artificial screening resume, and resume is averaged percent of pass 20% or so, this anticipates
Taste 100 parts of resumes of browsing, it is possible to only 20 parts are suitable, and this 20 parts of suitable resumes, and after carrying out telephonic communication, having can
Can only have 5 candidates to be ready to receive interview, practical perhaps there was only 2-3 people to face, such recruitment funnel makes HR daily
Have to have to run around all the time wears him out the constantly a large amount of screening resumes in ground, and enough energy cannot be put into relatively accurately on talent discerning.
C. the talent bank of enterprise itself cannot use well: enterprise has accumulated a large amount of by screening, leaving in recruitment
The resume of evaluation is interviewed, wherein many resume Post Match Degrees are higher, but because a variety of causes does not receive Offer, with
The continuous promotion of the development of enterprise and candidate's experience, the resume in talent bank is an important recruitment channel source in fact,
But due to lacking efficient technological means, the energy of enterprise HR can only substantially take the letter newly obtained from major recruitment channel into account
It goes through, and the enterprise's talent bank being more worth cannot be efficiently used.
By analyzing above, that recruits at present is inefficient, and main cause cannot match well in candidate and enterprise
, job hunter needs to deliver position in different recruitment websites, and identical position has louver on several ten, substantially due to information
Identical, candidate is in order to save trouble, therefore resume " throwing in sea ", and then " mass-election ", both sides are time-consuming and laborious, inefficiency by company HR.
Summary of the invention
The purpose of the present invention is to provide a kind of resume intelligent recommendation algorithm based on natural semantic analysis technology, to solve
The problems mentioned above in the background art.
To achieve the above object, the invention provides the following technical scheme: a kind of resume based on natural semantic analysis technology
Intelligent recommendation algorithm, including following algorithm steps:
Base data platform: building Base data platform involved by position, resume, the lasting industry by position, resume,
The maintenances of information such as company, standard position title, school, profession, language, technical ability, specialized vocabulary enter in platform, to establish
Perfect position model and resume model；
Job data analysis: on the basis of position model abundant and resume model, pass through the essential information of parsing publication position
With JD content, intelligent extraction goes out position various information keyword, and position is decomposed into job information keyword by big data
Various demand conditions, system then carry out algorithm recommendation according to these position conditions；
Resume data analysis: on the basis of position model abundant and resume model, by parsing candidate's biographic information, intelligence
Resume various information keyword is extracted, resume is decomposed by biographic information keyword by various demand conditions by big data,
System then carries out algorithm recommendation according to these resume conditions；
Proposed algorithm: on the basis of position model abundant and resume model, pass through the essential information and JD of parsing publication position
Content, intelligent extraction go out position various information keyword, recommend to meet out according to the position or resume demand condition that parse
The resume or position of condition, and can be inclined according to the priority condition of position or resume, the weight of each priority condition, enterprises recruit persons for jobs
Good resume or position to recommendation carries out matching degree calculating, and passes through screening according to enterprise using big data digging technology, passes through
It interviews, send offer, the data foundation for entering official rank and optimization enterprises recruit persons for jobs preference portrait, recommend according to matching degree height is successive
Resume or position；
Resume is recommended: supporting enterprise customer to view the biographic information to match with position according to position in system background, filters
Fall unmatched biographic information, and resume sorts from high to low according to matching degree, more can efficiently view and more meet demand
Resume；
Position is recommended: candidate can be supported to view the job information for meeting oneself application and requiring on system foreground, filtered out
Incongruent job information, and position sorts from high to low according to matching degree, more can efficiently apply for the position more met.
Preferably, the Base data platform is high-performance high scalability database, to store the resume data of magnanimity,
Job data, behavioral data, the Base data platform is established improve after subsequent job data analysis, the analysis of resume data and
Proposed algorithm just can be carried out, data source of the Base data platform as big data technology, various each by machine learning
The job information of sample is established with biographic information and optimizes position model and resume model, especially believes from job requirements and resume
Extract valuable analysis data in being not fixed in text in breath and the data such as continually changing enterprise and industry, as
The basic data matched, in the above process, machine learning is gradually decreased by technologies such as meaning of a word similarity analysis in NLP technology
The manpower intervention ratio of tag library building, gradually by machine automatic identification key term and extracts JD and resume label, is aided with people
Work optimizes label, until the later period realizes the building of full-automatic tag library substantially.
Preferably, the various demand conditions in the job data analysis include job site condition, academic condition, work
Time limit condition, system then carry out algorithm recommendation according to these position conditions.
