CN111105209B - Job resume matching method and device suitable for person post matching recommendation system - Google Patents
Job resume matching method and device suitable for person post matching recommendation system Download PDFInfo
- Publication number
- CN111105209B CN111105209B CN201911304875.XA CN201911304875A CN111105209B CN 111105209 B CN111105209 B CN 111105209B CN 201911304875 A CN201911304875 A CN 201911304875A CN 111105209 B CN111105209 B CN 111105209B
- Authority
- CN
- China
- Prior art keywords
- information
- resume
- job
- text information
- matching
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
- G06Q10/1053—Employment or hiring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a job resume matching and device suitable for a person post matching recommendation system, wherein the method comprises the following steps: acquiring position text information input by a person unit and resume text information input by a job applicant, wherein the position text information is related information aiming at a job to be recruited, and the resume text information is a resume of the job applicant; text analysis is carried out on the position text information and the resume text information based on a text analysis algorithm, so that tag information is obtained; and performing matching calculation on the position label and the basic information in the position text information and the resume text information, and matching the resume which is most in line with the current position, wherein the basic information is the position text information and other basic information except the label information in the resume text information. By adopting the invention, by combining a plurality of artificial intelligence algorithms, the problem of slow pain point searching by pure manual operation can be solved, and the working efficiency of person post matching and the matching degree of final resume recommendation are improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a job resume matching method and device suitable for a person post matching recommendation system.
Background
The traditional recruitment service field is a business process that a recruiter searches for a proper candidate through position information and recommends the candidate to an enterprise, the candidate enters the job after being screened and interviewed by the resume of the enterprise, and the enterprise returns money to the recruiter. At present, certain problems exist in the process of matching positions and resume of a consultant, for example, how to quickly find out suitable candidates through position information, especially for recruitment consultants who just go into the field of strangeness, a long time is required to master related experiences, so that the efficiency of person post matching is lower and the matching degree is not high.
Disclosure of Invention
The embodiment of the invention provides a job resume matching method and device suitable for a person post matching recommendation system, which can improve the efficiency and the matching degree of person post matching.
The first aspect of the embodiment of the invention provides a job resume matching method suitable for a person post matching recommendation system, which can comprise the following steps:
acquiring position text information input by a person unit and resume text information input by a job applicant, wherein the position text information is related information aiming at a job to be recruited, and the resume text information is a resume of the job applicant;
text analysis is carried out on the position text information and the resume text information based on a text analysis algorithm, so that tag information is obtained;
and performing matching calculation on the position label and the basic information in the position text information and the resume text information, and matching the resume which is most in line with the current position, wherein the basic information is the position text information and other basic information except the label information in the resume text information.
The second aspect of the embodiment of the invention provides a job resume matching device suitable for a person post matching recommendation system, which can comprise:
the text acquisition module is used for acquiring position text information input by a personnel unit and resume text information input by a job seeker, wherein the position text information is related information aiming at a job to be recruited, and the resume text information is a resume of the job seeker;
the text analysis module is used for carrying out text analysis on the position text information and the resume text information based on a text analysis algorithm to obtain tag information;
the position resume matching module is used for carrying out matching calculation on position text information and position labels and basic information in the resume text information, and matching the resume which is most in line with the current position, wherein the basic information is the position text information and other basic information except the label information in the resume text information.
A third aspect of the embodiment of the present invention provides a computer device, where the device includes a processor and a memory, where the memory stores at least one instruction, at least one program, a code set, or an instruction set, where the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the job resume matching method applicable to the person post matching recommendation system in the foregoing aspect.
A fourth aspect of the present invention provides a computer storage medium, where at least one instruction, at least one program, a code set, or an instruction set is stored, where the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement a job resume matching method applicable to a person post matching recommendation system in the foregoing aspect.
In the embodiment of the invention, the position and resume related information acquired by the system are analyzed by introducing an artificial intelligence algorithm, and the analyzed information is processed by combining the position similarity and resume matching algorithm, so that the most matched resume is recommended for the current position, wherein feedback information for candidate resume is also introduced before the person post is matched. By combining multiple artificial intelligence algorithms, the problem of slow pain points found by pure manual operation is solved, and the working efficiency of person post matching and the matching degree of final resume recommendation are improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a job resume matching method suitable for a person post matching recommendation system provided by the embodiment of the invention;
fig. 2 is a schematic flow chart of job function classification according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of high-frequency keyword extraction provided by an embodiment of the invention;
FIG. 4 is a schematic flow chart of skill keyword extraction provided by an embodiment of the present invention;
FIG. 5 is a flow diagram of industry tag subdivision provided by an embodiment of the present invention;
FIG. 6 is a flow chart of the required operational life identification provided by an embodiment of the present invention;
FIG. 7 is a flow chart of the required academic recognition provided by an embodiment of the present invention;
FIG. 8 is a schematic flow chart of salary prediction provided by an embodiment of the present invention;
fig. 9 is a schematic flow chart of job resume matching according to an embodiment of the present invention;
FIG. 10 is a schematic flow chart of calculating similarity between positions and other positions under the same secondary classification according to the embodiment of the present invention;
FIG. 11 is a schematic flow chart of a person post matching recommendation method provided by an embodiment of the invention;
FIG. 12 is a schematic structural diagram of a job resume matching device suitable for a person post matching recommendation system according to an embodiment of the present invention;
fig. 13 is a schematic structural diagram of a job resume matching module according to an embodiment of the present invention;
fig. 14 is a schematic structural diagram of a computer device according to an embodiment of 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.
The terms "comprising" and "having" and any variations thereof in the description and claims of the invention and in the foregoing drawings are intended to cover non-exclusive inclusions, the terms "first" and "second" being used merely for distinguishing between them and not for the purpose of a numerical size or ordering. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
It should be noted that, the job resume matching method suitable for the post matching recommendation system provided by the application can be applied to application scenes of a hunter for screening suitable candidates according to recruitment positions of enterprises and recommending the candidates to the enterprises.
In the embodiment of the invention, the job resume matching method suitable for the person post matching recommendation system can be applied to computer equipment, wherein the computer equipment can be a computer or a smart phone, and can also be other electronic equipment with calculation processing capability.
As shown in FIG. 1, the job resume matching method suitable for the person post matching recommendation system at least comprises the following steps:
s101, acquiring position text information input by a personnel unit and resume text information input by a job seeker.
It is to be appreciated that the job text information can be relevant information for the job to be recruited entered by a human entity (i.e., the business requiring recruitment of employees) on the matching system of the subject application or other recruitment website, such as, for example, job names, recruitment requirements, basic information (e.g., academic, age, job site, payroll conditions, etc.) can be included. The resume text information can be a resume uploaded by a job seeker in the system or other recruitment websites, and can comprise job names of job seekers, work experiences, skills and basic information. Alternatively, the job text information and resume text information may be manually entered into the system by a recruiter, i.e., a hunter, or linked to the system from another website.
S102, text analysis is carried out on the position text information and the resume text information based on a text analysis algorithm, and tag information is obtained.
It will be appreciated that the text parsing algorithm may split the job text information and resume text information into a plurality of tag information including, but not limited to, job classification, high frequency keywords, skill keywords, subdivision industry, salary prediction, job required years, job required academy, etc.
In a specific implementation, the process of analyzing the tag information by the text analysis algorithm is as follows:
1) The process for job function classification in job text information and resume text information may be as shown in fig. 2: the method comprises the steps of extracting position names in texts respectively, classifying the position names, and storing classification results into a database.
In a specific implementation, the system can classify the job functions through three steps: pre-training a job position and job position classification model; acquiring position name information in position text information and resume text information; and putting the acquired job name information into the classification model to match, and outputting a classification result. In the process of training a classification model, a position text information resource in a system can be utilized, a 3-layer position classification system (1-level 52 classification identifications, 2-level 800 classification identifications and 3-level 4000+ classification identifications) is integrated and arranged by combining a TFIDF algorithm, low-frequency word filtering, bi-gram mutual information calculation and manual integration, a 3-level corresponding 2-level tier tree is built by utilizing the arranged classification identifications (for example, 3-level identification java research and development and java background development belong to 2-level identification java development, the tier tree relationship is { j- > a- > v- > a- > research- > java development } and { j- > a- > v- > a- > post- > station- > java development), and then the built relationship is stored in a tier tree structure. Further, when the obtained job name information is put into the classification model to be matched and a classification result is output, the system can compare from the existing characters and output the result by a greedy algorithm at the end part, for example, the job name is 'deep java back end development', the words are skipped because the words are 'resource' and 'deep' are not stored in the initial search list of the tier tree, the words are stopped from j to { j- > a- > v- > a- > after }, the end words are positioned in { j- > a- > v- > a- > after- > a- > on- > java development }, and the result of matching classification is output as java development and is stored in a database.
2) The extraction process for the high frequency keyword may be as shown in fig. 3: extracting working experience and project experience in resume text information, and extracting position description and position requirements in position text information; and extracting high-frequency keywords according to the extracted data, and then putting the keyword extraction result into a database.
In specific implementation, the system can extract the high-frequency keywords through three steps: respectively acquiring position descriptions and position requirements in position text information, acquiring working experience and project experience in resume text information, and performing word segmentation on the acquired information; then comprehensively judging the key degree of a single word according to the word frequency, the part of speech and the semantic relativity of the word segmentation result; and finally, sorting the score of each word from high to low and storing the score into a database. It should be noted that, the score of each word reflects the keyword degree of the word, and the scoring ratio of word frequency, part of speech and semantic relevance may be 40%, 10% and 50% in scoring. Wherein, TFIDF algorithm can be used to replace traditional word frequency. It can be understood that judging the importance of words through parts of speech is a relatively common method, and can well process partial situations, for example, words without practical meaning such as imaginary words, number words and the like can be scored very low, and user-defined words, english words and the like can be scored very high. It should be noted that, the semantic relevance refers to the overall relevance of this word to other words in the whole text.
