CN113298505A - Talent recommendation system and method based on big data - Google Patents
Talent recommendation system and method based on big data Download PDFInfo
- Publication number
- CN113298505A CN113298505A CN202110833849.7A CN202110833849A CN113298505A CN 113298505 A CN113298505 A CN 113298505A CN 202110833849 A CN202110833849 A CN 202110833849A CN 113298505 A CN113298505 A CN 113298505A
- Authority
- CN
- China
- Prior art keywords
- paper
- value
- journal
- talent
- keywords
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
- G06Q10/1053—Employment or hiring
-
- 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
- G06F16/35—Clustering; Classification
-
- 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
- G06F16/9532—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a talent recommendation system based on big data, which is characterized by comprising the following components: the system comprises a data acquisition module, a talent screening and matching module, a talent capability evaluation module and a talent recommendation module, wherein the data acquisition module is used for extracting information of a recruiter and a job seeker; and the talent screening and matching module is used for receiving the information acquired by the data acquisition module and processing the received information. The method can actively extract and match the keywords in the recruitment information and the resume of the job seeker, and screen the job seekers meeting the requirements; the ability of job seekers can be judged from multiple aspects, and job seekers with weak ability can be eliminated. The method reduces the workload of the recruiters, improves the recruitment efficiency, screens the abilities of the job seekers and provides high-potential high-quality talents which accord with the recruitment information and have strong abilities for the recruiting companies.
Description
Technical Field
The invention relates to the technical field of big data, in particular to a talent recommendation system and method based on big data.
Background
Along with the development of the society, the recruiting company recruits the job seekers in a manner of publishing the recruiting information on the network, the manner is quick, simple and convenient, the recruiters of the recruiting company can list the requirement of the job of the recruiting company in advance, and then screen the recruiters, the manner can lead the recruiters to communicate and know the job seekers in advance, further determine whether the job seekers meet the requirement of the recruiting company, and improve the recruiting efficiency.
However, the competitive pressure of job seekers is continuously increased, many job seekers will carry out mass delivery resumes when finding work, and whether the conditions of the job seekers meet the requirements of a recruiting company is not detailed, so that the behavior of the job seekers greatly increases the workload of the job seekers.
Meanwhile, some job seekers do not see the job sites corresponding to the recruitment information in detail during recruitment, and therefore, the result of the behavior is that some job seekers have job problems due to too long distance between the job sites when interviewing is successful.
In view of the above situation, a system and a method for talent recommendation based on big data are needed, which can not only actively extract and match the recruitment information and the keywords in the resume of job seeker, but also screen job seeker meeting the requirement; the ability of job seekers can be judged from multiple aspects, and job seekers with weak ability can be eliminated. The method reduces the workload of the recruiters, improves the recruitment efficiency, screens the abilities of the job seekers and provides high-potential high-quality talents which accord with the recruitment information and have strong abilities for the recruiting companies.
Disclosure of Invention
The invention aims to provide a talent recommendation system and method based on big data to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: a talent recommendation system based on big data, comprising: a data acquisition module, a talent screening and matching module, a talent capability evaluation module and a talent recommendation module,
the data acquisition module is used for extracting the information of the recruitment company and the job seeker;
the talent screening and matching module is used for receiving the information acquired by the data acquisition module and processing the received information;
the talent ability evaluation module is used for evaluating the ability corresponding to the screened talents in the talent screening and matching module and sequencing the screened talents according to the ability;
the talent recommendation module is used for recommending talents to the corresponding recruiter according to the evaluation result of the talent capability evaluation module;
the talent screening and recommending module extracts the recruitment information and information of job seekers, the talent screening and matching module performs matching according to keywords in the acquired data to screen out job seekers which meet the requirement of the recruitment information and are close to a company, and the talent ability evaluating module judges the ability of the job seekers obtained from the talent screening and matching module, screens again, sorts the job seekers according to the ability values, and then recommends the obtained results to a recruitment company through the talent recommending module.
The data acquisition module is used for respectively extracting keywords from the recruitment information corresponding to the recruitment company and the resume of the job seeker, the talent screening and matching module is used for comparing the keywords extracted from the recruitment company and the resume of the job seeker, counting the number of the overlapped keywords of the talents, dividing the number of the overlapped keywords of the talents by the number of the keywords extracted from the recruitment information corresponding to the recruitment company, and taking the obtained ratio as the post matching degree A of the job seeker and the corresponding recruitment information in the recruitment company;
the data acquisition module extracts the recruitment information corresponding to the recruitment company and the keywords in the resume of the job seeker, and indicates that the resume of the job seeker conforms to the requirement of the recruitment information and is matched with the corresponding post in the recruitment information according to the proportion that the number of the keywords overlapped with each other is higher than the number of the keywords in the recruitment information.
The talent screening and matching module further judges the post matching degree A,
when the A is larger than or equal to a first preset value, judging that the resume of the job seeker meets the requirement of the recruitment information of the recruitment company;
when A is smaller than a first preset value, judging that the resume of the job seeker does not accord with the requirement of the recruitment information of the recruitment company;
the talent screening and matching module extracts job seeker information with resumes meeting the requirement of the recruitment information of the recruitment company, sorts the distances between the current position of the job seeker and the position of the recruitment company from big to small,
and multiplying the number of the persons to be recruited corresponding to the recruitment information by a preselection coefficient q to obtain a preselected number B corresponding to the recruitment information, and screening the job seekers corresponding to the former B names from the sorting of the distances between the positions of the job seekers and the positions of the recruitment companies as preselections.
The talent screening module screens the job seeker from two angles of post matching degree and the distance between the current position of the job seeker and the position of the recruiting company, the post matching degree directly reflects the degree of conformity of the job seeker with the post corresponding to the recruitment information, the distance between the current position of the job seeker and the position of the recruiting company takes the bearing capacity of the job seeker on the employment scope into consideration, and the farther the current position of the job seeker is away from the recruiting company, the smaller the possibility of the job seeker to work and the smaller the possibility of the job seeker to develop in the recruiting company for a long time.
Further, the talent ability evaluation module evaluates the ability of the B-preselectors screened in the talent screening matching module, wherein the evaluation content comprises the section v of the papers published by the preselectors during the school and the corresponding gold-containing value of each paper,
the ability of the preselector is digitalized according to the volume v of published papers and the gold-containing value corresponding to each paper, the gold-containing values corresponding to each paper of job seekers are accumulated to obtain the ability value W of the preselector,
dividing the preselected person's ability value W by the preselected person's published paper volume v during the school to obtain the gold-bearing value E corresponding to each paper on average of the preselected person, determining the preselected person's ability value W and the gold-bearing value E corresponding to each paper on average of the preselected person,
when W is less than or equal to a second preset value, judging that the capability of the preselector is weak, and removing the preselector from a list of preselectors;
when W is larger than the second preset value and smaller than the third preset value, the value of E is compared,
if E is less than or equal to the fourth preset value, judging that the ability of the preselector is weak, removing the preselector from a list of preselectors,
if E is larger than a fourth preset value, judging that the preselector has normal capacity;
when W is larger than or equal to a third preset value, judging that the preselector is normal in capability;
and sorting the remaining preselectiors according to the capacity values W of the remaining preselectiors, wherein the larger the data of the corresponding capacity values W of the preselectiors is, the higher the rank of the preselectiors is.
The talent ability evaluation module considers the papers published by the preselector in the school period, associates the published papers, the personal ability and the job hunting, comprehensively considers two factors of the ability value W of the preselector and the gold-containing value E corresponding to each average paper of the preselector, eliminates the preselector with weak ability by comparing with a preset value, and sorts the rest preselector according to the ability value.
Furthermore, the judgment of the gold-containing value corresponding to each paper of the preselection by the talent capability evaluation module comprises two aspects, namely, on one hand, the evaluation of the content of the paper and the obtaining of a corresponding content evaluation value C; on the other hand, the publication journal of the article is evaluated, and a corresponding journal evaluation value D is obtained,
the preselectors each paper corresponds to a gold-bearing value = content evaluation value C × journal evaluation value D.
The talent ability evaluation module judges the corresponding gold content of the paper according to the content of the published paper and the corresponding journal, and the better the content evaluation result is, or the better the evaluation of the corresponding journal is, the better the value of the paper and the gold content of the paper can be reflected.
Further, the content evaluation value C is related to the number of research directions n of the paper, the professional coefficient u of the paper and the moisture degree f of the paper,
the search of the number n of the thesis research directions needs to extract keywords in the thesis content, compare the extracted keywords with a preset comparison database, classify the extracted keywords according to the categories of the keywords in the comparison database, count the number m of various keywords in the classified keywords, compare the number m of various keywords with a fifth preset value,
when m is larger than a fifth preset value, judging the keyword category as an effective category,
when m is smaller than a fifth preset value, judging the keyword category as an invalid category,
counting the number of the effective keyword categories to obtain a numerical value which is the number n of the thesis research directions;
the professional coefficient u of the paper is obtained by analyzing the keywords in the extracted paper content, the extracted keywords are compared with a comparison database, the uncommon keywords related to the research topic are screened out, the number of the uncommon keywords appearing in the paper is counted, the number u1 of the uncommon keywords appearing in each thousand words in the average paper is calculated, the professional coefficient u of the paper is equal to the number u1 of the uncommon keywords appearing in each thousand words in the average paper plus 1,
namely, it is
，
The judgment mode of the uncommon keywords is as follows: in the statistics of all extracted keywords in the comparison database, keywords with the frequency less than 5 times in each unit number of extracted keywords are rare keywords;
the water content degree f is embodied by the similarity of the paper content with the same subject in other periodicals, firstly, all papers with the same subject in other periodicals are obtained, then the first three sections of the papers are respectively compared with the obtained first three sections of the papers, the corresponding similarity degrees f1 are respectively obtained, the obtained similarity degrees f1 are sequenced, and the highest similarity degree f is sequencedComparing the three papers in the publication with the above paper in their entirety, finding out the corresponding similarity f2, and finding out the maximum value of the three similarities f2
As the value of the water degree f in this paper;
the value of the content evaluation value C is equal to the product of the number n of research directions of the paper, the professional coefficient u of the paper and the moisture degree f of the paper, namely
，
Further obtain
。
The invention obtains the content evaluation value through the number n of research directions of the paper, the professional coefficient u of the paper and the moisture degree f of the paper, in the calculation of the number n of the research directions of the paper, the keywords extracted from the paper are compared and classified with a comparison database, and the number of each category is compared with a fifth preset value, so as to judge whether the category is an effective category, the more the number of the effective categories is, namely the larger the number of the research directions of the paper is, the better the paper is, the more the rarely-used keywords appear on the professional coefficient u of the paper is, the more the paper is highlighted in the writing depth, the more professional content of the paper can be obtained, the professional coefficient is set to be the number u1 plus 1 of the rarely-used keywords appearing on each thousand words of the paper on average, because the obtained integral result C is equal to 0 when the number u1 is equal to 0, and the influence caused by other factors is ignored, in the calculation of the moisture degree f, the first three sections are compared firstly to reduce the workload of data comparison and improve the comparison efficiency, and similarly, only the three papers with the highest similarity are compared with the paper in full text to improve the comparison efficiency and reduce the workload of data comparison, and the final comparison result is not greatly influenced.
Further, the journal assessment value D is related to the level value h of published journal of the paper and the authority k of each paper published in the journal,
the level value h for publishing the journal of the paper is set according to the level of the department of charge to which the journal of the paper belongs, and the level of the department of charge to which the journal belongs comprises: the state level, the provincial level, the city level, the level of the competent departments to which the journal belongs are different, the corresponding value of the level value h for publishing the journal of the paper is also different,
when the level of the department of charge to which the journal belongs is the national level, the corresponding level value h for publishing the journal of the paper is j1,
when the level of the department in charge of the periodical belongs to province level, the corresponding level value h for publishing the periodical is j2,
when the level of the department in charge to which the journal belongs is the market level, the corresponding level value h for publishing the journal of the paper is j3,
the value of j1 is greater than the value of j2, the value of j2 is greater than the value of j 3;
the authority degree k of each paper published in the journal is influenced by the ratio i of the total number of browsed people p in unit time of the paper to the total number of browsed people of students or teachers belonging to 985 colleges and universities in the corresponding number of browsed people, and the authority degree k is determined by the ratio of the total number of browsed people p to the total number of students or teachers belonging to the 985 colleges and universities
L is an authority coefficient of a paper published in a periodical;
respectively calculating the product of the rank value h of the journal and the authority k of each paper published by the journal, accumulating the obtained product results, and dividing the accumulated sum by the paper number s of the journal to obtain a value which is a journal evaluation value D, namely:
said
Authority of the x-th paper published for the journal, said
In the unit of time of the x article published for the journalTotal number of browsing people, said
The number of students or teachers belonging to 985 colleges and universities in the corresponding browsing population per unit time of the x paper published for the journal is the ratio of the total browsing population.
In the process of obtaining the evaluation value D of the journal, the rank value h of the journal publishing the paper and the authority k of each paper published by the journal are comprehensively considered, the rank of a competent department to which the journal belongs can intuitively feed back the rank of the journal, the authority k of each paper published by the journal is influenced by the total browsing number p of the paper in unit time and the ratio i of the number of students or teachers belonging to 985 colleges to the total browsing number in corresponding browsing numbers, and the larger the total browsing number in unit time and the larger the ratio of the number of students or teachers belonging to 985 colleges to the total browsing number, the more authoritative the journal is.
Further, the ability value W of the preselected person is the sum of the gold-containing values corresponding to each of the v papers published by the preselected person during the school, namely:
the above-mentioned
For the content evaluation corresponding to the y-th paper published by the pre-selector during the school, said
For the journal evaluation corresponding to the y-th paper published by the pre-selector during the school,
the above-mentioned
The number of research directions of the corresponding papers for the y-th paper published by the pre-selected person during the school period, said
The number of rare keywords appearing on average per thousand words for the relevant paper of the y paper published by the pre-selected person during the school period
For the y-th paper published by the pre-selected person during the school
Value of, said
A rating of a journal corresponding to the y-th paper published by the preselected person during the school, said journal being associated with a journal
A journal published paper piece corresponding to the y-th paper published by the preselected person during the school, said
Total number of views per unit time for the x-th paper published in a journal corresponding to the y-th paper published by the preselected person during the school
The number of students or teachers belonging to 985 colleges in the browsing number corresponding to the corresponding journal published by the pre-selected paper during the school is the ratio of the total browsing number.
A talent recommendation method based on big data comprises the following specific operation steps:
s1, extracting the information of the recruitment company and the job seeker in the data acquisition module;
s2, receiving the information acquired by the data acquisition module through the talent screening and matching module, and processing the received information;
s3, in the talent ability evaluation module, evaluating the ability corresponding to the screened talents in the talent screening and matching module, and auditing and sequencing the screened talents according to the ability;
and S4, in the talent recommendation module, recommending talents to the corresponding recruiter according to the evaluation result of the talent capability evaluation module.
Compared with the prior art, the invention has the following beneficial effects: the method can actively extract and match the keywords in the recruitment information and the resume of the job seeker, and screen the job seekers meeting the requirements; the ability of job seekers can be judged from multiple aspects, and job seekers with weak ability can be eliminated. The method reduces the workload of the recruiters, improves the recruitment efficiency, screens the abilities of the job seekers and provides high-potential high-quality talents which accord with the recruitment information and have strong abilities for the recruiting companies.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram of a big data-based talent recommendation system and method according to the present invention;
FIG. 2 is a schematic flow chart of talent screening and matching modules in the big data based talent recommendation system and method according to the present invention;
FIG. 3 is a schematic flow chart of a talent ability evaluation module in the system and method for talent recommendation based on big data according to the present invention;
FIG. 4 is a schematic flow chart of the big data-based talent recommendation system and method for finding the gold-bearing value consideration of each paper of the preselectiors.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-4, the present invention provides a technical solution: a talent recommendation system based on big data, comprising: a data acquisition module, a talent screening and matching module, a talent capability evaluation module and a talent recommendation module,
the data acquisition module is used for extracting the information of the recruitment company and the job seeker;
the talent screening and matching module is used for receiving the information acquired by the data acquisition module and processing the received information;
the talent ability evaluation module is used for evaluating the ability corresponding to the screened talents in the talent screening and matching module and sequencing the screened talents according to the ability;
the talent recommendation module is used for recommending talents to the corresponding recruiter according to the evaluation result of the talent capability evaluation module;
the talent screening and recommending module extracts the recruitment information and information of job seekers, the talent screening and matching module performs matching according to keywords in the acquired data to screen out job seekers which meet the requirement of the recruitment information and are close to a company, and the talent ability evaluating module judges the ability of the job seekers obtained from the talent screening and matching module, screens again, sorts the job seekers according to the ability values, and then recommends the obtained results to a recruitment company through the talent recommending module.
The data acquisition module is used for respectively extracting keywords from the recruitment information corresponding to the recruitment company and the resume of the job seeker, the talent screening and matching module is used for comparing the keywords extracted from the recruitment company and the resume of the job seeker, counting the number of the overlapped keywords of the talents, dividing the number of the overlapped keywords of the talents by the number of the keywords extracted from the recruitment information corresponding to the recruitment company, and taking the obtained ratio as the post matching degree A of the job seeker and the corresponding recruitment information in the recruitment company;
the data acquisition module extracts the recruitment information corresponding to the recruitment company and the keywords in the resume of the job seeker, and indicates that the resume of the job seeker conforms to the requirement of the recruitment information and is matched with the corresponding post in the recruitment information according to the proportion that the number of the keywords overlapped with each other is higher than the number of the keywords in the recruitment information.
The talent screening and matching module further judges the post matching degree A,
when the A is larger than or equal to a first preset value, judging that the resume of the job seeker meets the requirement of the recruitment information of the recruitment company;
when A is smaller than a first preset value, judging that the resume of the job seeker does not accord with the requirement of the recruitment information of the recruitment company;
the talent screening and matching module extracts job seeker information with resumes meeting the requirement of the recruitment information of the recruitment company, sorts the distances between the current position of the job seeker and the position of the recruitment company from big to small,
and multiplying the number of the persons to be recruited corresponding to the recruitment information by a preselection coefficient q to obtain a preselected number B corresponding to the recruitment information, and screening the job seekers corresponding to the former B names from the sorting of the distances between the positions of the job seekers and the positions of the recruitment companies as preselections.
The talent screening module screens the job seeker from two angles of post matching degree and the distance between the current position of the job seeker and the position of the recruiting company, the post matching degree directly reflects the degree of conformity of the job seeker with the post corresponding to the recruitment information, the distance between the current position of the job seeker and the position of the recruiting company takes the bearing capacity of the job seeker on the employment scope into consideration, and the farther the current position of the job seeker is away from the recruiting company, the smaller the possibility of the job seeker to work and the smaller the possibility of the job seeker to develop in the recruiting company for a long time.
In this embodiment, the number of the keywords extracted from the recruitment information is 10, the number of the keywords overlapped with the recruitment information in the keywords extracted from the resume is 9, the first preset value is 0.8,
the job seeker and the post corresponding to the recruitment information in the recruitment companyDegree of bit matching
，
Since 0.9>0.8, the job seeker resume meets the requirement for the recruitment information by the recruiter.
The talent ability evaluation module evaluates the ability of the B-number preselectiors screened in the talent screening matching module, the evaluation content comprises the volume v of papers published by the preselectiors during the school and the corresponding gold-bearing value of each paper,
the ability of the preselector is digitalized according to the volume v of published papers and the gold-containing value corresponding to each paper, the gold-containing values corresponding to each paper of job seekers are accumulated to obtain the ability value W of the preselector,
dividing the preselected person's ability value W by the preselected person's published paper volume v during the school to obtain the gold-bearing value E corresponding to each paper on average of the preselected person, determining the preselected person's ability value W and the gold-bearing value E corresponding to each paper on average of the preselected person,
when W is less than or equal to a second preset value, judging that the capability of the preselector is weak, and removing the preselector from a list of preselectors;
when W is larger than the second preset value and smaller than the third preset value, the value of E is compared,
if E is less than or equal to the fourth preset value, judging that the ability of the preselector is weak, removing the preselector from a list of preselectors,
if E is larger than a fourth preset value, judging that the preselector has normal capacity;
when W is larger than or equal to a third preset value, judging that the preselector is normal in capability;
and sorting the remaining preselectiors according to the capacity values W of the remaining preselectiors, wherein the larger the data of the corresponding capacity values W of the preselectiors is, the higher the rank of the preselectiors is.
The talent ability evaluation module considers the papers published by the preselector in the school period, associates the published papers, the personal ability and the job hunting, comprehensively considers two factors of the ability value W of the preselector and the gold-containing value E corresponding to each average paper of the preselector, eliminates the preselector with weak ability by comparing with a preset value, and sorts the rest preselector according to the ability value.
In this embodiment, if the preselected capability value is 16, the average gold-bearing value for each article is 8, the second predetermined value is 20, the fourth predetermined value is 6,
because 16<20, and 8>6, the preselected person is determined to be normal in ability.
The judgment of the gold-containing value corresponding to each paper of the preselection by the talent capability evaluation module comprises two aspects, namely, on one hand, the evaluation of the content of the paper and the acquisition of a corresponding content evaluation value C; on the other hand, the publication journal of the article is evaluated, and a corresponding journal evaluation value D is obtained,
the preselectors each paper corresponds to a gold-bearing value = content evaluation value C × journal evaluation value D.
The talent ability evaluation module judges the corresponding gold content of the paper according to the content of the published paper and the corresponding journal, and the better the content evaluation result is, or the better the evaluation of the corresponding journal is, the better the value of the paper and the gold content of the paper can be reflected.
The content evaluation value C is related to the number of research directions n of the paper, the professional coefficient u of the paper and the moisture degree f of the paper,
the search of the number n of the thesis research directions needs to extract keywords in the thesis content, compare the extracted keywords with a preset comparison database, classify the extracted keywords according to the categories of the keywords in the comparison database, count the number m of various keywords in the classified keywords, compare the number m of various keywords with a fifth preset value,
when m is larger than a fifth preset value, judging the keyword category as an effective category,
when m is smaller than a fifth preset value, judging the keyword category as an invalid category,
counting the number of the effective keyword categories to obtain a numerical value which is the number n of the thesis research directions;
the professional coefficient u of the paper is obtained by analyzing the keywords in the extracted paper content, the extracted keywords are compared with a comparison database, the uncommon keywords related to the research topic are screened out, the number of the uncommon keywords appearing in the paper is counted, the number u1 of the uncommon keywords appearing in each thousand words in the average paper is calculated, the professional coefficient u of the paper is equal to the number u1 of the uncommon keywords appearing in each thousand words in the average paper plus 1,
namely, it is
，
The judgment mode of the uncommon keywords is as follows: in the statistics of all extracted keywords in the comparison database, keywords with the frequency less than 5 times in each unit number of extracted keywords are rare keywords;
the water content degree f is embodied by the similarity of the content of the paper with the same subject in other journals, firstly, all the papers with the same subject in other journals are obtained, then the first three sections of the papers are respectively compared with the obtained first three sections of the papers, the corresponding similarity degrees f1 are respectively obtained, the obtained similarity degrees f1 are sequenced, the three papers with the highest similarity degrees are compared with the paper in full text, the corresponding similarity degrees f2 are obtained, and the maximum value of the three similarity degrees f2 is used as a reference
As the value of the water degree f in this paper;
the value of the content evaluation value C is equal to the product of the number n of research directions of the paper, the professional coefficient u of the paper and the moisture degree f of the paper, namely
，
Further obtain
。
The invention obtains the content evaluation value through the number n of research directions of the paper, the professional coefficient u of the paper and the moisture degree f of the paper, in the calculation of the number n of the research directions of the paper, the keywords extracted from the paper are compared and classified with a comparison database, and the number of each category is compared with a fifth preset value, so as to judge whether the category is an effective category, the more the number of the effective categories is, namely the larger the number of the research directions of the paper is, the better the paper is, the more the rarely-used keywords appear on the professional coefficient u of the paper is, the more the paper is highlighted in the writing depth, the more professional content of the paper can be obtained, the professional coefficient is set to be the number u1 plus 1 of the rarely-used keywords appearing on each thousand words of the paper on average, because the obtained integral result C is equal to 0 when the number u1 is equal to 0, and the influence caused by other factors is ignored, in the calculation of the moisture degree f, the first three sections are compared firstly to reduce the workload of data comparison and improve the comparison efficiency, and similarly, only the three papers with the highest similarity are compared with the paper in full text to improve the comparison efficiency and reduce the workload of data comparison, and the final comparison result is not greatly influenced.
The journal assessment value D is related to the level value h of journal published by the paper and the authority k of each paper published by the journal,
the level value h for publishing the journal of the paper is set according to the level of the department of charge to which the journal of the paper belongs, and the level of the department of charge to which the journal belongs comprises: the state level, the provincial level, the city level, the level of the competent departments to which the journal belongs are different, the corresponding value of the level value h for publishing the journal of the paper is also different,
when the level of the department of charge to which the journal belongs is the national level, the corresponding level value h for publishing the journal of the paper is j1,
when the level of the department in charge of the periodical belongs to province level, the corresponding level value h for publishing the periodical is j2,
when the level of the department in charge to which the journal belongs is the market level, the corresponding level value h for publishing the journal of the paper is j3,
the value of j1 is greater than the value of j2, the value of j2 is greater than the value of j 3;
the authority degree k of each paper published in the journal is influenced by the ratio i of the total number of browsed people p in unit time of the paper to the total number of browsed people of students or teachers belonging to 985 colleges and universities in the corresponding number of browsed people, and the authority degree k is determined by the ratio of the total number of browsed people p to the total number of students or teachers belonging to the 985 colleges and universities
L is an authority coefficient of a paper published in a periodical;
respectively calculating the product of the rank value h of the journal and the authority k of each paper published by the journal, accumulating the obtained product results, and dividing the accumulated sum by the paper number s of the journal to obtain a value which is a journal evaluation value D, namely:
said
Authority of the x-th paper published for the journal, said
Total number of browsers per unit time for the xth paper published for the journal, said
The number of students or teachers belonging to 985 colleges and universities in the corresponding browsing population per unit time of the x paper published for the journal is the ratio of the total browsing population.
In the process of obtaining the evaluation value D of the journal, the rank value h of the journal publishing the paper and the authority k of each paper published by the journal are comprehensively considered, the rank of a competent department to which the journal belongs can intuitively feed back the rank of the journal, the authority k of each paper published by the journal is influenced by the total browsing number p of the paper in unit time and the ratio i of the number of students or teachers belonging to 985 colleges to the total browsing number in corresponding browsing numbers, and the larger the total browsing number in unit time and the larger the ratio of the number of students or teachers belonging to 985 colleges to the total browsing number, the more authoritative the journal is.
In this embodiment, if a journal published in a certain paper of a preselected person has a rank value of j1 and a value of j1 is 8, if the journal published two papers a and b, the authority coefficient of the published paper is 100,
the total number of brows in the unit time of the first paper is 900, the ratio of the number of students or teachers belonging to 985 colleges to the total number of brows is 35 percent,
the total number of brows in unit time of the second thesis is 841, the ratio of the number of students or teachers belonging to 985 colleges to the total number of brows is 30 percent,
then the periodical evaluation value
。
The preselected person's ability value W is the sum of the gold-bearing values corresponding to each of the v papers published by the preselected person during the school, i.e.:
the above-mentioned
For the content evaluation corresponding to the y-th paper published by the pre-selector during the school, said
For the journal evaluation corresponding to the y-th paper published by the pre-selector during the school,
the above-mentioned
Publication for the preselector during the schooly number of study directions of papers corresponding to said
The number of rare keywords appearing on average per thousand words for the relevant paper of the y paper published by the pre-selected person during the school period
For the y-th paper published by the pre-selected person during the school
Value of, said
A rating of a journal corresponding to the y-th paper published by the preselected person during the school, said journal being associated with a journal
A journal published paper piece corresponding to the y-th paper published by the preselected person during the school, said
Total number of views per unit time for the x-th paper published in a journal corresponding to the y-th paper published by the preselected person during the school
The number of students or teachers belonging to 985 colleges in the browsing number corresponding to the corresponding journal published by the pre-selected paper during the school is the ratio of the total browsing number.
A talent recommendation method based on big data comprises the following specific operation steps:
s1, extracting the information of the recruitment company and the job seeker in the data acquisition module;
s2, receiving the information acquired by the data acquisition module through the talent screening and matching module, and processing the received information;
s3, in the talent ability evaluation module, evaluating the ability corresponding to the screened talents in the talent screening and matching module, and auditing and sequencing the screened talents according to the ability;
and S4, in the talent recommendation module, recommending talents to the corresponding recruiter according to the evaluation result of the talent capability evaluation module.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. A talent recommendation system based on big data, comprising: a data acquisition module, a talent screening and matching module, a talent capability evaluation module and a talent recommendation module,
the data acquisition module is used for extracting the information of the recruitment company and the job seeker;
the talent screening and matching module is used for receiving the information acquired by the data acquisition module and processing the received information;
the talent ability evaluation module is used for evaluating the ability corresponding to the screened talents in the talent screening and matching module and sequencing the screened talents according to the ability;
the talent recommendation module is used for recommending talents to the corresponding recruiter according to the evaluation result of the talent capability evaluation module;
the data acquisition module is used for respectively extracting keywords from the recruitment information corresponding to the recruitment company and the resume of the job seeker, the talent screening and matching module is used for comparing the keywords extracted from the recruitment company and the resume of the job seeker, counting the number of the overlapped keywords of the talents, dividing the number of the overlapped keywords of the talents by the number of the keywords extracted from the recruitment information corresponding to the recruitment company, and taking the obtained ratio as the post matching degree A of the job seeker and the corresponding recruitment information in the recruitment company;
the talent screening and matching module further judges the post matching degree A,
when the A is larger than or equal to a first preset value, judging that the resume of the job seeker meets the requirement of the recruitment information of the recruitment company;
when A is smaller than a first preset value, judging that the resume of the job seeker does not accord with the requirement of the recruitment information of the recruitment company;
the talent screening and matching module extracts job seeker information with resumes meeting the requirement of the recruitment information of the recruitment company, sorts the distances between the current position of the job seeker and the position of the recruitment company from big to small,
and multiplying the number of the persons to be recruited corresponding to the recruitment information by a preselection coefficient q to obtain a preselected number B corresponding to the recruitment information, and screening the job seekers corresponding to the former B names from the sorting of the distances between the positions of the job seekers and the positions of the recruitment companies as preselections.
2. The big data-based talent recommendation system according to claim 1, wherein: the talent ability evaluation module evaluates the ability of the B-number preselectiors screened in the talent screening matching module, the evaluation content comprises the volume v of papers published by the preselectiors during the school and the corresponding gold-bearing value of each paper,
the ability of the preselector is digitalized according to the volume v of published papers and the gold-containing value corresponding to each paper, the gold-containing values corresponding to each paper of job seekers are accumulated to obtain the ability value W of the preselector,
dividing the preselected person's ability value W by the preselected person's published paper volume v during the school to obtain the gold-bearing value E corresponding to each paper on average of the preselected person, determining the preselected person's ability value W and the gold-bearing value E corresponding to each paper on average of the preselected person,
when W is less than or equal to a second preset value, judging that the capability of the preselector is weak, and removing the preselector from a list of preselectors;
when W is larger than the second preset value and smaller than the third preset value, the value of E is compared,
if E is less than or equal to the fourth preset value, judging that the ability of the preselector is weak, removing the preselector from a list of preselectors,
if E is larger than a fourth preset value, judging that the preselector has normal capacity;
when W is larger than or equal to a third preset value, judging that the preselector is normal in capability;
and sorting the remaining preselectiors according to the capacity values W of the remaining preselectiors, wherein the larger the data of the corresponding capacity values W of the preselectiors is, the higher the rank of the preselectiors is.
3. The big data-based talent recommendation system according to claim 2, wherein: the judgment of the gold-containing value corresponding to each paper of the preselection by the talent capability evaluation module comprises two aspects, namely, on one hand, the evaluation of the content of the paper and the acquisition of a corresponding content evaluation value C; on the other hand, the publication journal of the article is evaluated, and a corresponding journal evaluation value D is obtained,
the preselectors each paper corresponds to a gold-bearing value = content evaluation value C × journal evaluation value D.
4. The big data-based talent recommendation system according to claim 3, wherein: the content evaluation value C is related to the number of research directions n of the paper, the professional coefficient u of the paper and the moisture degree f of the paper,
the search of the number n of the thesis research directions needs to extract keywords in the thesis content, compare the extracted keywords with a preset comparison database, classify the extracted keywords according to the categories of the keywords in the comparison database, count the number m of various keywords in the classified keywords, compare the number m of various keywords with a fifth preset value,
when m is larger than a fifth preset value, judging the keyword category as an effective category,
when m is smaller than a fifth preset value, judging the keyword category as an invalid category,
counting the number of the effective keyword categories to obtain a numerical value which is the number n of the thesis research directions;
the professional coefficient u of the paper is obtained by analyzing the keywords in the extracted paper content, the extracted keywords are compared with a comparison database, the uncommon keywords related to the research topic are screened out, the number of the uncommon keywords appearing in the paper is counted, the number u1 of the uncommon keywords appearing in each thousand words in the average paper is calculated, the professional coefficient u of the paper is equal to the number u1 of the uncommon keywords appearing in each thousand words in the average paper plus 1,
namely, it is
，
The judgment mode of the uncommon keywords is as follows: in the statistics of all extracted keywords in the comparison database, keywords with the frequency less than 5 times in each unit number of extracted keywords are rare keywords;
the moisture degree f is embodied by the similarity of the content of the paper with the same theme in other periodicals, firstly, all the papers with the same theme as the paper in other periodicals are obtained, and then the first three papers of the paper are put into practiceComparing the segments with the first three segments of the obtained paper respectively, respectively obtaining corresponding similarity f1, sequencing the obtained similarity f1, comparing the three papers with the highest similarity with the whole paper, obtaining the corresponding similarity f2, and comparing the maximum value of the three similarities f2
As the value of the water degree f in this paper;
the value of the content evaluation value C is equal to the product of the number n of research directions of the paper, the professional coefficient u of the paper and the moisture degree f of the paper, namely
，
Further obtain
。
5. The big data-based talent recommendation system according to claim 4, wherein: the journal assessment value D is related to the level value h of journal published by the paper and the authority k of each paper published by the journal,
the level value h for publishing the journal of the paper is set according to the level of the department of charge to which the journal of the paper belongs, and the level of the department of charge to which the journal belongs comprises: the state level, the provincial level, the city level, the level of the competent departments to which the journal belongs are different, the corresponding value of the level value h for publishing the journal of the paper is also different,
when the level of the department of charge to which the journal belongs is the national level, the corresponding level value h for publishing the journal of the paper is j1,
when the level of the department in charge of the periodical belongs to province level, the corresponding level value h for publishing the periodical is j2,
when the level of the department in charge to which the journal belongs is the market level, the corresponding level value h for publishing the journal of the paper is j3,
the value of j1 is greater than the value of j2, the value of j2 is greater than the value of j 3;
the authority degree k of each paper published in the journal is influenced by the ratio i of the total number of browsed people p in unit time of the paper to the total number of browsed people of students or teachers belonging to 985 colleges and universities in the corresponding number of browsed people, and the authority degree k is determined by the ratio of the total number of browsed people p to the total number of students or teachers belonging to the 985 colleges and universities
L is an authority coefficient of a paper published in a periodical;
respectively calculating the product of the rank value h of the journal and the authority k of each paper published by the journal, accumulating the obtained product results, and dividing the accumulated sum by the paper number s of the journal to obtain a value which is a journal evaluation value D, namely:
said
Authority of the x-th paper published for the journal, said
Total number of browsers per unit time for the xth paper published for the journal, said
The number of students or teachers belonging to 985 colleges and universities in the corresponding browsing population per unit time of the x paper published for the journal is the ratio of the total browsing population.
6. The big data-based talent recommendation system according to claim 5, wherein: the preselected person's ability value W is the sum of the gold-bearing values corresponding to each of the v papers published by the preselected person during the school, i.e.:
the above-mentioned
For the content evaluation corresponding to the y-th paper published by the pre-selector during the school, said
For the journal evaluation corresponding to the y-th paper published by the pre-selector during the school,
the above-mentioned
The number of research directions of the corresponding papers for the y-th paper published by the pre-selected person during the school period, said
The number of rare keywords appearing on average per thousand words for the relevant paper of the y paper published by the pre-selected person during the school period
For the y-th paper published by the pre-selected person during the school
Value of, said
A rating of a journal corresponding to the y-th paper published by the preselected person during the school, said journal being associated with a journal
A journal published paper piece corresponding to the y-th paper published by the preselected person during the school, said
Total number of views per unit time for the x-th paper published in a journal corresponding to the y-th paper published by the preselected person during the school
The number of students or teachers belonging to 985 colleges in the browsing number corresponding to the corresponding journal published by the pre-selected paper during the school is the ratio of the total browsing number.
7. The big-data-based talent recommendation method applying the big-data-based talent recommendation system according to any one of claims 1-6, is characterized by comprising the following specific operation steps:
s1, extracting the information of the recruitment company and the job seeker in the data acquisition module;
s2, receiving the information acquired by the data acquisition module through the talent screening and matching module, and processing the received information;
s3, in the talent ability evaluation module, evaluating the ability corresponding to the screened talents in the talent screening and matching module, and auditing and sequencing the screened talents according to the ability;
and S4, in the talent recommendation module, recommending talents to the corresponding recruiter according to the evaluation result of the talent capability evaluation module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110833849.7A CN113298505A (en) | 2021-07-23 | 2021-07-23 | Talent recommendation system and method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110833849.7A CN113298505A (en) | 2021-07-23 | 2021-07-23 | Talent recommendation system and method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113298505A true CN113298505A (en) | 2021-08-24 |
Family
ID=77330797
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110833849.7A Pending CN113298505A (en) | 2021-07-23 | 2021-07-23 | Talent recommendation system and method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113298505A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113902400A (en) * | 2021-09-26 | 2022-01-07 | 上海嵘仕企业管理咨询有限公司 | Data collection, transmission and storage system |
| CN117114514A (en) * | 2023-10-24 | 2023-11-24 | 中电科大数据研究院有限公司 | Talent information analysis management method, system and device based on big data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446886A (en) * | 2018-01-31 | 2018-08-24 | 合肥和钧正策信息技术有限公司 | Personnel recruitment system and method based on big data |
| CN108596567A (en) * | 2018-04-19 | 2018-09-28 | 蔡丽煌 | A kind of talent recommendation method and system based on block chain technology |
| CN110929974A (en) * | 2019-05-15 | 2020-03-27 | 国网浙江省电力有限公司电力科学研究院 | Power innovation talent capability assessment method based on big data model |
| US20200250511A1 (en) * | 2019-02-01 | 2020-08-06 | Zhaoyang Hu | Artist comprehensive ability evaluation and cultivation assistant system based on artificial intelligence |
| CN112734382A (en) * | 2021-01-12 | 2021-04-30 | 杭州好职途信息科技有限公司 | Talent recruitment system capable of quickly matching related job seekers according to enterprise requirements |
| CN112749951A (en) * | 2021-01-18 | 2021-05-04 | 南京可宇科技有限公司 | Human resource intelligent matching management system based on multivariate data analysis |
-
2021
- 2021-07-23 CN CN202110833849.7A patent/CN113298505A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446886A (en) * | 2018-01-31 | 2018-08-24 | 合肥和钧正策信息技术有限公司 | Personnel recruitment system and method based on big data |
| CN108596567A (en) * | 2018-04-19 | 2018-09-28 | 蔡丽煌 | A kind of talent recommendation method and system based on block chain technology |
| US20200250511A1 (en) * | 2019-02-01 | 2020-08-06 | Zhaoyang Hu | Artist comprehensive ability evaluation and cultivation assistant system based on artificial intelligence |
| CN110929974A (en) * | 2019-05-15 | 2020-03-27 | 国网浙江省电力有限公司电力科学研究院 | Power innovation talent capability assessment method based on big data model |
| CN112734382A (en) * | 2021-01-12 | 2021-04-30 | 杭州好职途信息科技有限公司 | Talent recruitment system capable of quickly matching related job seekers according to enterprise requirements |
| CN112749951A (en) * | 2021-01-18 | 2021-05-04 | 南京可宇科技有限公司 | Human resource intelligent matching management system based on multivariate data analysis |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113902400A (en) * | 2021-09-26 | 2022-01-07 | 上海嵘仕企业管理咨询有限公司 | Data collection, transmission and storage system |
| CN117114514A (en) * | 2023-10-24 | 2023-11-24 | 中电科大数据研究院有限公司 | Talent information analysis management method, system and device based on big data |
| CN117114514B (en) * | 2023-10-24 | 2024-01-02 | 中电科大数据研究院有限公司 | Talent information analysis management method, system and device based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109558429B (en) | Talent service bidirectional recommendation method and system based on Internet big data | |
| Edris | Services considered important to business customers and determinants of bank selection in Kuwait: a segmentation analysis | |
| CN113298505A (en) | Talent recommendation system and method based on big data | |
| Kipperberg | A comparison of household recycling behaviors in Norway and the United States | |
| CN105574216A (en) | Personalized recommendation method and system based on probability model and user behavior analysis | |
| US20120130773A1 (en) | System and method for determining applicants' working process with an administrative agency based on past data collection and analysis of past administrative agents performance | |
| CN101609450A (en) | Web page classification method based on training set | |
| CN112989070B (en) | Core periodical quantitative evaluation system and method based on computer system | |
| CN111738819A (en) | Method, device and equipment for screening characterization data | |
| CN116644184B (en) | Human resource information management system based on data clustering | |
| CN108897821A (en) | The method and device of automatically generated data conclusion | |
| CN109559152A (en) | A kind of network marketing method, system and computer storage medium | |
| CN107239964A (en) | User is worth methods of marking and system | |
| CN105786810B (en) | The method for building up and device of classification mapping relations | |
| Febrian et al. | Decision support system employee performance appraisal method using topsis | |
| CN112258067A (en) | Low-voltage user payment behavior classification method based on Gaussian mixture model clustering algorithm | |
| Stormer | Improving e-commerce recommender systems by the identification of seasonal products | |
| Blair | Quality of life and economic development policy. | |
| Herrendorf et al. | How barriers to international trade affect TFP | |
| CN113297190B (en) | Visualization method, device and medium based on data comprehensive analysis | |
| CN113051482A (en) | Web page search intelligent matching recommendation method based on user feature recognition and behavior analysis | |
| Oudshoff et al. | Knowledge discovery in virtual community texts: Clustering virtual communities | |
| CN109460518A (en) | A kind of book recommendation method based on user website access record | |
| Tang et al. | Research on the pricing of Chinese artwork based on unascertained measure and GM (1, N) model | |
| Horowitz | The Status of Artists in the USA |
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 |