Preferably, the various demand conditions in the resume data analysis include existing residence, expectation job site, expectation
Wages, expectation industry, educational background, length of service, system then carry out algorithm recommendation according to these resume conditions.
Preferably, it is applied to resume intelligent recommendation module in the resume recommendation, the resume intelligent recommendation module includes
With position resume function matching module, resume necessary condition filtering module, resume priority condition bonus point module and resume matching degree
Four parts of computing module.
Preferably, the detailed process of the resume intelligent recommendation module are as follows: in position model abundant and resume model base
On plinth, system firstly the need of to resume information intelligent analysis extract resume in as the age, educational background, the length of service, work pass through
It goes through, it is expected the key messages such as job site, Expectant salary, technical ability, further according to the key message and publication duty extracted in resume
The necessary condition of position is matched, and resume is recommended user if matching, is not recommended if mismatching, further according to extraction
The key message in resume is matched with the necessary condition of publication position out, resume is recommended user if matching, such as
Fruit, which mismatches, does not recommend then, the information for meeting the resume of position necessary condition is matched with the priority condition of position again, root
Bonus point is carried out to resume according to the bonus point weight of each condition, the matching degree of resume is calculated by last score, enterprise is supported to use
Family views the biographic information to match with position in system background according to position, filters out unmatched biographic information, and
Resume sorts from high to low according to matching degree, and rationale for the recommendation is shown in biographic information, i.e., the letter of job requirement is matched in resume
Breath, allows enterprise that can more efficiently view the resume for more meeting demand.
Preferably, it is applied to position intelligent analysis module in the position recommendation, the position intelligent analysis module includes
Two parts of position JD intelligent analysis module and position basic condition analysis module.
Preferably, the detailed process of the position intelligent analysis module are as follows: firstly, it is necessary to establish Base data platform and lead to
The various job informations of machine learning and biographic information are crossed to establish and optimize position model and resume model, especially from
It is extracted in being not fixed in text in job requirements and biographic information and the data such as continually changing enterprise and industry valuable
Analysis data as matched basic data；Secondly, on the basis of position model abundant and resume model, by hair
The essential information of cloth position and JD information carry out intellectual analysis, extract in position as position title, job site, educational requirement,
Wages range, length of service requirement, age requirement, professional requirement, smi request, household register requirement, affiliated industry, skill requirement etc.
Key message；Then, the decomposition that the basic condition of position is carried out according to the position key message extracted, includes necessary condition
With the decomposition of priority condition.
Preferably, the necessary condition is the job requirement information that the resume recommended has to satisfaction, and the preferential item
Part be then meet job requirement can to recommend resume carry out bonus point information.
Compared with prior art, the beneficial effects of the present invention are: the present invention is based on the deliveries of cloud recruitment platform magnanimity, sieve
It selects, interview, entering official rank user behavior data, designing the matching proposed algorithm of resume, position, can be automatically according to the algorithm
Recruitment side and job hunter recommend suitable resume or position, to improve the efficiency of E-Recruit, job hunting；Traditional recommendation is calculated
Method or recommend based on commending contents or based on hobby, and algorithm of the invention is added simultaneously based on the combination that the two cooperates with
The underlying factors such as some industries, company make every effort to accurate, quick recommendation, it is advantageous that being based on cloud recruitment platform, platform is
Through having precipitated the recruitment behavioral data of several hundred million meters, proposed algorithm is based not only on the matching degree in post itself, is also based on user behavior
Preference, such as which type of data passed through screening, enters interview, and which data last registration is again, simultaneously
The intelligentized position demand for understanding enterprise again extracts effective, crucial word and is added on analysis, reject invalid information, recommends
Second step be the feedback based on recommendation results, after recommending, according to the processing result of user, feed back to recommender system,
Recommender system learns data model again, so that accuracy is higher and higher.