3) The extraction process for skill keywords may be as shown in fig. 4: the method comprises the steps of pre-training a skill keyword extraction model; respectively acquiring position descriptions and position requirements in position text information, and acquiring working experience and project experience in resume text information; and putting the obtained data into a keyword extraction model to calculate and outputting a result to a database.
4) The subdivision process for the subdivision industry label may be as shown in FIG. 5: the method comprises the steps of pre-training a subdivision industry label system based on all job text information and resume text information in a system; acquiring relevant information (such as company description and company camping) of a company by analyzing the company to which the job position belongs and the company where the resume work experience is located; and (3) putting the related information of the company into a subdivision industry label system to calculate classification labels of the primary subdivision industry and the secondary subdivision industry, and storing the classification labels into a database.
5) The identification process for the required working years for the job position may be as shown in fig. 6: the method comprises the steps of extracting position requirements in position text information, and further identifying the working years required by the position. Preferably, the system can extract the minimum working period and the maximum working period required by the job position by using a regular matching formula, for example, the working experience of more than three years is required to extract the minimum working period of 3 and the maximum working period of 99.
6) The identification process for the required learning of the job position may be as shown in fig. 7: extracting position requirements in position text information, and further identifying the required academic of the position. Preferably, the system can identify the lowest academy required for a job position using a canonical matching formula, such as the above academy of the family to extract the minimum family.
7) The prediction process for salary prediction may be as shown in fig. 8: including pre-training payroll prediction models; judging whether payroll requirements are filled in the resume text information, if so, directly storing the resume text information into a database, and if not, acquiring tag information and basic information of the resume from the database; and calculating the obtained label information and the predicted salary corresponding to the basic information based on the salary prediction model, and storing the obtained label information and the predicted salary into a database.
It should be noted that, when training the salary prediction model, the text analysis algorithm in the system may be utilized to analyze the resume into tag information, then the basic information (such as working city, age, etc.) of the resume stored in the database is added, and then the salary classification model is built by combining with the xgboost algorithm, and further, the algorithm model of salary prediction is built on the basis of the classification model by adopting the ridge regression algorithm. When calculating the obtained label information and the predicted salary corresponding to the basic information based on the salary prediction model, the information can be judged whether to be high salary/medium salary or not through a salary classification model, and then the corresponding salary prediction model is called to calculate the predicted salary.
In an alternative implementation, after a resume is recommended to a person, the candidate resume as recommended may face the following cases: selected or unselected resume or not recorded after interview, etc. In view of the above, the hunter consultant may manually consult the user unit and then upload the state information of the resume to the system, and further, the system may add new tag information to the corresponding resume text information based on the resume state information. For example, company a may interview candidate X and then not record, and the consultant may add the reason for not recording to the resume as a new tag for the resume. By enriching the label information of the resume, the probability of successful matching of the subsequent post is increased.
In the embodiment of the application, when a hunter thief logs in the system to perform related operation, the system firstly confirms whether the hunter thief is a value-added member, if so, the hunter thief directly accesses the system, and if not, only other functions of the website can be accessed.
And S103, performing matching calculation on the position labels and the basic information in the position text information and the resume text information, and matching the resume which is most in line with the current position.
It can be understood that the resume most conforming to the current position may be a TopN resume corresponding to a similar position with higher similarity to the current position after the matching calculation, that is, a candidate resume corresponding to a TopN position most similar to the current position, where N is a positive integer greater than or equal to 1.
In a specific implementation, a process of performing job resume matching by the device is shown in fig. 9, and the method comprises the following steps:
firstly, acquiring label information and basic information of positions in position text information and resume text information; and then eliminating the resume with non-conforming hard overrule items, such as non-conforming gender, non-conforming age, non-conforming academic background, non-conforming city and the like. Further, in the resume meeting the hard requirement, the position keyword matching score is calculated by combining the tag information, wherein the position keyword matching score comprises a skill keyword score 9BM25 score and a high-frequency keyword BM25 score, and preferably, at least 10% of keywords are required to be matched. Further, in the resume meeting the hardness requirement, other information weighted scores are calculated by combining the tag information and the basic information, wherein the scores comprise whether job function identifiers are consistent, whether working years are consistent, whether subdivision industries are consistent, whether salary ranges are included and the like. Further, summarizing the position keyword matching score and other information weighted scores, and calculating a final position and resume matching score, wherein the specific formula is as follows: score5 = score3 x score4, where score5 is the total score of the final job and resume match, score3 is the job keyword match score, and score4 is the other information weighted score. Further, the calculation results can be sorted from high to low and stored in a database.
In an alternative embodiment, the device may further calculate a similarity value between job labels in any two job text messages by combining a job similarity algorithm, as a similarity value between the two job text messages, further, may sort the similar job text messages according to the size of the similarity value, and select a candidate resume corresponding to the TopN job most similar to the current job as the resume to be recommended.
