CN111078971A - Resume file screening method and device, terminal and storage medium - Google Patents
Resume file screening method and device, terminal and storage medium Download PDFInfo
- Publication number
- CN111078971A CN111078971A CN201911137207.2A CN201911137207A CN111078971A CN 111078971 A CN111078971 A CN 111078971A CN 201911137207 A CN201911137207 A CN 201911137207A CN 111078971 A CN111078971 A CN 111078971A
- Authority
- CN
- China
- Prior art keywords
- resume
- information
- resume file
- file
- matching degree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/907—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Computational Linguistics (AREA)
- Library & Information Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of similarity matching, and provides a resume file screening method, a resume file screening device, a resume file screening terminal and a resume file storage medium. The screening method of the resume file comprises the following steps: acquiring a resume file to be matched from a resume library; extracting characteristic information of each information item from each resume file, and inputting the characteristic information and description information related to the recruitment release information into a pre-trained matching model for matching degree identification to determine the matching degree between any information item in each resume file and the description information; and calculating the score value corresponding to the resume file according to the matching degree and the weight value corresponding to each information item, comparing the score value of each resume file with a set threshold value respectively, and taking the resume file with the score value larger than the threshold value as a target resume file. According to the method, the importance degree of each information item in the resume file is fully considered, and the target resume file meeting the recruitment requirement is screened out, so that the matching accuracy is improved.
Description
Technical Field
The invention relates to the technical field of similarity matching, in particular to a method, a device, a terminal and a storage medium for screening resume files.
Background
With the development of the network, most job seekers deliver resume files through the network, and one resume file can be easily delivered to a plurality of recruiters, so that a recruiter often receives a large amount of resumes; when a large number of resume documents are faced, the efficiency of manual screening is undoubtedly very low, so that currently, computer technology is utilized, and the required resume documents are screened out by intelligently matching resume and recruitment information received through artificial intelligence analysis.
At present, when the resume files are screened, the resume files and the recruitment release information are generally adopted for matching, generally, keywords of the resume files are extracted, and then target resume files are matched according to preset screening conditions and the keywords.
Disclosure of Invention
The invention provides a method, a device, a terminal and a storage medium for screening resume files, which aim to solve the problem that the matching accuracy is low due to the fact that key words cannot reflect important differences among microscopic information on the resume files by adopting a matching method of the key words at present.
In order to solve the problems, the invention adopts the following technical scheme:
the invention provides a method for screening resume files, which comprises the following steps:
acquiring a resume file to be matched from a resume library;
extracting characteristic information of each information item from each resume file, and inputting the characteristic information and description information related to the recruitment release information into a pre-trained matching model for matching degree identification;
respectively determining the matching degree between any information item in each resume file and the description information according to the output result of the matching model;
and calculating the score value corresponding to the resume file according to the matching degree and the weight value corresponding to each information item, comparing the score value of each resume file with a set threshold value respectively, and taking the resume file with the score value larger than the threshold value as a target resume file.
In an embodiment, before calculating the score value corresponding to the resume file according to the matching degree and the weight value corresponding to each information item, the method further includes:
calculating the correlation between the characteristic information of each information item in the resume file and the description information;
determining a weight value corresponding to each information item according to the correlation; wherein the weight value is proportional to the degree of correlation.
In an embodiment, the step of calculating the correlation between the feature information of each information item in the resume file and the description information includes:
constructing a relevant semantic knowledge base;
determining the collocation frequency of keywords between the characteristic information and the description information by utilizing the relevant semantic knowledge base;
and calculating the correlation between the characteristic information and the description information according to the collocation frequency.
In an embodiment, the feature information includes first structured data and first unstructured data, the description information includes second structured data and second unstructured data, and the step of inputting the description information related to the feature information and the recruitment information into a pre-trained matching model for matching degree recognition includes:
completely matching the first structural data of the characteristic information of the resume file with the second structural data of the description information to obtain a completely matched first resume file; the first structured data and the second structured data are necessary conditions for screening the resume file;
carrying out matching degree identification on first unstructured data of the first resume file and second unstructured data in the description information by using a pre-trained matching model to obtain the matching degree between the information item of the first resume file and the description information; the first unstructured data and the second unstructured data are non-essential conditions for screening the resume file.
In an embodiment, the step of performing matching degree identification on the first unstructured data of the first resume file and the second unstructured data in the description information by using a pre-trained matching model to obtain the matching degree between the information item of the first resume file and the description information includes:
respectively extracting a first feature corresponding to the first unstructured data and a second feature corresponding to the second unstructured data by using a pre-trained matching model;
performing feature vectorization processing on the first feature and the second feature to obtain a first feature vector and a second feature vector;
calculating the cosine distance between the first characteristic vector and the second characteristic vector;
and determining the matching degree between the information item of the first resume file and the description information according to the cosine distance.
In an embodiment, the information item includes an item experience item, and the step of extracting a first feature vector corresponding to the first unstructured data includes:
extracting first unstructured data of the project experience item;
and carrying out vectorization processing on the first unstructured data of the project experience item by using a word vector database to obtain a first feature vector.
In an embodiment, the step of calculating the score value corresponding to the resume file according to the matching degree and the weight value corresponding to each information item includes:
calculating the sub-grade value of each information item in the resume file according to the matching degree and the weight value corresponding to each information item;
and accumulating the sub-credit values of all the information items in the resume file to obtain the credit value of the resume file.
In one embodiment, the information items include item experience items, and after the resume file with the score value larger than the threshold value is taken as the target resume file, the method further includes:
taking the resume file with the score value smaller than the threshold value as a candidate resume file;
acquiring sub-scoring values of the project experience items in the candidate resume file;
and when the number of the target resume files is lower than the preset number, taking the candidate resume files with the sub-grade values of the project experience items larger than the preset value as the target resume files.