Detailed description of the invention
Fig. 1 is program circuit structural schematic diagram of the invention；
Fig. 2 is the modular structure schematic diagram of position intellectual analysis of the invention；
Fig. 3 is the modular structure schematic diagram of resume intelligent recommendation of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Fig. 1-3 is please referred to, the present invention provides a kind of technical solution: a kind of resume intelligence based on natural semantic analysis technology
Proposed algorithm, including following algorithm steps:
Base data platform: building Base data platform involved by position, resume, the lasting industry by position, resume,
The maintenances of information such as company, standard position title, school, profession, language, technical ability, specialized vocabulary enter in platform, to establish
Perfect position model and resume model；
Job data analysis: on the basis of position model abundant and resume model, pass through the essential information of parsing publication position
With JD content, intelligent extraction goes out position various information keyword, and position is decomposed into job information keyword by big data
Various demand conditions, system then carry out algorithm recommendation according to these position conditions；
Resume data analysis: on the basis of position model abundant and resume model, by parsing candidate's biographic information, intelligence
Resume various information keyword is extracted, resume is decomposed by biographic information keyword by various demand conditions by big data,
System then carries out algorithm recommendation according to these resume conditions；
Proposed algorithm: on the basis of position model abundant and resume model, pass through the essential information and JD of parsing publication position
Content, intelligent extraction go out position various information keyword, recommend to meet out according to the position or resume demand condition that parse
The resume or position of condition, and can be inclined according to the priority condition of position or resume, the weight of each priority condition, enterprises recruit persons for jobs
Good resume or position to recommendation carries out matching degree calculating, and passes through screening according to enterprise using big data digging technology, passes through
It interviews, send offer, the data foundation for entering official rank and optimization enterprises recruit persons for jobs preference portrait, recommend according to matching degree height is successive
Resume or position；
Resume is recommended: supporting enterprise customer to view the biographic information to match with position according to position in system background, filters
Fall unmatched biographic information, and resume sorts from high to low according to matching degree, more can efficiently view and more meet demand
Resume；
Position is recommended: candidate can be supported to view the job information for meeting oneself application and requiring on system foreground, filtered out
Incongruent job information, and position sorts from high to low according to matching degree, more can efficiently apply for the position more met.
Further, Base data platform is high-performance high scalability database, to store the resume data of magnanimity, duty
Position data, behavioral data, Base data platform, which is established, to be improved rear subsequent job data analysis, the analysis of resume data and recommends to calculate
Method just can be carried out, data source of the Base data platform as big data technology, be believed by the various positions of machine learning
Breath establishes and optimizes position model and resume model with biographic information, especially from not solid in job requirements and biographic information
Determine in text and the data such as continually changing enterprise and industry in extract valuable analysis data, as matched basic
Data, in the above process, machine learning gradually decreases tag library building by technologies such as meaning of a word similarity analysis in NLP technology
Manpower intervention ratio, gradually by machine automatic identification key term and extract JD and resume label, be aided with manually to label into
Row optimization, until the later period realizes the building of full-automatic tag library substantially.
Further, the various demand conditions in job data analysis include job site condition, academic condition, working year
Limit condition, system then carry out algorithm recommendation according to these position conditions.
Further, the various demand conditions in the analysis of resume data include existing residence, expectation job site, expectation firewood
Money, expectation industry, educational background, length of service, system then carry out algorithm recommendation according to these resume conditions.
Further, it is applied to resume intelligent recommendation module in resume recommendation, resume intelligent recommendation module includes same position
Resume function matching module, resume necessary condition filtering module, resume priority condition bonus point module and resume matching degree calculate mould
Four parts of block.
Further, the detailed process of resume intelligent recommendation module are as follows: in position model abundant and resume model basis
On, system firstly the need of to resume information intelligent analysis extract resume in as the age, educational background, the length of service, work experience,
It is expected that the key messages such as job site, Expectant salary, technical ability, further according to the key message and publication position extracted in resume
Necessary condition is matched, and resume recommended user if matching, is not recommended if mismatching, further according to extracting letter
Key message in going through is matched with the necessary condition of publication position, resume is recommended user if matching, if not
Matching is not recommended then, the information for meeting the resume of position necessary condition is matched with the priority condition of position again, according to every
The bonus point weight of a condition carries out bonus point to resume, and the matching degree of resume is calculated by last score, and enterprise customer is supported to exist
System background views the biographic information to match with position according to position, filters out unmatched biographic information, and resume
It is sorted from high to low according to matching degree, rationale for the recommendation is shown in biographic information, i.e., matched the information of job requirement in resume, allow
Enterprise can more efficiently view the resume for more meeting demand.
Further, it is applied to position intelligent analysis module in position recommendation, position intelligent analysis module includes position JD
Two parts of intelligent analysis module and position basic condition analysis module.
