CN110020327A - A kind of resume resolution system based on vertical search engine - Google Patents
A kind of resume resolution system based on vertical search engine Download PDFInfo
- Publication number
- CN110020327A CN110020327A CN201910302297.XA CN201910302297A CN110020327A CN 110020327 A CN110020327 A CN 110020327A CN 201910302297 A CN201910302297 A CN 201910302297A CN 110020327 A CN110020327 A CN 110020327A
- Authority
- CN
- China
- Prior art keywords
- resume
- content
- text
- module
- unit
- 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
- G06F16/9577—Optimising the visualization of content, e.g. distillation of HTML documents
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
Abstract
The invention discloses a kind of resume resolution system based on vertical search engine, including resume body of an instrument extracting unit, resume content segmentation unit and resume content analysis optimize unit;Resume body of an instrument extracting unit does not have actual resume content and only links for the resume of some channels in mail, the content of true resume is obtained by opening link;Resume content segmentation unit is used to set the keyword of resume parsing information collection, such as work experience, education experience, and the big classification of resume is distinguished using these keywords;Resume content analysis optimization unit is used to parse the content item of a plurality of record, as work experience, education experience carry out record division first;The present invention can uniformly be converted into text using text conversion techniques with the resume of automatic identification different-format, then content of text is parsed into the resume of formatting, be shown resume content with unified format.
Description
Technical field
The present invention relates to information retrieval field, specially a kind of resume resolution system based on vertical search engine.
Background technique
That recruits at present is inefficient, and main cause cannot match well in candidate and enterprise, and job hunter needs
Different recruitment websites delivers position, and identical position has louver on several ten, candidate artificial since information is roughly the same
It saves trouble, therefore resume " throwing in sea ", then " mass-election ", both sides are time-consuming and laborious, inefficiency company HR.
The resume of disadvantage one, different-format needs different tools to check, such as checks word, excel using Office
The resume of format checks the resume of pdf using Re1der, and the resume etc. of html, mht format is checked using browser.
Disadvantage two, resume content, resume format are varied, such as contact method, age, length of service, job intension
Equal key messages, some are in resume content finally, some are mixed in self-assessment, some are even without directly description.
Disadvantage three, resume storage dispersion, file format is various, not manageability, not easy-to-search.
Disadvantage four, often receive the same person different channels resume, be not easy to judge whether this people delivered position,
Whether it has been eliminated in the position.
Summary of the invention
The purpose of the present invention is to provide a kind of resume resolution system based on vertical search engine, to solve above-mentioned background
The problem of being proposed in technology.
To achieve the above object, the invention provides the following technical scheme: a kind of resume parsing based on vertical search engine
System, including resume body of an instrument extracting unit, resume content segmentation unit and resume content analysis optimize unit;
Resume body of an instrument extracting unit does not have actual resume content and only chain for the resume of some channels in mail
It connects, the content of true resume is obtained by opening link;
Resume content segmentation unit: the keyword of setting resume parsing information collection, such as work experience, education experience use this
A little keywords distinguish the big classification of resume;
Resume content analysis optimizes unit: the content item of a plurality of record is parsed, as work experience, education experience are recorded first
It divides.
Preferably, the resume body of an instrument extracting unit is connected to resume content segmentation unit, resume content segmentation list
Member is connected to resume content analysis optimization unit.
Preferably, the resume body of an instrument extracting unit includes Office text and picture abstraction module, pdf text and
Picture abstraction module, picture OCR Text region module, html text and picture abstraction module;Wherein:
Office text and picture abstraction module directly read the text inside file for the resume of Word, excel format
Content;
Pdf text and picture abstraction module directly read the content of text inside file for the resume of pdf format;
Picture OCR Text region module identifies word content by OCR character recognition technology for the resume of picture format;
Html text and picture abstraction module can access mail server automatically, obtain Mail Contents, Mail Contents include text
And attachment, resume may also be in texts or attachment;All message bodies and attachment format information are obtained, it is preferential to read HTML lattice
The content of formula.