The invention provides a screening device for resume files, which comprises:
the acquisition module is used for acquiring resume files to be matched from the resume library;
the recognition module is used for extracting the characteristic information of each information item from each resume file and respectively inputting the characteristic information and the description information related to the recruitment release information into a pre-trained matching model for matching degree recognition;
the determining module is used for respectively determining the matching degree between any information item in each resume file and the description information according to the output result of the matching model;
and the calculating module is used for calculating the score values corresponding to the resume files according to the matching degrees and the weight values corresponding to the information items, comparing the score values of the resume files with a set threshold value respectively, and taking the resume files with the score values larger than the threshold value as target resume files.
The invention provides a terminal, which comprises a memory and a processor, wherein the memory is stored with computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the resume file screening method.
The present invention provides a storage medium having stored thereon a computer program which, when executed by a processor, implements the method of filtering resume files as described in any one of the above.
Compared with the prior art, the technical scheme of the invention at least has the following advantages:
the method, the device, the terminal and the storage medium for screening the resume files provided by the invention firstly obtain the resume files to be matched from the resume library; extracting characteristic information of each information item from each resume file, and inputting the characteristic information and description information related to the recruitment release information into a pre-trained matching model for matching degree identification; then, respectively determining the matching degree between any information item in each resume file and the description information according to the output result of the matching model; and calculating the score value corresponding to the resume file according to the matching degree and the weight value corresponding to each information item, comparing the score value of each resume file with a set threshold value respectively, and taking the resume file with the score value larger than the threshold value as a target resume file. According to the method, the matching degree of the characteristic information of each information item in the resume file and the description information related to the recruitment release information is identified, the score value corresponding to the resume file is calculated according to the matching degree and the weight value corresponding to each information item, so that the importance degree of each information item is considered, the target resume file meeting the recruitment requirement is screened out, and the matching accuracy is improved.
Drawings
Fig. 1 is an implementation environment diagram of a method for screening resume files according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating an embodiment of a method for screening resume files according to the present invention;
FIG. 3 is a block diagram of an embodiment of a resume file screening apparatus according to the present invention;
fig. 4 is a block diagram of the internal structure of the terminal in one embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention.
In some of the flows described in the present specification and claims and in the above-described figures, a number of operations are included that occur in a particular order, but it should be clearly understood that these operations may be performed out of order or in parallel as they occur herein, with the order of the operations being numbered, e.g., S11, S12, etc., merely to distinguish between various operations, and the order of the operations by themselves is not meant to imply any order of execution. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first", "second", etc. in this document are used for distinguishing different messages, devices, modules, etc., and do not represent a sequential order, nor limit the types of "first" and "second" to be different.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
It will be understood by those of ordinary skill in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a diagram of an implementation environment of a method for filtering resume files provided in an embodiment, as shown in fig. 1, in the implementation environment, including a server 110 and a terminal 120. The terminal 120 is connected with the server through a network, a client or a browser is installed on the terminal 120, a user can upload resume files to the server 110 through the client or the browser, and the server 110 screens out target resume files meeting the recruitment requirement from the uploaded resume files according to the recruitment release information. The network may include the internet, 2G/3G/4G, wifi, etc.
The server 110 may be an independent physical server or terminal, may be a server cluster composed of a plurality of physical servers, and may be a cloud server providing basic cloud computing services such as a cloud server, a cloud database, a cloud storage, and a CDN.
The terminal 120 may be, but is not limited to, a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and the like.
Referring to fig. 2, the method for screening resume files provided by the present invention is provided to solve the problem that the matching accuracy is not high due to the fact that the keyword cannot reflect the importance difference between the microscopic information for the resume files in the current matching method using the keyword. In one embodiment, the method for screening the resume file comprises the following steps:
and S21, acquiring the resume file to be matched from the resume library.
In this step, the server may collect resume information for job hunting received by each of the recruitment channels, and collate the resume information for job hunting into a document set, thereby obtaining resume files, and store the resume files in the resume repository. The resume file can include information such as talent basic information, a study calendar, a work experience (including work time, a post name, a project experience, work content and the like), expected salaries, expected work places and the like.
And S22, extracting the feature information of each information item from each resume file, and inputting the feature information and the description information related to the recruitment and release information into a pre-trained matching model for matching degree recognition.
In the step, each resume file can be divided into a plurality of information items, then the characteristic information of each information item is extracted, and the characteristic information and the description information related to the recruitment release information are input into a pre-trained matching model for matching degree recognition to obtain the matching degree of each characteristic information and the description information. When the matching degree is calculated, each matched feature information in the resume file can be labeled, and the matching degree is determined according to the labeled number of the feature information.
The information items may include a personal profile item, a work experience item, a learning experience item, a personal preference item, and the like, and each information item includes characteristic information describing the information item, such as sex, age, and the like in the personal profile item, and school, achievement, and the like in the learning experience item. The description information can include the requirement of the recruitment position on the academic calendar, the related professional requirement and the requirement of the talent skill, the salary and welfare of the position, the work content and the like.
And S23, respectively determining the matching degree between any information item in each resume file and the description information according to the output result of the matching model.
In an embodiment, after the server obtains the matching degree between each feature information and the description information, the average value of all the matching degrees is used as the matching degree between any information item in each resume file and the description information, and the subsequent processing steps only process the resume files with higher matching degree, so as to improve the processing efficiency. For example, when an IT research and development engineer engaged in a high-end medical industry needs to be recruited, but a salesman engaged in a common medical industry is described in the resume file, the matching degree of the resume file and the post requirement is low, and the resume file can be directly ignored.
For another example, when a research and development engineer engaged in the education industry needs to be recruited and has online education project experience, and the resume document describes the research and development engineer engaged in the education industry and has live broadcast project development experience, the matching degree obtained by calculation is relatively higher, and the resume document is subjected to subsequent processing.