Further, the detailed process of position intelligent analysis module are as follows: firstly, it is necessary to establish Base data platform and pass through
The various job informations of machine learning and biographic information are established and optimize position model and resume model, especially from times
It is extracted in being not fixed in text in duty requirement and biographic information and the data such as continually changing enterprise and industry valuable
Data are analyzed as matched basic data；Secondly, on the basis of position model abundant and resume model, by publication
The essential information and JD information of position carry out intellectual analysis, extract in position such as position title, job site, educational requirement, firewood
Range, length of service requirement, age requirement, professional requirement, smi request, household register requirement, affiliated industry, skill requirement etc. is provided to close
Key information；Then, the decomposition that the basic condition of position is carried out according to the position key message that extracts includes necessary condition with
The decomposition of priority condition.
Further, necessary condition is that the resume recommended has to the job requirement information met, and priority condition is then
Meeting job requirement can be to the information for recommending resume to carry out bonus point.
It the present invention is based on the delivery of cloud recruitment platform magnanimity, screening, interviews, enter official rank user behavior data, design letter
It goes through, the matching proposed algorithm of position, suitable resume or position can be recommended automatically for recruitment side and job hunter according to the algorithm,
To improve the efficiency of E-Recruit, job hunting；Traditional proposed algorithm or recommend based on commending contents or based on hobby,
And the underlying factors such as some industries, company are added simultaneously in the combination that algorithm of the invention is cooperateed with based on the two, make every effort to precisely,
Quickly recommend, it is advantageous that being based on cloud recruitment platform, platform has precipitated the recruitment behavioral data of several hundred million meters, proposed algorithm
It is based not only on the matching degree in post itself, also based on the preference of user behavior, such as which type of data has passed through screening, enters
Interview, and which data last registration is again, while the intelligentized position demand for understanding enterprise again, has been extracted
Effect, crucial word are added on analysis, and rejecting invalid information, the second step of recommendation is the feedback based on recommendation results, when recommending it
Afterwards, according to the processing result of user, recommender system is fed back to, recommender system learns data model again, so that accuracy is more next
It is higher.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (9)
1. a kind of resume intelligent recommendation algorithm based on natural semantic analysis technology, it is characterised in that: including following algorithm steps:
Base data platform: building Base data platform involved by position, resume, the lasting industry by position, resume,
The maintenances of information such as company, standard position title, school, profession, language, technical ability, specialized vocabulary enter in platform, to establish
Perfect position model and resume model；
Job data analysis: on the basis of position model abundant and resume model, pass through the essential information of parsing publication position
With JD content, intelligent extraction goes out position various information keyword, and position is decomposed into job information keyword by big data
Various demand conditions, system then carry out algorithm recommendation according to these position conditions；
Resume data analysis: on the basis of position model abundant and resume model, by parsing candidate's biographic information, intelligence
Resume various information keyword is extracted, resume is decomposed by biographic information keyword by various demand conditions by big data,
System then carries out algorithm recommendation according to these resume conditions；
Proposed algorithm: on the basis of position model abundant and resume model, pass through the essential information and JD of parsing publication position
Content, intelligent extraction go out position various information keyword, recommend to meet out according to the position or resume demand condition that parse
The resume or position of condition, and can be inclined according to the priority condition of position or resume, the weight of each priority condition, enterprises recruit persons for jobs
Good resume or position to recommendation carries out matching degree calculating, and passes through screening according to enterprise using big data digging technology, passes through
It interviews, send offer, the data foundation for entering official rank and optimization enterprises recruit persons for jobs preference portrait, recommend according to matching degree height is successive
Resume or position；
Resume is recommended: supporting enterprise customer to view the biographic information to match with position according to position in system background, filters
Fall unmatched biographic information, and resume sorts from high to low according to matching degree, more can efficiently view and more meet demand
Resume；
Position is recommended: candidate can be supported to view the job information for meeting oneself application and requiring on system foreground, filtered out
Incongruent job information, and position sorts from high to low according to matching degree, more can efficiently apply for the position more met.
2. a kind of resume intelligent recommendation algorithm based on natural semantic analysis technology according to claim 1, feature exist
In: the Base data platform is high-performance high scalability database, to store the resume data of magnanimity, job data, row
For data, the Base data platform, which is established, improves rear subsequent job data analysis, the analysis of resume data and proposed algorithm
It can be carried out, data source of the Base data platform as big data technology, believed by the various positions of machine learning
Breath establishes and optimizes position model and resume model with biographic information, especially from not solid in job requirements and biographic information
Determine in text and the data such as continually changing enterprise and industry in extract valuable analysis data, as matched basic
Data, in the above process, machine learning gradually decreases tag library building by technologies such as meaning of a word similarity analysis in NLP technology
Manpower intervention ratio, gradually by machine automatic identification key term and extract JD and resume label, be aided with manually to label into
Row optimization, until the later period realizes the building of full-automatic tag library substantially.
