CN115471184A - Intelligent recruitment information pushing method and system - Google Patents
Intelligent recruitment information pushing method and system Download PDFInfo
- Publication number
- CN115471184A CN115471184A CN202211057853.XA CN202211057853A CN115471184A CN 115471184 A CN115471184 A CN 115471184A CN 202211057853 A CN202211057853 A CN 202211057853A CN 115471184 A CN115471184 A CN 115471184A
- Authority
- CN
- China
- Prior art keywords
- target
- recruitment information
- hard
- recruitment
- sentence
- 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
- 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
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses an intelligent recruitment information pushing method and system, belonging to the field of artificial intelligence, wherein the method comprises the following steps: the method comprises the steps of building a hard index set based on big data, extracting and obtaining a target hard index parameter set of a target applicant by combining a target resume of the target applicant, building a recruitment information database, analyzing a plurality of recruitment information based on the target hard index parameter set, screening to obtain a target recruitment information set, analyzing a plurality of target recruitment information to obtain a plurality of target recruitment hard requirements, sequentially counting the target recruitment hard index number of each target recruitment hard requirement in the plurality of target recruitment hard requirements, performing descending order arrangement on the plurality of target recruitment information based on the target recruitment hard index number, and obtaining a target recruitment information push list. The technical problems of low intelligence degree of recruitment information push, low recommendation accuracy and low individuation in the prior art are solved. The technical effects of optimizing the recruitment information pushing method and improving the pushing quality and efficiency are achieved.
Description
Technical Field
The application relates to the field of artificial intelligence, in particular to an intelligent recruitment information pushing method and system.
Background
Along with the refinement of social division of labor, more and more posts emerge, and for enterprises, matched talents are searched for related posts of the enterprises through various channels, so that the method is a fundamental measure for improving the competitiveness of the enterprises. With the rapid development of internet technology, the network recruitment industry in China is rapidly developing and becomes an important platform for job hunting, flow and configuration of human resources.
At present, network recruitment mainly generates talent demands from enterprise posts, formulates recruitment standards through human resource departments, selects a recruitment information publishing channel and publishes recruitment information. And the applicants screen the recruitment information on the recruitment platform and deliver resumes to the intention company. And the enterprise human resource department screens qualified recruiters of resumes by screening and performing written test and interview to obtain the most suitable job object.
However, the huge amount of data generated in the network recruitment can not be quickly identified and processed, so that the information transmission is not equal, and the applicant can not find the most suitable position from a plurality of recruitment information based on the selection of the applicant. The energy and time of the applicant are wasted, and the work of finding the heart instrument cannot be quickly carried out. The technical problems of low recruitment information pushing intelligence degree and low recommendation accuracy and individuation exist in the prior art.
Disclosure of Invention
The application aims to provide an intelligent recruitment information pushing method and system, and the method and system are used for solving the technical problems of low intelligence degree, low recommendation accuracy and low individuation of recruitment information pushing in the prior art.
In view of the above problems, the present application provides an intelligent recruitment information pushing method and system.
In a first aspect, the application provides an intelligent recruitment information pushing method, where the method includes: building a hard index set based on the big data, wherein the hard index set comprises a plurality of hard indexes; obtaining a target resume of a target applicant, and extracting a target hard index parameter set of the target applicant by combining the plurality of hard indexes; the method comprises the steps of establishing a recruitment information database, wherein the recruitment information database comprises a plurality of pieces of recruitment information; analyzing the plurality of recruitment information based on the target hard index parameter set, and screening to obtain a target recruitment information set, wherein the target recruitment information set comprises a plurality of target recruitment information; analyzing the plurality of target recruitment information to obtain a plurality of target recruitment hard requirements; sequentially counting the number of the target recruitment rigid indicators of each target recruitment rigid requirement in the plurality of target recruitment rigid requirements; and performing descending order arrangement on the plurality of target recruitment information based on the target recruitment hard index number to obtain a target recruitment information push list.
On the other hand, the application also provides an intelligent recruitment information pushing system, wherein the system comprises: the index set building module is used for building a hard index set based on big data, wherein the hard index set comprises a plurality of hard indexes; the hard index extraction module is used for obtaining a target resume of a target applicant and extracting a target hard index parameter set of the target applicant by combining the plurality of hard indexes; the system comprises a database construction module, a data processing module and a data processing module, wherein the database construction module is used for constructing a recruitment information database, and the recruitment information database comprises a plurality of recruitment information; the information screening module is used for analyzing the plurality of recruitment information based on the target hard index parameter set and screening to obtain a target recruitment information set, wherein the target recruitment information set comprises a plurality of target recruitment information; a hard requirement obtaining module, configured to analyze the multiple pieces of target recruitment information to obtain multiple target recruitment hard requirements; the index number counting module is used for sequentially counting the target recruitment hard index number of each target recruitment hard requirement in the plurality of target recruitment hard requirements; and the push list module is used for performing descending order arrangement on the plurality of target recruitment information based on the target recruitment hard index number to obtain a target recruitment information push list.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the method, a hard index set is established according to big data, a target hard index parameter set is obtained by combining a target resume of a target applicant with a plurality of hard indexes, a recruitment information database is established, the recruitment information database comprises a plurality of pieces of recruitment information, the plurality of pieces of recruitment information are analyzed based on the target hard index parameter set, a target recruitment information set meeting the requirements of the target applicant is obtained by screening, the target recruitment information set comprises a plurality of pieces of target recruitment information, the plurality of pieces of target recruitment information are analyzed to obtain a plurality of target recruitment hard requirements, the number of target recruitment hard indexes of each target recruitment hard requirement in the plurality of target recruitment hard requirements is counted in sequence, and the plurality of pieces of target recruitment information are subjected to descending order arrangement based on the number of the target recruitment hard indexes to obtain a target recruitment information push list. The technical effects of optimizing the recruitment information pushing method, intelligently pushing the recruitment information according to the requirements and improving the pushing quality and efficiency are achieved.
Drawings
In order to more clearly illustrate the technical solutions in the present application or prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, it is obvious that the drawings in the description below are only exemplary, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flowchart of an intelligent recruitment information pushing method according to an embodiment of the present application;
fig. 2 is a schematic flow chart illustrating sequential adjustment of a target recruitment information push list in an intelligent recruitment information push method according to an embodiment of the present application;
fig. 3 is a diagram illustrating an intelligent recruitment information pushing method according to an embodiment of the present application: taking the result of the resume keyword group addition as a flow schematic diagram of the resume keyword group;
fig. 4 is a schematic structural diagram of an intelligent recruitment information push system according to the present application;
description of the reference numerals: the system comprises an index set building module 11, a hard index extraction module 12, a database building module 13, an information screening module 14, a hard requirement obtaining module 15, an index number counting module 16 and a push list module 17.
Detailed Description
The method and the system for intelligently pushing the recruitment information solve the technical problems of low intelligence degree of recruitment information pushing and low recommendation accuracy and individuation in the prior art. The technical effects of optimizing the recruitment information pushing method, improving the intelligent matching degree of the recruitment information and improving the pushing quality and efficiency are achieved.
According to the technical scheme, the data acquisition, storage, use, processing and the like meet relevant regulations of national laws and regulations.
In the following, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings, and it is to be understood that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments of the present application, and it is to be understood that the present application is not limited by the example embodiments described herein. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without making any creative effort belong to the protection scope of the present application. It should be further noted that, for the convenience of description, only some but not all of the elements relevant to the present application are shown in the drawings.
Example one
As shown in fig. 1, the present application provides an intelligent push method of recruitment information, wherein the method includes:
step S100: establishing a hard index set based on the big data, wherein the hard index set comprises a plurality of hard indexes;
specifically, the hard index set refers to a general collected information index of a corresponding recruiter in the recruitment process, and is used for acquiring basic information of the recruiter. Optionally, the multiple hard indices include: name, age, nationality, marital status, political aspect, academic calendar, professional background, work experience, work place, and expected compensation, etc. The indexes which need to be collected in the recruitment process of the enterprise are obtained through searching of the big data, preferably, the hard index set can be indexes with structural attributes, namely the indexes can be directly used in a quantitative mode, secondary analysis is not needed, and the universality of information collection is improved. Therefore, the technical effects of improving the accuracy of index acquisition data and reducing the error rate of information identification are achieved.
For example, in the recruitment process, the personnel cost is an important condition for judging the economic benefit of the employment for most enterprises, and whether the recruitment enterprise and the applicant can achieve consensus on the salary treatment or not has a very important influence on whether the recruitment can be successful or not. Therefore, the expected salary is regarded as a hard index, the matching accuracy of the applicant and the corresponding recruitment information is improved by quantifying the requirement of the applicant on treatment, and the efficiency of recommending the recruitment information can be improved by filling the corresponding post when the resume is filled.
Step S200: obtaining a target resume of a target applicant, and extracting and obtaining a target hard index parameter set of the target applicant by combining the hard indexes;
specifically, the target applicant is any person who needs to perform work application. The target resume is a written introduction that may reflect the personal information and job hunting intent of the target applicant. And matching the target resume with a plurality of hard indexes, and extracting information in the target resume according to the hard indexes to obtain the satisfying result of the target applicant on the hard indexes. The target hard index parameter set is a data set obtained by extracting information in a target resume according to the characteristics of a plurality of hard indexes. Therefore, the technical effects of accurately acquiring the information of the target applicant and improving the accuracy and the analysis efficiency of subsequent data analysis are achieved.
Step S300: constructing a recruitment information database, wherein the recruitment information database comprises a plurality of recruitment information;
specifically, the recruitment information database is a database obtained by collecting recruitment information according to a data mining technology in big data. Optionally, the recruitment information in the database can be uploaded by a recruitment enterprise. The recruitment information comprises post information of various types and corresponding post requirement information. Therefore, the goal of summarizing the recruitment information is achieved, and the technical effects of improving the transparency of the recruitment information, improving the information collection degree and improving the push quality are achieved.
Step S400: analyzing the plurality of recruitment information based on the target hard index parameter set, and screening to obtain a target recruitment information set, wherein the target recruitment information set comprises a plurality of target recruitment information;
specifically, the target hard index parameter set is reference information reflecting the matching of the target applicant and the recruitment information. And screening and analyzing the plurality of recruitment information according to the target hard index parameter set, analyzing information related to the target hard index in the plurality of recruitment information, and matching the information with the data information in the target hard index parameter set to obtain the recruitment information with high matching degree, so as to form the target recruitment information set. Wherein the target recruitment information is a set of all recruitment information meeting the information and job hunting intentions of the target applicant. Therefore, the technical effects of matching and obtaining the recruitment information and providing basic data for the subsequent further pushing of the recruitment information are achieved.
Step S500: analyzing the plurality of target recruitment information to obtain a plurality of target recruitment hard requirements;
specifically, the plurality of pieces of target recruitment information are further analyzed, and the hard requirements for posts in the information are extracted. Extracting information by keywords, the keywords comprising: the above, at least, must, satisfy, etc. may express words of restricted class of meaning. And further determining the hard requirement by positioning sentences containing the hard requirement in the recruitment information according to the keywords. Wherein the target recruit hard requirement is a condition that reflects a requirement that a recruit position must satisfy for the setting of an applicant.
Illustratively, the sewage treatment plant prepares to recruit a laboratory technician, and the post requirements set forth in the recruitment information are as follows: under 45 years of age, the academic calendar is the subject and above, the specialty is the environmental engineering, more than three years of working experience exist, and the experiment can be skillfully performed. The hard requirements of the post are obtained by extracting keywords such as "above", "below", "can", and the like. For example: the professional must be environmental engineering, and if the professional is an automation professional, the delivery condition of the post cannot be met.
Step S600: sequentially counting the number of the target recruitment hard indicators of each target recruitment hard requirement in the plurality of target recruitment hard requirements;
step S700: and performing descending order arrangement on the plurality of target recruitment information based on the target recruitment hard index number to obtain a target recruitment information push list.
Specifically, the target recruitment rigid index number refers to the number of rigid indexes in each target recruitment rigid requirement. The higher the number of the indicators is, the higher the requirement of the target recruitment information is, the higher the requirement on the applicants is, and meanwhile, the target recruitment information is information that the target applicants accord with the recruitment conditions, so the higher the number of the target recruitment rigid indicators is, the better the post quality is, the higher the satisfaction degree of the applicants on the recruitment post is, and the more suitable the applicants are.
Specifically, the target recruitment information is sorted in a descending order according to the sorting standard of the number of the target recruitment rigid indexes, and the higher the number of the target recruitment rigid indexes is, the higher the position in the push list is. Therefore, the goal of intelligently pushing the recruitment information is achieved, the pushing quality and efficiency are improved, and the time cost of the applicants is reduced.
Further, as shown in fig. 2, step S700 in the embodiment of the present application further includes:
step S710: sequentially extracting each target recruitment information in the plurality of target recruitment information to obtain a plurality of target post descriptions;
step S720: sequentially extracting a plurality of key phrases of each target position description in the plurality of target position descriptions, wherein the plurality of key phrases and the plurality of target position descriptions have a mapping relation;
step S730: marking the plurality of target recruitment information according to the mapping relation between the plurality of key word groups and the plurality of target post descriptions to obtain a target recruitment information marking result;
step S740: extracting and obtaining a resume key phrase of the target resume;
step S750: traversing and matching the resume keyword group in the target recruitment information marking result to obtain a plurality of matching degrees, wherein the matching degrees refer to a plurality of matching degrees of the target resume and the target recruitment information;
step S760: and performing descending order arrangement on the plurality of matching degrees to obtain a matching degree descending sequence table, and performing order adjustment on the target recruitment information push list according to the matching degree descending sequence table.
Specifically, post description information corresponding to the recruitment information is obtained by sequentially extracting the target recruitment information. The post description information is introduction of work content of a recruiting post and work requirement information of the post. The plurality of key phrases can reflect key information of the content of each target post, and the plurality of key phrases and the plurality of target posts construct a one-to-one mapping relation to provide convenience for subsequent marking. The target recruitment information marking result is obtained by performing association marking on the recruitment information post and a key phrase describing the post, so that the corresponding recruitment post information can be conveniently found by marking after the key phrase is obtained.
Specifically, extracting key phrases in the target resume to obtain the resume key phrases. The resume key phrase is a phrase capable of reflecting information about personal ability, work experience and the like in the target resume. And matching the resume keyword groups with the keyword groups in the target recruitment information marking result, and calculating according to the meaning consistency and the character overlap ratio of the keyword groups to obtain the matching degree. And the matching degree reflects the degree of coincidence between the information reflected in the target resume and the target recruitment information. The higher the matching degree is, the more the target applicant accords with the post corresponding to the target recruitment information. And performing descending order arrangement on the plurality of target recruitment information according to the matching degree to obtain the matching degree descending sequence list. The matching degree reduced sequence list reflects the matching degree of the recruitment information and the applicant. And sequentially adjusting the target recruitment information push list according to the matching descending list, so that the aim of optimizing the push list according to the matching degree can be fulfilled, and the technical effects of improving the push quality of the recruitment information and improving the push accuracy are achieved.
Further, as shown in fig. 3, after the extracting obtains the resume keyword group of the target resume, step S740 in the embodiment of the present application further includes:
step S741: obtaining a manual adjustment instruction, wherein the manual adjustment instruction comprises a manual adding instruction and a manual deleting instruction;
step S742: according to the manual deleting instruction, carrying out keyword deletion on the resume keyword group to obtain a resume keyword group deleting result;
step S743: according to the manual adding instruction, performing keyword addition on the resume keyword group deleting result to obtain a resume keyword group adding result;
step S744: and taking the result of the resume keyword group addition as the resume keyword group.
Specifically, the manual adjustment instruction is a command for the applicant to adjust the resume keyword set by himself. And the manual adding instruction is a command for manually adding the resume key phrase. The manual deleting instruction is a command for manually deleting the resume keyword group. The resume keyword group deleting result refers to that a candidate deletes part of keywords in the resume keyword group extracted from the resume, and a result is obtained after deleting content keywords which are not wanted to be engaged. And the resume keyword group adding result is a result obtained after the applicant adds the content keyword which the applicant wants to engage in into the resume keyword group. Through manual adjustment, the technical effects of improving the individuation degree of the recruitment information push content by the applicants and improving the push intellectualization degree of the recruitment information are achieved.
Further, the step S720 in this embodiment of the present application further includes:
step S721: extracting any one target position description in the target position descriptions;
step S722: performing stop word elimination pretreatment on any one target post description to obtain a pretreatment result;
step S723: according to the preprocessing result, sequentially building a word vector set and a sentence vector set described by any one target post;
step S724: performing calculation analysis on the word vector set to obtain a word graph, and performing calculation analysis on the sentence vector set to obtain a sentence graph;
step S725: carrying out comprehensive calculation analysis on the word vector set and the sentence vector set to obtain a word and sentence graph;
step S726: constructing a graph model of any one target position description based on the word graph, the sentence graph and the word graph;
step S727: and screening to obtain the key phrase described by any one target post according to the graph model.
Specifically, the target post description reflects the work content and the application requirements of the post. The stop words are dummy words in the target post description, and in order to make the description sentence smooth, the words are irrelevant to the main content of the description and can be ignored in the analysis. The preprocessing result is the post description left after the stop words in the post description are deleted. The word vector set is a set obtained by vectorizing words used when describing a target post. The sentence vector set is a set obtained by vectorizing the sentences describing the target posts. The word and word graph is a visual graph which is used for computing the word vector set and representing the association relation between words in the word vector set. The word and sentence graph is a visual graph obtained by calculating and analyzing the word vector set and the sentence vector set and analyzing the incidence relation between the word vectors and the sentence vectors.
Specifically, the graphic model described in any one target position is a model describing the characteristics of the target position. The word graph model is constructed by word graphs, sentence graphs and word and sentence graphs, and is constructed by association among words, association among sentences and association among words and sentences in position description. According to the graph model, a keyword group related to the target post description can be obtained by inputting the target post description, and the technical effects of improving the accuracy of the recruitment information post characteristics and improving the pushing accuracy can be achieved.
Further, the step S724 of performing calculation analysis on the sentence vector set to obtain a sentence graph in the embodiment of the present application further includes:
step S7241: extracting any two sentences in the sentence vector set, and setting the two sentences as a first sentence and a second sentence respectively;
step S7242: sequentially building a first word set of the first sentence and a second word set of the second sentence, and performing union operation to obtain a total set;
step S7243: combining the first word set and the total set, and carrying out vectorization processing on the first word set to obtain a first vector;
step S7244: combining the second word set and the total set, and performing vectorization processing on the second word set to obtain a second vector;
step S7245: calculating the similarity of the first vector and the second vector by using cosine similarity to obtain sentence similarity;
step S7246: and obtaining the sentence graph based on the first sentence, the second sentence and the sentence similarity.
Specifically, the first sentence is any one of the sentences in the sentence vector set, and the second sentence is any one of the sentences in the sentence vector set except the first sentence. And performing word analysis on the first sentence, extracting words in the first sentence to form the first word set, extracting words in the second sentence to form the second word set, and performing union set operation on the first word set and the second word set to obtain the total set. And the total set is a set obtained by summarizing the words of the first sentence and the second sentence together.
Specifically, the language understanding problem is converted to a mathematical quantization problem by converting the words in the first set of words into vectors. The vectorization processing refers to a conversion process of converting words into vectors by using a set of scores to represent one word from the aspects of part of speech, emotional color, degree and the like. The first vector is a vector obtained after the words in the first word set are scored. The second vector is a vector obtained after the words in the second word set are scored.
Specifically, the cosine similarity measures the similarity between two vectors by measuring the cosine value of the included angle between the two vectors. And substituting the first vector and the second vector into a cosine similarity calculation formula for calculation to obtain the sentence similarity. The sentence similarity may reflect a degree of similarity between two sentences. The higher the similarity degree is, the greater the relevance is, and the greater the relevance of the target content of the sentence corresponding description is. And associating the first sentence, the second sentence and the sentence similarity to obtain a sentence graph capable of reflecting the association relation among the sentences. Therefore, the goal of visually displaying the relevance between the sentences described in the post is achieved, and the technical effect of improving the accuracy of recruitment information push is achieved.
Further, step S760 in the embodiment of the present application further includes:
step S761: collecting browsing records of each target recruitment information in the target recruitment information push list browsed by the target applicant;
step S762: according to the browsing record, establishing an uninteresting mark record of the target applicant;
step S763: analyzing the uninteresting mark records and establishing an exclusion key phrase of the target applicant;
step S764: traversing to obtain target recruitment information to be eliminated based on the exclusion keyword group, wherein the target recruitment information to be eliminated is the target recruitment information containing the exclusion keyword;
step S765: and removing the target recruitment information to be removed from the target recruitment information push list.
Specifically, the browsing record is a record generated when the target recruiter browses each target recruitment information according to the target recruitment information push list sequence, and if the target recruiter does not meet the recruitment requirement of the target recruiter in the browsing process, the recruiter marks the target recruiter for non-interest to obtain the non-interest mark record. And the uninteresting mark record is obtained after the target recruiter marks the uninteresting recruitment information in the target recruitment information push list.
Specifically, the uninteresting label records are further analyzed, common phrases contained in the records are analyzed, and the rejection key phrases are obtained after the common phrases are collected. And screening the target recruitment information according to the exclusion keyword group to obtain target recruitment information to be eliminated containing the exclusion keyword group, and further eliminating the target recruitment information to be eliminated from the target recruitment information pushing list. By deleting the recruitment push list, the push content is reduced, and the pushed recruitment information better meets the individual requirements of the target applicant, so that the recruitment efficiency is improved, and the time cost is reduced.
Further, step S765 in the embodiment of the present application further includes:
step S7651: obtaining historical browsing records of each target recruitment information in the target recruitment information push list based on big data;
step S7652: obtaining a history interesting mark record according to the history browsing record;
step S7653: analyzing the historical interest mark record to obtain the times of interest marks of each piece of target recruitment information in the target recruitment information push list;
step S7654; constructing a target recruitment information-interest mark frequency list;
step S7655: and performing recruitment information heat analysis according to the target recruitment information-interest marking frequency list, and obtaining a target recruitment information push list with a recruitment information heat mark.
Specifically, the historical browsing records are records of browsing of the target recruitment information in historical time, and include browsing time, browsing times and staying time. The historical interest mark record is the record condition that each target recruitment information is used as the interest mark by an applicant in historical time, and reflects the attention degree of each target recruitment information. And counting the marking times to obtain the target recruitment information-interested marking time list. Wherein the target recruitment information in the list corresponds to the number of the interested marks one by one. The more the number of the interested marks is, the higher the attention degree of the target recruitment information is, the higher the popularity is, and the higher the competitive pressure is. The recruitment information is subjected to heat marking on each piece of target recruitment information in the target recruitment information pushing list, and the competition condition of the post is visually presented to an applicant, so that the applicant can comprehensively know the post, and the richness of the recruitment information pushing content is improved.
In summary, the intelligent recruitment information pushing method provided by the application has the following technical effects:
according to the method and the device, parameters in a target resume of a target applicant are extracted by establishing a group hard index set to obtain a target hard index parameter set of the target applicant, a recruitment information database is further established, a plurality of pieces of recruitment information are analyzed according to the target hard index parameter set, a target recruitment information set is obtained by screening, the target recruitment information set comprises a plurality of pieces of target recruitment information, the plurality of pieces of target recruitment information are analyzed to obtain a plurality of target recruitment hard requirements, the number of target recruitment hard indexes of each target recruitment hard requirement in the plurality of target recruitment hard requirements is collected to obtain the quality of a recruitment position, the plurality of pieces of target recruitment information are arranged in a descending order according to the number of the target recruitment hard indexes to obtain a target recruitment information push list, and the target applicant is pushed according to the target recruitment list. The technical effects of intelligently pushing the recruitment information and improving the pushing efficiency and accuracy are achieved.
Example two
Based on the same inventive concept as the intelligent recruitment information pushing method in the foregoing embodiment, as shown in fig. 4, the present application further provides an intelligent recruitment information pushing system, wherein the system includes:
the index set building module 11 is configured to build a hard index set based on big data, where the hard index set includes a plurality of hard indexes;
the hard index extraction module 12 is configured to obtain a target resume of a target applicant, and extract a target hard index parameter set of the target applicant by combining the plurality of hard indexes;
the database building module 13 is used for building a recruitment information database, wherein the recruitment information database comprises a plurality of recruitment information;
the information screening module 14 is configured to analyze the plurality of recruitment information based on the target hard index parameter set, and screen to obtain a target recruitment information set, where the target recruitment information set includes a plurality of target recruitment information;
a hard requirement obtaining module 15, wherein the hard requirement obtaining module 15 is configured to analyze the plurality of pieces of target recruitment information to obtain a plurality of target recruitment hard requirements;
the index number counting module 16, wherein the index number counting module 16 is configured to count the target recruitment hard index number of each target recruitment hard requirement in the plurality of target recruitment hard requirements in sequence;
and the push list module 17 is configured to perform descending order arrangement on the plurality of target recruitment information based on the number of the target recruitment hard indicators to obtain a target recruitment information push list.
Further, the system further comprises:
the information extraction unit is used for sequentially extracting each piece of target recruitment information in the plurality of pieces of target recruitment information to obtain a plurality of target post descriptions;
the key phrase extraction unit is used for sequentially extracting a plurality of key phrases of each target position description in the target position descriptions, wherein the key phrases and the target position descriptions have a mapping relation;
the marking unit is used for marking the plurality of target recruitment information according to the mapping relation between the plurality of key word groups and the plurality of target post descriptions to obtain a target recruitment information marking result;
the resume keyword group extracting unit is used for extracting and obtaining the resume keyword group of the target resume;
a matching degree obtaining unit, configured to perform traversal matching on the resume keyword groups in the target recruitment information tagging result to obtain multiple matching degrees, where the multiple matching degrees refer to multiple matching degrees between the target resume and the multiple target recruitment information;
and the sequence adjusting unit is used for arranging the plurality of matching degrees in a descending order to obtain a matching degree descending sequence table and adjusting the sequence of the target recruitment information push list according to the matching degree descending sequence table.
Further, the system further comprises:
the instruction obtaining unit is used for obtaining manual adjustment instructions, wherein the manual adjustment instructions comprise manual adding instructions and manual deleting instructions;
the keyword deleting unit is used for deleting the keywords of the resume keyword group according to the manual deleting instruction to obtain a deletion result of the resume keyword group;
the keyword adding unit is used for adding keywords to the resume keyword group deleting result according to the manual adding instruction to obtain a resume keyword group adding result;
and the resume keyword group obtaining unit is used for taking the resume keyword group adding result as the resume keyword group.
Further, the system further comprises:
a post description unit, configured to extract any one target post description in the target post descriptions;
the preprocessing unit is used for carrying out stop word elimination preprocessing on any one target post description to obtain a preprocessing result;
a vector set building unit, configured to build a word vector set and a sentence vector set described in any one of the target posts in sequence according to the preprocessing result;
the calculation analysis unit is used for calculating and analyzing the word vector set to obtain a word and word graph and calculating and analyzing the sentence vector set to obtain a sentence graph;
the word and sentence graph obtaining unit is used for carrying out comprehensive calculation analysis on the word vector set and the sentence vector set to obtain a word and sentence graph;
the graph model building unit is used for building a graph model of any target post description based on the word graph, the sentence graph and the word and sentence graph;
and the key phrase screening unit is used for screening the key phrases described by any one target post according to the graph model.
Further, the system further comprises:
a sentence setting unit, configured to extract any two sentences in the sentence vector set, and set the two sentences as a first sentence and a second sentence respectively;
a total set obtaining unit, configured to sequentially set up a first word set of the first sentence and a second word set of the second sentence, and perform union operation to obtain a total set;
a first vector obtaining unit, configured to combine the first word set and the total set to perform vectorization processing on the first word set to obtain a first vector;
a second vector obtaining unit, configured to perform vectorization processing on the second word set by combining the second word set and the total set to obtain a second vector;
the similarity obtaining unit is used for calculating the similarity of the first vector and the second vector by using cosine similarity to obtain sentence similarity;
a sentence graph obtaining unit, configured to obtain the sentence graph based on the first sentence, the second sentence, and the sentence similarity.
Further, the system further comprises:
the browsing record acquisition unit is used for acquiring browsing records of the target recruiters browsing the target recruitment information in the target recruitment information push list;
a mark record obtaining unit, configured to construct a mark record of no interest of the target applicant according to the browsing record;
the rejection key phrase obtaining unit is used for analyzing the uninteresting mark records and establishing the rejection key phrase of the target applicant;
the information processing device comprises an information obtaining unit to be eliminated, a search unit and a search unit, wherein the information obtaining unit to be eliminated is used for obtaining target recruitment information to be eliminated in a traversing mode based on the rejection key word group, and the target recruitment information to be eliminated is target recruitment information containing rejection key words;
and the elimination processing unit is used for eliminating the target recruitment information to be eliminated from the target recruitment information pushing list.
Further, the system further comprises:
the historical browsing record obtaining unit is used for obtaining a historical browsing record of each target recruitment information in the target recruitment information push list based on big data;
an interested mark record obtaining unit, configured to obtain a historical interested mark record according to the historical browsing record;
a marking frequency obtaining unit, configured to analyze the historical interest mark record to obtain the interest marking frequency of each target recruitment information in the target recruitment information push list;
the listing construction unit is used for constructing a target recruitment information-interest mark number list;
and the popularity analysis unit is used for carrying out popularity analysis on the recruitment information according to the target recruitment information-interest mark frequency list and obtaining a target recruitment information push list with the popularity mark of the recruitment information.
The embodiments in the present description are described in a progressive manner, and each embodiment focuses on a difference from other embodiments, and the aforementioned intelligent push method and specific example of recruitment information in the first embodiment of fig. 1 are also applicable to the intelligent push system of recruitment information in the present embodiment, and through the foregoing detailed description of the intelligent push method of recruitment information, a person skilled in the art can clearly know the intelligent push system of recruitment information in the present embodiment, so details are not described here for brevity of description. The device disclosed in the embodiment corresponds to the method disclosed in the embodiment, so that the description is simple, and the relevant points can be referred to the description of the method part.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. An intelligent recruitment information pushing method is characterized by comprising the following steps:
building a hard index set based on the big data, wherein the hard index set comprises a plurality of hard indexes;
obtaining a target resume of a target applicant, and extracting and obtaining a target hard index parameter set of the target applicant by combining the hard indexes;
constructing a recruitment information database, wherein the recruitment information database comprises a plurality of recruitment information;
analyzing the plurality of recruitment information based on the target hard index parameter set, and screening to obtain a target recruitment information set, wherein the target recruitment information set comprises a plurality of target recruitment information;
analyzing the plurality of target recruitment information to obtain a plurality of target recruitment hard requirements;
sequentially counting the number of the target recruitment hard indicators of each target recruitment hard requirement in the plurality of target recruitment hard requirements;
and performing descending order arrangement on the plurality of target recruitment information based on the target recruitment hard index number to obtain a target recruitment information push list.
2. The method of claim 1, further comprising:
sequentially extracting each target recruitment information in the plurality of target recruitment information to obtain a plurality of target post descriptions;
sequentially extracting a plurality of key phrases of each target position description in the plurality of target position descriptions, wherein the plurality of key phrases and the plurality of target position descriptions have a mapping relation;
marking the plurality of target recruitment information according to the mapping relation between the plurality of key word groups and the plurality of target post descriptions to obtain a target recruitment information marking result;
extracting and obtaining a resume key phrase of the target resume;
traversing and matching the resume key phrase in the target recruitment information marking result to obtain a plurality of matching degrees, wherein the matching degrees refer to a plurality of matching degrees of the target resume and the target recruitment information;
and performing descending order arrangement on the plurality of matching degrees to obtain a matching degree descending sequence table, and performing order adjustment on the target recruitment information push list according to the matching degree descending sequence table.
3. The method according to claim 2, further comprising, after the extracting the resume keyword group of the target resume, the steps of:
obtaining a manual adjusting instruction, wherein the manual adjusting instruction comprises a manual adding instruction and a manual deleting instruction;
according to the manual deleting instruction, carrying out keyword deletion on the resume keyword group to obtain a resume keyword group deleting result;
according to the manual adding instruction, performing keyword addition on the resume keyword group deleting result to obtain a resume keyword group adding result;
and taking the result of the resume keyword group addition as the resume keyword group.
4. The method according to claim 2, wherein said sequentially extracting a plurality of key phrases of each target position description in the plurality of target position descriptions comprises:
extracting any one target position description in the target position descriptions;
performing stop word elimination pretreatment on any one target post description to obtain a pretreatment result;
according to the preprocessing result, sequentially building a word vector set and a sentence vector set described by any one target post;
performing calculation analysis on the word vector set to obtain a word graph, and performing calculation analysis on the sentence vector set to obtain a sentence graph;
carrying out comprehensive calculation analysis on the word vector set and the sentence vector set to obtain a word and sentence graph;
constructing a graph model of any one target position description based on the word graph, the sentence graph and the word graph;
and screening to obtain the key phrase described by any one target post according to the graph model.
5. The method of claim 4, wherein the performing computational analysis on the set of sentence vectors to obtain a sentence graph comprises:
extracting any two sentences in the sentence vector set, and setting the two sentences as a first sentence and a second sentence respectively;
sequentially building a first word set of the first sentence and a second word set of the second sentence, and performing union operation to obtain a total set;
combining the first word set and the total set, and performing vectorization processing on the first word set to obtain a first vector;
combining the second word set and the total set, and performing vectorization processing on the second word set to obtain a second vector;
calculating the similarity of the first vector and the second vector by using cosine similarity to obtain sentence similarity;
and obtaining the sentence graph based on the first sentence, the second sentence and the sentence similarity.
6. The method of claim 1, further comprising:
collecting browsing records of each target recruitment information in the target recruitment information push list browsed by the target applicant;
according to the browsing record, establishing an uninteresting mark record of the target applicant;
analyzing the uninteresting mark records and establishing an exclusion key phrase of the target applicant;
traversing to obtain target recruitment information to be eliminated based on the exclusion keyword group, wherein the target recruitment information to be eliminated is target recruitment information containing exclusion keywords;
and removing the target recruitment information to be removed from the target recruitment information push list.
7. The method of claim 1, further comprising:
obtaining historical browsing records of each target recruitment information in the target recruitment information push list based on big data;
obtaining a history interesting mark record according to the history browsing record;
analyzing the historical interest mark records to obtain the interest mark times of each target recruitment information in the target recruitment information push list;
constructing a target recruitment information-interest marking frequency list;
and performing recruitment information heat analysis according to the target recruitment information-interest mark frequency list, and obtaining a target recruitment information push list with a recruitment information heat mark.
8. An intelligent recruitment information pushing system, which is characterized by comprising:
the index set building module is used for building a hard index set based on big data, wherein the hard index set comprises a plurality of hard indexes;
the hard index extraction module is used for obtaining a target resume of a target applicant and extracting a target hard index parameter set of the target applicant by combining the plurality of hard indexes;
the system comprises a database construction module, a job information database and a job information management module, wherein the database construction module is used for constructing a job information database, and the job information database comprises a plurality of job information;
the information screening module is used for analyzing the plurality of recruitment information based on the target hard index parameter set and screening to obtain a target recruitment information set, wherein the target recruitment information set comprises a plurality of target recruitment information;
a hard requirement obtaining module, configured to analyze the plurality of target recruitment information to obtain a plurality of target recruitment hard requirements;
the index number counting module is used for sequentially counting the target recruitment hard index number of each target recruitment hard requirement in the plurality of target recruitment hard requirements;
and the push list module is used for performing descending order arrangement on the plurality of target recruitment information based on the target recruitment hard index number to obtain a target recruitment information push list.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211057853.XA CN115471184A (en) | 2022-08-30 | 2022-08-30 | Intelligent recruitment information pushing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211057853.XA CN115471184A (en) | 2022-08-30 | 2022-08-30 | Intelligent recruitment information pushing method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115471184A true CN115471184A (en) | 2022-12-13 |
Family
ID=84370922
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211057853.XA Pending CN115471184A (en) | 2022-08-30 | 2022-08-30 | Intelligent recruitment information pushing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115471184A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107145584A (en) * | 2017-05-10 | 2017-09-08 | 西南科技大学 | A kind of resume analytic method based on n gram models |
| 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 |
| CN109740046A (en) * | 2018-11-22 | 2019-05-10 | 北京网聘咨询有限公司 | Aerial double choosings based on internet recruitment can platform |
| CN110059162A (en) * | 2019-04-28 | 2019-07-26 | 苏州创汇智信息技术有限公司 | A kind of matching process and device of job seeker resume and position vacant |
| CN113886684A (en) * | 2021-09-22 | 2022-01-04 | 佛山市勇合科技有限公司 | Network recruitment intelligent recommendation method and system and computer readable storage medium |
| CN113962668A (en) * | 2021-11-05 | 2022-01-21 | 北京麦多贝科技有限公司 | Recruitment method and recruitment server for recruitment end and job hunting end |
-
2022
- 2022-08-30 CN CN202211057853.XA patent/CN115471184A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107145584A (en) * | 2017-05-10 | 2017-09-08 | 西南科技大学 | A kind of resume analytic method based on n gram models |
| 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 |
| CN109740046A (en) * | 2018-11-22 | 2019-05-10 | 北京网聘咨询有限公司 | Aerial double choosings based on internet recruitment can platform |
| CN110059162A (en) * | 2019-04-28 | 2019-07-26 | 苏州创汇智信息技术有限公司 | A kind of matching process and device of job seeker resume and position vacant |
| CN113886684A (en) * | 2021-09-22 | 2022-01-04 | 佛山市勇合科技有限公司 | Network recruitment intelligent recommendation method and system and computer readable storage medium |
| CN113962668A (en) * | 2021-11-05 | 2022-01-21 | 北京麦多贝科技有限公司 | Recruitment method and recruitment server for recruitment end and job hunting end |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110059311B (en) | Judicial text data-oriented keyword extraction method and system | |
| US20230281230A1 (en) | Automatically assessing structured data for decision making | |
| CN109065157B (en) | Disease diagnosis standardized code recommendation list determination method and system | |
| CN106649260B (en) | Product characteristic structure tree construction method based on comment text mining | |
| CN111008262A (en) | Lawyer evaluation method and recommendation method based on knowledge graph | |
| DE102012221251A1 (en) | Semantic and contextual search of knowledge stores | |
| CN110334343B (en) | Method and system for extracting personal privacy information in contract | |
| CN113360647B (en) | 5G mobile service complaint source-tracing analysis method based on clustering | |
| CN116739541B (en) | Intelligent talent matching method and system based on AI technology | |
| CN112818661A (en) | Patent technology keyword unsupervised extraction method | |
| CN112051986A (en) | Code search recommendation device and method based on open source knowledge | |
| CN114238655A (en) | Enterprise association relation identification method, device, equipment and medium | |
| CN116645129A (en) | Manufacturing resource recommendation method based on knowledge graph | |
| CN114579720A (en) | Hydropower project progress intelligent assessment method based on text mining | |
| CN117574858A (en) | Automatic generation method of class case retrieval report based on large language model | |
| CN116304115B (en) | Knowledge-graph-based material matching and replacing method and device | |
| CN115471184A (en) | Intelligent recruitment information pushing method and system | |
| CN116342167A (en) | Intelligent cost measurement method and device based on sequence labeling named entity recognition | |
| CN115660580A (en) | Data analysis management system based on whole-process engineering consultation platform | |
| CN117056392A (en) | Big data retrieval service system and method based on dynamic hypergraph technology | |
| CN113239145A (en) | Resume retrieval method based on job description | |
| CN117556118B (en) | Visual recommendation system and method based on scientific research big data prediction | |
| CN117057667B (en) | Scientific and technological achievement statistical analysis management system based on Internet of things | |
| Deng | Research on personalized recommendation from the perspective of staff-position matching | |
| CN111814457B (en) | Power grid engineering contract text generation method |
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 |