In one implementation, the device may perform job classification on the job in the job text information when performing job similarity calculation, and store the job classification in the database according to the secondary job classification identifier.
Further, after the secondary classification identification classification is stored, the system may perform vector dictionary pre-training. The specific training process is as follows: performing word segmentation on all position text information in the system, including position names, position descriptions and position requirements by using a jieba word segmentation device; and merging, de-duplicating and establishing a vector dictionary according to the word segmentation results. For example, two of the min/like/eat/ice cream/also/like/eat/hot pot, min/like/play/game create a vector dictionary [ min: 1, like: 2, eat: 3, ice cream: 4, also: 5, hot pot: 6, play: 7, game: 8], vector dictionary store in database.
Further, the system may calculate similarity between the job position and other job positions under the same secondary classification, and the flow is shown in fig. 10, and specifically includes: a) Performing job position classification processing on the job position to be calculated to obtain a secondary job position mark; b) Selecting all positions under the same secondary position mark in the result of the step a); c) And b) performing vectorization on the position word segmentation obtained in the step b) according to the pre-trained vector dictionary, and performing vectorization processing on the position to be calculated. The vectorization means that the word segmentation result is converted into a vector according to the number of times of word occurrence and the position of the word in a vector dictionary, for example, the result after vectorization of the min/like/eat/ice cream/also/like/eat/hot pot is [1,2,2,1,1,0,0,0]. d) And c) sequentially using cosine vectors to calculate the similarity of the positions obtained in the step a) and the positions to be calculated.
Further, the system can order the calculation of the similarity from high to low, and the result is stored in the database.
It should be noted that, in order to ensure timeliness of the information, the data processing and algorithm executing processes in this embodiment all use real-time calculation.
It should be noted that, if the device performs job similarity calculation in the process of performing job resume matching, the device may also perform result ranking based on a preset priority on the calculation result of the job similarity algorithm and the matching result of the job resume matching algorithm by using a recommendation ranking algorithm. The preset priority may be a result priority of the job resume matching algorithm, a candidate list priority obtained by the job similarity algorithm, or a ratio of the two. The recommended sorting algorithm can adopt implementation calculation or timing calculation, so that the timeliness of the algorithm and the elastic balance of research and development cost are achieved.
In the embodiment of the invention, the position and resume related information acquired by the system are analyzed by introducing an artificial intelligence algorithm, and the analyzed information is processed by combining the position similarity and resume matching algorithm, so that the most matched resume is recommended for the current position, wherein feedback information for candidate resume is also introduced before the person post is matched. By combining multiple artificial intelligence algorithms, the problem of slow pain points found by pure manual operation is solved, and the working efficiency of person post matching and the matching degree of final resume recommendation are improved.
Referring to fig. 11, a flowchart of person post matching recommendation in the present application is shown, wherein three-party data stored in a database in the present process is label information corresponding to job position, resume and candidate status information, and recruitment consultants are required to input data into the system and receive final recommendation results of the system as personnel operating the system. The candidate state information in the figure is input and is resume state information in the embodiment of the method.
It should be noted that, the specific implementation process of this embodiment may be referred to the detailed description in the above method embodiment, and will not be repeated here.
In the embodiment of the invention, the position and resume related information acquired by the system are analyzed by introducing an artificial intelligence algorithm, and the analyzed information is processed by combining the position similarity and resume matching algorithm, so that the most matched resume is recommended for the current position, wherein feedback information for candidate resume is also introduced before the person post is matched. By combining multiple artificial intelligence algorithms, the problem of slow pain points found by pure manual operation is solved, and the working efficiency of person post matching and the matching degree of final resume recommendation are improved.
The job resume matching device suitable for the person post matching recommendation system provided by the embodiment of the invention is described in detail below with reference to fig. 12. It should be noted that, the job resume matching device shown in fig. 12 and suitable for the person post matching recommendation system is used for executing the method of the embodiment shown in fig. 1 to 11 of the present invention, for convenience of explanation, only the portion relevant to the embodiment of the present invention is shown, and specific technical details are not disclosed, please refer to the embodiment shown in fig. 1 to 11 of the present invention.
Referring to fig. 12, a schematic structural diagram of a job resume matching device is provided in an embodiment of the present invention. As shown in fig. 12, the job resume matching apparatus 10 of the embodiment of the present invention may include: a text acquisition module 101, a text analysis module 102, a job resume matching module 103, a resume primary screening module 104 and a score ordering module 105. The job resume matching module 103 includes, as shown in fig. 13, an information acquisition unit 1031, a keyword score calculation unit 1032, an information weighted score calculation unit 1033, and a job resume matching unit 1034.
The text acquisition module 101 is configured to acquire position text information entered by a person unit and resume text information entered by a job applicant, where the position text information is related information for a job to be recruited, and the resume text information is a resume of the job applicant.