3. a kind of resume intelligent recommendation algorithm based on natural semantic analysis technology according to claim 1, feature exist
In: the various demand conditions in the job data analysis include job site condition, academic condition, length of service condition, are
System then carries out algorithm recommendation according to these position conditions.
4. a kind of resume intelligent recommendation algorithm based on natural semantic analysis technology according to claim 1, feature exist
In: the various demand conditions in the resume data analysis include existing residence, expectation job site, Expectant salary, desired row
Industry, educational background, length of service, system then carry out algorithm recommendation according to these resume conditions.
5. a kind of resume intelligent recommendation algorithm based on natural semantic analysis technology according to claim 1, feature exist
In: it is applied to resume intelligent recommendation module in the resume recommendation, the resume intelligent recommendation module includes same position resume duty
It can matching module, resume necessary condition filtering module, resume priority condition bonus point module and resume matching degree computing module four
Part.
6. a kind of resume intelligent recommendation algorithm based on natural semantic analysis technology according to claim 5, feature exist
In: the detailed process of the resume intelligent recommendation module are as follows: on the basis of position model abundant and resume model, system is first
Need to extract the analysis of the information intelligent of resume in resume such as age, educational background, length of service, work experience, expectation place of working
The key messages such as point, Expectant salary, technical ability, further according to the necessary condition of the key message that extracts in resume and publication position into
Row matching, recommends user for resume if matching, does not recommend if mismatching, further according to the key extracted in resume
Information is matched with the necessary condition of publication position, and resume is recommended user if matching, is not pushed away if mismatching
It recommends, the information for meeting the resume of position necessary condition is matched with the priority condition of position again, according to adding for each condition
Fraction carries out bonus point to resume again, and the matching degree of resume is calculated by last score, supports enterprise customer in system background root
The biographic information to match with position is viewed according to position, filters out unmatched biographic information, and resume is according to matching degree
It sorts from high to low, rationale for the recommendation is shown in biographic information, i.e., match the information of job requirement in resume, allow enterprise can be faster
Prompt views the resume for more meeting demand.
7. a kind of resume intelligent recommendation algorithm based on natural semantic analysis technology according to claim 1, feature exist
In: position intelligent analysis module is applied in the position recommendation, the position intelligent analysis module includes that position JD intelligently divides
Analyse two parts of module and position basic condition analysis module.
8. a kind of resume intelligent recommendation algorithm based on natural semantic analysis technology according to claim 7, feature exist
In the detailed process of the position intelligent analysis module are as follows: firstly, it is necessary to establish Base data platform and each by machine learning
The job information of kind various kinds is established with biographic information and optimizes position model and resume model, especially from job requirements and letter
It goes through in being not fixed in text in information and the data such as continually changing enterprise and industry and extracts valuable analysis data work
For matched basic data；Secondly, on the basis of position model abundant and resume model, by the basic of publication position
Information and JD information carry out intellectual analysis, extract in position such as position title, job site, educational requirement, wages range, work
The key messages such as time limit requirement, age requirement, professional requirement, smi request, household register requirement, affiliated industry, skill requirement；So
Afterwards, the decomposition that the basic condition of position is carried out according to the position key message extracted, includes necessary condition and priority condition
Decomposition.