S24, calculating the score value corresponding to the resume file according to the matching degree and the weight value corresponding to each information item, comparing the score value of each resume file with a set threshold value respectively, and taking the resume file with the score value larger than the threshold value as a target resume file.
Calculating the score value corresponding to the resume file by using the weight value and the matching degree corresponding to each information item, wherein the weight value of each information item can be set according to the emphasis point of the recruiter. Specifically, when the resume file has two information items, one of the information items has a weight value of 10 and a matching degree of 0.8, and the other information item has a weight value of 5 and a matching degree of 0.6, the value of the score corresponding to the resume file is 10 × 0.8+5 × 0.6 — 11.
And after calculating the score value of each resume file, comparing the score value of each resume file with a set threshold value respectively, and taking the resume file with the score value larger than the threshold value as a target resume file. And if the resume documents with the score values larger than 80 are screened out, obtaining the resume documents which are matched with the positions better.
For example, when a company needs to recruit a worker, it is usually necessary to acquire an application resume file of the application member from a recruitment website, a recruitment system or a recruitment mailbox of the company, take the application resume file of the application member as a resume file to be matched, judging whether the applicant is qualified for the current recruitment position or not by extracting and analyzing the characteristic information of each information item on the resume of the file to be matched, if the matching degree of the feature information of each information item and the description information related to the recruitment release information is identified through a matching model, the matching degree between any information item in each resume file and the description information is obtained, and calculating the score value of each resume file according to the matching degree and the weight value corresponding to each information item, and sorting the resume files according to the scoring values, and screening out the target resume files with the top ranking, thereby obtaining the resume files matched with the positions.
The method for screening the resume files comprises the steps of firstly obtaining the resume files to be matched from a resume library; extracting characteristic information of each information item from each resume file, and inputting the characteristic information and description information related to the recruitment release information into a pre-trained matching model for matching degree identification; then, respectively determining the matching degree between any information item in each resume file and the description information according to the output result of the matching model; and calculating the score value corresponding to the resume file according to the matching degree and the weight value corresponding to each information item, comparing the score value of each resume file with a set threshold value respectively, and taking the resume file with the score value larger than the threshold value as a target resume file. According to the method, the matching degree of the characteristic information of each information item in the resume file and the description information related to the recruitment release information is identified, the score value corresponding to the resume file is calculated according to the matching degree and the weight value corresponding to each information item, so that the importance degree of each information item is considered, the target resume file meeting the recruitment requirement is screened out, and the matching accuracy is improved.
In an embodiment, before calculating the score value corresponding to the resume file according to the matching degree and the weight value corresponding to each information item, the method may further include:
calculating the correlation between the characteristic information of each information item in the resume file and the description information;
determining a weight value corresponding to each information item according to the correlation; wherein the weight value is proportional to the degree of correlation.
In this embodiment, a basic weight value may be set for each information item in advance, and then, when matching subsequently, in addition to considering the basic weight value of each information item, a relationship between feature information and description information is further fused, a degree of correlation between the feature information and the description information of each information item in the resume file is calculated, and the weight value of each information item is automatically adjusted according to the degree of correlation between the feature information and the description information, for example, when the feature information and the description information of the first resume file are "university" and "automation specialty", respectively, and the feature information and the description information of the second resume are "gender" and "automation specialty", respectively, since the degree of correlation of "university" and "automation specialty" is higher than the degree of correlation of "gender" and "automation specialty", the weight value corresponding to the first resume file is increased; and the weight value of the second resume is reduced or kept unchanged, so that the current characteristic information is fully utilized, and a more appropriate resume file is recommended to the recruiter.
In an embodiment, the step of calculating the correlation between the feature information of each information item in the resume file and the description information may specifically include:
constructing a relevant semantic knowledge base;
determining the collocation frequency of keywords between the characteristic information and the description information by utilizing the relevant semantic knowledge base;
and calculating the correlation between the characteristic information and the description information according to the collocation frequency.
In the embodiment, based on the constructed related semantic knowledge base, semantic knowledge described in the dictionary is fully mined and represented, a knowledge acquisition method is constructed by fully utilizing the canonical paraphrase mode of the dictionary, and the knowledge base containing rich semantics is flexibly and quickly constructed from the dictionary. The related semantic knowledge base can comprise relational knowledge such as superior-inferior relation, synonymy relation, near-synonymy relation and antisense relation among the words, and can also comprise attribute knowledge such as epoch attribute, revising attribute and language attribute and example sentence word collocation knowledge.
The implementation can use the matching frequency as the correlation between the feature information of each information item in the resume file and the description information by respectively extracting all keywords between the feature information and the description information, determining which keywords are frequently matched by using the relevant semantic knowledge base, and calculating the matching frequency of the keywords. The matching frequency of the keywords can be determined according to the historical matching times of the keywords, and the more the historical matching times recorded in the searchable text are, the higher the matching frequency of the keywords is.
For example, when the keywords in the resume document include "work" and the recruitment release information includes the keywords "experience", "gender" and "university", the matching frequency of "work" and "experience" is higher than that of "gender" and "university" according to the semantic relationship between the keywords. When the feature information contains more keywords with higher collocation frequency with the description information, the calculated correlation degree is higher.
In an embodiment, the feature information includes first structured data and first unstructured data, the description information includes second structured data and second unstructured data, and the step of inputting the description information related to the feature information and the recruitment information into a pre-trained matching model for matching degree recognition may specifically include:
completely matching the first structural data of the characteristic information of the resume file with the second structural data of the description information to obtain a completely matched first resume file; the first structured data and the second structured data are necessary conditions for screening the resume file;
carrying out matching degree identification on first unstructured data of the first resume file and second unstructured data in the description information by using a pre-trained matching model to obtain the matching degree between the information item of the first resume file and the description information; the first unstructured data and the second unstructured data are non-essential conditions for screening the resume file.
In this embodiment, all resume files are preliminarily screened to filter the apparently unmatched resume files, so as to obtain the first resume file which is relatively matched. The first structured data is a hard condition in the post requirement, for example, when the requirement of the recruiting post on the gender must be a male, the resume files of the female are filtered out, and the first resume files of which all the genders are males are obtained, so that the workload of performing deep analysis on the first resume files in the follow-up process is reduced. Specifically, the embodiment first divides the feature information of the resume file into first structured data and first unstructured data by dividing the feature information of the resume file and description information related to the recruitment release information; and dividing the description information related to the recruitment release information into second structured data and second unstructured data. And then, completely matching the first structured data with the second structured data to preliminarily screen the resume files to obtain a first resume, and subsequently further matching the first resume file.
And during subsequent matching, performing matching analysis on the semantics of each first unstructured data of the first resume file and the semantics of second unstructured data in the description information by using an LSTM model to obtain the matching degree of each first unstructured data and each second unstructured data in the first resume file, and taking the matching degree as the matching degree of each characteristic information and the description information.
The structured data are necessary conditions for screening resume documents, such as sex, position name, work place, recruiter number, salary, academic requirement, professional requirement and age requirement, and account for about 20% -30% of the whole recruitment release information. The unstructured data are optional conditions which can be flexibly selected, and mainly comprise position description (comprising position responsibility and position requirements), work experience, learning experience and welfare treatment, and account for 70% -80% of the whole recruitment release information.
In an embodiment, the step of performing matching degree identification on the first unstructured data of the first resume file and the second unstructured data in the description information by using a pre-trained matching model to obtain the matching degree between the information item of the first resume file and the description information may specifically include:
respectively extracting a first feature corresponding to the first unstructured data and a second feature corresponding to the second unstructured data by using a pre-trained matching model;
performing feature vectorization processing on the first feature and the second feature to obtain a first feature vector and a second feature vector;
calculating the cosine distance between the first characteristic vector and the second characteristic vector;
and determining the matching degree between the information item of the first resume file and the description information according to the cosine distance.
In this embodiment, when matching the first unstructured data of the resume file with the second unstructured data in the description information, first a first feature corresponding to the first unstructured data of the resume file and a second feature corresponding to the second unstructured data of the resume file may be obtained, and the first feature and the second feature are converted into a first feature vector and a second feature vector respectively by using a feature vectorization processing method; and then, distance measurement is carried out on the first feature vector and the second feature vector, and the cosine distance between the first feature vector and the second feature vector is calculated, so that the matching degree of the first unstructured data of the resume and the second unstructured data in the position information is determined according to the cosine distance, and when the distance between the first unstructured data and the second unstructured data is shorter, the corresponding matching degree is higher. The first feature and the second feature may be text features, and in this case, the feature vectorization processing method is a text feature vectorization method.
In an embodiment, the information item includes an item experience item, and the step of extracting a first feature vector corresponding to the first unstructured data may specifically include:
extracting first unstructured data of the project experience item;
and carrying out vectorization processing on the first unstructured data of the project experience item by using a word vector database to obtain a first feature vector.
Taking professional vectorization as an example, vectorization of the "professional requirement" in the recruitment release information can be performed according to the field content corresponding to the "professional requirement" in the recruitment release information, such as: the automation, economics, computer and the like calculate the word vector corresponding to the field in the matching model as the vectorized result; for example: the 'professional requirement' of a certain recruitment release information is as follows: and the term "computer" is searched in the word vector database, and the n-dimensional vector corresponding to the "computer" is obtained as the vectorization result of the "professional requirement" here. If the professional requirement is as follows: and (3) searching three words of automation, economics and computer and corresponding word vectors in the word vector database by using the automation, economics and computer, wherein the three word vectors are used as vectorization results of professional requirements.
In an embodiment, the step of calculating the score value corresponding to the resume file according to the matching degree and the weight value corresponding to each information item includes:
calculating the sub-grade value of each information item in the resume file according to the matching degree and the weight value corresponding to each information item;
and accumulating the sub-credit values of all the information items in the resume file to obtain the credit value of the resume file.
In this embodiment, the feature information of the resume file and the related description information of the recruitment release information can be subjected to word segmentation to obtain a plurality of position description words and a plurality of resume words, and the feature information of the resume file is represented by the resume words. And then matching the position description words with the resume words to obtain the matching degree of the resume words, wherein the matching degree of the computer specialty and the software specialty is higher than that of the computer specialty and the accounting specialty. Then, a weight value corresponding to each resume description term is inquired according to a preset list, namely different resume description terms have different importance, for example, the resume description terms include: the employment positions may have different recruitment requirements, and the resume description words have different degrees of importance, and if a recruitment enterprise is an external enterprise, the recruitment enterprise may pay more attention to the english level, and the weighted value corresponding to the english eight-level position description words is higher. Finally, calculating the sub-grade value of the information item of each resume file according to the matching degree and the weight value; and accumulating all the sub-scoring values to obtain the scoring value of the resume file.
In an embodiment, the matching model is an LSTM model, the LSTM model is utilized to perform word segmentation on unstructured data of the description information and the feature information to obtain a plurality of job description words and a plurality of resume words respectively, then the number of overlapping the job description words and the resume words is judged, the corresponding evaluation value of the matching degree system is determined according to the number of overlapping, the more the number of overlapping, the higher the matching degree of the job to be recruited and the resume document is, the higher the evaluation value is, and then the grade corresponding to each evaluation value is queried according to a preset list to obtain the resume document with a higher grade as the target resume document with an ideal grade.
In an embodiment, the information items include item experience items, and after the resume file with the score value greater than the threshold value is taken as the target resume file, the method may further include:
taking the resume file with the score value smaller than the threshold value as a candidate resume file;
acquiring sub-scoring values of the project experience items in the candidate resume file;
and when the number of the target resume files is lower than the preset number, taking the candidate resume files with the sub-grade values of the project experience items larger than the preset value as the target resume files.
The implementation can fully utilize the current resume file, and when the score value or the matching degree is low, the project experience items of the information items are further analyzed. If the resume file with the score value smaller than the threshold value is used as the candidate resume file, the sub-score values of the project experience items in the candidate resume file are extracted, and when the number of the target resume files is lower than the preset number, the resume file with the higher sub-score value of the project experience items is used as the target resume file, so that the personalized requirement is realized.
In an embodiment, the resume file with the score value smaller than the threshold value can be used as a candidate resume file, and the candidate resume file is recommended to other positions with higher matching degree, so that talent drainage is realized.
In an embodiment, before the obtaining the resume file to be matched from the resume repository, the method further includes:
acquiring sample resume files and matched recruitment release information corresponding to the sample resume files;
performing characterization processing on the feature information of the sample resume file and the description information of the recruitment release information;
inputting the characteristic information of the sample resume file after the characteristic processing and the description information of the recruitment release information into a convolutional neural network model for training until the convolutional neural network model converges, and obtaining a matching model.
According to the embodiment, data preparation of resume documents and recruitment release information is carried out firstly, the feature information of sample resume documents and the description information of recruitment release information can be characterized through trained Transformer model training, and then the two characterized data are input into a convolutional neural network for model training, so that a matching model is trained. After the training is finished, any one or more resume files can be input into the matching model for matching degree identification, the matching model returns whether the resume files are matched or not, the matching degree and the corresponding sub-scoring value of each information item in each resume file, and then the sub-scoring values are weighted and summarized to obtain the scoring value of each resume file.
In an embodiment, the step of obtaining a matching model until the convolutional neural network model converges includes:
calculating a loss value of the trained convolutional neural network model;
when the loss value is lower than a preset value, obtaining a matching model;
otherwise, adjusting the parameters of the convolutional neural network model, and continuing training the convolutional neural network model until the loss is lower than a preset value.
In the embodiment, the training result of the trained convolutional neural network model is analyzed, the loss of the convolutional neural network model is calculated, and when the loss is lower than a preset value, the convolutional neural network model can meet the preset requirement, so that a matching model is obtained; otherwise, adjusting the parameters of the convolutional neural network model, and continuing training the convolutional neural network model until the loss is lower than a preset value.
Referring to fig. 3, an embodiment of the present invention further provides a device for screening resume files, and in an embodiment, the device includes an obtaining module 31, an identifying module 32, a determining module 33, and a calculating module 34. The obtaining module 31 is configured to obtain the resume file to be matched from the resume repository.
In the module, the server can collect job-seeking resume information received by each recruitment channel, and arrange the job-seeking resume information into a document set, so as to obtain resume files, and store the resume files into a resume library. The resume file can include information such as talent basic information, a study calendar, a work experience (including work time, a post name, a project experience, work content and the like), expected salaries, expected work places and the like.
And the recognition module 32 is configured to extract feature information of each information item from each resume file, and input the feature information and description information related to the recruitment release information into a pre-trained matching model for matching degree recognition.
The module can divide each resume file into a plurality of information items, then extract the characteristic information of each information item, input the characteristic information and the description information related to the recruitment release information into a pre-trained matching model for matching degree recognition, and obtain the matching degree of each characteristic information and the description information. When the matching degree is calculated, each matched feature information in the resume file can be labeled, and the matching degree is determined according to the labeled number of the feature information.
The information items may include a personal profile item, a work experience item, a learning experience item, a personal preference item, and the like, and each information item includes characteristic information describing the information item, such as sex, age, and the like in the personal profile item, and school, achievement, and the like in the learning experience item. The description information can include the requirement of the recruitment position on the academic calendar, the related professional requirement and the requirement of the talent skill, the salary and welfare of the position, the work content and the like.
And the determining module 33 is configured to determine, according to the output result of the matching model, the matching degree between any information item in each resume file and the description information.
In an embodiment, after the server obtains the matching degree between each feature information and the description information, the average value of all the matching degrees is used as the matching degree between any information item in each resume file and the description information, and the subsequent processing steps only process the resume files with higher matching degree, so as to improve the processing efficiency. For example, when an IT research and development engineer engaged in a high-end medical industry needs to be recruited, but a salesman engaged in a common medical industry is described in the resume file, the matching degree of the resume file and the post requirement is low, and the resume file can be directly ignored.
For another example, when a research and development engineer engaged in the education industry needs to be recruited and has online education project experience, and the resume document describes the research and development engineer engaged in the education industry and has live broadcast project development experience, the matching degree obtained by calculation is relatively higher, and the resume document is subjected to subsequent processing.
And the calculating module 34 is configured to calculate a score value corresponding to the resume file according to the matching degree and the weight value corresponding to each information item, compare the score value of each resume file with a set threshold, and use the resume file with the score value greater than the threshold as the target resume file.
The module calculates the score value corresponding to the resume file by using the weight value and the matching degree corresponding to each information item, wherein the weight value of each information item can be set according to the emphasis point of the recruiter. Specifically, when the resume file has two information items, one of the information items has a weight value of 10 and a matching degree of 0.8, and the other information item has a weight value of 5 and a matching degree of 0.6, the value of the score corresponding to the resume file is 10 × 0.8+5 × 0.6 — 11.
And after calculating the score value of each resume file, comparing the score value of each resume file with a set threshold value respectively, and taking the resume file with the score value larger than the threshold value as a target resume file. And if the resume documents with the score values larger than 80 are screened out, obtaining the resume documents which are matched with the positions better.
For example, when a company needs to recruit a worker, it is usually necessary to acquire an application resume file of the application member from a recruitment website, a recruitment system or a recruitment mailbox of the company, take the application resume file of the application member as a resume file to be matched, judging whether the applicant is qualified for the current recruitment position or not by extracting and analyzing the characteristic information of each information item on the resume of the file to be matched, if the matching degree of the feature information of each information item and the description information related to the recruitment release information is identified through a matching model, the matching degree between any information item in each resume file and the description information is obtained, and calculating the score value of each resume file according to the matching degree and the weight value corresponding to each information item, and sorting the resume files according to the scoring values, and screening out the target resume files with the top ranking, thereby obtaining the resume files matched with the positions.
The invention provides a screening device of resume files, which firstly obtains resume files to be matched from a resume library; extracting characteristic information of each information item from each resume file, and inputting the characteristic information and description information related to the recruitment release information into a pre-trained matching model for matching degree identification; then, respectively determining the matching degree between any information item in each resume file and the description information according to the output result of the matching model; and calculating the score value corresponding to the resume file according to the matching degree and the weight value corresponding to each information item, comparing the score value of each resume file with a set threshold value respectively, and taking the resume file with the score value larger than the threshold value as a target resume file. According to the method, the matching degree of the characteristic information of each information item in the resume file and the description information related to the recruitment release information is identified, the score value corresponding to the resume file is calculated according to the matching degree and the weight value corresponding to each information item, so that the importance degree of each information item is considered, the target resume file meeting the recruitment requirement is screened out, and the matching accuracy is improved.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
The invention provides a terminal, which comprises a memory and a processor, wherein the memory is stored with computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the resume file screening method.
In one embodiment, the terminal is a computer device, as shown in fig. 4. The computer device described in this embodiment may be a server, a personal computer, a network device, and other devices. The computer device comprises a processor 402, a memory 403, an input unit 404, and a display unit 405. Those skilled in the art will appreciate that the device configuration means shown in fig. 4 do not constitute a limitation of all devices and may include more or less components than those shown, or some components in combination. The memory 403 may be used to store the computer program 401 and the functional modules, and the processor 402 runs the computer program 401 stored in the memory 403 to execute various functional applications of the device and data processing. The memory may be internal or external memory, or include both internal and external memory. The memory may comprise read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), flash memory, or random access memory. The external memory may include a hard disk, a floppy disk, a ZIP disk, a usb-disk, a magnetic tape, etc. The disclosed memory includes, but is not limited to, these types of memory. The disclosed memory is by way of example only and not by way of limitation.
The input unit 404 is used for receiving input of signals and receiving keywords input by a user. The input unit 404 may include a touch panel and other input devices. The touch panel can collect touch operations of a user on or near the touch panel (for example, operations of the user on or near the touch panel by using any suitable object or accessory such as a finger, a stylus and the like) and drive the corresponding connecting device according to a preset program; other input devices may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., play control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like. The display unit 405 may be used to display information input by a user or information provided to a user and various menus of the computer device. The display unit 405 may take the form of a liquid crystal display, an organic light emitting diode, or the like. The processor 402 is a control center of the computer device, connects various parts of the entire computer using various interfaces and lines, and performs various functions and processes data by operating or executing software programs and/or modules stored in the memory 402 and calling data stored in the memory.
As one embodiment, the computer device includes: one or more processors 402, a memory 403, one or more computer programs 401, wherein the one or more computer programs 401 are stored in the memory 403 and configured to be executed by the one or more processors 402, the one or more computer programs 401 being configured to perform the method for filtering resume files as described in the above embodiments.
In one embodiment, the present invention further provides a storage medium storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to execute the above method for filtering resume files. For example, the storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by a computer program, which may be stored in a storage medium and executed by a computer, and the processes of the embodiments of the methods may be included. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).
The embodiment is combined to show that the invention has the following maximum beneficial effects:
the method, the device, the terminal and the storage medium for screening the resume files provided by the invention firstly obtain the resume files to be matched from the resume library; extracting characteristic information of each information item from each resume file, and inputting the characteristic information and description information related to the recruitment release information into a pre-trained matching model for matching degree identification; then, respectively determining the matching degree between any information item in each resume file and the description information according to the output result of the matching model; and calculating the score value corresponding to the resume file according to the matching degree and the weight value corresponding to each information item, comparing the score value of each resume file with a set threshold value respectively, and taking the resume file with the score value larger than the threshold value as a target resume file. According to the method, the matching degree of the characteristic information of each information item in the resume file and the description information related to the recruitment release information is identified, the score value corresponding to the resume file is calculated according to the matching degree and the weight value corresponding to each information item, so that the importance degree of each information item is considered, the target resume file meeting the recruitment requirement is screened out, and the matching accuracy is improved.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for screening resume files is characterized by comprising the following steps:
acquiring a resume file to be matched from a resume library;
extracting characteristic information of each information item from each resume file, and inputting the characteristic information and description information related to the recruitment release information into a pre-trained matching model for matching degree identification;
respectively determining the matching degree between any information item in each resume file and the description information according to the output result of the matching model;
and calculating the score value corresponding to the resume file according to the matching degree and the weight value corresponding to each information item, comparing the score value of each resume file with a set threshold value respectively, and taking the resume file with the score value larger than the threshold value as a target resume file.
2. The method for screening resume files according to claim 1, wherein before calculating the score value corresponding to the resume file according to the matching degree and the weight value corresponding to each information item, the method further comprises:
calculating the correlation between the characteristic information of each information item in the resume file and the description information;
determining a weight value corresponding to each information item according to the correlation; wherein the weight value is proportional to the degree of correlation.
3. The method for screening resume files according to claim 2, wherein the step of calculating the correlation between the feature information and the description information of each information item in the resume files comprises:
constructing a relevant semantic knowledge base;
determining the collocation frequency of keywords between the characteristic information and the description information by utilizing the relevant semantic knowledge base;
and calculating the correlation between the characteristic information and the description information according to the collocation frequency.
4. The method for screening resume documents according to claim 1, wherein the feature information includes first structured data and first unstructured data, the description information includes second structured data and second unstructured data, and the step of inputting the feature information and the description information related to the recruitment issue information into a pre-trained matching model for matching degree recognition comprises:
completely matching the first structural data of the characteristic information of the resume file with the second structural data of the description information to obtain a completely matched first resume file; the first structured data and the second structured data are necessary conditions for screening the resume file;
carrying out matching degree identification on first unstructured data of the first resume file and second unstructured data in the description information by using a pre-trained matching model to obtain the matching degree between the information item of the first resume file and the description information; the first unstructured data and the second unstructured data are non-essential conditions for screening the resume file.
5. The method for screening resume files according to claim 4, wherein the step of identifying the matching degree between the first unstructured data of the first resume file and the second unstructured data in the description information by using a pre-trained matching model to obtain the matching degree between the information item of the first resume file and the description information comprises:
respectively extracting a first feature corresponding to the first unstructured data and a second feature corresponding to the second unstructured data by using a pre-trained matching model;
performing feature vectorization processing on the first feature and the second feature to obtain a first feature vector and a second feature vector;
calculating the cosine distance between the first characteristic vector and the second characteristic vector;
and determining the matching degree between the information item of the first resume file and the description information according to the cosine distance.
6. The method for screening resume files according to claim 1, wherein the step of calculating the score value corresponding to the resume files according to the matching degree and the weight value corresponding to each information item comprises:
calculating the sub-grade value of each information item in the resume file according to the matching degree and the weight value corresponding to each information item;
and accumulating the sub-credit values of all the information items in the resume file to obtain the credit value of the resume file.
7. The method for screening resume files according to claim 6, wherein the information items comprise project experience items, and after the resume file with the score value larger than the threshold value is taken as the target resume file, the method further comprises:
taking the resume file with the score value smaller than the threshold value as a candidate resume file;
acquiring sub-scoring values of the project experience items in the candidate resume file;
and when the number of the target resume files is lower than the preset number, taking the candidate resume files with the sub-grade values of the project experience items larger than the preset value as the target resume files.
8. A screening device for resume files is characterized by comprising:
the acquisition module is used for acquiring resume files to be matched from the resume library;
the recognition module is used for extracting the characteristic information of each information item from each resume file and respectively inputting the characteristic information and the description information related to the recruitment release information into a pre-trained matching model for matching degree recognition;
the determining module is used for respectively determining the matching degree between any information item in each resume file and the description information according to the output result of the matching model;
and the calculating module is used for calculating the score values corresponding to the resume files according to the matching degrees and the weight values corresponding to the information items, comparing the score values of the resume files with a set threshold value respectively, and taking the resume files with the score values larger than the threshold value as target resume files.
9. A terminal comprising a memory and a processor, the memory having stored therein computer readable instructions which, when executed by the processor, cause the processor to perform the steps of the method of screening of resume files according to any one of claims 1 to 7.
10. A storage medium on which a computer program is stored, the computer program, when executed by a processor, implementing the method of filtering resume files according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911137207.2A CN111078971A (en) | 2019-11-19 | 2019-11-19 | Resume file screening method and device, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911137207.2A CN111078971A (en) | 2019-11-19 | 2019-11-19 | Resume file screening method and device, terminal and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111078971A true CN111078971A (en) | 2020-04-28 |
Family
ID=70311081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911137207.2A Pending CN111078971A (en) | 2019-11-19 | 2019-11-19 | Resume file screening method and device, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111078971A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111914191A (en) * | 2020-06-29 | 2020-11-10 | 长沙市到家悠享网络科技有限公司 | Target sorting method, device and equipment and model training method |
| CN112036647A (en) * | 2020-09-02 | 2020-12-04 | 中国平安人寿保险股份有限公司 | Resume information processing method, device, equipment and medium based on artificial intelligence |
| CN112184140A (en) * | 2020-08-19 | 2021-01-05 | 长沙市到家悠享网络科技有限公司 | Data processing method and device |
| CN112287109A (en) * | 2020-10-29 | 2021-01-29 | 北京希瑞亚斯科技有限公司 | Information matching method and device, electronic equipment and computer readable storage medium |
| CN112307081A (en) * | 2020-10-24 | 2021-02-02 | 上海东方投资监理有限公司 | Project budget cost management system, method, electronic device and readable storage medium |
| CN112488641A (en) * | 2020-11-19 | 2021-03-12 | 深圳市中博科创信息技术有限公司 | User evaluation data processing method, terminal device and readable storage medium |
| CN112700207A (en) * | 2020-12-11 | 2021-04-23 | 五八到家有限公司 | Resume information processing method, device and storage medium |
| CN113570348A (en) * | 2021-09-26 | 2021-10-29 | 山东光辉人力资源科技有限公司 | Resume screening method |
| CN113641794A (en) * | 2021-08-17 | 2021-11-12 | 中国民生银行股份有限公司 | Resume text evaluation method and device and server |
| CN113793199A (en) * | 2021-09-14 | 2021-12-14 | 北京捷风数据技术有限公司 | Bid inviting information recommendation method, system and storage medium |
| WO2022247231A1 (en) * | 2021-05-27 | 2022-12-01 | 中国科学院深圳先进技术研究院 | Resume screening method, resume screening apparatus, terminal device and storage medium |
| CN118013245A (en) * | 2024-04-09 | 2024-05-10 | 杭州东方网升科技股份有限公司 | Matching degree evaluation method based on deep learning model |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110078154A1 (en) * | 2009-09-28 | 2011-03-31 | Accenture Global Services Gmbh | Recruitment screening tool |
| CN105117863A (en) * | 2015-09-28 | 2015-12-02 | 北京橙鑫数据科技有限公司 | Resume position matching method and device |
| CN105608136A (en) * | 2015-12-17 | 2016-05-25 | 华中师范大学 | Semantic relevancy calculation method based on Chinese complex sentences |
| CN107590133A (en) * | 2017-10-24 | 2018-01-16 | 武汉理工大学 | The method and system that position vacant based on semanteme matches with job seeker resume |
| CN108665242A (en) * | 2018-05-09 | 2018-10-16 | 北京邦邦共赢网络科技有限公司 | A kind of resume matching process and device |
| CN110377702A (en) * | 2019-07-18 | 2019-10-25 | 中科鼎富（北京）科技发展有限公司 | A kind of biographic information matching process and device |
-
2019
- 2019-11-19 CN CN201911137207.2A patent/CN111078971A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110078154A1 (en) * | 2009-09-28 | 2011-03-31 | Accenture Global Services Gmbh | Recruitment screening tool |
| CN105117863A (en) * | 2015-09-28 | 2015-12-02 | 北京橙鑫数据科技有限公司 | Resume position matching method and device |
| CN105608136A (en) * | 2015-12-17 | 2016-05-25 | 华中师范大学 | Semantic relevancy calculation method based on Chinese complex sentences |
| CN107590133A (en) * | 2017-10-24 | 2018-01-16 | 武汉理工大学 | The method and system that position vacant based on semanteme matches with job seeker resume |
| CN108665242A (en) * | 2018-05-09 | 2018-10-16 | 北京邦邦共赢网络科技有限公司 | A kind of resume matching process and device |
| CN110377702A (en) * | 2019-07-18 | 2019-10-25 | 中科鼎富（北京）科技发展有限公司 | A kind of biographic information matching process and device |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111914191A (en) * | 2020-06-29 | 2020-11-10 | 长沙市到家悠享网络科技有限公司 | Target sorting method, device and equipment and model training method |
| CN111914191B (en) * | 2020-06-29 | 2023-09-19 | 长沙市到家悠享网络科技有限公司 | Target ordering method, device and equipment |
| CN112184140B (en) * | 2020-08-19 | 2023-08-11 | 长沙市到家悠享网络科技有限公司 | Data processing method and device |
| CN112184140A (en) * | 2020-08-19 | 2021-01-05 | 长沙市到家悠享网络科技有限公司 | Data processing method and device |
| CN112036647A (en) * | 2020-09-02 | 2020-12-04 | 中国平安人寿保险股份有限公司 | Resume information processing method, device, equipment and medium based on artificial intelligence |
| CN112307081A (en) * | 2020-10-24 | 2021-02-02 | 上海东方投资监理有限公司 | Project budget cost management system, method, electronic device and readable storage medium |
| CN112287109A (en) * | 2020-10-29 | 2021-01-29 | 北京希瑞亚斯科技有限公司 | Information matching method and device, electronic equipment and computer readable storage medium |
| CN112488641A (en) * | 2020-11-19 | 2021-03-12 | 深圳市中博科创信息技术有限公司 | User evaluation data processing method, terminal device and readable storage medium |
| CN112700207A (en) * | 2020-12-11 | 2021-04-23 | 五八到家有限公司 | Resume information processing method, device and storage medium |
| WO2022247231A1 (en) * | 2021-05-27 | 2022-12-01 | 中国科学院深圳先进技术研究院 | Resume screening method, resume screening apparatus, terminal device and storage medium |
| CN113641794A (en) * | 2021-08-17 | 2021-11-12 | 中国民生银行股份有限公司 | Resume text evaluation method and device and server |
| CN113793199A (en) * | 2021-09-14 | 2021-12-14 | 北京捷风数据技术有限公司 | Bid inviting information recommendation method, system and storage medium |
| CN113570348A (en) * | 2021-09-26 | 2021-10-29 | 山东光辉人力资源科技有限公司 | Resume screening method |
| CN118013245A (en) * | 2024-04-09 | 2024-05-10 | 杭州东方网升科技股份有限公司 | Matching degree evaluation method based on deep learning model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111078971A (en) | Resume file screening method and device, terminal and storage medium | |
| CN111144723B (en) | Person post matching recommendation method, system and storage medium | |
| CN111105209B (en) | Job resume matching method and device suitable for person post matching recommendation system | |
| US9171078B2 (en) | Automatic recommendation of vertical search engines | |
| US8341112B2 (en) | Annotation by search | |
| WO2020253503A1 (en) | Talent portrait generation method, apparatus and device, and storage medium | |
| CN108345686B (en) | Data analysis method and system based on search engine technology | |
| CA2940760A1 (en) | Intelligent data munging | |
| CN106708929B (en) | Video program searching method and device | |
| CN108846097B (en) | User interest tag representation method, article recommendation device and equipment | |
| WO2018176913A1 (en) | Search method and apparatus, and non-temporary computer-readable storage medium | |
| CN103646070A (en) | Data processing method and device for search engine | |
| CN109710918B (en) | Public opinion identification method, public opinion identification device, computer equipment and storage medium | |
| AU2018226420B2 (en) | Voice assisted intelligent searching in mobile documents | |
| US12008047B2 (en) | Providing an object-based response to a natural language query | |
| US20190340517A2 (en) | A method for detection and characterization of technical emergence and associated methods | |
| Wu et al. | Extracting topics based on Word2Vec and improved Jaccard similarity coefficient | |
| CN110321561A (en) | A kind of keyword extracting method and device | |
| CN115630144B (en) | Document searching method and device and related equipment | |
| US20240160642A1 (en) | Systems and methods for categorization of ingested database entries to determine topic frequency | |
| CN114255096A (en) | Data requirement matching method and device, electronic equipment and storage medium | |
| US20170154294A1 (en) | Performance evaluation device, control method for performance evaluation device, and control program for performance evaluation device | |
| CN114253990A (en) | Database query method and device, computer equipment and storage medium | |
| CN112579750A (en) | Similar medical record retrieval method, device, equipment and storage medium | |
| CN106570196B (en) | Video program searching method and device |
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 |