The text parsing module 102 is configured to perform text parsing on the job text information and the resume text information based on a text parsing algorithm, so as to obtain tag information.
The job resume matching module 103 is configured to perform matching calculation on job text information and job labels and basic information in the resume text information, where the basic information is job text information and other basic information except for the label information in the resume text information, and match a resume most corresponding to the current job.
The label information includes one or more of job function classification, high-frequency keywords, skill keywords, subdivision industry, salary prediction, job service life required by the job, and academic required by the job.
In an alternative embodiment, the job resume matching module 103 includes:
an information acquiring unit 1031 for acquiring tag information and basic information of a position in the position text information and resume text information.
The keyword score calculating unit 1032 is configured to calculate a keyword score in the target resume text information in combination with the tag information, where the target resume text information is a resume remaining after the preliminary screening of the resume text information.
An information weighted score calculating unit 1033 for calculating other information weighted scores in the target resume text information in combination with the tag information and the basic information.
And a job resume matching unit 1034 for calculating final job and resume matching scores in combination with the keyword scores and other information weighted scores.
Preferably, the resume initial screening module 104 is configured to perform preliminary screening on the resume text information based on the basic information to obtain the target resume text information meeting the hardness requirement.
The score ranking module 105 is used for ranking the calculated resume and job matching scores from high to low and storing the result in the database.
It should be noted that, in this embodiment, the execution process of each module and unit may be referred to the description in the above method embodiment, which is not repeated herein.
In the embodiment of the invention, the position and resume related information acquired by the system are analyzed by introducing an artificial intelligence algorithm, and the analyzed information is processed by combining the position similarity and resume matching algorithm, so that the most matched resume is recommended for the current position, wherein feedback information for candidate resume is also introduced before the person post is matched. By combining multiple artificial intelligence algorithms, the problem of slow pain points found by pure manual operation is solved, and the working efficiency of person post matching and the matching degree of final resume recommendation are improved.
The embodiment of the present invention further provides a computer storage medium, where the computer storage medium may store a plurality of instructions, where the instructions are adapted to be loaded by a processor and execute the method steps of the embodiment shown in fig. 1 to 11, and the specific execution process may refer to the specific description of the embodiment shown in fig. 1 to 11, which is not repeated herein.
The embodiment of the application also provides computer equipment. As shown in fig. 14, the computer device 20 may include: at least one processor 201, such as a CPU, at least one network interface 204, a user interface 203, memory 205, at least one communication bus 202, and optionally, a display 206. Wherein the communication bus 202 is used to enable connected communication between these components. The user interface 203 may include a touch screen, a keyboard or mouse, among others. The network interface 204 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), and a communication connection may be established with a server through the network interface 204. The memory 205 may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one disk memory, where the memory 205 includes a flash in an embodiment of the present invention. The memory 205 may also optionally be at least one storage system located remotely from the aforementioned processor 201. As shown in fig. 14, an operating system, a network communication module, a user interface module, and program instructions may be included in the memory 205, which is a type of computer storage medium.
It should be noted that, the network interface 204 may be connected to a receiver, a transmitter, or other communication modules, which may include, but are not limited to, a WiFi module, a bluetooth module, etc., and it is understood that in embodiments of the present invention, the computer device may also include a receiver, a transmitter, other communication modules, etc.
Processor 201 may be used to invoke program instructions stored in memory 205 and cause computer device 20 to:
acquiring position text information input by a person unit and resume text information input by a job applicant, wherein the position text information is related information aiming at a job to be recruited, and the resume text information is a resume of the job applicant;
text analysis is carried out on the position text information and the resume text information based on a text analysis algorithm, so that tag information is obtained;
and performing matching calculation on the position label and the basic information in the position text information and the resume text information, and matching the resume which is most in line with the current position, wherein the basic information is the position text information and other basic information except the label information in the resume text information.
In some embodiments, the tag information includes one or more of job function classification, high frequency keywords, skill keywords, subdivision industry, salary prediction, job desired working years, job desired academies.
In some embodiments, the device 20 is specifically configured to, when performing a matching calculation on the position tag and the basic information in the position text information and the resume text information, match the resume that best matches the current position:
acquiring label information and basic information of positions in the position text information and the resume text information;
calculating keyword scores in target resume text information by combining the label information, wherein the target resume text information is the resume remained after preliminary screening of the resume text information;
calculating other information weighted scores in the target resume text information by combining the tag information and the basic information;
and calculating a final position and resume matching score by combining the keyword score and the other information weighted score.
In some embodiments, the device 20 is further configured to perform a preliminary screening on the resume text information based on the basic information to obtain the target resume text information meeting the hardness requirement.
In some embodiments, the device 20 is further configured to rank the calculated resume and job matching scores from high to low and store in the database.