9. a kind of resume intelligent recommendation algorithm based on natural semantic analysis technology according to claim 8, feature exist
In: the necessary condition is that the resume recommended has to the job requirement information met, and the priority condition is then to meet duty
Position requirement can be to the information for recommending resume to carry out bonus point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910302296.5A CN110032637A (en) | 2019-04-16 | 2019-04-16 | A kind of resume intelligent recommendation algorithm based on natural semantic analysis technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910302296.5A CN110032637A (en) | 2019-04-16 | 2019-04-16 | A kind of resume intelligent recommendation algorithm based on natural semantic analysis technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110032637A true CN110032637A (en) | 2019-07-19 |
Family
ID=67238478
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910302296.5A Pending CN110032637A (en) | 2019-04-16 | 2019-04-16 | A kind of resume intelligent recommendation algorithm based on natural semantic analysis technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110032637A (en) |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110866734A (en) * | 2019-11-11 | 2020-03-06 | 北京网聘咨询有限公司 | Intelligent recruitment method and system based on deep learning |
| CN110955836A (en) * | 2019-11-28 | 2020-04-03 | 重庆大数据研究院有限公司 | Resume recommendation method based on big data technology |
| CN111062685A (en) * | 2019-12-02 | 2020-04-24 | 匠云科技(武汉)有限公司 | Internet-based network recruitment system and method |
| CN111080076A (en) * | 2019-11-25 | 2020-04-28 | 埃摩森网络科技(上海)有限公司 | Intelligent recommendation method and system, equipment and server |
| 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 |
| CN111144723A (en) * | 2019-12-17 | 2020-05-12 | 埃摩森网络科技(上海)有限公司 | Method and system for recommending people's job matching and storage medium |
| CN111144781A (en) * | 2019-12-31 | 2020-05-12 | 江苏德尔斐数字科技有限公司 | Intelligent talent evaluation screening method based on cloud data |
| CN111160850A (en) * | 2019-12-11 | 2020-05-15 | 浙江微元智能科技股份有限公司 | Matching system and matching method suitable for person discrimination |
| CN111340436A (en) * | 2019-12-02 | 2020-06-26 | 匠云科技(武汉)有限公司 | Network recruitment optimization method for construction industry |
| CN111460813A (en) * | 2020-03-04 | 2020-07-28 | 北京网聘咨询有限公司 | Method and system for matching recruitment information and job hunting resume |
| CN111914191A (en) * | 2020-06-29 | 2020-11-10 | 长沙市到家悠享网络科技有限公司 | Target sorting method, device and equipment and model training method |
| CN111967858A (en) * | 2020-08-29 | 2020-11-20 | 深圳呗佬智能有限公司 | Talent intelligent recommendation method and system, computer equipment and storage medium |
| CN112232773A (en) * | 2020-10-19 | 2021-01-15 | 北京人人众包科技有限公司 | Software recommendation method and system |
| CN112258032A (en) * | 2020-10-22 | 2021-01-22 | 上海腾竞商务咨询有限公司 | Recruitment service method based on talent data |
| CN112598399A (en) * | 2020-12-31 | 2021-04-02 | 五八有限公司 | Information processing method and device |
| WO2021062920A1 (en) * | 2019-09-30 | 2021-04-08 | 深圳春沐源控股有限公司 | Information processing method and device, and computer-readable storage medium |
| CN113221013A (en) * | 2021-06-04 | 2021-08-06 | 金保信社保卡科技有限公司 | Occupational development planning application method and system |
| CN113468317A (en) * | 2021-06-26 | 2021-10-01 | 北京网聘咨询有限公司 | Resume screening method, system, equipment and storage medium |
| CN113807088A (en) * | 2021-09-22 | 2021-12-17 | 长沙麦都网络科技有限公司 | Job matching system |
| CN115170094A (en) * | 2022-09-07 | 2022-10-11 | 泰盈科技集团股份有限公司 | Big data artificial intelligence recruitment system and method |
| CN115456584A (en) * | 2022-09-16 | 2022-12-09 | 深圳今日人才信息科技有限公司 | Similar JD recall and recommendation method based on deep learning model and expert system |
| CN115577983A (en) * | 2022-11-24 | 2023-01-06 | 神华上航疏浚有限责任公司 | Enterprise task matching method based on block chain, server and storage medium |
| CN115775140A (en) * | 2023-02-10 | 2023-03-10 | 北京中科航天人才服务有限公司 | System and method for urban talent planning and intelligent human resource allocation |
| CN116595973A (en) * | 2023-05-19 | 2023-08-15 | 广东职教桥数据科技有限公司 | Post function identification method based on natural language processing classification technology |
| CN117931996A (en) * | 2024-01-25 | 2024-04-26 | 北京网聘信息技术有限公司 | B-terminal AI recruitment method based on large language model development |
| CN117993876A (en) * | 2024-04-03 | 2024-05-07 | 四川蓉城蕾茗科技有限公司 | Resume evaluation system, method, device and medium |
| CN118313804A (en) * | 2024-05-30 | 2024-07-09 | 北京数字众智科技有限公司 | System and method for matching recruiter with working post |
| CN118503547A (en) * | 2024-07-18 | 2024-08-16 | 北京华普亿方科技集团股份有限公司 | Artificial intelligence-based person post intelligent matching method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005196722A (en) * | 2004-01-09 | 2005-07-21 | Yasushi Matsuda | Job seeker recommendation service |
| US7720791B2 (en) * | 2005-05-23 | 2010-05-18 | Yahoo! Inc. | Intelligent job matching system and method including preference ranking |
| CN105488662A (en) * | 2016-01-07 | 2016-04-13 | 北京歌利沃夫企业管理有限公司 | Bi-directional recommendation-based online recruitment system |
| CN107590133A (en) * | 2017-10-24 | 2018-01-16 | 武汉理工大学 | The method and system that position vacant based on semanteme matches with job seeker resume |
| CN107704485A (en) * | 2017-07-31 | 2018-02-16 | 北京拉勾科技有限公司 | A kind of position recommends method and computing device |
| CN107844595A (en) * | 2017-11-21 | 2018-03-27 | 安徽网才信息技术股份有限公司 | A kind of job hunting website position intelligent recommendation method |
| 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 |
-
2019
- 2019-04-16 CN CN201910302296.5A patent/CN110032637A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005196722A (en) * | 2004-01-09 | 2005-07-21 | Yasushi Matsuda | Job seeker recommendation service |
| US7720791B2 (en) * | 2005-05-23 | 2010-05-18 | Yahoo! Inc. | Intelligent job matching system and method including preference ranking |
| CN105488662A (en) * | 2016-01-07 | 2016-04-13 | 北京歌利沃夫企业管理有限公司 | Bi-directional recommendation-based online recruitment system |
| CN107704485A (en) * | 2017-07-31 | 2018-02-16 | 北京拉勾科技有限公司 | A kind of position recommends method and computing device |
| CN107590133A (en) * | 2017-10-24 | 2018-01-16 | 武汉理工大学 | The method and system that position vacant based on semanteme matches with job seeker resume |
| CN107844595A (en) * | 2017-11-21 | 2018-03-27 | 安徽网才信息技术股份有限公司 | A kind of job hunting website position intelligent recommendation method |
| 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 |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021062920A1 (en) * | 2019-09-30 | 2021-04-08 | 深圳春沐源控股有限公司 | Information processing method and device, and computer-readable storage medium |
| CN110866734A (en) * | 2019-11-11 | 2020-03-06 | 北京网聘咨询有限公司 | Intelligent recruitment method and system based on deep learning |
| CN111080076A (en) * | 2019-11-25 | 2020-04-28 | 埃摩森网络科技(上海)有限公司 | Intelligent recommendation method and system, equipment and server |
| CN110955836A (en) * | 2019-11-28 | 2020-04-03 | 重庆大数据研究院有限公司 | Resume recommendation method based on big data technology |
| CN111062685A (en) * | 2019-12-02 | 2020-04-24 | 匠云科技(武汉)有限公司 | Internet-based network recruitment system and method |
| CN111340436A (en) * | 2019-12-02 | 2020-06-26 | 匠云科技(武汉)有限公司 | Network recruitment optimization method for construction industry |
| CN111160850A (en) * | 2019-12-11 | 2020-05-15 | 浙江微元智能科技股份有限公司 | Matching system and matching method suitable for person discrimination |
| 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 |
| CN111144723A (en) * | 2019-12-17 | 2020-05-12 | 埃摩森网络科技(上海)有限公司 | Method and system for recommending people's job matching and storage medium |
| CN111144781A (en) * | 2019-12-31 | 2020-05-12 | 江苏德尔斐数字科技有限公司 | Intelligent talent evaluation screening method based on cloud data |
| CN111460813A (en) * | 2020-03-04 | 2020-07-28 | 北京网聘咨询有限公司 | Method and system for matching recruitment information and job hunting resume |
| CN111914191A (en) * | 2020-06-29 | 2020-11-10 | 长沙市到家悠享网络科技有限公司 | Target sorting method, device and equipment and model training method |
| CN111914191B (en) * | 2020-06-29 | 2023-09-19 | 长沙市到家悠享网络科技有限公司 | Target ordering method, device and equipment |
| CN111967858A (en) * | 2020-08-29 | 2020-11-20 | 深圳呗佬智能有限公司 | Talent intelligent recommendation method and system, computer equipment and storage medium |
| CN112232773A (en) * | 2020-10-19 | 2021-01-15 | 北京人人众包科技有限公司 | Software recommendation method and system |
| CN112258032A (en) * | 2020-10-22 | 2021-01-22 | 上海腾竞商务咨询有限公司 | Recruitment service method based on talent data |
| CN112598399A (en) * | 2020-12-31 | 2021-04-02 | 五八有限公司 | Information processing method and device |
| CN113221013A (en) * | 2021-06-04 | 2021-08-06 | 金保信社保卡科技有限公司 | Occupational development planning application method and system |
| CN113468317A (en) * | 2021-06-26 | 2021-10-01 | 北京网聘咨询有限公司 | Resume screening method, system, equipment and storage medium |
| CN113468317B (en) * | 2021-06-26 | 2024-03-08 | 北京网聘信息技术有限公司 | Resume screening method, system, equipment and storage medium |
| CN113807088A (en) * | 2021-09-22 | 2021-12-17 | 长沙麦都网络科技有限公司 | Job matching system |
| CN115170094A (en) * | 2022-09-07 | 2022-10-11 | 泰盈科技集团股份有限公司 | Big data artificial intelligence recruitment system and method |
| CN115170094B (en) * | 2022-09-07 | 2022-11-29 | 泰盈科技集团股份有限公司 | Big data artificial intelligence recruitment system and method |
| CN115456584A (en) * | 2022-09-16 | 2022-12-09 | 深圳今日人才信息科技有限公司 | Similar JD recall and recommendation method based on deep learning model and expert system |
| CN115577983A (en) * | 2022-11-24 | 2023-01-06 | 神华上航疏浚有限责任公司 | Enterprise task matching method based on block chain, server and storage medium |
| CN115775140A (en) * | 2023-02-10 | 2023-03-10 | 北京中科航天人才服务有限公司 | System and method for urban talent planning and intelligent human resource allocation |
| CN116595973A (en) * | 2023-05-19 | 2023-08-15 | 广东职教桥数据科技有限公司 | Post function identification method based on natural language processing classification technology |
| CN116595973B (en) * | 2023-05-19 | 2023-10-03 | 广东职教桥数据科技有限公司 | Post function identification method based on natural language processing classification technology |
| CN117931996A (en) * | 2024-01-25 | 2024-04-26 | 北京网聘信息技术有限公司 | B-terminal AI recruitment method based on large language model development |
| CN117993876A (en) * | 2024-04-03 | 2024-05-07 | 四川蓉城蕾茗科技有限公司 | Resume evaluation system, method, device and medium |
| CN117993876B (en) * | 2024-04-03 | 2024-08-02 | 四川蓉城蕾茗科技有限公司 | Resume evaluation system, method, device and medium |
| CN118313804A (en) * | 2024-05-30 | 2024-07-09 | 北京数字众智科技有限公司 | System and method for matching recruiter with working post |
| CN118503547A (en) * | 2024-07-18 | 2024-08-16 | 北京华普亿方科技集团股份有限公司 | Artificial intelligence-based person post intelligent matching method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110032637A (en) | A kind of resume intelligent recommendation algorithm based on natural semantic analysis technology | |
| CN110825882B (en) | Knowledge graph-based information system management method | |
| CN109189901B (en) | Method for automatically discovering new classification and corresponding corpus in intelligent customer service system | |
| CN109558429B (en) | Talent service bidirectional recommendation method and system based on Internet big data | |
| CN110472017A (en) | A kind of analysis of words art and topic point identify matched method and system | |
| CN109754233A (en) | A kind of method and system of intelligent recommendation job information | |
| CN107705066A (en) | Information input method and electronic equipment during a kind of commodity storage | |
| CN104077407B (en) | A kind of intelligent data search system and method | |
| CN109165294A (en) | Short text classification method based on Bayesian classification | |
| CN107273295B (en) | Software problem report classification method based on text chaos | |
| CN103310003A (en) | Method and system for predicting click rate of new advertisement based on click log | |
| CN109840532A (en) | A kind of law court's class case recommended method based on k-means | |
| CN110196943A (en) | A kind of position intelligent recommendation system, method and its system | |
| CN111241361A (en) | Intelligent referral system and method for enterprises and colleges based on cloud platform | |
| CN110020327A (en) | A kind of resume resolution system based on vertical search engine | |
| CN110069629A (en) | House transaction task processing method, equipment, storage medium and device | |
| CN107194617A (en) | A kind of app software engineers soft skill categorizing system and method | |
| CN110929007A (en) | Electric power marketing knowledge system platform and application method | |
| CN110704574A (en) | Method and system for managing bank business demand assets | |
| CN116361367A (en) | Content identification system and method for efficiently publishing recruitment information | |
| CN114372731B (en) | Post target making method, device, equipment and storage medium based on big data | |
| CN114722810A (en) | Real estate customer portrait method and system based on information extraction and multi-attribute decision | |
| CN1367446A (en) | Chinese personal biographical notes information treatment system and method | |
| CN110334188A (en) | A kind of multi-document summary generation method and system | |
| CN104679836B (en) | A kind of automatic extending method of Agricultural ontology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190719 |
|
| RJ01 | Rejection of invention patent application after publication |