Preferably, the resume content segmentation unit includes more people's resumes, multilingual resume segmentation module, biographic information collection
Divide module, biographic information item divides module;Wherein:
More people's resumes and multilingual resume divide module, and for dividing multilingual resume content, resume content may be simultaneously
Resume comprising multilingual: the starting keyword of the setting various language of resume divides not by searching for the starting keyword arrived
With the resume content of language, then according to the language form of resume text, the resume content of different language is distinguished;
Biographic information collection divides module, and traversal full text searches keyword present in text, and recording key position,
Divide paragraph according to the sequencing of key position;
Biographic information item divides module;The keyword, such as name, gender etc. for setting resume parsing item of information use these passes
Key stroke divides the content of disparity items.
Preferably, resume content analysis optimization unit includes resume content analysis module, resume content optimization module,
Resume content verification module;Wherein:
The condition of a plurality of record is distinguished in resume content analysis module, setting, and such as beginning and ending time searches qualified content and carries out
Record segmentation, handles the record content being partitioned into one by one, and treatment process is identical as the process of paragraph is divided;
Resume content optimization module, the project of keyword, does not look into cover in full in paragraph, then does optimization processing to content;
Resume content verification module, is integrated by interface and enterprises recruitment system, by integration and the resume data after screening
Pass to enterprises recruitment management system.
Preferably, the resume body of an instrument extracting unit is supported from the local Chinese and English resume text for uploading various formats
Part, such as word, excel, pdf, txt, html, eml, msg;Also support that resume file, which is packaged batch, to be uploaded.
Preferably, the resume content segmentation unit can exclude the resume being put on the blacklist automatically, can collect automatically
The resume of white list.
Preferably, the resume content analysis optimization unit can merge the repetition resume for applying for identical position, and
Retain newest resume.Position vacant can be created and a key is published to mainstream recruitment website and all kinds of social network sites, microblogging
Equal recruitment channels.
Preferably, the resume content segmentation unit can be managed recruitment channel, and resume can automatic identification when parsing
Channel source, in order to be analyzed by channel effect of the report to resume.
Compared with prior art, the beneficial effects of the present invention are: the present invention can be made with the resume of automatic identification different-format
With text conversion techniques, it is uniformly converted into text, then content of text is parsed into the resume of formatting, it will with unified format
Resume content is shown;Including following advantages: 1, local not need to install any software, so that it may to check various lattice beyond the clouds
The resume of formula;System can be gone out matched resume in enterprise's resume library by automatic calculating sifting and recommend HR, and resume selection is improved
200% or more working efficiency (about at least saving 1.5 hours or more operating times daily), revitalizing an enterprise talent bank is sent out in enterprise
Out when position demand, matched candidate's resume is excavated from enterprise's talent bank at the first time;System is automatically according to applicant's letter
It goes through and calculates matched position and recommend its application, evade applicant sea and throw the waste plenty of time, push matching position, mentions in 3 seconds
High applicant's self-confidence is accelerated both sides' intention and is reached.2, resume uniform format is conveniently checked, is screened.It supports candidate by parsing
Each content in people's resume, can intelligent extraction go out resume key message, and based on basic data, closed according to biographic information
Parsing resume can be decomposed into various demand conditions by keyword, such as now residence, expectation job site, Expectant salary, desired row
The conditions such as industry, educational background, length of service, system then carry out algorithm recommendation according to these resume conditions.3, some not describe directly
Information, analytic technique will automatically calculate out.Such as the length of service.It is flat to build basic data involved by position, resume
Platform, continue by position, resume industry, company, the length of service, standard position title, school, profession, language, technical ability, specially
The maintenances of information such as industry vocabulary enter in platform, to establish perfect position model and resume model, subsequent job data
Analysis, the analysis of resume data and proposed algorithm just can be carried out.4, the resume after parsing has had the pass such as name, contact method
Key information, it can be determined that whether repeat to deliver.Resume resolves to cloud recruitment platform core technology, by participle technique, vertically searches
Rope is arranged based on the huge keyword of platform and special field, is compared to resume content, sets according to platform specification
Automatically generate unitized format resume;And it can judge whether there is repetitive operation early period, and result push is presented by platform and is formed
It reminds and suggests.5, mail parses, and can automatically parse position title, be matched under corresponding position.(the duty of existing mass data source
Position data, resume data) it is supplied to intelligent recommendation system, intelligent recommendation system passes through natural language, big data analysis, intelligence sieve
The technologies such as choosing carry out detailed analysis, and formation recommendation results are pushed to platform and are shown, and make for recruitment enterprise and candidate's reference
With.6, the resume mail of mailbox is read automatically, and resume automatically parses into system, and it is short that resume collects delay time, without artificial
Intervene.The accuracy of recommendation is the key that intelligently to recruit, and the advantage of the project is that, based on cloud recruitment platform, platform has precipitated
The recruitment behavioral data of several hundred million meters, proposed algorithm not only will be based on the matching degrees in post itself, will also be based on user behavior
Preference, such as which type of data have passed through screening, enter interview, and which data last registration is again;Simultaneously again
The intelligentized position demand for understanding enterprise is wanted, effective, crucial word is extracted and is added on analysis, reject invalid information.Recommend
Second step is the feedback based on recommendation results, after recommending, according to the processing result of user, feeds back to recommender system, pushes away
It recommends system and data model is learnt again, so that accuracy is higher and higher.
Detailed description of the invention
Fig. 1 is workflow schematic diagram 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.
Referring to Fig. 1, the present invention provides a kind of technical solution: a kind of resume resolution system based on vertical search engine,
Optimize unit including resume body of an instrument extracting unit, resume content segmentation unit and resume content analysis;
Resume body of an instrument extracting unit does not have actual resume content and only chain for the resume of some channels in mail
It connects, the content of true resume is obtained by opening link;
Resume content segmentation unit: the keyword of setting resume parsing information collection, such as work experience, education experience use this
A little keywords distinguish the big classification of resume;
Resume content analysis optimizes unit: the content item of a plurality of record is parsed, as work experience, education experience are recorded first
It divides.
Further, the resume body of an instrument extracting unit is connected to resume content segmentation unit, resume content segmentation
Unit is connected to resume content analysis optimization unit.
Further, the resume body of an instrument extracting unit includes Office text and picture abstraction module, pdf text
And picture abstraction module, picture OCR Text region module, html text and picture abstraction module;Wherein:
Office text and picture abstraction module directly read the text inside file for the resume of Word, excel format
Content;
Pdf text and picture abstraction module directly read the content of text inside file for the resume of pdf format;
Picture OCR Text region module identifies word content by OCR character recognition technology for the resume of picture format;
Html text and picture abstraction module can access mail server automatically, obtain Mail Contents, Mail Contents include text
And attachment, resume may also be in texts or attachment;All message bodies and attachment format information are obtained, it is preferential to read HTML lattice
The content of formula.
Further, the resume content segmentation unit includes more people's resumes, multilingual resume segmentation module, biographic information
Collection segmentation module, biographic information item divide module;Wherein:
More people's resumes and multilingual resume divide module, and for dividing multilingual resume content, resume content may be simultaneously
Resume comprising multilingual: the starting keyword of the setting various language of resume divides not by searching for the starting keyword arrived
With the resume content of language, then according to the language form of resume text, the resume content of different language is distinguished;
Biographic information collection divides module, and traversal full text searches keyword present in text, and recording key position,
Divide paragraph according to the sequencing of key position;
Biographic information item divides module;The keyword, such as name, gender etc. for setting resume parsing item of information use these passes
Key stroke divides the content of disparity items.
Further, the resume content analysis optimization unit includes resume content analysis module, resume content optimization mould
Block, resume content verification module;Wherein:
The condition of a plurality of record is distinguished in resume content analysis module, setting, and such as beginning and ending time searches qualified content and carries out
Record segmentation, handles the record content being partitioned into one by one, and treatment process is identical as the process of paragraph is divided;
Resume content optimization module, the project of keyword, does not look into cover in full in paragraph, then does optimization processing to content;
Resume content verification module, is integrated by interface and enterprises recruitment system, by integration and the resume data after screening
Pass to enterprises recruitment management system.
Further, the resume body of an instrument extracting unit is supported from the local Chinese and English resume text for uploading various formats
Part, such as word, excel, pdf, txt, html, eml, msg;Also support that resume file, which is packaged batch, to be uploaded.
Further, the resume content segmentation unit can exclude the resume being put on the blacklist automatically, can receive automatically
Take the resume of white list.
Further, the resume content analysis optimization unit can merge the repetition resume for applying for identical position,
And retain newest resume.Position vacant can be created and a key is published to mainstream recruitment website and all kinds of social network sites, micro-
It is rich to wait recruitment channels.
Further, the resume content segmentation unit can be managed recruitment channel, and resume can be known automatically when parsing
Other channel source, in order to be analyzed by channel effect of the report to resume.
Working principle: 1, resume content is read:
1) resume of the formats such as Word, excel, pdf, directly reads the content of text inside file.
2) resume of picture format identifies word content by OCR character recognition technology.
3) mail server is accessed automatically, obtains Mail Contents.Mail Contents include text and attachment, and resume may also be
In text or attachment, so all message bodies and attachment format information are obtained, the preferential content for reading html format.
4) resume of some channels does not have actual resume content in mail, only one link, and opening link just can be with
See real resume content, needs to obtain the content of true resume by link.
2, divide multilingual resume content:
1) resume content may include the resume of multilingual simultaneously
2) the starting keyword of the various language of resume is set, is divided in the resume of different language by searching for the starting keyword arrived
Hold.
3) according to the language form of resume text, the resume content of different language is distinguished.
3, resume division of teaching contents paragraph:
1) keyword of setting resume parsing information collection, such as work experience, education experience, distinguish resume using these keywords
Big classification.
2) traversal full text searches keyword present in text, and recording key position
3) divide paragraph according to the sequencing of key position
4, the content item for parsing a plurality of record, such as work experience, education experience:
1) record division is carried out first.The condition of a plurality of record is distinguished in setting, such as beginning and ending time, search qualified content into
Row record segmentation.
2) the record content being partitioned into is handled one by one, treatment process is identical as the process of paragraph is divided.
5, the processing of biographic information item:
1) keyword, such as name, gender etc. of setting resume parsing item of information, divides disparity items using these keywords
Content.
2) the not no project of keyword, is searched in full in paragraph
3) optimization processing is done to content.
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 resolution system based on vertical search engine, it is characterised in that: including resume body of an instrument extracting unit,
Resume content segmentation unit and resume content analysis optimize unit;
Resume body of an instrument extracting unit does not have actual resume content and only chain for the resume of some channels in mail
It connects, the content of true resume is obtained by opening link;
Resume content segmentation unit: the keyword of setting resume parsing information collection, such as work experience, education experience use this
A little keywords distinguish the big classification of resume;
Resume content analysis optimizes unit: the content item of a plurality of record is parsed, as work experience, education experience are recorded first
It divides.
2. a kind of resume resolution system based on vertical search engine according to claim 1, it is characterised in that: the letter
It goes through body of an instrument extracting unit and is connected to resume content segmentation unit, it is excellent that resume content segmentation unit is connected to resume content analysis
Change unit.
3. a kind of resume resolution system based on vertical search engine according to claim 1, it is characterised in that: the letter
Going through body of an instrument extracting unit includes Office text and picture abstraction module, pdf text and picture abstraction module, picture OCR
Text region module, html text and picture abstraction module;Wherein:
Office text and picture abstraction module directly read the text inside file for the resume of Word, excel format
Content;
Pdf text and picture abstraction module directly read the content of text inside file for the resume of pdf format;
Picture OCR Text region module identifies word content by OCR character recognition technology for the resume of picture format;
Html text and picture abstraction module can access mail server automatically, obtain Mail Contents, Mail Contents include text
And attachment, resume may also be in texts or attachment;All message bodies and attachment format information are obtained, it is preferential to read HTML lattice
The content of formula.
4. a kind of resume resolution system based on vertical search engine according to claim 1, it is characterised in that: the letter
Going through content segmentation unit includes more people's resumes, multilingual resume segmentation module, and biographic information collection divides module, biographic information item point
Cut module;Wherein:
More people's resumes and multilingual resume divide module, and for dividing multilingual resume content, resume content may be simultaneously
Resume comprising multilingual: the starting keyword of the setting various language of resume divides not by searching for the starting keyword arrived
With the resume content of language, then according to the language form of resume text, the resume content of different language is distinguished;
Biographic information collection divides module, and traversal full text searches keyword present in text, and recording key position,
Divide paragraph according to the sequencing of key position;
Biographic information item divides module;The keyword, such as name, gender etc. for setting resume parsing item of information use these passes
Key stroke divides the content of disparity items.
5. a kind of resume resolution system based on vertical search engine according to claim 1, it is characterised in that: the letter
Going through content analysis optimization unit includes resume content analysis module, resume content optimization module, resume content verification module;Its
In:
The condition of a plurality of record is distinguished in resume content analysis module, setting, and such as beginning and ending time searches qualified content and carries out
Record segmentation, handles the record content being partitioned into one by one, and treatment process is identical as the process of paragraph is divided;
Resume content optimization module, the project of keyword, does not look into cover in full in paragraph, then does optimization processing to content;
Resume content verification module, is integrated by interface and enterprises recruitment system, by integration and the resume data after screening
Pass to enterprises recruitment management system.
6. a kind of resume resolution system based on vertical search engine according to claim 1, it is characterised in that: the letter
Body of an instrument extracting unit is gone through to support from the local Chinese and English resume file for uploading various formats, as word, excel, pdf,
Txt, html, eml, msg etc.;Also support that resume file, which is packaged batch, to be uploaded.
7. a kind of resume resolution system based on vertical search engine according to claim 1, it is characterised in that: the letter
The resume being put on the blacklist can be excluded automatically by going through content segmentation unit, can collect the resume of white list automatically.
8. a kind of resume resolution system based on vertical search engine according to claim 1, it is characterised in that: the letter
The repetition resume for applying for identical position can be merged by going through content analysis optimization unit, and retain newest resume, can be created
It builds position vacant and a key is published to the recruitment channels such as mainstream recruitment website and all kinds of social network sites, microblogging.
9. a kind of resume resolution system based on vertical search engine according to claim 1, it is characterised in that: the letter
Recruitment channel can be managed by going through content segmentation unit, resume parse when can automatic identification channel source, in order to pass through report
Table analyzes the channel effect of resume.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910302297.XA CN110020327A (en) | 2019-04-16 | 2019-04-16 | A kind of resume resolution system based on vertical search engine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910302297.XA CN110020327A (en) | 2019-04-16 | 2019-04-16 | A kind of resume resolution system based on vertical search engine |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110020327A true CN110020327A (en) | 2019-07-16 |
Family
ID=67191383
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910302297.XA Pending CN110020327A (en) | 2019-04-16 | 2019-04-16 | A kind of resume resolution system based on vertical search engine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110020327A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110377560A (en) * | 2019-07-18 | 2019-10-25 | 中科鼎富(北京)科技发展有限公司 | A kind of structural method and device of biographic information |
CN110956022A (en) * | 2019-12-04 | 2020-04-03 | 青岛盈智科技有限公司 | Document processing method and system |
CN111737969A (en) * | 2020-07-27 | 2020-10-02 | 北森云计算有限公司 | Resume parsing method and system based on deep learning |
CN112232750A (en) * | 2020-04-23 | 2021-01-15 | 苏州有信有服信息技术有限公司 | Recruitment website job hunting and recruitment information management system |
CN113343816A (en) * | 2021-05-31 | 2021-09-03 | 的卢技术有限公司 | Automatic testing method and system for OCR resume recognition algorithm |
CN117058699A (en) * | 2023-08-28 | 2023-11-14 | 深圳夸夸菁领科技有限公司 | Resume layout dividing method, system and storage medium based on LayoutLMv3 model |
CN117058699B (en) * | 2023-08-28 | 2024-04-19 | 深圳夸夸菁领科技有限公司 | Resume layout dividing method, system and storage medium based on LayoutLMv model |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103634420A (en) * | 2013-11-22 | 2014-03-12 | 北京极客优才科技有限公司 | Resume e-mail screening system and method |
CN105183742A (en) * | 2015-06-12 | 2015-12-23 | 南京富士通南大软件技术有限公司 | Resume identification method |
CN105787047A (en) * | 2016-02-29 | 2016-07-20 | 河南中欧企业咨询有限公司 | Extraction, analysis and conversion method of resume information |
CN106096913A (en) * | 2016-06-14 | 2016-11-09 | 嘉兴飞刀软件科技有限公司 | A kind of resume mail analysis system and method based on cloud service |
CN106777296A (en) * | 2016-12-30 | 2017-05-31 | 深圳爱拼信息科技有限公司 | Method and system are recommended in a kind of talent's search based on semantic matches |
CN108305047A (en) * | 2018-01-31 | 2018-07-20 | 合肥和钧正策信息技术有限公司 | A kind of talent's big data enterprises service system |
CN108874928A (en) * | 2018-05-31 | 2018-11-23 | 平安科技(深圳)有限公司 | Resume data information analyzing and processing method, device, equipment and storage medium |
CN109460976A (en) * | 2018-11-02 | 2019-03-12 | 广州至拓网络科技有限公司 | A kind of personal scheduling and enterprises recruitment comprehensive management platform |
CN109472310A (en) * | 2018-11-12 | 2019-03-15 | 深圳八爪网络科技有限公司 | Determine the recognition methods and device that two parts of resumes are the identical talent |
CN109614546A (en) * | 2018-11-26 | 2019-04-12 | 河南大瑞物联网科技有限公司 | A method of for auxiliary enterprises Human Resource Department recruitment and job hunting personnel |
-
2019
- 2019-04-16 CN CN201910302297.XA patent/CN110020327A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103634420A (en) * | 2013-11-22 | 2014-03-12 | 北京极客优才科技有限公司 | Resume e-mail screening system and method |
CN105183742A (en) * | 2015-06-12 | 2015-12-23 | 南京富士通南大软件技术有限公司 | Resume identification method |
CN105787047A (en) * | 2016-02-29 | 2016-07-20 | 河南中欧企业咨询有限公司 | Extraction, analysis and conversion method of resume information |
CN106096913A (en) * | 2016-06-14 | 2016-11-09 | 嘉兴飞刀软件科技有限公司 | A kind of resume mail analysis system and method based on cloud service |
CN106777296A (en) * | 2016-12-30 | 2017-05-31 | 深圳爱拼信息科技有限公司 | Method and system are recommended in a kind of talent's search based on semantic matches |
CN108305047A (en) * | 2018-01-31 | 2018-07-20 | 合肥和钧正策信息技术有限公司 | A kind of talent's big data enterprises service system |
CN108874928A (en) * | 2018-05-31 | 2018-11-23 | 平安科技(深圳)有限公司 | Resume data information analyzing and processing method, device, equipment and storage medium |
CN109460976A (en) * | 2018-11-02 | 2019-03-12 | 广州至拓网络科技有限公司 | A kind of personal scheduling and enterprises recruitment comprehensive management platform |
CN109472310A (en) * | 2018-11-12 | 2019-03-15 | 深圳八爪网络科技有限公司 | Determine the recognition methods and device that two parts of resumes are the identical talent |
CN109614546A (en) * | 2018-11-26 | 2019-04-12 | 河南大瑞物联网科技有限公司 | A method of for auxiliary enterprises Human Resource Department recruitment and job hunting personnel |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110377560A (en) * | 2019-07-18 | 2019-10-25 | 中科鼎富(北京)科技发展有限公司 | A kind of structural method and device of biographic information |
CN110377560B (en) * | 2019-07-18 | 2021-11-26 | 鼎富智能科技有限公司 | Method and device for structuring resume information |
CN110956022A (en) * | 2019-12-04 | 2020-04-03 | 青岛盈智科技有限公司 | Document processing method and system |
CN112232750A (en) * | 2020-04-23 | 2021-01-15 | 苏州有信有服信息技术有限公司 | Recruitment website job hunting and recruitment information management system |
CN111737969A (en) * | 2020-07-27 | 2020-10-02 | 北森云计算有限公司 | Resume parsing method and system based on deep learning |
CN111737969B (en) * | 2020-07-27 | 2020-12-08 | 北森云计算有限公司 | Resume parsing method and system based on deep learning |
CN113343816A (en) * | 2021-05-31 | 2021-09-03 | 的卢技术有限公司 | Automatic testing method and system for OCR resume recognition algorithm |
CN117058699A (en) * | 2023-08-28 | 2023-11-14 | 深圳夸夸菁领科技有限公司 | Resume layout dividing method, system and storage medium based on LayoutLMv3 model |
CN117058699B (en) * | 2023-08-28 | 2024-04-19 | 深圳夸夸菁领科技有限公司 | Resume layout dividing method, system and storage medium based on LayoutLMv model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110020327A (en) | A kind of resume resolution system based on vertical search engine | |
CN107563725B (en) | Recruitment system for optimizing fussy talent recruitment process | |
CN100371927C (en) | System for identifying paraphrases using machine translation techniques | |
US20140304267A1 (en) | Suffix tree similarity measure for document clustering | |
CN111831802B (en) | Urban domain knowledge detection system and method based on LDA topic model | |
CN106570171A (en) | Semantics-based sci-tech information processing method and system | |
CA2720167A1 (en) | An automated media analysis and document management system | |
CN106649778B (en) | Interaction method and device based on deep question answering | |
CN110852095B (en) | Statement hot spot extraction method and system | |
US11687826B2 (en) | Artificial intelligence (AI) based innovation data processing system | |
CN110929007A (en) | Electric power marketing knowledge system platform and application method | |
CN115544348A (en) | Intelligent mass information searching system based on Internet big data | |
CN113282729A (en) | Question-answering method and device based on knowledge graph | |
CN1167026C (en) | Chinese personal biographical notes information treatment system and method | |
KR20210062934A (en) | Text document cluster and topic generation apparatus and method thereof | |
CN117171650A (en) | Document data processing method, system and medium based on web crawler technology | |
CN109446277A (en) | Relational data intelligent search method and system based on Chinese natural language | |
CN112380848A (en) | Text generation method, device, equipment and storage medium | |
CN109543049B (en) | Method and system for automatically pushing materials according to writing characteristics | |
CN108595466B (en) | Internet information filtering and internet user information and network card structure analysis method | |
CN109902215A (en) | A kind of method and system of deals match | |
CN106407271B (en) | Intelligent customer service system and updating method of intelligent customer service knowledge base thereof | |
CN108038124A (en) | A kind of PDF document acquiring and processing method, system and device based on big data | |
CN113742496A (en) | Power knowledge learning system and method based on heterogeneous resource fusion | |
CN114065934A (en) | Method and system for constructing semantic knowledge base in environmental impact evaluation field |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190716 |