In the embodiment of the invention, the position and resume related information acquired by the system are analyzed by introducing an artificial intelligence algorithm, and then the analyzed information is processed by combining a job similarity and resume matching algorithm, so that the most matched resume is recommended for the current position, wherein feedback information for candidate resume is also introduced before the person post is matched. By combining multiple artificial intelligence algorithms, the problem of slow pain points found by pure manual operation difference is solved, and the working efficiency of person post matching and the matching degree of final recommended resume are improved.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in the embodiments may be accomplished by computer programs stored in a computer-readable storage medium, which when executed, may include the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), or the like.
The foregoing disclosure is illustrative of the present invention and is not to be construed as limiting the scope of the invention, which is defined by the appended claims.
Claims (8)
1. The job resume matching method suitable for the person post matching recommendation system is characterized by comprising the following steps of:
acquiring position text information input by a person unit and resume text information input by a job seeker, wherein the position text information is related information aiming at a job to be recruited, and the resume text information is a resume of the job seeker;
text analysis is carried out on the job position text information and the resume text information based on a text analysis algorithm, so that tag information is obtained;
performing matching calculation on position labels and basic information in the position text information and the resume text information, and matching the resume which is most in line with the current position, wherein the basic information is information except the label information in the position text information and the resume text information; the label information comprises job position classification, high-frequency keywords, skill keywords, subdivision industry, salary prediction, job position required working years and job position required academic;
the label information comprises job function classification, the text analysis algorithm is based on text analysis of the job text information and the resume text information to obtain label information, and the label information comprises:
pre-training a job position and job position classification model; acquiring position name information in position text information and resume text information; the acquired job name information is put into the job classification model for matching, and a classification result is output; the method comprises the steps of utilizing position text information resources in a system in the process of training a classification model, combining a TFIDF algorithm, low-frequency word filtering, bi-gram mutual information calculation and manual integration to arrange a 3-layer position classification system, wherein the 3-layer position classification system comprises 52 classification identifications of 1 level, 800 classification identifications of 2 level and 4000 classification identifications of 3 level; then, a tier tree corresponding to the tier 2 of the tier 3 is established by utilizing the sorted classification marks, and then the established relation is stored in a tier tree structure;
the tag information comprises a high-frequency keyword, the text analysis is carried out on the job position text information and the resume text information based on a text analysis algorithm to obtain the tag information, and the tag information comprises:
respectively acquiring position descriptions and position requirements in position text information, acquiring working experience and project experience in resume text information, and performing word segmentation on the acquired information; then comprehensively judging the key degree of the single word by word frequency, part of speech and semantic relativity of the word segmentation result; finally, the score of each word is sorted from high to low and then stored in a database; wherein the score for each word reflects the criticality of the word;
performing matching calculation on the job position text information and the job position label and the basic information in the resume text information to match the resume which is most in line with the current job position, wherein the matching comprises the following steps:
acquiring label information and basic information of positions in the position text information and the resume text information; then eliminating the resume which is not in accordance with the hard overrule item, wherein the resume comprises gender incongruity, age incongruity, academic background incongruity and city incongruity; in the resume meeting the hard requirement, calculating position keyword matching scores comprising skill keyword scores 9BM25 scores and high-frequency keyword BM25 scores by combining label information; in the resume meeting the hardness requirement, combining the tag information and the basic information, and calculating the weighting score of other information; the other information comprises whether job function marks are consistent, whether working years are consistent, whether subdivision industries are consistent and whether salary ranges are included; summarizing the position keyword matching scores and other information weighted scores, calculating final position and resume matching scores, sequencing the calculation results from high to low, and storing the calculation results in a database;
the specific formula for calculating the final position and resume matching score is as follows:
score5＝score3*score4
score5 is the total score of the final position and resume matches, score3 is the position keyword match score, and score4 is the other information weighted score.
2. The method according to claim 1, wherein the matching calculation is performed on the job label and the basic information in the job text information and the resume text information, and the matching of the resume most conforming to the current job comprises:
acquiring label information and basic information of positions in the position text information and the resume text information;
calculating keyword scores in target resume text information in combination with the tag information, wherein the target resume text information is the resume remained after the preliminary screening of the resume text information;
calculating other information weighted scores in the target resume text information by combining the tag information and the basic information;
and calculating a final position and resume matching score by combining the keyword score and the other information weighted score.
3. The method according to claim 2, wherein the method further comprises:
and performing preliminary screening on the resume text information based on the basic information to obtain target resume text information meeting the hardness requirement.
4. The method according to claim 1, wherein the method further comprises:
and sorting the calculated resume and job matching scores from high to low, and storing the result in a database.
5. The utility model provides a job resume matching device suitable for people's post matches recommendation system which characterized in that includes:
the text acquisition module is used for acquiring position text information input by a personnel unit and resume text information input by a job seeker, wherein the position text information is related information aiming at a job to be recruited, and the resume text information is a resume of the job seeker;
the text analysis module is used for carrying out text analysis on the job position text information and the resume text information based on a text analysis algorithm to obtain tag information;
the job resume matching module is used for carrying out matching calculation on the job text information, job labels in the resume text information and basic information, and matching the resume which is most in line with the current job, wherein the basic information is information except the label information in the job text information and the resume text information; the label information comprises job position classification, high-frequency keywords, skill keywords, subdivision industry, salary prediction, job position required working years and job position required academic;
the label information comprises job function classification, the text analysis algorithm is based on text analysis of the job text information and the resume text information to obtain label information, and the label information comprises:
pre-training a job position and job position classification model; acquiring position name information in position text information and resume text information; the acquired job name information is put into the job classification model for matching, and a classification result is output; the method comprises the steps of utilizing position text information resources in a system in the process of training a classification model, combining a TFIDF algorithm, low-frequency word filtering, bi-gram mutual information calculation and manual integration to arrange a 3-layer position classification system, wherein the 3-layer position classification system comprises 52 classification identifications of 1 level, 800 classification identifications of 2 level and 4000 classification identifications of 3 level; then, a tier tree corresponding to the tier 2 of the tier 3 is established by utilizing the sorted classification marks, and then the established relation is stored in a tier tree structure;
the tag information comprises a high-frequency keyword, the text analysis is carried out on the job position text information and the resume text information based on a text analysis algorithm to obtain the tag information, and the tag information comprises:
respectively acquiring position descriptions and position requirements in position text information, acquiring working experience and project experience in resume text information, and performing word segmentation on the acquired information; then comprehensively judging the key degree of the single word by word frequency, part of speech and semantic relativity of the word segmentation result; finally, the score of each word is sorted from high to low and then stored in a database; wherein the score for each word reflects the criticality of the word;
performing matching calculation on the job position text information and the job position label and the basic information in the resume text information to match the resume which is most in line with the current job position, wherein the matching comprises the following steps:
acquiring label information and basic information of positions in the position text information and the resume text information; then eliminating the resume which is not in accordance with the hard overrule item, wherein the resume comprises gender incongruity, age incongruity, academic background incongruity and city incongruity; in the resume meeting the hard requirement, calculating position keyword matching scores comprising skill keyword scores 9BM25 scores and high-frequency keyword BM25 scores by combining label information; in the resume meeting the hardness requirement, combining the tag information and the basic information, calculating other information weighted scores, wherein the other information comprises whether job function marks are consistent, whether working years are consistent, whether subdivision industries are consistent and whether salary ranges are included; summarizing the position keyword matching scores and other information weighted scores, calculating final position and resume matching scores, sequencing the calculation results from high to low, and storing the calculation results in a database;
the specific formula for calculating the final position and resume matching score is as follows:
score5＝score3*score4
score5 is the total score of the final position and resume matches, score3 is the position keyword match score, and score4 is the other information weighted score.
6. The apparatus of claim 5, wherein the job resume matching module comprises:
the information acquisition unit is used for acquiring label information and basic information of positions in the position text information and the resume text information;
the keyword score calculation unit is used for calculating keyword scores in target resume text information in combination with the tag information, wherein the target resume text information is a resume remained after the preliminary screening of the resume text information;
an information weighted score calculating unit for calculating other information weighted scores in the target resume text information by combining the tag information and the basic information;
and the position resume matching unit is used for calculating a final position and resume matching score by combining the keyword score and the other information weighted score.
7. The apparatus of claim 6, wherein the apparatus further comprises:
and the resume initial screening module is used for primarily screening the resume text information based on the basic information to obtain target resume text information meeting the hardness requirement.
8. A computer readable storage medium having stored therein at least one instruction, at least one program, code set, or instruction set loaded and executed by a processor to implement the position resume matching method of any of claims 1-4 for use with a person post matching recommendation system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911304875.XA CN111105209B (en) | 2019-12-17 | 2019-12-17 | Job resume matching method and device suitable for person post matching recommendation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911304875.XA CN111105209B (en) | 2019-12-17 | 2019-12-17 | Job resume matching method and device suitable for person post matching recommendation system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111105209A CN111105209A (en) | 2020-05-05 |
| CN111105209B true CN111105209B (en) | 2023-07-21 |
Family
ID=70421993
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911304875.XA Active CN111105209B (en) | 2019-12-17 | 2019-12-17 | Job resume matching method and device suitable for person post matching recommendation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111105209B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113722368B (en) * | 2020-05-22 | 2024-04-30 | 百度在线网络技术（北京）有限公司 | Data processing method, device, equipment and storage medium |
| CN111708929B (en) * | 2020-06-17 | 2023-05-30 | 北京字节跳动网络技术有限公司 | Information searching method, device, electronic equipment and storage medium |
| CN111967858A (en) * | 2020-08-29 | 2020-11-20 | 深圳呗佬智能有限公司 | Talent intelligent recommendation method and system, computer equipment and storage medium |
| CN113298495A (en) * | 2021-05-27 | 2021-08-24 | 中国科学院深圳先进技术研究院 | Resume screening method, resume screening device, terminal device and storage medium |
| CN113673943B (en) * | 2021-07-19 | 2023-02-10 | 清华大学深圳国际研究生院 | Personnel exemption aided decision making method and system based on historical big data |
| CN113822655A (en) * | 2021-10-23 | 2021-12-21 | 山东云享天空科技服务有限公司 | Recruitment requirement and personal information matching system for human resources |
| CN115526589B (en) * | 2022-09-16 | 2023-06-06 | 山东人才发展集团信息技术有限公司 | Employment information processing method and equipment for crowd to be employment |
| CN116628340B (en) * | 2023-06-15 | 2024-01-02 | 中科聚信信息技术（北京）有限公司 | Position agent recommending method and system |
| CN116596496A (en) * | 2023-07-18 | 2023-08-15 | 金现代信息产业股份有限公司 | Person post matching method, system, medium and equipment based on labeling |
| CN117094691B (en) * | 2023-10-16 | 2024-02-02 | 四川省瑞人网络科技有限公司 | Human resource management method based on big data platform |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107729532A (en) * | 2017-10-30 | 2018-02-23 | 北京拉勾科技有限公司 | A kind of resume matching process and computing device |
| 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 |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105159962B (en) * | 2015-08-21 | 2018-08-17 | 北京全聘致远科技有限公司 | Position recommends method and apparatus, resume to recommend method and apparatus, recruitment platform |
| CN105677902A (en) * | 2016-02-05 | 2016-06-15 | 北京普猎创新网络科技有限公司 | Resume display method |
| CN106447285B (en) * | 2016-09-12 | 2020-06-12 | 北京大学 | Recruitment information matching method based on multi-dimensional domain key knowledge |
| CN108874928B (en) * | 2018-05-31 | 2024-02-02 | 平安科技（深圳）有限公司 | Resume data information analysis processing method, device, equipment and storage medium |
| CN109345201A (en) * | 2018-09-20 | 2019-02-15 | 成都辰语轩科技有限公司 | Human Resources Management Method, device, electronic equipment and storage medium |
| CN109492164A (en) * | 2018-11-26 | 2019-03-19 | 北京网聘咨询有限公司 | A kind of recommended method of resume, device, electronic equipment and storage medium |
| CN109754233B (en) * | 2019-01-29 | 2024-05-07 | 上海嘉道信息技术有限公司 | Method and system for intelligently recommending position information |
| CN110032637A (en) * | 2019-04-16 | 2019-07-19 | 上海大易云计算股份有限公司 | A kind of resume intelligent recommendation algorithm based on natural semantic analysis technology |
| CN110019689A (en) * | 2019-04-17 | 2019-07-16 | 北京网聘咨询有限公司 | Position matching process and position matching system |
-
2019
- 2019-12-17 CN CN201911304875.XA patent/CN111105209B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107729532A (en) * | 2017-10-30 | 2018-02-23 | 北京拉勾科技有限公司 | A kind of resume matching process and computing device |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| 中文简历自动解析及推荐算法;谷楠楠;冯筠;孙霞;赵妍;张蕾;;计算机工程与应用(第18期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111105209A (en) | 2020-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111105209B (en) | Job resume matching method and device suitable for person post matching recommendation system | |
| CN111125343B (en) | Text analysis method and device suitable for person post matching recommendation system | |
| CN111144723A (en) | Method and system for recommending people's job matching and storage medium | |
| CN106649818B (en) | Application search intention identification method and device, application search method and server | |
| US20230195773A1 (en) | Text classification method, apparatus and computer-readable storage medium | |
| CN111767716B (en) | Method and device for determining enterprise multi-level industry information and computer equipment | |
| CN104933152B (en) | Name entity recognition method and device | |
| WO2017097231A1 (en) | Topic processing method and device | |
| CN111078971A (en) | Resume file screening method and device, terminal and storage medium | |
| CN111104526A (en) | Financial label extraction method and system based on keyword semantics | |
| KR20200007969A (en) | Information processing methods, terminals, and computer storage media | |
| CN112035599B (en) | Query method and device based on vertical search, computer equipment and storage medium | |
| CN106708929B (en) | Video program searching method and device | |
| JP6056610B2 (en) | Text information processing apparatus, text information processing method, and text information processing program | |
| US12008047B2 (en) | Providing an object-based response to a natural language query | |
| CN112579729B (en) | Training method and device for document quality evaluation model, electronic equipment and medium | |
| CN111078837A (en) | Intelligent question and answer information processing method, electronic equipment and computer readable storage medium | |
| US11537918B2 (en) | Systems and methods for document similarity matching | |
| CN110310012B (en) | Data analysis method, device, equipment and computer readable storage medium | |
| CN106570196B (en) | Video program searching method and device | |
| CN113609847B (en) | Information extraction method, device, electronic equipment and storage medium | |
| CN114281972A (en) | Dialog control method, system storage medium and server based on subject object tracking and cognitive inference | |
| CN109344400A (en) | A kind of judgment method and device of document storage | |
| CN113515699A (en) | Information recommendation method and device, computer-readable storage medium and processor | |
| CN112527985A (en) | Unknown problem processing method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |