[go: up one dir, main page]

CN119025620A - Personnel matching method and system based on artificial intelligence - Google Patents

Personnel matching method and system based on artificial intelligence Download PDF

Info

Publication number
CN119025620A
CN119025620A CN202411000443.0A CN202411000443A CN119025620A CN 119025620 A CN119025620 A CN 119025620A CN 202411000443 A CN202411000443 A CN 202411000443A CN 119025620 A CN119025620 A CN 119025620A
Authority
CN
China
Prior art keywords
recruitment
job
keyword
intention
record
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
Application number
CN202411000443.0A
Other languages
Chinese (zh)
Inventor
江海
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Subang Information Technology Co ltd
Original Assignee
Zhejiang Subang Information Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang Subang Information Technology Co ltd filed Critical Zhejiang Subang Information Technology Co ltd
Priority to CN202411000443.0A priority Critical patent/CN119025620A/en
Publication of CN119025620A publication Critical patent/CN119025620A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/3332—Query translation
    • G06F16/3334—Selection or weighting of terms from queries, including natural language queries
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3344—Query execution using natural language analysis
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/10—Text processing
    • G06F40/12—Use of codes for handling textual entities
    • G06F40/151—Transformation
    • G06F40/16—Automatic learning of transformation rules, e.g. from examples
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Computational Linguistics (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Databases & Information Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本发明属于人员匹配技术领域，本发明公开了基于人工智能的人员匹配方法及系统；方法包括：采集求职者的简历内容；获取求职者和招聘人员沟通记录中的关键词集合；所述关键词集合包括意向关键词集和招聘关键词集；对意向关键词集和招聘关键词集分别进行处理，得到意向属性标签集和招聘属性标签集；采集岗位基本信息，所述岗位基本信息包括招聘岗位要求和招聘岗位属性；将招聘属性标签集与招聘岗位属性进行对比，对不一致的部分，用招聘属性标签集中的招聘关键词标签替换招聘岗位属性；通过识别出招聘岗位中的虚假岗位属性，并以真实的招聘岗位属性进行人员匹配，实现推荐的简历和招聘岗位高度相关，提升了人员匹配的准确性。

The present invention belongs to the technical field of personnel matching, and discloses an artificial intelligence-based personnel matching method and system; the method comprises: collecting resume contents of job seekers; obtaining a keyword set in communication records between job seekers and recruiters; the keyword set comprises an intention keyword set and a recruitment keyword set; processing the intention keyword set and the recruitment keyword set respectively to obtain an intention attribute tag set and a recruitment attribute tag set; collecting basic position information, wherein the basic position information comprises recruitment position requirements and recruitment position attributes; comparing the recruitment attribute tag set with the recruitment position attributes, and replacing the recruitment position attributes with the recruitment keyword tags in the recruitment attribute tag set for inconsistent parts; by identifying false position attributes in the recruitment positions, and performing personnel matching with real recruitment position attributes, a high correlation between the recommended resume and the recruitment positions is achieved, thereby improving the accuracy of personnel matching.

Description

Personnel matching method and system based on artificial intelligence
Technical Field
The invention relates to the technical field of personnel matching, in particular to an artificial intelligence-based personnel matching method and system.
Background
In current recruitment environments, businesses often face thousands of resumes, and the human resources department spends a great deal of time and effort screening and matching suitable personnel.
In order to improve efficiency and accuracy of personnel screening and matching, a personnel resume matching method and system based on artificial intelligence big data is provided by the prior application publication No. CN1 16578933A, and the method comprises the following steps: s100, resume information and recruitment demand information are acquired, and a first data set in the resume information and a second data set in the recruitment demand information are respectively acquired through a preset intelligent model; s200, large data acquisition is carried out according to the first data set and the second data set respectively, and the first associated data set and the second associated data set are obtained; s300, respectively inputting a first association data set and a second association data set into a training model to obtain a first tag tree and a second tag tree; evaluating the matching degree of resume information and recruitment demand information according to the comparison of the first tag tree and the second tag tree; the method can realize the matching degree evaluation process of the resume information and the recruitment requirement professionality, and assist the recruiter and the efficient screening process of the recruiter.
Although the method can meet most of the scenes, research and practical application of the method and the prior art find that the method and the prior art have at least the following partial defects:
In the actual job hunting process, the prior art cannot identify false job attributes in the recruitment job, for example, the recruitment job attributes are technical jobs, but the actual recruitment is sales jobs; recruitment station attribute is double-break, but is actually weekend plus half day shift; the false post attribute of the post misleads the job seeker, increases the communication time cost of the job seeker and the recruiter, and leads to low accuracy of personnel matching.
In view of the above, the present invention proposes an artificial intelligence based personnel matching method and system to solve the above-mentioned problems.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides the following technical scheme for achieving the purposes: the personnel matching method based on artificial intelligence comprises the following steps:
Collecting resume content of job seekers;
Acquiring a keyword set in communication records of a job seeker and a recruiter; the keyword set comprises an intention keyword set and a recruitment keyword set;
Processing the intent keyword set and the recruitment keyword set respectively to obtain an intent attribute tag set and a recruitment attribute tag set;
Acquiring post basic information, wherein the post basic information comprises recruitment post requirements and recruitment post attributes;
Comparing the recruitment attribute tag set with the recruitment post attribute, and replacing the recruitment post attribute with a recruitment keyword tag in the recruitment attribute tag set for the inconsistent part;
Inputting the personnel matching data set into a pre-trained personnel matching model to obtain a matching tag value, if the personnel matching data set is matched, pushing the job hunting resume to a recruitment terminal, and pushing the recruitment post to the job hunting terminal; the personnel matching data set comprises post basic information, resume content and intent attribute label set.
Further, the keyword set acquisition method comprises the following steps:
s131: anonymizing the communication record;
s132: predefining a stop word list, and removing corresponding words in the communication record according to the stop word list;
s133: removing punctuation marks and special characters from the communication records by using an NLP technology, and segmenting the communication records to obtain a keyword set;
S134: dividing the keyword set into an intention keyword set and a recruitment keyword set according to the sending main body; the sending main body corresponding to the intention keyword set is a job hunting terminal, and the sending main body corresponding to the recruitment keyword set is a recruitment terminal.
Further, the method for acquiring the intent attribute tag set comprises the following steps:
s141: converting the keywords in the intent keyword set into intent keyword vectors by using Word2 Vec;
s142: classifying similar intention keyword vectors by using a clustering algorithm to obtain an intention keyword vector set;
S143: inputting the classified intention keyword vector into an intention recognition model to obtain an intention attribute label corresponding to the intention keyword vector;
The training method of the intention recognition model comprises the following steps:
The method comprises the steps of collecting an intention label data set in advance, wherein the intention label data comprises an intention keyword vector and an intention attribute label corresponding to the intention keyword vector, dividing the intention label data set into a training set and a test set, constructing a classifier, taking the intention keyword vector in the training set as input of an intention recognition model, taking the intention attribute label in the training set as output of the intention recognition model, training the classifier to obtain an initial classifier, testing the initial classifier by using the test set, and outputting a classifier meeting preset accuracy as the intention recognition model, wherein the classifier is a naive Bayesian model or a support vector machine model;
s144: the intent attribute tag is added to the intent attribute tag set.
Further, the recruitment attribute tag set obtaining method includes:
s151: converting keywords in the recruitment keyword set into recruitment keyword vectors by using Word2 Vec;
S152: classifying the similar recruitment keyword vectors by using a clustering algorithm to obtain a recruitment keyword vector set;
S153: inputting the classified recruitment keyword vector into a recruitment recognition model to obtain a recruitment keyword label corresponding to the recruitment keyword vector;
the recruitment recognition model training method comprises the following steps:
The recruitment tag data set is collected in advance, the recruitment tag data comprises recruitment keyword vectors and recruitment keyword tags corresponding to the recruitment keyword vectors, the recruitment tag data set is divided into a training set and a test set, a classifier is built, the recruitment keyword vectors in the training set are used as input of a recruitment recognition model, the recruitment keyword tags in the training set are used as output of the recruitment recognition model, the classifier is trained to obtain an initial classifier, the initial classifier is tested by using the test set, the classifier meeting preset accuracy is output to serve as the recruitment recognition model, and the recruitment recognition model is a naive Bayesian model or a support vector machine model;
S154: and adding the recruitment keyword tag to the recruitment attribute tag set.
Further, the training method of the personnel matching model comprises the following steps:
Pre-collecting a post matching data set, wherein the post matching data set comprises a personnel matching data set and matching label values corresponding to the personnel matching data set, dividing the post matching data set into a training set and a testing set, constructing a classifier, taking the personnel matching data set in the training set as the input of a personnel matching model, taking the matching label values in the training set as the output of the personnel matching model, and taking the sum of the prediction accuracy of all the predicted matching label values as a training target; stopping training until the sum of the prediction accuracy reaches convergence; the personnel matching model is an RNN model;
The calculation formula of the prediction accuracy is: l z＝(Yz-Sz)2, wherein L z is prediction accuracy, Y z is a predicted matching tag value corresponding to the z-th group of personnel matching data set, and S z is an actual matching tag value corresponding to the z-th group of personnel matching data set.
Further, the person matching data set further includes an intention post set, and the intention post set obtaining method includes:
Collecting post browsing records and resume delivery records of job seekers;
processing the post browsing records and the resume delivery records to obtain a post browsing record set and a resume delivery record set;
And processing the post browsing record set and the resume delivery record set to obtain an intention post set.
Further, the post browsing record set obtaining method comprises the following steps:
S101: acquiring a post browsing record;
S102: grouping the browsing post names in the acquired post browsing records, namely grouping the same browsing post names into a group;
S103: counting the browsing times corresponding to the browsing post names in each group;
s104: sequencing the browsing times of all groups;
S105: adding the browsing post names and the corresponding browsing times into a post browsing record set according to the sequence of the browsing times from high to low; the post browsing record set comprises m browsing record subsets, and is expressed as follows:
{{L1：M1},{L2：M2}...{Lm：Mm}}；
L m is the browsing post name in the mth browsing record subset; m m is the browsing times of the browsing post names in the mth browsing record subset; m 1＞M2>Mm.
Further, the resume delivery record set obtaining method comprises the following steps:
s111: acquiring resume delivery records;
s112: grouping delivery post names in the obtained resume delivery records, namely grouping the same delivery post names into a group;
s113: counting the delivery times corresponding to the delivery post names in each group;
s114: sequencing the delivery times of all groups;
S115: adding the delivery post names and the delivery times corresponding to the delivery post names into the resume delivery record set according to the order of the delivery times from high to low; the resume delivery record set comprises n resume delivery record subsets expressed as follows:
{{T1：N1},{T2：N2}...{Tn：Nn}}；
T n is the name of the delivery post in the n resume delivery record subset; n n is the delivery times of the delivery post names in the N resume delivery record subset; n 1＞N2>Nn.
Further, the acquisition method of the intention post set comprises the following steps:
s121: presetting an initial value of i as 1, wherein i is epsilon m; the weight of the preset browsing times is that The weight of the preset delivery times is as follows
S122: acquiring an ith browse record subset in the post browse record set, wherein browse posts L i and M i;Li in the browse record subset are browse post names in the ith browse record subset, and M i is browse times of the browse post names in the ith browse record subset;
S123: judging whether the resume delivery record set has the delivery post name same as L i; if yes, acquiring delivery times corresponding to the delivery post name which is the same as L i from the profile delivery record subset, and marking the delivery times as TD; if not, setting TD to 0;
S124: substituting M i and TD into a post intention score formula to obtain an intention score of browsing post i;
the post intent score formula is as follows:
a post intent score of L i;
S125: adding the intent scores of L i and L i to a temporary data table; let i=i+1, if i is less than or equal to m, continuing to execute S122 to S124; if i is equal to m, then S126 is performed;
s126: the temporary data table is ordered according to the intention scores of the browsing posts from high to low, and the browsing post names of r before the intention scores of the posts are added to the intention post set;
S127: judging whether the browsing post names of k before the browsing times in the post browsing record set are in the intention post set, if not, adding the browsing post names in the intention post set to the intention post set; judging whether the delivery post name of k before the delivery times in the resume delivery record set is in the intention post set, if not, adding the delivery post in the intention post set to the intention post set.
The personnel matching method based on the artificial intelligence is implemented by the personnel matching system based on the artificial intelligence, and comprises the following steps:
The first acquisition module is used for acquiring resume contents of job seekers;
the second acquisition module is used for acquiring a keyword set in the communication records of the job seeker and the recruiter; the keyword set comprises an intention keyword set and a recruitment keyword set;
The first processing module is used for respectively processing the intent keyword set and the recruitment keyword set to obtain an intent attribute tag set and a recruitment attribute tag set;
the third acquisition module is used for acquiring post basic information, wherein the post basic information comprises recruitment post requirements and recruitment post attributes;
the second processing module is used for comparing the recruitment attribute tag set with the recruitment post attributes, and replacing the recruitment post attributes with recruitment keyword tags in the recruitment attribute tag set for inconsistent parts;
The personnel matching module inputs the personnel matching data set into a pre-trained personnel matching model to obtain a matching tag value, if the personnel matching data set is matched, the job hunting resume is pushed to the recruitment terminal, and the recruitment post is pushed to the job hunting terminal; the personnel matching data set comprises post basic information, resume content and intent attribute tag sets;
the fourth acquisition module is used for acquiring post browsing records and resume delivery records of job seekers;
The third processing module is used for processing the post browsing record and the resume delivery record to obtain a post browsing record set and a resume delivery record set;
The fourth processing module is used for processing the post browsing record set and the resume delivery record set to obtain an intention post set; the person matching dataset also includes an intent post set.
The personnel matching method and system based on artificial intelligence have the technical effects and advantages that:
By analyzing keywords in the job seeker communication records, the post attribute valued by the job seeker is inferred more accurately; by analyzing keywords in the recruiter communication records, false position attributes in the recruitment positions are identified, and person matching is performed by means of the real recruitment position attributes, so that highly-relevant recommended resume and recruitment positions are achieved, accuracy of person matching is improved, communication time cost of both the recruiter and the recruiter is reduced, use experience of the recruiter and the recruiter is improved, repeated work is reduced, and recruitment process are smoother and efficient.
Drawings
FIG. 1 is a schematic diagram of an artificial intelligence based personnel matching system according to embodiment 1 of the present invention;
FIG. 2 is a schematic diagram of an artificial intelligence based personnel matching system according to embodiment 2 of the present invention;
FIG. 3 is a flowchart of an artificial intelligence based person matching method according to embodiment 3 of the present invention;
FIG. 4 is a schematic diagram of an electronic device according to the present invention;
FIG. 5 is a schematic diagram of a storage medium according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, the personnel matching method and system based on artificial intelligence in this embodiment includes a first acquisition module, a second acquisition module, a first processing module, a third acquisition module, a second processing module, and a personnel matching module, where each module is connected by a wire and/or a wireless to realize data transmission.
The first acquisition module is used for acquiring resume contents of job seekers; the resume content comprises expected salary, academic, graduation school, work experience and work skills.
The intent data is obtained from a background database of the recruitment platform.
The second acquisition module is used for acquiring a keyword set in the communication records of the job seeker and the recruiter; the keywords are collected on the premise that the job seeker and recruiter agree with privacy policies and use terms of the job seeker platform; the keyword set comprises an intention keyword set and a recruitment keyword set; the intention keyword set is a keyword set reflected when the recruiter communicates, and the recruitment keyword set is a keyword set reflected when the recruiter communicates.
The keyword set acquisition method comprises the following steps:
S131: anonymizing the communication record; for example, the name, contact and address in the communication record are replaced with "[ name ]", "[ contact ]" and "[ address ]".
Examples of recruiter and job seeker communication records are as follows:
Recruiters: "you good please provide your name and contact means, we contact you later.
Job seekers: "Xiaoming 12345678910". "
Examples of the communication record after anonymization processing are as follows:
Recruiters: "you good please provide your name and contact means, we contact you later.
Job seekers: "[ name ], [ contact ]".
It should be noted that, anonymizing the communication record can avoid collecting the privacy information, and only the anonymized collected information is analyzed in the subsequent process.
S132: predefining a stop word list, and removing corresponding words in the communication record according to the stop word list; the deactivation vocabulary includes "me", "yes", "this", and the like.
S133: removing punctuation marks and special characters from the communication records by using an NLP technology (such as jieba, NLTK, spaCy and the like), and segmenting the communication records to obtain a keyword set; if the 'I like the post of the weekend double rest' is divided, the steps of { { like }, { weekend }, { double rest }, and }; the special characters include "(", ")" and "-etc.
S134: dividing the keyword set into an intention keyword set and a recruitment keyword set according to the sending main body; the sending main body corresponding to the intention keyword set is a job hunting terminal, and the sending main body corresponding to the recruitment keyword set is a recruitment terminal.
The first processing module is used for respectively processing the intent keyword set and the recruitment keyword set to obtain an intent attribute tag set and a recruitment attribute tag set.
The acquisition method of the intent attribute tag set comprises the following steps:
S141: converting the keywords in the intent keyword set into intent keyword vectors by using Word2 Vec; word2Vec is a Word embedding technique.
S142: and classifying similar intention keyword vectors by using a clustering algorithm K-means to obtain an intention keyword vector set.
S143: inputting the classified intention keyword vector into an intention recognition model to obtain an intention attribute label corresponding to the intention keyword vector; if the weekend is not in duty, the corresponding intent attribute labels of the weekend is double-break.
The training method of the intention recognition model comprises the following steps:
The method comprises the steps of collecting an intention label data set in advance, wherein the intention label data comprises an intention keyword vector and an intention attribute label corresponding to the intention keyword vector, dividing the intention label data set into a training set and a test set, constructing a classifier, taking the intention keyword vector in the training set as input of an intention recognition model, taking the intention attribute label in the training set as output of the intention recognition model, training the classifier to obtain an initial classifier, testing the initial classifier by utilizing the test set, and outputting the classifier meeting the preset accuracy as the intention recognition model, wherein the classifier is a naive Bayesian model or a support vector machine model.
S144: the intent attribute tag is added to the intent attribute tag set.
The recruitment attribute tag set acquisition method comprises the following steps:
S151: and converting the keywords in the recruitment keyword set into recruitment keyword vectors by using Word2 Vec.
S152: and classifying the similar recruitment keyword vectors by using a clustering algorithm K-means to obtain a recruitment keyword vector set.
S153: inputting the classified recruitment keyword vector into a recruitment recognition model to obtain a recruitment keyword label corresponding to the recruitment keyword vector; and the recruitment keywords corresponding to the 'shift "," weekend plus half a day shift' and the 'big and small weeks' are marked as non-double-break.
The recruitment recognition model training method comprises the following steps:
The recruitment tag data set is collected in advance, the recruitment tag data comprises recruitment keyword vectors and recruitment keyword tags corresponding to the recruitment keyword vectors, the recruitment tag data set is divided into a training set and a test set, a classifier is built, the recruitment keyword vectors in the training set are used as input of a recruitment recognition model, the recruitment keyword tags in the training set are used as output of the recruitment recognition model, the classifier is trained to obtain an initial classifier, the initial classifier is tested by using the test set, the classifier meeting preset accuracy is output to serve as the recruitment recognition model, and the recruitment recognition model is a naive Bayesian model or a support vector machine model.
S154: and adding the recruitment keyword tag to the recruitment attribute tag set.
The third acquisition module is used for acquiring post basic information, wherein the post basic information comprises recruitment post requirements and recruitment post attributes; the recruitment post requirements comprise recruitment post names, post salaries, academia, graduation schools, work experiences and work skills; the recruitment post attributes include salary, academic, working time, whether double-break, work experience, work place, work skills and recruitment properties; the recruitment properties include full-time recruitment, part-time recruitment, practice recruitment, and outsource recruitment.
The post basic information is set by a recruiter and is acquired through the setting of the recruiter.
And the second processing module is used for comparing the recruitment attribute tag set with the recruitment post attributes, replacing the recruitment post attributes with recruitment keyword tags in the recruitment attribute tag set for inconsistent parts, and further obtaining updated recruitment post attributes.
It should be noted that, the recruitment attribute tag set is compared with the recruitment post attributes, if there is an inconsistent part, the recruitment attribute tag set is used to replace the recruitment post attributes for false post attributes in the recruitment post, so that the actual recruitment post attributes are obtained and then matched by personnel, and the recommended resume and the recruitment post are highly relevant.
For example: the recruiter sets the recruitment position attribute as 'double-break', but the recruitment attribute label is concentrated to form 'non-double-break', and the 'double-break' in the recruitment position attribute is replaced by the 'non-double-break'; the recruiter sets the recruitment position attribute as 'full-time recruitment', but 'outsourcing' exists in the recruitment attribute tag set, and the 'full-time recruitment' in the recruitment position attribute is replaced by 'outsourcing recruitment'.
The personnel matching module inputs the personnel matching data set into a pre-trained personnel matching model to obtain a matching tag value, if the personnel matching data set is matched, the job hunting resume is pushed to the recruitment terminal, and the recruitment post is pushed to the job hunting terminal; the personnel matching data set comprises post basic information, resume content and intent attribute tag sets; the match tag value includes 0 and 1,0 indicating no match and 1 indicating a match.
The training method of the personnel matching model comprises the following steps:
Pre-collecting a post matching data set, wherein the post matching data set comprises a personnel matching data set and matching label values corresponding to the personnel matching data set, dividing the post matching data set into a training set and a testing set, constructing a classifier, taking the personnel matching data set in the training set as the input of a personnel matching model, taking the matching label values in the training set as the output of the personnel matching model, and taking the sum of the prediction accuracy of all the predicted matching label values as a training target; stopping training until the sum of the prediction accuracy reaches convergence; the personnel matching model is an RNN model.
The calculation formula of the prediction accuracy is: l z＝(Yz-Sz)2, wherein L z is prediction accuracy, Y z is a predicted matching tag value corresponding to the z-th group of personnel matching data set, and S z is an actual matching tag value corresponding to the z-th group of personnel matching data set.
The method for acquiring the matching tag value comprises the following steps:
s161: counting the required quantity of recruitment posts, and marking the required quantity as H; and sequentially matching the recruitment post requirements with the intention post set and the resume content respectively, counting the successfully matched quantity, and marking as G.
S162: counting the number of recruitment post attributes, and marking the number as U; and sequentially matching the recruitment post attribute with the intent attribute tag set, counting the successful matching quantity, and marking as Y.
S163: calculating a matching rate; the calculation formula of the matching rate is as follows.
The sum of the number H of recruitment requirements and the number U of recruitment attributes is used as a denominator, the number G of successful recruitment requirements and the number Y of successful recruitment attributes are used as molecules, the number of the recruitment requirements met by the personnel is reflected, the higher the sum of G and Y is, the higher the matching rate is, and the more the personnel and the recruitment are matched.
S164: presetting a matching rate threshold beta, and if PP is greater than or equal to beta, the matching label value is 1; if PP is less than β, the match tag value is 0.
Example 2
Referring to fig. 2, the present embodiment provides an artificial intelligence based personnel matching system, which further includes:
And the fourth acquisition module is used for acquiring post browsing records and resume delivery records of job seekers.
And the post browsing record and the resume delivery record are acquired from a background database of the recruitment platform.
The third processing module is used for processing the post browsing record and the resume delivery record to obtain a post browsing record set and a resume delivery record set.
The post browsing record set acquisition method comprises the following steps:
s101: and acquiring a post browsing record.
S102: grouping the browsing post names in the acquired post browsing records, namely grouping the same browsing post names into a group.
S103: and counting the browsing times corresponding to the browsing post names in each group.
S104: the browsing times of all groups are ordered.
S105: adding the browsing post names and the corresponding browsing times into a post browsing record set according to the sequence of the browsing times from high to low; the post browsing record set comprises m browsing record subsets, and is expressed as follows:
{{L1：M1},{L2：M2}...{Lm：Mm}}。
It should be noted that, L m is a browsing post name in the mth browsing record subset; m m is the browsing times of the browsing post names in the mth browsing record subset; m 1＞M2>Mm; the post browsing record set can reflect the attention degree of job seekers to different posts; the more browses, the higher the attention to the post.
The resume delivery record set acquisition method comprises the following steps:
s111: and obtaining resume delivery records.
S112: grouping the delivery post names in the obtained resume delivery records, namely grouping the same delivery post names into a group.
S113: and counting the delivery times corresponding to the delivery post names in each group.
S114: the delivery times for all groups are ordered.
S115: adding the delivery post names and the delivery times corresponding to the delivery post names into the resume delivery record set according to the order of the delivery times from high to low; the resume delivery record set comprises n resume delivery record subsets expressed as follows:
{{T1：N1},{T2：N2}...{Tn：Nn}}。
It should be noted that, T n is a delivery post name in the n-th resume delivery record subset; n n is the delivery times of the delivery post names in the N resume delivery record subset; n 1>N2>Nn; the resume delivery record set can reflect the attention degree of job seekers to different posts; the more delivery times, the higher the attention to the post.
And the fourth processing module is used for processing the post browsing record set and the resume delivery record set to obtain an intention post set. The person matching dataset also includes an intent post set.
The set of intent posts is expressed as follows:
{YX1,YX2...YXx}。
note that YX x is the x-th intention post name in the intention post set.
The acquisition method of the intention post set comprises the following steps:
s121: presetting an initial value of i as 1, wherein i is epsilon m; the weight of the preset browsing times is that The weight of the preset delivery times is as follows.
S122: acquiring an ith browse record subset in the post browse record set, wherein browse posts L i and M i;Li in the browse record subset are browse post names in the ith browse record subset, and M i is browse times of the browse post names in the ith browse record subset.
S123: judging whether the resume delivery record set has the delivery post name same as L i; if yes, acquiring delivery times corresponding to the delivery post name which is the same as L i from the profile delivery record subset, and marking the delivery times as TD; if not, TD is set to 0.
S124: substituting M i and TD into a post intention score formula to obtain an intention score of browsing post i;
the post intent score formula is as follows:
Wherein, Is the post intent score of L i.
The weight factor isAnd weight factorAll are larger than 0, the higher the browsing times M i are, the higher the intention of the job seeker to the position is, otherwise, the higher the delivery times TD are, the higher the intention of the job seeker to the position is, and the comprehensive browsing times and delivery times can be weighted and summed to more accurately reflect the intention of the job seeker; the higher the position intent score, the higher the intent of the job seeker for that position.
S125: adding the intent scores of L i and L i to a temporary data table; let i=i+1, if i is less than or equal to m, continuing to execute S122 to S124; if i is equal to m, S126 is performed.
S126: the temporary data table is ordered according to the intention scores of the browsing posts from high to low, and the browsing post names of r before the intention scores of the posts are added to the intention post set.
S127: judging whether the browsing post names of k before the browsing times in the post browsing record set are in the intention post set, if not, adding the browsing post names in the intention post set to the intention post set; judging whether the delivery post name of k before the delivery times in the resume delivery record set is in the intention post set, if not, adding the delivery post in the intention post set to the intention post set.
It should be noted that, the number of browses in the post browsing record set is ranked at the top k, but the post attribute does not meet the expectations of the job seeker, such as unexpected salary, academic, graduation school, work experience or work skill, i.e. no resume is delivered or the number of delivery times is small, so that the post intention score is not the top r, but the scene can infer that the intention degree of the job seeker to the post is high, so that the post is added to the intention post set.
Similarly, there is a front k of delivery times, but the number of posts pushed to the job seeker is small, and the browsing times are not high, resulting in a non-front r of intent post score, but the scenario can infer that the job seeker has high intent to a post, so the post is added to the intent post set.
By analyzing the post browsing records and the resume delivery records of the job seeker, the true job seeking intention posts of the job seeker are inferred more accurately, and mismatching caused by relying on the intention posts in the resume is avoided.
Example 3
Referring to fig. 3, the embodiment provides a person matching method based on artificial intelligence, which includes:
Collecting resume content of job seekers;
Acquiring a keyword set in communication records of a job seeker and a recruiter; the keyword set comprises an intention keyword set and a recruitment keyword set;
Processing the intent keyword set and the recruitment keyword set respectively to obtain an intent attribute tag set and a recruitment attribute tag set;
Acquiring post basic information, wherein the post basic information comprises recruitment post requirements and recruitment post attributes;
Comparing the recruitment attribute tag set with the recruitment post attribute, and replacing the recruitment post attribute with a recruitment keyword tag in the recruitment attribute tag set for the inconsistent part;
Inputting the personnel matching data set into a pre-trained personnel matching model to obtain a matching tag value, if the personnel matching data set is matched, pushing the job hunting resume to a recruitment terminal, and pushing the recruitment post to the job hunting terminal; the personnel matching data set comprises post basic information, resume content and intent attribute label set.
Example 4
Referring to fig. 4, an electronic device 500 is also provided in accordance with yet another aspect of the present application. The electronic device 500 may include one or more processors and one or more memories. Wherein the memory has stored therein computer readable code which, when executed by the one or more processors, may perform the artificial intelligence based person matching method as described above.
The method or system according to embodiments of the application may also be implemented by means of the architecture of the electronic device shown in fig. 4. As shown in fig. 4, the electronic device 500 may include a bus 501, one or more CPUs 502, a ROM503, a RAM504, a communication port 505 connected to a network, an input/output 506, a hard disk 507, and the like. A storage device in electronic device 500, such as ROM503 or hard disk 507, may store the artificial intelligence based person matching method provided by the present application. Further, the electronic device 500 may also include a user interface 508. Of course, the architecture shown in fig. 4 is merely exemplary, and one or more components of the electronic device shown in fig. 3 may be omitted as may be desired in implementing different devices.
Example 5
Referring to FIG. 5, a computer readable storage medium 600 according to one embodiment of the application is shown. Computer readable storage medium 600 has stored thereon computer readable instructions. The artificial intelligence based person matching method according to embodiments of the present application described with reference to the above figures may be performed when the computer readable instructions are executed by a processor. Storage medium 600 includes, but is not limited to, for example, volatile memory and/or nonvolatile memory. Volatile memory can include, for example, random Access Memory (RAM), cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like.
In addition, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, the present application provides a non-transitory machine-readable storage medium storing machine-readable instructions executable by a processor to perform instructions corresponding to the method steps provided by the present application, such as: an artificial intelligence-based personnel matching method. The above-described functions defined in the method of the present application are performed when the computer program is executed by a Central Processing Unit (CPU).
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.

Claims (10)

1.基于人工智能的人员匹配方法，其特征在于，包括：1. A personnel matching method based on artificial intelligence, characterized by comprising: 采集求职者的简历内容；Collect resume content of job seekers; 获取求职者和招聘人员沟通记录中的关键词集合；所述关键词集合包括意向关键词集和招聘关键词集；Obtaining a keyword set in the communication record between the job seeker and the recruiter; the keyword set includes an intended keyword set and a recruitment keyword set; 对意向关键词集和招聘关键词集分别进行处理，得到意向属性标签集和招聘属性标签集；The intention keyword set and the recruitment keyword set are processed separately to obtain the intention attribute label set and the recruitment attribute label set; 采集岗位基本信息，所述岗位基本信息包括招聘岗位要求和招聘岗位属性；Collecting basic job information, including job requirements and job attributes; 将招聘属性标签集与招聘岗位属性进行对比，对不一致的部分，用招聘属性标签集中的招聘关键词标签替换招聘岗位属性；Compare the recruitment attribute tag set with the recruitment position attributes, and replace the recruitment position attributes with the recruitment keyword tags in the recruitment attribute tag set for the inconsistent parts; 将人员匹配数据集输入至预先训练的人员匹配模型中，得到匹配标签值，若匹配，则将求职简历推送给招聘端，将招聘岗位推送给求职端；所述人员匹配数据集包括岗位基本信息、简历内容和意向属性标签集。The personnel matching data set is input into the pre-trained personnel matching model to obtain the matching label value. If there is a match, the job application resume is pushed to the recruitment end, and the recruitment position is pushed to the job seeker end; the personnel matching data set includes basic position information, resume content and intention attribute label set. 2.根据权利要求1所述的基于人工智能的人员匹配方法，其特征在于，所述关键词集合的获取方法为：2. The personnel matching method based on artificial intelligence according to claim 1, characterized in that the method for obtaining the keyword set is: S131：对沟通记录进行匿名化处理；S131: Anonymize communication records; S132：预定义停用词表，根据停用词表去除沟通记录中的对应词汇；S132: pre-define a stop word list, and remove corresponding words in the communication record according to the stop word list; S133：使用NLP技术对沟通记录去除标点符号和特殊字符，并将沟通记录分词得到关键词集合；S133: using NLP technology to remove punctuation marks and special characters from the communication records, and segmenting the communication records to obtain a keyword set; S134：根据发送主体将关键词集合划分成意向关键词集和招聘关键词集；意向关键词集对应的发送主体为求职端，招聘关键词集对应的发送主体为招聘端。S134: Divide the keyword set into an intention keyword set and a recruitment keyword set according to the sending subject; the sending subject corresponding to the intention keyword set is the job seeker end, and the sending subject corresponding to the recruitment keyword set is the recruitment end. 3.根据权利要求2所述的基于人工智能的人员匹配方法，其特征在于，所述意向属性标签集的获取方法包括：3. According to the artificial intelligence-based personnel matching method of claim 2, it is characterized in that the method for obtaining the intention attribute tag set includes: S141：使用Word2Vec将意向关键词集中的关键词转换成意向关键词向量；S141: using Word2Vec to convert keywords in the intended keyword set into intended keyword vectors; S142：使用聚类算法对相似的意向关键词向量进行归类，得到意向关键词向量集；S142: using a clustering algorithm to classify similar intention keyword vectors to obtain an intention keyword vector set; S143：将归类后的意向关键词向量输入意向识别模型中，得到意向关键词向量对应的意向属性标签；S143: inputting the classified intention keyword vector into the intention recognition model to obtain the intention attribute label corresponding to the intention keyword vector; 所述意向识别模型的训练方法包括：The training method of the intention recognition model includes: 预先收集意向标签数据集，所述意向标签数据包括意向关键词向量，以及意向关键词向量对应的意向属性标签，将所述意向标签数据集划分为训练集与测试集，构建分类器，将训练集中的意向关键词向量作为意向识别模型的输入，将训练集中的意向属性标签作为意向识别模型的输出，对分类器进行训练，得到初始分类器，利用测试集对初始分类器进行测试，输出满足预设准确度的分类器作为意向识别模型，分类器为朴素贝叶斯模型或支持向量机模型；Pre-collect an intention label data set, wherein the intention label data includes an intention keyword vector and an intention attribute label corresponding to the intention keyword vector, divide the intention label data set into a training set and a test set, construct a classifier, use the intention keyword vector in the training set as the input of the intention recognition model, use the intention attribute label in the training set as the output of the intention recognition model, train the classifier to obtain an initial classifier, test the initial classifier using the test set, and output a classifier that meets a preset accuracy as the intention recognition model, wherein the classifier is a naive Bayes model or a support vector machine model; S144：将意向属性标签添加至意向属性标签集。S144: Add the intent attribute label to the intent attribute label set. 4.根据权利要求3所述的基于人工智能的人员匹配方法，其特征在于，所述招聘属性标签集的获取方法包括：4. The personnel matching method based on artificial intelligence according to claim 3 is characterized in that the method for obtaining the recruitment attribute tag set comprises: S151：使用Word2Vec将招聘关键词集中的关键词转换成招聘关键词向量；S151: Use Word2Vec to convert keywords in the recruitment keyword set into recruitment keyword vectors; S152：使用聚类算法对相似的招聘关键词向量进行归类，得到招聘关键词向量集；S152: using a clustering algorithm to classify similar recruitment keyword vectors to obtain a recruitment keyword vector set; S153：将归类后的招聘关键词向量输入招聘识别模型中，得到招聘关键词向量对应的招聘关键词标签；S153: inputting the classified recruitment keyword vector into a recruitment recognition model to obtain a recruitment keyword label corresponding to the recruitment keyword vector; 所述招聘识别模型的训练方法包括：The training method of the recruitment recognition model includes: 预先收集招聘标签数据集，所述招聘标签数据包括招聘关键词向量以及招聘关键词向量对应的招聘关键词标签，将所述招聘标签数据集划分为训练集与测试集，构建分类器，将训练集中的招聘关键词向量作为招聘识别模型的输入，将训练集中的招聘关键词标签作为招聘识别模型的输出，对分类器进行训练，得到初始分类器，利用测试集对初始分类器进行测试，输出满足预设准确度的分类器作为招聘识别模型，招聘识别模型为朴素贝叶斯模型或支持向量机模型；Pre-collecting a recruitment label data set, wherein the recruitment label data includes a recruitment keyword vector and a recruitment keyword label corresponding to the recruitment keyword vector, dividing the recruitment label data set into a training set and a test set, constructing a classifier, using the recruitment keyword vector in the training set as the input of a recruitment recognition model, using the recruitment keyword label in the training set as the output of the recruitment recognition model, training the classifier to obtain an initial classifier, testing the initial classifier using the test set, and outputting a classifier that meets a preset accuracy as a recruitment recognition model, wherein the recruitment recognition model is a naive Bayes model or a support vector machine model; S154：将招聘关键词标签添加至招聘属性标签集。S154: Add the recruitment keyword tag to the recruitment attribute tag set. 5.根据权利要求4所述的基于人工智能的人员匹配方法，其特征在于，所述人员匹配模型的训练方法包括：5. The personnel matching method based on artificial intelligence according to claim 4, characterized in that the training method of the personnel matching model comprises: 预先收集岗位匹配数据集，所述岗位匹配数据集包括人员匹配数据集以及人员匹配数据集对应的匹配标签值，将所述岗位匹配数据集划分为训练集与测试集，构建分类器，将训练集中的人员匹配数据集作为人员匹配模型的输入，将训练集中的匹配标签值作为人员匹配模型的输出，以最小化所有预测的匹配标签值的预测准确度之和作为训练目标；直至预测准确度之和达到收敛时停止训练；所述人员匹配模型为RNN模型。A job matching data set is collected in advance, wherein the job matching data set includes a personnel matching data set and matching label values corresponding to the personnel matching data set. The job matching data set is divided into a training set and a test set, a classifier is constructed, the personnel matching data set in the training set is used as the input of the personnel matching model, and the matching label values in the training set are used as the output of the personnel matching model, and the training goal is to minimize the sum of the prediction accuracies of all predicted matching label values; the training is stopped when the sum of the prediction accuracies converges; the personnel matching model is an RNN model. 6.根据权利要求1所述的基于人工智能的人员匹配方法，其特征在于，所述人员匹配数据集还包括意向岗位集合，所述意向岗位集合获得方法包括：6. The personnel matching method based on artificial intelligence according to claim 1, characterized in that the personnel matching data set also includes a set of intended positions, and the method for obtaining the set of intended positions includes: 采集求职者的岗位浏览记录和简历投递记录；Collect job seekers’ job browsing records and resume submission records; 将岗位浏览记录和简历投递记录进行处理，得到岗位浏览记录集合和简历投递记录集合；Process the job browsing records and resume delivery records to obtain a job browsing record set and a resume delivery record set; 对岗位浏览记录集合和简历投递记录集合进行处理，得到意向岗位集合。The job browsing record set and the resume submission record set are processed to obtain the intended job set. 7.根据权利要求6所述的基于人工智能的人员匹配方法，其特征在于，所述岗位浏览记录集合的获取方法为：7. The personnel matching method based on artificial intelligence according to claim 6, characterized in that the method for obtaining the post browsing record set is: S101：获取岗位浏览记录；S101: Obtaining job browsing records; S102：对获取的岗位浏览记录中的浏览岗位名称进行分组，即将相同的浏览岗位名称归为一组；S102: Grouping the browsed job titles in the acquired job browsing records, that is, grouping the same browsed job titles into one group; S103：统计每一组中浏览岗位名称对应的浏览次数；S103: Count the number of views corresponding to the browsed job titles in each group; S104：对所有组的浏览次数进行排序；S104: sorting the browsing times of all groups; S105：按照浏览次数由高到低的顺序，将浏览岗位名称及其对应的浏览次数添加到岗位浏览记录集合中；所述岗位浏览记录集合包括m个浏览记录子集合，表达如下：S105: Add the browsed job titles and their corresponding browsed times to a job browsed record set in descending order of browsed times; the job browsed record set includes m browsed record subsets, which are expressed as follows: {{L1：M1}，{L2：M2}...{Lm：Mm}}；{{L 1 : M 1 }, {L 2 : M 2 }...{L m : M m }}; Lm为第m个浏览记录子集合中浏览岗位名称；Mm为第m个浏览记录子集合中浏览岗位名称的浏览次数；M1＞M2>Mm。L m is the browsed job title in the mth browsed record subset; M m is the browsed times of the browsed job title in the mth browsed record subset; M 1 >M 2 >M m . 8.根据权利要求7所述的基于人工智能的人员匹配方法，其特征在于，所述简历投递记录集合的获取方法为：8. The personnel matching method based on artificial intelligence according to claim 7, characterized in that the method for obtaining the resume delivery record set is: S111：获取简历投递记录；S111: Obtain resume delivery records; S112：对获取的简历投递记录中的投递岗位名称进行分组，即将相同的投递岗位名称归为一组；S112: Grouping the job titles in the obtained resume delivery records, that is, grouping the same job titles into one group; S113：统计每一组中投递岗位名称对应的投递次数；S113: Count the number of submissions corresponding to the submission job names in each group; S114：对所有组的投递次数进行排序；S114: sorting the delivery times of all groups; S115：按照投递次数由高到低的顺序，将投递岗位名称及其对应的投递次数添加到简历投递记录集合中；所述简历投递记录集合包括n个简历投递记录子集合，表达如下：S115: Add the job titles and their corresponding submission times to a resume submission record set in descending order of submission times; the resume submission record set includes n resume submission record subsets, which are expressed as follows: {{T1：N1]，{T2：N2}...{Tn：Nn}}；{{T 1 : N 1 ], {T 2 : N 2 }...{T n : N n }}; Tn为第n个简历投递记录子集合中投递岗位名称；Nn为第n个简历投递记录子集合中投递岗位名称的投递次数；N1＞N2>Nn。T n is the name of the post in the nth resume delivery record subset; N n is the number of times the post is delivered in the nth resume delivery record subset; N 1 >N 2 >N n . 9.根据权利要求8所述的基于人工智能的人员匹配方法，其特征在于，所述意向岗位集合的获取方法为：9. The personnel matching method based on artificial intelligence according to claim 8, characterized in that the method for obtaining the intended job set is: S121：预设i的初始值为1，i∈m；预设浏览次数的权重为预设投递次数的权重为 S121: The initial value of i is preset to be 1, i∈m; the weight of the number of views is preset to be The weight of the preset delivery times is S122：获取岗位浏览记录集合中第i个浏览记录子集合，获取浏览记录子集合中的浏览岗位Li和Mi；Li为第i个浏览记录子集合中浏览岗位名称，Mi为第i个浏览记录子集合中浏览岗位名称的浏览次数；S122: Obtain the i-th browsing record subset in the job browsing record set, and obtain the browsed jobs Li and Mi in the browsing record subset; Li is the browsed job name in the i-th browsing record subset, and Mi is the number of views of the browsed job name in the i-th browsing record subset; S123：判断简历投递记录集合中是否存在与Li相同的投递岗位名称；若存在，则从简历投递记录子集合中获取与Li相同的投递岗位名称对应的投递次数，记为TD；若不存在，则将TD置为0；S123: Determine whether there is a resume delivery record set with the same delivery position name as Li ; if so, obtain the number of delivery times corresponding to the same delivery position name as Li from the resume delivery record subset, and record it as TD; if not, set TD to 0; S124：将Mi和TD代入岗位意向得分公式，得到浏览岗位i的意向得分；S124: Substitute Mi and TD into the position intention score formula to obtain the intention score of browsing position i; 所述岗位意向得分公式如下：The job intention scoring formula is as follows: 为Li的岗位意向得分； Score Li ’s job intention; S125：将Li和Li的意向得分加入临时数据表中；令i＝i+1，若i小于或等于m，则继续执行S122至S124；若i等于m，则执行S126；S125: Add L i and the intention score of L i to the temporary data table; let i=i+1, if i is less than or equal to m, continue to execute S122 to S124; if i is equal to m, execute S126; S126：将临时数据表按照浏览岗位的意向得分由高到低进行排序，将岗位意向得分前r的浏览岗位名称添加至意向岗位集合；S126: sorting the temporary data table from high to low according to the intention scores of the browsed positions, and adding the browsed position names with the top r position intention scores to the intended position set; S127：判断岗位浏览记录集合中浏览次数前k的浏览岗位名称，是否在意向岗位集合中，若不在，则将不在意向岗位集合中浏览岗位名称添加至意向岗位集合；判断简历投递记录集合中投递次数前k的投递岗位名称，是否在意向岗位集合中，若不在，则将不在意向岗位集合中投递岗位添加至意向岗位集合。S127: Determine whether the names of the k most viewed positions in the position browsing record set are in the intended position set. If not, add the names of the viewed positions that are not in the intended position set to the intended position set; determine whether the names of the k most submitted positions in the resume submission record set are in the intended position set. If not, add the submitted positions that are not in the intended position set to the intended position set. 10.基于人工智能的人员匹配系统，实施权利要求1-9任一项所述基于人工智能的人员匹配方法，其特征在于，包括：10. An artificial intelligence-based personnel matching system, implementing the artificial intelligence-based personnel matching method according to any one of claims 1 to 9, characterized in that it comprises: 第一采集模块，用于采集求职者的简历内容；The first collection module is used to collect the resume content of job seekers; 第二采集模块，用于获取求职者和招聘人员沟通记录中的关键词集合；所述关键词集合包括意向关键词集和招聘关键词集；The second acquisition module is used to obtain a keyword set in the communication records between job seekers and recruiters; the keyword set includes an intention keyword set and a recruitment keyword set; 第一处理模块，用于对意向关键词集和招聘关键词集分别进行处理，得到意向属性标签集和招聘属性标签集；The first processing module is used to process the intention keyword set and the recruitment keyword set respectively to obtain the intention attribute tag set and the recruitment attribute tag set; 第三采集模块，用于采集岗位基本信息，所述岗位基本信息包括招聘岗位要求和招聘岗位属性；The third collection module is used to collect basic information of the position, and the basic information of the position includes the requirements and attributes of the recruitment position; 第二处理模块，用于将招聘属性标签集与招聘岗位属性进行对比，对不一致的部分，用招聘属性标签集中的招聘关键词标签替换招聘岗位属性；The second processing module is used to compare the recruitment attribute tag set with the recruitment position attributes, and replace the recruitment position attributes with the recruitment keyword tags in the recruitment attribute tag set for the inconsistent parts; 人员匹配模块，将人员匹配数据集输入至预先训练的人员匹配模型中，得到匹配标签值，若匹配，则将求职简历推送给招聘端，将招聘岗位推送给求职端；所述人员匹配数据集包括岗位基本信息、简历内容和意向属性标签集；The personnel matching module inputs the personnel matching data set into the pre-trained personnel matching model to obtain the matching label value. If there is a match, the job application resume is pushed to the recruitment end, and the recruitment position is pushed to the job application end; the personnel matching data set includes basic position information, resume content and intention attribute label set; 第四采集模块，用于采集求职者的岗位浏览记录和简历投递记录；The fourth collection module is used to collect job seekers' job browsing records and resume submission records; 第三处理模块，用于将岗位浏览记录和简历投递记录进行处理，得到岗位浏览记录集合和简历投递记录集合；The third processing module is used to process the job browsing records and resume submission records to obtain a job browsing record set and a resume submission record set; 第四处理模块，用于对岗位浏览记录集合和简历投递记录集合进行处理，得到意向岗位集合；所述人员匹配数据集还包括意向岗位集合。The fourth processing module is used to process the job browsing record set and the resume submission record set to obtain the intended job set; the personnel matching data set also includes the intended job set.
CN202411000443.0A 2024-07-24 2024-07-24 Personnel matching method and system based on artificial intelligence Pending CN119025620A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411000443.0A CN119025620A (en) 2024-07-24 2024-07-24 Personnel matching method and system based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411000443.0A CN119025620A (en) 2024-07-24 2024-07-24 Personnel matching method and system based on artificial intelligence

Publications (1)

Publication Number Publication Date
CN119025620A true CN119025620A (en) 2024-11-26

Family

ID=93531963

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411000443.0A Pending CN119025620A (en) 2024-07-24 2024-07-24 Personnel matching method and system based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN119025620A (en)

Similar Documents

Publication Publication Date Title
WO2020224097A1 (en) Intelligent semantic document recommendation method and device, and computer-readable storage medium
AU2024204609A1 (en) System and engine for seeded clustering of news events
US11474978B2 (en) Systems and methods for a data search engine based on data profiles
CN109829104A (en) Pseudo-linear filter model information search method and system based on semantic similarity
CN106547864B (en) A Personalized Information Retrieval Method Based on Query Expansion
CN107844533A (en) A kind of intelligent Answer System and analysis method
CN104834651B (en) Method and device for providing high-frequency question answers
US11599666B2 (en) Smart document migration and entity detection
CN110019474B (en) Automatic synonymy data association method and device in heterogeneous database and electronic equipment
CN112380421B (en) Resume search method, device, electronic device and computer storage medium
JP2020512651A (en) Search method, device, and non-transitory computer-readable storage medium
CN113792131B (en) Keyword extraction method and device, electronic equipment and storage medium
EP4207035A1 (en) Sorting method, apparatus and device, and computer storage medium
WO2021190662A1 (en) Medical text sorting method and apparatus, electronic device, and storage medium
US12406008B1 (en) Using intent-based rankings to generate large language model responses
Tenenboim et al. Ontology-based classification of news in an electronic newspaper
CN113486232B (en) Query method, device, server, medium and product
CN116804998A (en) Medical terminology retrieval method and system based on medical semantic understanding
CN112256863A (en) A method, device and electronic device for determining the intent of corpus
EP3815026B1 (en) Systems and methods for identifying and linking events in structured proceedings
CN115358817A (en) Intelligent product recommendation method, device, equipment and medium based on social data
CN113688633B (en) Method and device for determining outline
CN109299007A (en) An automatic recommendation method for defect fixers
CN119106116A (en) Question retrieval and answering method based on large language model and multi-dimensional technology fusion
CN113468422A (en) Searching method, searching device, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination