CN106777296A - Method and system are recommended in a kind of talent's search based on semantic matches - Google Patents
Method and system are recommended in a kind of talent's search based on semantic matches Download PDFInfo
- Publication number
- CN106777296A CN106777296A CN201611252522.6A CN201611252522A CN106777296A CN 106777296 A CN106777296 A CN 106777296A CN 201611252522 A CN201611252522 A CN 201611252522A CN 106777296 A CN106777296 A CN 106777296A
- Authority
- CN
- China
- Prior art keywords
- vectorization
- user
- data
- information
- searches
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Recommend method and system the present invention relates to a kind of talent's search based on semantic matches, retrieval threshold is high caused by overcoming the diversity of language expression, the problem that time-consuming, high dimension vector is carried out by semantic parsing system to the various expression in position vacant requirement to represent, no longer retrieved by the literal matching of language performance, but be converted into mathematic vector and retrieved.Can be represented by the distance in higher dimensional space by the similarity between the expression after vectorization, so user only needs to the one kind being input into various expression, system is recognizable close expression and sets up contact, solve the problems, such as fuzzy and various semantic identification, the time of talent's search is shortened, the search efficiency of user is improve.
Description
Technical field
Recommend the present invention relates to a kind of talent search recommended technology, more particularly to a kind of talent's search based on semantic matches
Method and system.
Background technology
Talent's search commending system of the various recruitment websites of in the market is all the keyword retrieval technology that uses, and system is by using
The keyword of family input, in a pile resume, finds the resume of corresponding keyword, and current way of search has following asking
Topic：User is needed to the enough understandings of position vacant, can just be extracted accurately keyword and be searched out suitable resume, has one to user
Fixed specialty requirement；Required for not being user by keyword search resume major part out, because keyword is in difference
Sentence in be with the different meanings, the implication of system None- identified keyword, as long as there is this word to be found in resume
Come, so as to cause the Quality Down of matching；Keyword is unilateral comparing, post can have many crucial phrases into, but
Each keyword search can only find part resume, miss out the suitable resume of similar key；Current talent's search
Commending system, when the keyword of input is more, due to needing all to match, the resume for searching out can be little.Input keyword compared with
When few, it may appear that a large amount of is not the resume that user needs；User looks for a resume for position, it is necessary to frequently enter different keys
Word searches resume, and the inefficiency of search, repeated work is more；For keyword that the sequence of Search Results is normally based on input
Whether the probability of appearance, demand is met rather than the identification resume text meaning, causes user to need to check up to a hundred resumes, ability
Find several suitable resumes.
Due to the ambiguity and diversity of language expression, it is possible that same word is different upper in job requirement
The different situation of the meaning hereinafter, it is also possible to different vocabularys up to the situation for being the same meaning occur.In keyword inspection
In cable system, due to word be it is strict matched according to literal, user need searched in strict accordance with keyword, Cai Nengjian
To suitable resume, this characteristic causes user more long in the time of the cost using existing talent's searching system to rope.Cause
The profound cause of this problem is that to be the Computer Storage content based on spoken and written languages do present searching system, word
Storage is coding（That general is UTF-8）Binary content afterwards, a word is usually 1 ~ 4 byte, and searching system exists
There is the text of these byte contents in accurate lookup in storehouse.
The content of the invention
It is contemplated that at least solving one of technical problem present in prior art.
Therefore, it is an object of the present invention in order to caused by the diversity for overcoming language expression retrieve threshold it is high, time-consuming
Problem, the various expression in position vacant requirement have been carried out by high dimension vector represented by semantic parsing system, no longer lead to
Cross the literal matching of language performance to retrieve, but be converted into mathematic vector and retrieve.By between the expression after vectorization
Similarity can represent that such user only needs to the one kind being input into various expression, system by the distance in higher dimensional space
Can recognize that close expression and set up contact, solve the problems, such as fuzzy and various semantic identification, shorten talent's search
Time, improve the search efficiency of user.
To achieve the above object, the present invention provides a kind of talent's search recommendation method based on semantic matches, including：
Step 1, receives the recruitment information of user terminal input；
Step 2, according to the recruitment information for obtaining, is parsed；
Step 3, vectorization calculating is carried out to the recruitment information after parsing, generates vectorization data；
Step 4, the vectorization data of relatively more described generation and the similarity of vectorization data pre-stored in database；
Step 5, comparative result is exported to user terminal.
More specifically, also include before step 1：
The biographic information of each channel is collected, the biographic information that will be collected into carries out unified structure, extract effective field, will be each
Individual field carries out vectorization treatment, generates vectorization data, stores in database.
Preferably, the resume form of collection includes text, HTML, Word, PDF.
Preferably, the biographic information for collecting each channel, the biographic information that will be collected into carries out unified structure, carries
Effective field is taken, each field is carried out into vectorization treatment, generate vectorization data, stored in database, also included：
Biographic information to collecting carries out data cleansing, tagged from each different field of resume information extraction；By field
Content unification is converted to canonical form.
Preferably, it is described to be parsed according to the recruitment information for obtaining, specifically include：
Obtain the recruitment information of user input, analyze the demand of user, including educational background, school, specialty, the length of service, emolument,
City, industry, sex, age, ability, the demand of experience；Operation is standardized to these data, standardized looking into is converted to
Inquiry condition.
Preferably, with reference to user's usage behavior, suitable resume is regularly recommended into user.
The present invention also provides a kind of talent's search commending system based on semantic matches, including：
Receiver module, the recruitment information for receiving user terminal input；
Parsing module, for according to the recruitment information for obtaining, being parsed；
Quantization modules, for carrying out vectorization calculating to the recruitment information after parsing, generate vectorization data；
Comparison module, the vectorization data for comparing the generation are similar to the vectorization data being pre-stored in database
Degree；
Output module, for comparative result to be exported to user terminal.
Preferably, also include：
Database, the biographic information for collecting each channel, the biographic information that will be collected into carries out unified structure, and extraction has
Effect field, vectorization treatment is carried out by each field, generates vectorization data, is stored in database.
Preferably, also include：
Data cleansing module, the biographic information to collecting carries out data cleansing, from each different field of resume information extraction, beats
Upper label；Field contents unification is converted into canonical form.
Preferably, the parsing module concrete function is：The recruitment information of user input is obtained, the need of user are analyzed
Ask, including educational background, school, specialty, length of service, emolument, city, industry, sex, age, ability, the demand of experience；To this
A little data are standardized operation, are converted to standardized querying condition.
The present invention in order to caused by the diversity for overcoming language expression retrieve threshold it is high, the problem that time-consuming, by semanteme
Analysis system has carried out high dimension vector and has represented to the various expression in position vacant requirement, no longer by the literal of language performance
Matching retrieves, but is converted into mathematic vector and retrieves.Can be by height by the similarity between the expression after vectorization
Distance in dimension space represents that such user only needs to the one kind being input into various expression, system is recognizable close table
Up to and set up contact, solve the problems, such as fuzzy and various semantic identification, shorten the time of talent's search, improve and use
The search efficiency of person.
The technical solution adopted in the present invention retrieves resume using semantic matches technology, and user only needs to be input into whole duty
Position requires that just man-to-man Keywords matching can be taken leave of by the language search of various dimensions, does not find out text description singly the same
Resume, moreover it is possible to excavate the resume of more matchings.The precision of matching can come also above keyword search to searching out
Resume carry out intelligent sequencing by matching degree, greatly shorten position retrieval time, improve the search efficiency of user.
It is aided with keyword, conditional filtering, intelligent sequencing on the basis of semantic matches, allows the search of user to greatly promote.Simultaneity factor
Change actively search actively to recommend, allow user in the case of no removal search, the very first time receives the newly-increased suitable letter in market
Go through, so that shortening recruitment cycle improves efficiency.
Brief description of the drawings
Fig. 1 shows that method flow diagram is recommended in a kind of talent's search based on semantic matches of the present invention；
Fig. 2 shows a kind of talent's search commending system structured flowchart based on semantic matches of the present invention；
Fig. 3 shows that method flow diagram is recommended in talent's search of one embodiment of the invention.
Specific embodiment
It is below in conjunction with the accompanying drawings and specific real in order to be more clearly understood that the above objects, features and advantages of the present invention
Mode is applied to be further described in detail the present invention.It should be noted that in the case where not conflicting, the implementation of the application
Feature in example and embodiment can be mutually combined.
Many details are elaborated in the following description in order to fully understand the present invention, but, the present invention may be used also
Implemented with being different from mode described here using other, therefore, protection scope of the present invention does not receive following public tool
The limitation of body embodiment.
Core point of the invention is to breach word computer code memory module in itself, understanding of spoken and written languages and is recruiting
The profound implication in field is engaged, then these implications is expressed with higher-dimension mathematic vector, and the similar of word is expressed with space length
Degree.
Based on exclusive semantic matching method, the present invention has merged complex conditions screening, keyword filtering simultaneously, so that can
To retrieve the candidate most matched with employing unit demand, and give an efficient visualization output template.
The technical solution adopted in the present invention retrieves resume using semantic matches technology, and user only needs to be input into whole duty
Position requires that just man-to-man Keywords matching can be taken leave of by the language search of various dimensions, does not find out text description singly the same
Resume, moreover it is possible to excavate the resume of more matchings.The precision of matching can come also above keyword search to searching out
Resume carry out intelligent sequencing by matching degree, greatly shorten position retrieval time, improve the search efficiency of user.
It is aided with keyword, conditional filtering, intelligent sequencing on the basis of semantic matches, allows the search of user to greatly promote.Simultaneity factor
Change actively search actively to recommend, allow user in the case of no removal search, the very first time receives the newly-increased suitable letter in market
Go through, so that shortening recruitment cycle improves efficiency.
Fig. 1 shows that method flow diagram is recommended in a kind of talent's search based on semantic matches of the present invention.
As shown in figure 1, recommendation method is searched for according to a kind of talent based on semantic matches of the present invention, including：
Step 1, receives the recruitment information of user terminal input；
Step 2, according to the recruitment information for obtaining, is parsed；
Step 3, vectorization calculating is carried out to the recruitment information after parsing, generates vectorization data；
Step 4, the vectorization data of relatively more described generation and the similarity of vectorization data pre-stored in database；
Step 5, comparative result is exported to user terminal.
Wherein, step 2 is specifically, the recruitment information of acquisition user input, analyzes the demand of user, including educational background,
School, specialty, length of service, emolument, city, industry, sex, age, ability, the demand of experience；Standard is carried out to these data
Change operation, be converted to standardized querying condition.
More specifically, also include before step 1：
The biographic information of each channel is collected, the biographic information that will be collected into carries out unified structure, extract effective field, will be each
Individual field carries out vectorization treatment, generates vectorization data, stores in database.Vectorization treatment is conventional in this area
Technology, the present invention is no longer repeated one by one.
More specifically, the resume form of collection includes text, HTML, Word, PDF.The resume of collection can be asked
Duty person is by attachment formats such as word, PDF online web page editing, or that job hunter uploads.
, wherein it is desired to the biographic information to collecting carries out data cleansing, from each different field of resume information extraction, beat
Upper label；Field contents unification is converted into canonical form.
User's usage behavior is can be combined with, suitable resume is regularly recommended into user.For example, on a daily or weekly basis
Satisfactory biographic information is provided to recruitment user.
Fig. 2 shows a kind of talent's search commending system structured flowchart based on semantic matches of the present invention.
As shown in Fig. 2 the present invention also provides a kind of talent's search commending system based on semantic matches, including：
Receiver module, the recruitment information for receiving user terminal input；
Parsing module, for according to the recruitment information for obtaining, being parsed；
Quantization modules, for carrying out vectorization calculating to the recruitment information after parsing, generate vectorization data；
Comparison module, the vectorization data for comparing the generation are similar to the vectorization data being pre-stored in database
Degree；
Output module, for comparative result to be exported to user terminal.
Also include database, the biographic information for collecting each channel, the biographic information that will be collected into carries out unifying knot
Structure, extracts effective field, and each field is carried out into vectorization treatment, generates vectorization data, stores in database.
Data cleansing module, the biographic information to collecting carries out data cleansing, from each different word of resume information extraction
Section, it is tagged；Field contents unification is converted into canonical form.
More specifically, parsing module concrete function is：
Obtain the recruitment information of user input, analyze the demand of user, including educational background, school, specialty, the length of service, emolument,
City, industry, sex, age, ability, the demand of experience；Operation is standardized to these data, standardized looking into is converted to
Inquiry condition.
Wherein, each module of system carries out data interaction and connection according to respective function with corresponding module, and this is
What those skilled in the art beyond all doubt can draw, the present invention is no longer repeated one by one.
The process for wherein carrying out resume collection for background server also includes with lower module：
Resume collection module：Collect various forms, the resume of various typesettings
Data cleansing module：Automatically the resume content being collected into is parsed, each field is extracted
Enter library module：With data cleansing module coupling, each field is carried out into structuring, be stored in database
Vectorization module：With storage module couples, by the field of structuring by word change into high dimension vector and storage corresponding
Database in
Input module：The requirement of user's position vacant is obtained, various demands, including educational background, are extracted from one section of text demand
The demand of school, specialty, length of service, emolument, city, industry, sex, age, ability, experience etc..
Matching module：With input module, vectorization module couples, the height that will be stored with vectorization module after input vector
Dimensional vector calculates similarity, and by sequencing of similarity
Recommending module：It is automatic in the resume of magnanimity daily, matching degree is calculated, periodically recommend resume to give automatically according to recommendation rules
User.
Fig. 3 shows that method flow diagram is recommended in talent's search of one embodiment of the invention.
This talent's search commending system based on semantic matches is comprised the following steps：
（One）Data preparation stage
Magnanimity resume is collected, form includes the common format such as text, HTML, Word, PDF.
Form is changed and extracts the content of text in resume；
Resume to collecting carries out data cleansing, and each different field is extracted from resume text, tagged；
Field contents unification is converted into canonical form, such as place unification national standard code is represented；
The content of each field is stored in database；
Content of text is converted into high dimension vector, database is stored in.
（Two）User mutual-input phase
The input of user is obtained, including text input and condition select two parts；
Intellectual analysis go out the demand of user, including educational background, school, specialty, length of service, emolument, city, industry, sex, year
The demand of age, ability, experience etc..Operation is standardized to these data, standardized querying condition is converted to；And by user
The content of text of input carries out high dimension vector；
Querying condition is sent to computing module；
（Three）Calculation stages
According to the querying condition of user input, the target resume for most matching is quickly found out in storehouse, and it is defeated to be sorted by specified rule
Go out；Lookup is divided into the data of three types：
Conditional filtering：For example age atmosphere, length of service scope, point range etc.；
Keyword requirement：The keyword specified must be included
Semantic vector distance is calculated：User input content and distance vectorial in database.
Querying condition, user are checked that record, user operation records are all stored in database.
（Four）User mutual-visualization output stage
The resume that will most match shows according to the form being readily appreciated that, and by the semantic highlighted output of content for most matching, carries
The efficiency that user high checks.
（Five）The recommendation stage
Resume data enter system in constantly renewal, and system can be carried out new resume with the user in system to the demand of the talent
Matching degree is calculated, and combines user's usage behavior, and suitable resume regularly is recommended into user.
Core point of the invention is to breach word computer code memory module in itself, understanding of spoken and written languages and is recruiting
The profound implication in field is engaged, then these implications is expressed with higher-dimension mathematic vector, and the similar of word is expressed with space length
Degree.
Based on exclusive semantic matching method, the present invention has merged complex conditions screening, keyword filtering simultaneously, so that can
To retrieve the candidate most matched with employing unit demand, and give an efficient visualization output template.
In the description of this specification, the term such as term " installation ", " connected ", " connection " all should be interpreted broadly, for example,
" connection " can be fixedly connected, or be detachably connected, or be integrally connected；" connected " can be joined directly together,
Can be indirectly connected to by intermediary.For the ordinary skill in the art, on can understanding as the case may be
State term concrete meaning in the present invention.
In the description of this specification, the description of term " one embodiment ", " some embodiments ", " specific embodiment " etc.
Mean that the specific features, structure, material or the feature that are described with reference to the embodiment or example are contained in of the invention at least one real
In applying example or example.In this manual, the schematic representation to above-mentioned term is not necessarily referring to identical embodiment or reality
Example.And, the specific features of description, structure, material or feature can in one or more any embodiments or example with
Suitable mode is combined.
The preferred embodiments of the present invention are the foregoing is only, is not intended to limit the invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.It is all within the spirit and principles in the present invention, made any repair
Change, equivalent, improvement etc., should be included within the scope of the present invention.
Claims (10)
1. a kind of talent based on semantic matches searches for recommendation method, it is characterised in that including：
Step 1, receives the recruitment information of user terminal input；
Step 2, according to the recruitment information for obtaining, is parsed；
Step 3, vectorization calculating is carried out to the recruitment information after parsing, generates vectorization data；
Step 4, the vectorization data of relatively more described generation and the similarity of vectorization data pre-stored in database；
Step 5, comparative result is exported to user terminal.
2. a kind of talent based on semantic matches according to claim 1 searches for recommendation method, it is characterised in that in step
Also included before 1：
The biographic information of each channel is collected, the biographic information that will be collected into carries out unified structure, extract effective field, will be each
Individual field carries out vectorization treatment, generates vectorization data, stores in database.
3. a kind of talent based on semantic matches according to claim 2 searches for recommendation method, it is characterised in that
The resume form of collection includes text, HTML, Word, PDF.
4. a kind of talent based on semantic matches according to claim 2 searches for recommendation method, it is characterised in that the receipts
Collect the biographic information of each channel, the biographic information that will be collected into carries out unified structure, effective field is extracted, by each field
Vectorization treatment is carried out, vectorization data are generated, stored in database, also included：
Biographic information to collecting carries out data cleansing, tagged from each different field of resume information extraction；By field
Content unification is converted to canonical form.
5. a kind of talent based on semantic matches according to claim 1 searches for recommendation method, it is characterised in that described
According to the recruitment information for obtaining, parsed, specifically included：
Obtain the recruitment information of user input, analyze the demand of user, including educational background, school, specialty, the length of service, emolument,
City, industry, sex, age, ability, the demand of experience；Operation is standardized to these data, standardized looking into is converted to
Inquiry condition.
6. a kind of talent based on semantic matches according to claim 1 searches for recommendation method, it is characterised in that also wrap
Include：
With reference to user's usage behavior, suitable resume is regularly recommended into user.
7. a kind of talent based on semantic matches searches for commending system, it is characterised in that including：
Receiver module, the recruitment information for receiving user terminal input；
Parsing module, for according to the recruitment information for obtaining, being parsed；
Quantization modules, for carrying out vectorization calculating to the recruitment information after parsing, generate vectorization data；
Comparison module, the vectorization data for comparing the generation are similar to the vectorization data being pre-stored in database
Degree；
Output module, for comparative result to be exported to user terminal.
8. a kind of talent based on semantic matches according to claim 7 searches for commending system, it is characterised in that also wrap
Include：
Database, the biographic information for collecting each channel, the biographic information that will be collected into carries out unified structure, and extraction has
Effect field, vectorization treatment is carried out by each field, generates vectorization data, is stored in database.
9. a kind of talent based on semantic matches according to claim 7 searches for commending system, it is characterised in that also wrap
Include：
Data cleansing module, the biographic information to collecting carries out data cleansing, from each different field of resume information extraction, beats
Upper label；Field contents unification is converted into canonical form.
10. a kind of talent based on semantic matches according to claim 7 searches for recommendation method, it is characterised in that described
Parsing module concrete function is：
Obtain the recruitment information of user input, analyze the demand of user, including educational background, school, specialty, the length of service, emolument,
City, industry, sex, age, ability, the demand of experience；Operation is standardized to these data, standardized looking into is converted to
Inquiry condition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611252522.6A CN106777296A (en) | 2016-12-30 | 2016-12-30 | Method and system are recommended in a kind of talent's search based on semantic matches |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611252522.6A CN106777296A (en) | 2016-12-30 | 2016-12-30 | Method and system are recommended in a kind of talent's search based on semantic matches |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106777296A true CN106777296A (en) | 2017-05-31 |
Family
ID=58928152
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611252522.6A Pending CN106777296A (en) | 2016-12-30 | 2016-12-30 | Method and system are recommended in a kind of talent's search based on semantic matches |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106777296A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN108021655A (en) * | 2017-12-01 | 2018-05-11 | 广东工业大学 | A kind of data processing method, device, equipment and readable storage medium storing program for executing |
| 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 |
| CN109614486A (en) * | 2018-11-28 | 2019-04-12 | 宇捷东方(北京)科技有限公司 | A kind of service automatic Recommendation System and method based on natural language processing technique |
| CN109740147A (en) * | 2018-12-14 | 2019-05-10 | 国云科技股份有限公司 | A kind of big quantity personnel resume duplicate removal Match Analysis |
| CN109754233A (en) * | 2019-01-29 | 2019-05-14 | 上海嘉道信息技术有限公司 | A kind of method and system of intelligent recommendation job information |
| CN109902726A (en) * | 2019-02-02 | 2019-06-18 | 天津字节跳动科技有限公司 | Biographic information processing method and processing device |
| CN110020327A (en) * | 2019-04-16 | 2019-07-16 | 上海大易云计算股份有限公司 | A kind of resume resolution system based on vertical search engine |
| CN110378544A (en) * | 2018-04-12 | 2019-10-25 | 百度在线网络技术（北京）有限公司 | A kind of personnel and post matching analysis method, device, equipment and medium |
| CN110472108A (en) * | 2019-06-05 | 2019-11-19 | 东华大学 | Garment fabric sample retrieving method based on text profile matching |
| CN111080221A (en) * | 2018-10-21 | 2020-04-28 | 张孟强 | Bidirectional bidding matching method and system based on demands of both job hunting and recruitment parties |
| 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 |
| TWI696966B (en) * | 2018-10-03 | 2020-06-21 | 一零四資訊科技股份有限公司 | Recommended server and method thereof |
| CN112396401A (en) * | 2020-11-23 | 2021-02-23 | 五八到家有限公司 | Method and equipment for pushing resume of worker and storage medium |
| CN112908436A (en) * | 2021-02-09 | 2021-06-04 | 北京药明津石医药科技有限公司 | Clinical test data structuring method, clinical test recommending method and device |
| CN113421006A (en) * | 2021-07-01 | 2021-09-21 | 宁波大学 | Semantic-based interpretable human and job matching method and system |
| CN113806598A (en) * | 2021-09-23 | 2021-12-17 | 广东省通信产业服务有限公司广州分公司 | Professional talent classification statistical database and method beneficial to cloud search |
| CN117236322A (en) * | 2023-10-07 | 2023-12-15 | 深圳夸夸菁领科技有限公司 | NLP-based virtual hunting assistant system and hunting method |
| CN117314381A (en) * | 2023-11-29 | 2023-12-29 | 山东杰出人才发展集团有限公司 | Person post matching system based on intelligent data analysis |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105786781A (en) * | 2016-03-14 | 2016-07-20 | 裴克铭管理咨询（上海）有限公司 | Job description text similarity calculation method based on topic model |
-
2016
- 2016-12-30 CN CN201611252522.6A patent/CN106777296A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105786781A (en) * | 2016-03-14 | 2016-07-20 | 裴克铭管理咨询（上海）有限公司 | Job description text similarity calculation method based on topic model |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
| 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 |
| CN108021655A (en) * | 2017-12-01 | 2018-05-11 | 广东工业大学 | A kind of data processing method, device, equipment and readable storage medium storing program for executing |
| US11238381B2 (en) | 2018-04-12 | 2022-02-01 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for talent-post matching and computer readable storage medium |
| CN110378544A (en) * | 2018-04-12 | 2019-10-25 | 百度在线网络技术（北京）有限公司 | A kind of personnel and post matching analysis method, device, equipment and medium |
| TWI696966B (en) * | 2018-10-03 | 2020-06-21 | 一零四資訊科技股份有限公司 | Recommended server and method thereof |
| CN111080221A (en) * | 2018-10-21 | 2020-04-28 | 张孟强 | Bidirectional bidding matching method and system based on demands of both job hunting and recruitment parties |
| CN109614486A (en) * | 2018-11-28 | 2019-04-12 | 宇捷东方(北京)科技有限公司 | A kind of service automatic Recommendation System and method based on natural language processing technique |
| CN109740147A (en) * | 2018-12-14 | 2019-05-10 | 国云科技股份有限公司 | A kind of big quantity personnel resume duplicate removal Match Analysis |
| CN109754233A (en) * | 2019-01-29 | 2019-05-14 | 上海嘉道信息技术有限公司 | A kind of method and system of intelligent recommendation job information |
| CN109754233B (en) * | 2019-01-29 | 2024-05-07 | 上海嘉道信息技术有限公司 | Method and system for intelligently recommending position information |
| CN109902726A (en) * | 2019-02-02 | 2019-06-18 | 天津字节跳动科技有限公司 | Biographic information processing method and processing device |
| CN110020327A (en) * | 2019-04-16 | 2019-07-16 | 上海大易云计算股份有限公司 | A kind of resume resolution system based on vertical search engine |
| CN110472108A (en) * | 2019-06-05 | 2019-11-19 | 东华大学 | Garment fabric sample retrieving method based on text profile matching |
| CN110472108B (en) * | 2019-06-05 | 2023-08-29 | 东华大学 | Clothing fabric sample retrieval method based on text description matching |
| 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 |
| CN112396401A (en) * | 2020-11-23 | 2021-02-23 | 五八到家有限公司 | Method and equipment for pushing resume of worker and storage medium |
| CN112908436A (en) * | 2021-02-09 | 2021-06-04 | 北京药明津石医药科技有限公司 | Clinical test data structuring method, clinical test recommending method and device |
| CN112908436B (en) * | 2021-02-09 | 2022-03-11 | 上海药明津石医药科技有限公司 | Clinical test data structuring method, clinical test recommending method and device |
| CN113421006B (en) * | 2021-07-01 | 2022-05-17 | 宁波大学 | Semantic-based interpretable human and job matching method and system |
| CN113421006A (en) * | 2021-07-01 | 2021-09-21 | 宁波大学 | Semantic-based interpretable human and job matching method and system |
| CN113806598A (en) * | 2021-09-23 | 2021-12-17 | 广东省通信产业服务有限公司广州分公司 | Professional talent classification statistical database and method beneficial to cloud search |
| CN113806598B (en) * | 2021-09-23 | 2024-04-05 | 广东省通信产业服务有限公司广州分公司 | Professional classification statistical database and method facilitating cloud search |
| CN117236322A (en) * | 2023-10-07 | 2023-12-15 | 深圳夸夸菁领科技有限公司 | NLP-based virtual hunting assistant system and hunting method |
| CN117314381A (en) * | 2023-11-29 | 2023-12-29 | 山东杰出人才发展集团有限公司 | Person post matching system based on intelligent data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106777296A (en) | Method and system are recommended in a kind of talent's search based on semantic matches | |
| CN109145260B (en) | Automatic text information extraction method | |
| CN112732934B (en) | Power grid equipment word segmentation dictionary and fault case library construction method | |
| CN111737496A (en) | Power equipment fault knowledge map construction method | |
| WO2018189589A2 (en) | Systems and methods for document processing using machine learning | |
| US8312041B2 (en) | Resource description framework network construction device and method using an ontology schema having class dictionary and mining rule | |
| CN112699246A (en) | Domain knowledge pushing method based on knowledge graph | |
| CN110175334B (en) | Text knowledge extraction system and method based on custom knowledge slot structure | |
| CN111832290B (en) | Model training method and device for determining text relevance, electronic equipment and readable storage medium | |
| CN113254507B (en) | Intelligent construction and inventory method for data asset directory | |
| CN116628173B (en) | Intelligent customer service information generation system and method based on keyword extraction | |
| CN112699232A (en) | Text label extraction method, device, equipment and storage medium | |
| CN114495143A (en) | Text object identification method and device, electronic equipment and storage medium | |
| CN112446209A (en) | Method, equipment and device for setting intention label and storage medium | |
| CN115292518A (en) | Power distribution network fault processing method and system based on knowledge type information extraction | |
| CN112560425B (en) | Template generation method and device, electronic equipment and storage medium | |
| CN112417996B (en) | Information processing method and device for industrial drawing, electronic equipment and storage medium | |
| CN111324705A (en) | System and method for adaptively adjusting related search terms | |
| US20190095525A1 (en) | Extraction of expression for natural language processing | |
| Loglisci et al. | Toward geographic information harvesting: Extraction of spatial relational facts from Web documents | |
| CN112182019A (en) | Semantic parsing search method for power grid statistics professional index feature extraction | |
| CN110309258B (en) | Input checking method, server and computer readable storage medium | |
| CN114741483B (en) | Data identification method and device | |
| CN101334793B (en) | Method for automatic recognition for dependency relationship of demand | |
| CN116304231A (en) | Query statement generation method and device based on grammar parsing tree, equipment and medium |
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: 20170531 |