CN110909120B - Resume searching/delivering method, device and system and electronic equipment - Google Patents

Resume searching/delivering method, device and system and electronic equipment Download PDF

Info

Publication number
CN110909120B
CN110909120B CN201811075813.1A CN201811075813A CN110909120B CN 110909120 B CN110909120 B CN 110909120B CN 201811075813 A CN201811075813 A CN 201811075813A CN 110909120 B CN110909120 B CN 110909120B
Authority
CN
China
Prior art keywords
talent
resume
determining
keyword
keywords
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201811075813.1A
Other languages
Chinese (zh)
Other versions
CN110909120A (en
Inventor
钊魁
林方全
李越川
杨超
杨程
张京桥
吴超
蒋澄宇
戈伟
周涛明
周恒�
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alibaba Group Holding Ltd
Original Assignee
Alibaba Group Holding Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Alibaba Group Holding Ltd filed Critical Alibaba Group Holding Ltd
Priority to CN201811075813.1A priority Critical patent/CN110909120B/en
Publication of CN110909120A publication Critical patent/CN110909120A/en
Application granted granted Critical
Publication of CN110909120B publication Critical patent/CN110909120B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/10Office automation; Time management
    • G06Q10/105Human resources
    • G06Q10/1053Employment or hiring

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Data Mining & Analysis (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The application discloses a resume searching method, device and system, a resume delivering method, device and system, a synonym dictionary constructing method, device and electronic equipment. The resume searching method comprises the following steps: receiving a talent resume screening request aiming at target position description and sent by a client; determining a first talent keyword of a target position description; determining second talent keywords of a plurality of talent resume to be screened; determining a second talent keyword matched with the first talent keyword according to a pre-generated synonym dictionary; and returning the talent resume corresponding to the matched second talent keyword to the client. By adopting the processing mode, the first talent keywords of the target position description and the second talent keywords of the plurality of talent resumes to be screened are matched according to the synonym dictionary, and the talent resume matched with the target position description is automatically determined according to the matching result; therefore, the recall rate and the recall rate of the resume search results can be effectively improved.

Description

Resume searching/delivering method, device and system and electronic equipment
Technical Field
The application relates to the technical field of natural language processing, in particular to a resume searching method, a resume searching device, a resume delivering method, a resume delivering device, a resume delivering system, a synonym dictionary constructing method, a synonym dictionary constructing device and electronic equipment.
Background
With the continuous development of computer technology, more and more enterprises adopt intelligent recruitment systems for talent screening, including: the delivery resume is automatically matched with the recruited position, and the talent resume which meets the position requirement is automatically screened, so that the workload of a human resource department can be reduced, and the effect of improving the working efficiency is achieved.
The intelligent recruitment system mainly works by automatically identifying a talent tag from recruitment related texts such as job descriptions, talent resume, interview records and the like, for example, a 'NLP' word appears in the job descriptions, a 'NLP' talent demand tag is attached to the job, a 'natural language processing' word appears in the talent resume, and a 'natural language processing' talent demand tag is attached to the job; and then, matching the job description and the talent resume according to the talent label. One typical method of talent-based label extraction is a method of extracting talent-based labels based on text keywords. The method utilizes Natural Language Processing (NLP) technology to extract keywords in the recruitment field from the text, for example, a TF-IDF algorithm is used to extract text keywords, and the processing procedure is as follows. Firstly, word segmentation is carried out on a text to be processed through a word segmentation technology; then, according to word segmentation results, counting word frequency (TF) and Inverse Document Frequency (IDF) of each word; and finally, determining TF-IDF values of the words according to the TF and the IDF, and taking the words with the TF-IDF values ranked at high positions as text keywords.
However, in the process of implementing the present invention, the inventors found that at least the following problems exist in this technical solution: the method can not identify the talent label near-meaning words in the recruitment field, so that the recall rate and the recall rate of resume search results are low, and the recall rate of resume delivery are also low.
Disclosure of Invention
The invention provides a resume searching method, which aims to solve the problem that the recall rate and the recall rate of resume searching results in the prior art are low. The application additionally provides a resume delivery method to solve the problem that the full rate and the accuracy rate of resume delivery in the prior art are low. The application additionally provides a resume searching device and system, a resume delivering device and system, a synonym dictionary building method and device and electronic equipment.
The application provides a resume searching method, which comprises the following steps:
receiving a talent resume screening request aiming at target position description and sent by a client;
determining a first talent keyword of the target position description; determining second talent keywords of a plurality of talent resume to be screened;
determining a second talent keyword matched with the first talent keyword according to a pre-generated synonym dictionary;
And returning the talent resume corresponding to the matched second talent keyword to the client.
Optionally, the method further comprises:
and capturing the talent resume to be screened from the mailbox server and/or the webpage server according to the identification of the target job description.
Optionally, the method further comprises:
determining recruitment data;
and constructing the synonym dictionary according to the recruitment data.
Optionally, the constructing the synonym dictionary according to the recruitment data includes:
determining an association relationship between at least two recruitment texts according to the recruitment data; the at least two recruitment texts correspond to different recruitment text categories;
extracting talent keywords from the recruitment text;
and determining the synonym relation between the talent keywords corresponding to each recruitment text of the association relation according to the association relation.
Optionally, the recruitment data includes resume delivery behavior data;
the determining the association relationship between at least two recruitment texts according to the recruitment data comprises the following steps:
and determining the association relationship between the talent resume and the job description according to the resume delivery behavior data.
Optionally, the recruitment data includes resume delivery behavior data;
the determining recruitment data includes:
and capturing the resume delivery behavior data from the mailbox server and/or the webpage server.
Optionally, the recruitment data includes interview data;
the determining the association relationship between at least two recruitment texts according to the recruitment data comprises the following steps:
and determining the association relationship between talent resume, job description and interview record according to the interview behavior data.
Optionally, the recruitment data includes interview data;
the determining recruitment data includes:
generating the interview behavior data according to the interview record.
Optionally, the determining, according to the association relationship, a synonym relationship between the talent-capable keywords corresponding to each recruitment text related to the association relationship includes:
determining a pair of talent-capable keywords between the at least two recruitment texts;
and determining the word pairs with the synonym relationship according to the occurrence times of the word pairs.
Optionally, the recruitment text category includes:
talent resume class, job description class, interview record class.
Optionally, the determining the first talent keyword of the target job description includes:
acquiring talent resume which is successfully recruited and corresponds to the target position description;
and taking the talent keywords of the talent resume successfully recruited as the first talent keywords.
The application also provides a resume searching method, which comprises the following steps:
receiving resume screening instructions aiming at target position descriptions;
sending a resume screening request aiming at the target position description to a server;
receiving talent resume matched with the target position description and returned by the server;
the talent resume matched with the target job description is determined by the following method:
the server determines second talent keywords of talent resume to be screened, which are matched with the first talent keywords described by the target position, according to a pre-generated synonym dictionary; and taking the talent resume corresponding to the matched second talent keyword as the talent resume matched with the target job description.
The application also provides a resume searching device, which comprises:
the request receiving unit is used for receiving talent resume screening requests aiming at target position descriptions and sent by the client;
The first talent keyword determining unit is used for determining a first talent keyword of the target position description;
the second talent keyword determining unit is used for determining second talent keywords of the plurality of talent resumes to be screened;
the talent keyword matching unit is used for determining a second talent keyword matched with the first talent keyword according to a pre-generated synonym dictionary;
and the talent resume returning unit is used for returning talent resume corresponding to the matched second talent keyword to the client.
The application also provides a resume searching device, which comprises:
the instruction receiving unit is used for receiving resume screening instructions aiming at target position descriptions;
the request sending unit is used for sending a resume screening request aiming at the target position description to a server;
the talent resume receiving unit is used for receiving talent resume matched with the target position description and returned by the server;
the talent resume matched with the target job description is determined by the following method:
the server determines second talent keywords of talent resume to be screened, which are matched with the first talent keywords described by the target position, according to a pre-generated synonym dictionary; and taking the talent resume corresponding to the matched second talent keyword as the talent resume matched with the target job description.
The application also provides a resume search system, comprising:
the resume searching device at the server side and the resume searching device at the client side.
The application also provides a resume delivery method, which comprises the following steps:
receiving a resume delivery request aiming at a target talent resume and sent by a client;
determining first talent keywords of a plurality of job descriptions to be delivered; determining a second talent keyword of the target talent resume;
determining the first talent keyword matched with the second talent keyword according to a pre-generated synonym dictionary;
and delivering the target talent resume to the job description corresponding to the matched first talent keyword.
The application also provides a resume delivery device, comprising:
the request receiving unit is used for receiving a resume delivery request aiming at the target talent resume, which is sent by the client;
the first talent keyword determining unit is used for determining first talent keywords of the plurality of job descriptions to be delivered;
a second talent keyword determining unit, configured to determine a second talent keyword of the target talent resume;
a talent keyword matching unit, configured to determine, according to a pre-generated synonym dictionary, the first talent keyword that matches the second talent keyword;
And the resume delivery unit is used for delivering the target talent resume to the job description corresponding to the matched first talent keyword.
The application also provides a resume delivery system, comprising:
according to the resume delivery device at the server side and the other resume delivery request device;
the other resume delivery request device is used for sending a resume delivery request aiming at the target talent resume to the resume delivery device.
The application also provides a synonym dictionary construction method, which comprises the following steps:
acquiring an association relationship between at least two recruitment texts; the at least two recruitment texts correspond to different recruitment text categories;
extracting talent keywords from the recruitment text;
and determining the synonym relation between the talent keywords corresponding to each recruitment text of the association relation according to the association relation.
Optionally, the recruitment text category includes:
talent resume class, job description class, interview record class.
Optionally, the method further comprises:
and determining the association relation according to recruitment data.
Optionally, the determining the association relationship according to recruitment data includes:
And determining the association relationship between the talent resume and the job description according to the resume delivery behavior data.
Optionally, the determining the association relationship according to recruitment data includes:
and determining the association relationship between talent resume, job description and interview record according to the interview behavior data.
Optionally, the determining, according to the association relationship, a synonym relationship between the talent-capable keywords corresponding to each recruitment text related to the association relationship includes:
determining a pair of talent-capable keywords between the at least two recruitment texts;
and determining the word pairs with the synonym relationship according to the occurrence times of the word pairs.
Optionally, the at least two recruitment texts include talent resume and job description;
determining the synonym relation between the talent-capable keywords corresponding to each recruitment text of the association relation according to the association relation comprises the following steps:
acquiring a plurality of talent resume corresponding to the job description according to the association relation;
forming talent keyword sets corresponding to the talent resume according to the talent keywords of the talent resume;
and selecting the talent keywords of the talent resume as synonyms of the talent keywords described by the job position according to the occurrence times of the talent keywords of the talent resume in the talent keyword set.
Optionally, the recruitment text includes a job description;
the extracting the talent keywords from the recruitment text includes:
acquiring talent resume which is successfully recruited and corresponds to the job description;
and taking the talent resume talent keywords as the talent keywords of the job description.
Optionally, the extracting the talent keyword from the recruitment text includes:
and extracting keywords contained in the recruitment domain dictionary from the recruitment text through a keyword extraction algorithm, and taking the keywords as talent keywords corresponding to the recruitment text.
Optionally, the extracting, by a keyword extraction algorithm, a keyword included in a recruitment domain dictionary from the recruitment text as a talent keyword corresponding to the recruitment text includes:
determining keywords of the recruitment text through a keyword extraction algorithm;
and selecting keywords contained in the recruitment domain dictionary from the keywords of the recruitment text as talent keywords corresponding to the recruitment text.
The application also provides a synonym dictionary construction device, which comprises:
the association relation acquisition unit is used for acquiring association relation between at least two recruitment texts; the at least two recruitment texts correspond to different recruitment text categories;
The talent keyword extraction unit is used for extracting talent keywords from the recruitment text;
and the synonym relation determining unit is used for determining synonym relations among the talent keywords corresponding to each recruitment text related to the association relation according to the association relation.
The application also provides an electronic device comprising:
a processor; and
a memory for storing a program for implementing the synonym dictionary construction method, the apparatus being powered on and executing the program of the synonym dictionary construction method by the processor, and performing the steps of: acquiring an association relationship between at least two recruitment texts; the at least two recruitment texts correspond to different recruitment text categories; extracting talent keywords from the recruitment text; and determining the synonym relation between the talent keywords corresponding to each recruitment text of the association relation according to the association relation.
The application also provides an electronic device comprising:
a processor; and
and the memory is used for storing a program for realizing the resume searching method, and after the device is electrified and runs the program of the resume searching method through the processor, the following steps are executed: receiving a talent resume screening request aiming at target position description and sent by a client; determining a first talent keyword of the target position description; determining second talent keywords of a plurality of talent resume to be screened; determining a second talent keyword matched with the first talent keyword according to a pre-generated synonym dictionary; and returning the talent resume corresponding to the matched second talent keyword to the client.
The application also provides an electronic device comprising:
a processor; and
the memory is used for storing a program for realizing the resume delivery method, and after the device is electrified and the program of the resume delivery method is run by the processor, the following steps are executed: receiving a resume delivery request aiming at a target talent resume and sent by a client; determining first talent keywords of a plurality of job descriptions to be delivered; determining a second talent keyword of the target talent resume; determining the first talent keyword matched with the second talent keyword according to a pre-generated synonym dictionary; and delivering the target talent resume to the job description corresponding to the matched first talent keyword.
The present application also provides a computer-readable storage medium having instructions stored therein that, when executed on a computer, cause the computer to perform the various methods described above.
The present application also provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the various methods described above.
Compared with the prior art, the application has the following advantages:
according to the resume searching method, the talent resume screening request aiming at the target position description and sent by the client side is received; determining a first talent keyword of the target position description; determining second talent keywords of a plurality of talent resume to be screened; determining a second talent keyword matched with the first talent keyword according to a pre-generated synonym dictionary; the talent resume corresponding to the matched second talent keyword is returned to the client; the processing mode is that the first talent keywords of the target position description and the second talent keywords of the plurality of talent resumes to be screened are matched according to the synonym dictionary, and the talent resume matched with the target position description is automatically determined according to the matching result; therefore, the recall rate and the recall rate of the resume search results can be effectively improved.
According to the resume delivery method, a resume delivery request aiming at a target talent resume sent by a client is received; determining first talent keywords of a plurality of job descriptions to be delivered; determining a second talent keyword of the target talent resume; determining the first talent keyword matched with the second talent keyword according to a pre-generated synonym dictionary; delivering the target talent resume to a job description corresponding to the matched first talent keyword; the processing mode is that the first talent keywords of the plurality of to-be-delivered job descriptions and the second talent keywords of the target talent resume are matched according to the synonym dictionary, and the job descriptions matched with the target talent resume are automatically determined according to the matching result; therefore, the overall rate and the accuracy rate of resume delivery can be effectively improved.
According to the synonym dictionary construction method, the association relation between at least two recruitment texts is obtained; the at least two recruitment texts correspond to different recruitment text categories; extracting talent keywords from the recruitment text; determining synonym relations among the talent-enabled keywords corresponding to each recruitment text according to the association relation; the processing mode can automatically establish the relation between the keywords with the same or similar semantics, for example, the NLP, the natural language processing and the natural language understanding can be classified as a label; therefore, the construction efficiency and accuracy of the synonym dictionary in the recruitment field can be effectively improved. Meanwhile, the synonym dictionary can be effectively updated and matched in time according to the newly added association relation, for example, the first round of synonym pair generation comprises (NLP, natural language processing), the second round of synonym pair generation comprises (natural language processing, natural language understanding), and the third round of update can deduce (NLP, natural language understanding) to be a synonym pair; therefore, the accuracy of the synonym dictionary can be effectively improved, and the synonym dictionary updating efficiency can be improved.
Drawings
FIG. 1 is a flow chart of an embodiment of a synonym dictionary construction method provided herein;
FIG. 2 is a schematic diagram of an embodiment of a synonym dictionary construction method provided herein;
FIG. 3 is a schematic diagram of an embodiment of a synonym dictionary construction apparatus provided herein;
FIG. 4 is a schematic diagram of an embodiment of an electronic device provided herein;
FIG. 5 is a flow chart of an embodiment of a resume search method provided herein;
FIG. 6 is a schematic diagram of an embodiment of a resume search device provided herein;
FIG. 7 is a schematic diagram of an embodiment of an electronic device provided herein;
FIG. 8 is a flow chart of an embodiment of a resume search method provided herein;
FIG. 9 is a schematic diagram of an embodiment of a resume search device provided herein;
FIG. 10 is a schematic diagram of an embodiment of an electronic device provided herein;
FIG. 11 is a schematic diagram of an embodiment of a resume search system provided herein;
FIG. 12 is a flow chart of an embodiment of a resume delivery method provided herein;
fig. 13 is a schematic view of an embodiment of a resume delivery device provided herein;
FIG. 14 is a schematic diagram of an embodiment of an electronic device provided herein;
Fig. 15 is a schematic view of an embodiment of a resume delivery system provided herein.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is, however, susceptible of embodiment in many other ways than those herein described and similar generalizations can be made by those skilled in the art without departing from the spirit of the application and the application is therefore not limited to the specific embodiments disclosed below.
In the application, a resume searching method, a resume searching device, a resume delivering method, a resume delivering device, a resume delivering system, a synonym dictionary constructing method, a synonym dictionary constructing device and electronic equipment are provided. The various schemes are described in detail one by one in the examples below.
Because the resume searching method, the resume searching device and the resume delivering method, the resume delivering device and the resume delivering system are designed based on the synonym dictionary building method and the synonym dictionary building device, the scheme of the synonym dictionary building method and the synonym dictionary building device is described first, and then the resume searching method, the resume searching device and the resume delivering system and the resume delivering method, the resume dictionary building device and the resume delivering system are described correspondingly.
First embodiment
Referring to fig. 1, a flowchart of an embodiment of a synonym dictionary construction method provided in the present application is provided, where an execution body of the method includes a synonym dictionary construction apparatus. The synonym dictionary construction method provided by the application comprises the following steps:
step S101: and acquiring the association relationship between at least two recruitment texts.
The at least two recruitment texts correspond to different recruitment text categories. The recruitment text categories include, but are not limited to: talent resume class, job description class, interview record class. For example, the association relationship corresponds to two recruitment texts, one of which is talent resume and the other of which is job description; or the association relationship corresponds to three recruitment texts, namely talent resume, job description and interview record.
In one example, the method further comprises the steps of: and determining the association relation according to recruitment data. The recruitment data includes, but is not limited to: resume delivery behavior data, interview behavior data.
The resume delivery behavior data comprises behavior data that a user delivers personal resume to a job description through a mailbox or a resume submitting webpage. In this embodiment, the resume delivery behavior data is obtained from a mailbox server and a web server (such as a recruitment website, etc.), and table 1 shows the resume delivery behavior data of this embodiment.
Figure BDA0001800723230000091
Figure BDA0001800723230000101
TABLE 1 resume delivery behavior data
As can be seen from the table 1, the association relationship between talent resume and job description can be determined according to resume delivery behavior data.
The interview behavioral data includes behavioral data formed at the time of interview. In the present embodiment, the interview behavior data is formed from interview records, and table 2 shows the interview behavior data of the present embodiment.
Figure BDA0001800723230000102
TABLE 2 resume delivery behavior data
From table 2, according to the interview data, the association relationship among talent resume, job description and interview record can be determined.
By adopting the processing mode, an effective closed loop is formed by collecting interaction behaviors in the recruitment process, connection among different recruitment files is generated by using recruitment data, for example, a 'resume delivery' behavior can connect a candidate resume with a job description, a 'interview' behavior can connect the candidate resume, the job description with an interview record, so that information flow is carried out on the talent keywords through the connection among the different recruitment files formed by the recruitment data, a connection relation among the talent keywords is further established, for example, a person with the talent keywords is delivered with a 'natural language processing' post, the association between the 'NLP' and the 'natural language processing' post can be established according to the information, and the synonym problem is solved.
Step S103: and extracting the talent keywords from the recruitment text.
According to the method, the keyword can be extracted from the recruitment text through step S103. For example, for talent information, skills mentioned in talent resume are extracted from the talent information; for interview records, interview officer time is valuable, the interview process is a huge financial effort, keywords in the interview records need to be effectively recorded and extracted, for example, candidates are unwitting, calls are not answered, some skills are strong, etc.
The talent keyword may be a talent keyword that appears in the recruitment text, or may be a talent keyword that does not appear in the recruitment text.
According to the method provided by the embodiment of the application, the talent keywords appearing in the recruitment text can be extracted from the recruitment text by utilizing a Natural Language Processing (NLP) technology. For example, a keyword extraction algorithm such as TF-IDF may be used to extract the talent keywords of the recruitment text, the processing of which is described below. Firstly, word segmentation processing is carried out on recruitment texts through a word segmentation technology; then, according to word segmentation results, counting word frequency (TF) and Inverse Document Frequency (IDF) of each word; and finally, determining TF-IDF values of the words according to the TF and the IDF, and taking the words with the TF-IDF values ranked at high positions as talent keywords of the recruitment text.
In one example, step S103 employs the following manner: and extracting keywords contained in the recruitment domain dictionary from the recruitment text through a keyword extraction algorithm, and taking the keywords as talent keywords corresponding to the recruitment text. In particular, the method can comprise the following substeps: 1) Determining keywords of the recruitment text through a keyword extraction algorithm; 2) And selecting keywords contained in the recruitment domain dictionary from the keywords of the recruitment text as talent keywords corresponding to the recruitment text.
The recruitment domain dictionary can be formed according to data such as corpus of recruitment domain and search keywords.
Corpus of the recruitment domain, including but not limited to: job descriptions, talent resume, interview recordings, and the like recruit corpus of documents.
The search keywords comprise search keywords of recruitment fields collected through a search engine of a recruitment website. The search keywords include, but are not limited to: job keywords such as JAVA, sales representative, administrative assistant, etc.
According to the method provided by the embodiment of the application, the vocabulary entry of the recruitment domain is extracted from the corpus set of the recruitment domain through the keyword extraction algorithm, so that the recruitment domain dictionary is formed. Taking the computer domain as an example, the recruitment domain dictionary may include machine learning, image processing, pattern recognition, databases, operating system, etc. terms.
In order to improve the coverage of the recruitment domain dictionary, the vocabulary entries can also be marked manually, for example, the vocabulary entries specific to the recruitment domain, such as no intention of the candidate, missed call, etc.
According to the method provided by the embodiment of the application, the graph propagation algorithm can be adopted to extract the non-appearing talent keywords in the recruitment text from the recruitment text.
In one example, the recruitment text is a job description, and to extract the talent keywords that do not appear in the job description through a graph propagation algorithm, the following steps may be adopted: 1) Acquiring talent resume which is successfully recruited and corresponds to the job description; 2) And taking the talent resume talent keywords as the talent keywords of the job description. For example, even if the "deep learning" keyword does not appear in the job description, if the job recruits a person who has "deep learning" ability according to the history, the job may be labeled with the "deep learning" ability.
In another example, the method can further identify the recruitment text with refined talent keywords according to a preset talent keyword hierarchy after extracting the talent keywords from the recruitment text. For example, for the job description, key word groups in the job description can be extracted, and requirements and work contents of the job description can be refined, for example, under the 'technology-algorithm-application algorithm', different subdivisions such as images, voices, NLP, information retrieval and the like can be extended.
Step S105: and determining the synonym relation between the talent keywords corresponding to each recruitment text of the association relation according to the association relation.
After the association relation between at least two recruitment texts is obtained and the talent keywords are extracted from the recruitment texts, the synonym relation between the talent keywords corresponding to each recruitment text of the association relation can be determined according to the association relation.
In one example, step S105 may be determined using the following substeps: 1) Determining a pair of talent-capable keywords between the at least two recruitment texts; 2) And determining the word pairs with the synonym relation according to the occurrence times of the word pairs, for example, taking the word pair with the largest occurrence times as the synonym, or taking the word pair with the occurrence times larger than a preset threshold value as the synonym, and the like.
Please refer to fig. 2, which is a schematic diagram of an embodiment of a synonym dictionary construction method provided in the present application. In this embodiment, the talent keywords of the talent resume include: NLP; the talent keywords of the job description include: natural language processing and machine learning; the talent keywords of the interview record include: natural language understanding and deep learning; the identification process of the synonym relationship between NLP, natural language processing, natural language understanding is as follows. Firstly, constructing association relations among talent resume, job description and interview record according to delivery behavior data and interview behavior data; then, extracting talent keywords from each recruitment text, and respectively counting the co-occurrence times of different word pairs, wherein in the example, resume delivery positions form (NLP, natural language processing), (NLP, machine learning) two word pairs; interview the corresponding candidate and comment will form (NLP, natural language processing), (NLP, deep learning) two word pairs. Then, global statistics can be made on the whole data set (i.e. all talent resume, job description, interview record, and all resume delivery behavior data and interview behavior data), namely: and counting the keyword pairs corresponding to all the association relations, and taking the word pair with the largest occurrence number as a synonym, wherein the synonym relation is not available for the word pair with the smaller occurrence number due to the fact that the number of the word pair with the largest occurrence number (NLP, machine learning) is the NLP, natural language processing and natural language understanding in the example.
In another example, step S105 may include the following sub-steps: 1) Acquiring a plurality of talent resume corresponding to the job description; 2) Forming talent keyword sets corresponding to the talent resume according to the talent keywords of the talent resume; 3) And selecting the talent keywords of the talent resume as synonyms of the talent keywords described by the job position according to the occurrence times of the talent keywords of the talent resume in the talent keyword set.
For example, the talent keywords of the job description include: natural language processing; according to the delivery behavior data, it can be determined that the job description is associated with 100 talent resume, wherein the talent keywords of talent resume 1 include: NLP and image processing, talent keywords of talent resume 2 include: machine learning and pattern recognition, talent keywords of talent resume 3 include: machine learning, NLP and the like, forming a non-duplicate talent keyword set by the respective talent keywords of the 100 personal resume, counting the occurrence times of the respective talent keywords, and taking the talent keywords with the occurrence times of more than 50 as synonyms of the talent keywords described by the job positions.
According to the embodiment, the synonym dictionary construction method provided by the embodiment of the application is implemented by acquiring the association relationship between at least two recruitment texts; the at least two recruitment texts correspond to different recruitment text categories; extracting talent keywords from the recruitment text; determining synonym relations among the talent-enabled keywords corresponding to each recruitment text according to the association relation; the processing mode can automatically establish the relation between the keywords with the same or similar semantics, for example, the NLP, the natural language processing and the natural language understanding can be classified as a label; therefore, the construction efficiency and accuracy of the synonym dictionary in the recruitment field can be effectively improved. Meanwhile, the synonym dictionary can be effectively updated and matched in time according to the newly added association relation, for example, the first round of synonym pair generation comprises (NLP, natural language processing), the second round of synonym pair generation comprises (natural language processing, natural language understanding), and the third round of update can deduce (NLP, natural language understanding) to be a synonym pair; therefore, the accuracy of the synonym dictionary can be effectively improved, and the synonym dictionary updating efficiency can be improved.
In the above embodiment, a synonym dictionary construction method is provided, and correspondingly, the application also provides a synonym dictionary construction device. The device corresponds to the embodiment of the method described above.
Second embodiment
Referring to FIG. 3, a schematic diagram of an embodiment of the synonym dictionary construction apparatus of the present application is shown. Since the apparatus embodiments are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
The present application additionally provides a synonym dictionary construction apparatus, comprising:
an association relationship obtaining unit 301, configured to obtain an association relationship between at least two recruitment texts; the at least two recruitment texts correspond to different recruitment text categories;
a talent keyword extraction unit 302, configured to extract talent keywords from the recruitment text;
and the synonym relation determining unit 303 is configured to determine synonym relations between the talent-capable keywords corresponding to each recruitment text corresponding to the association relation according to the association relation.
Optionally, the recruitment text category includes:
Talent resume class, job description class, interview record class.
Optionally, the method further comprises:
and the association relation determining unit is used for determining the association relation according to the recruitment behavior data.
Optionally, the association relation determining unit is specifically configured to determine an association relation between the talent resume and the job description according to resume delivery behavior data.
Optionally, the association relation determining unit is specifically configured to determine, according to the interview behavior data, an association relation among the talent resume, the job description and the interview record.
Optionally, the synonym relationship determining unit 303 includes:
a first word pair determining subunit configured to determine a pair of talent keywords between the at least two recruitment texts;
and the second word pair determining subunit is used for determining the word pair with the synonym relation according to the occurrence times of the word pair.
Optionally, the at least two recruitment texts include talent resume and job description;
the synonym relationship determination unit 303 includes:
the first subunit is used for acquiring a plurality of talent resume corresponding to the job description according to the association relation;
the second subunit is used for forming a talent keyword set corresponding to the talent resume according to the talent keywords of the talent resume;
And the third subunit is used for selecting the talent keywords of the talent resume as synonyms of the talent keywords described by the job position according to the occurrence times of the talent keywords of the talent resume in the talent keyword set.
Optionally, the recruitment text includes a job description;
the talent-capable keyword extraction unit 302 includes:
the talent resume acquisition subunit is used for acquiring talent resume which is successfully recruited and corresponds to the job description;
and the keyword setting subunit is used for taking the talent keywords of the talent resume as the talent keywords described by the job positions.
Optionally, the talent keyword extracting unit 302 is specifically configured to extract, by using a keyword extraction algorithm, a keyword included in a recruitment domain dictionary from the recruitment text, where the keyword is used as a talent keyword corresponding to the recruitment text.
Optionally, the talent-capable keyword extraction unit 302 includes:
the first subunit is used for determining the keywords of the recruitment text through a keyword extraction algorithm;
and the second subunit is used for selecting keywords contained in the recruitment domain dictionary from the keywords of the recruitment text as talent keywords corresponding to the recruitment text.
Third embodiment
Please refer to fig. 4, which is a schematic diagram of an embodiment of an electronic device of the present application. Since the apparatus embodiments are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
An electronic device of the present embodiment includes: a processor 401 and a memory 402; the memory is used for storing a program for realizing the synonym dictionary construction method, and after the device is powered on and runs the program of the synonym dictionary construction method through the processor, the following steps are executed: acquiring an association relationship between at least two recruitment texts; the at least two recruitment texts correspond to different recruitment text categories; extracting talent keywords from the recruitment text; and determining the synonym relation between the talent keywords corresponding to each recruitment text of the association relation according to the association relation.
In the above embodiment, a synonym dictionary construction method is provided, and correspondingly, a resume search method is also provided. The method corresponds to the embodiment of the method described above.
Fourth embodiment
Please refer to fig. 5, which is a schematic diagram of an embodiment of a resume search method of the present application. Since this method embodiment is based on the method embodiment of the first embodiment, the description of the relevant parts is relatively simple, and the relevant parts are referred to in the description of the method embodiment of the first embodiment.
The application additionally provides a resume search method, which comprises the following steps:
step S501: and receiving a talent resume screening request aiming at the target position description and sent by the client.
According to the method, talent resume matched with target position descriptions is automatically searched from a large number of talent resume to be screened, and second talent keywords of the talent resume to be screened, which are matched with the first talent keywords of the target position descriptions, are determined according to a pre-generated synonym dictionary, so that the recall rate and the recall rate of resume search results are improved.
The client described in the present application includes, but is not limited to, a mobile communication device, namely: the mobile phone or the intelligent mobile phone also comprises terminal equipment such as a personal computer, a PAD, an iPad and the like.
In one example, the method further comprises the steps of: and capturing a plurality of talent resume to be screened from the mailbox server and/or the webpage server according to the identification of the target job description. The web page server can be a resume release website, various recruitment websites and the like.
Step S503: determining a first talent keyword of the target position description; and determining second talent keywords of the plurality of talent resume to be screened.
According to the method provided by the implementation of the application, the talent keywords can be extracted from the target position description by utilizing Natural Language Processing (NLP) technology (such as keyword extraction algorithm and the like) and used as the first talent keywords; and the talent keywords extracted from talent resume are used as second talent keywords. The talent keywords may originate from a dictionary in the recruitment domain.
In one example, the step of determining the first talent capable keyword of the target job description may include the following sub-steps: 1) Acquiring talent resume which is successfully recruited and corresponds to the target position description; 2) And taking the talent keywords of the talent resume successfully recruited as the first talent keywords.
Step S505: and determining a second talent keyword matched with the first talent keyword according to a pre-generated synonym dictionary.
The pre-generated synonym dictionary can be manually marked, and the synonym dictionary can be automatically built and updated according to recruitment data.
In one example, the method further comprises the steps of: 1) Determining recruitment data; 2) And constructing a synonym dictionary according to the recruitment data.
1) Recruitment data is determined.
The recruitment data includes, but is not limited to: resume delivery behavior data, interview behavior data.
The resume delivery behavior data comprises behavior data that a user delivers personal resume to a job description through a mailbox or a resume submitting webpage. In this embodiment, the resume delivery behavior data is obtained from a mailbox server and a web server.
The interview behavioral data includes behavioral data formed at the time of interview. In this embodiment, the interview behavior data is formed from interview records.
2) And constructing a synonym dictionary according to the recruitment data.
The method for automatically constructing and updating the pre-generated synonym dictionary can be referred to the related description of the first embodiment, and will not be repeated here.
Further, the method may further comprise the steps of: and updating the synonym dictionary according to the newly added recruitment data.
After determining the talent keywords of the talent resume matched with the target position description, the talent resume corresponding to the matched (with the same or similar semantics) second talent keyword can be used as the talent resume matched with the target position description, and the association relationship between the talent resume and the target position description can be automatically constructed.
Step S507: and returning the talent resume corresponding to the matched second talent keyword to the client.
As can be seen from the above embodiments, in the resume searching method provided in the embodiments of the present application, a talent resume screening request for a target job description sent by a client is received; determining a first talent keyword of the target position description; determining second talent keywords of a plurality of talent resume to be screened; determining a second talent keyword matched with the first talent keyword according to a pre-generated synonym dictionary; the talent resume corresponding to the matched second talent keyword is returned to the client; the processing mode is that the first talent keywords of the target position description and the second talent keywords of the plurality of talent resumes to be screened are matched according to the synonym dictionary, and the talent resume matched with the target position description is automatically determined according to the matching result; therefore, the recall rate and the recall rate of the resume search results can be effectively improved.
In the above embodiment, a resume searching method is provided, and correspondingly, the application also provides a resume searching device. The device corresponds to the embodiment of the method described above.
Fifth embodiment
Please refer to fig. 6, which is a schematic diagram of an embodiment of a resume search device of the present application. Since the apparatus embodiments are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
The application additionally provides a resume search device comprising:
a request receiving unit 601, configured to receive a talent resume screening request for a target job description sent by a client;
a first talent keyword determining unit 602, configured to determine a first talent keyword of the target job description;
a second talent keyword determining unit 603, configured to determine second talent keywords of the plurality of talent resume to be screened;
a talent keyword matching unit 604, configured to determine, according to a pre-generated synonym dictionary, a second talent keyword that matches the first talent keyword;
and the talent resume returning unit 605 is configured to return, to the client, the talent resume corresponding to the matched second talent keyword.
Optionally, the method further comprises:
and the talent resume grabbing unit is used for grabbing the talent resume to be screened from the mailbox server and/or the webpage server according to the identification of the target position description.
Optionally, the method further comprises:
the recruitment data determining unit is used for determining recruitment data;
and the synonym dictionary construction unit is used for constructing the synonym dictionary according to the recruitment behavior data.
Optionally, the synonym dictionary building unit includes:
the association relation determining subunit is used for determining association relation between at least two recruitment texts according to the recruitment data; the at least two recruitment texts correspond to different recruitment text categories;
a talent keyword extraction subunit, configured to extract talent keywords from the recruitment text;
and the synonym relation determining subunit is used for determining the synonym relation between the talent keywords corresponding to each recruitment text related to the association relation according to the association relation.
Optionally, the recruitment data includes resume delivery behavior data;
the association relation determination subunit is specifically configured to determine an association relation between the talent resume and the job description according to resume delivery behavior data.
Optionally, the recruitment data includes resume delivery behavior data;
the recruitment behavior data determining unit is specifically configured to capture the resume delivery behavior data from a mailbox server and/or a web server.
Optionally, the recruitment data includes interview data;
the association relation determination subunit is specifically configured to determine association relation among talent resume, job description and interview record according to interview behavior data.
Optionally, the recruitment data includes interview data;
the recruitment data determining unit is specifically configured to generate the interview data according to an interview record.
Optionally, the synonym relationship determining subunit includes:
a first word pair determining subunit configured to determine a pair of talent keywords between the at least two recruitment texts;
and the second word pair determining subunit is used for determining the word pair with the synonym relation according to the occurrence times of the word pair.
Optionally, the recruitment text category includes:
talent resume class, job description class, interview record class.
Optionally, the first talent capable keyword determining unit includes:
the talent resume acquisition subunit is used for acquiring talent resume which is successfully recruited and corresponds to the target position description;
and the keyword setting subunit is used for taking the talent keywords of the talent resume successfully recruited as the first talent keywords.
Sixth embodiment
Please refer to fig. 7, which is a schematic diagram of an embodiment of an electronic device of the present application. Since the apparatus embodiments are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
An electronic device of the present embodiment includes: a processor 701 and a memory 702; the memory is used for storing a program for realizing a resume searching method, and after the device is electrified and the program of the resume searching method is run by the processor, the following steps are executed: receiving a talent resume screening request aiming at target position description and sent by a client; determining a first talent keyword of the target position description; determining second talent keywords of a plurality of talent resume to be screened; determining a second talent keyword matched with the first talent keyword according to a pre-generated synonym dictionary; and returning the talent resume corresponding to the matched second talent keyword to the client.
In the above embodiment, a resume searching method is provided, and correspondingly, the application also provides a resume searching method. The method corresponds to the embodiment of the method described above.
Seventh embodiment
Please refer to fig. 8, which is a schematic diagram illustrating an embodiment of a resume search method of the present application. Since this method embodiment corresponds to the above-described method embodiment, the description of the relevant portions is relatively simple, and the relevant portions are only required to refer to the partial description of the method embodiment of the first embodiment. The method embodiments described below are merely illustrative.
The application additionally provides a resume search method, which comprises the following steps:
step S801: and receiving resume screening instructions aiming at target position descriptions.
The main execution body of the resume search method comprises a resume search device which is generally deployed at a client, wherein the client comprises, but is not limited to, mobile communication equipment, namely: the mobile phone or the intelligent mobile phone also comprises terminal equipment such as a personal computer, a PAD, an iPad and the like.
Step S803: and sending a resume screening request aiming at the target position description to a server.
Step S805: and receiving talent resume matched with the target position description and returned by the server.
The server determines second talent keywords of talent resume to be screened, which are matched with the first talent keywords described by the target position, according to a pre-generated synonym dictionary; and taking the talent resume corresponding to the matched second talent keyword as the talent resume matched with the target job description.
After receiving talent resume matched with target job description designated by user, client can browse each talent resume to screen proper talents.
In one example, the method further comprises the steps of: receiving an interview notification instruction for a target talent resume input by a user, and sending interview notification to a communication address associated with the target talent resume, for example, sending interview notification mail to a mailbox of the target talent resume, or sending interview notification short message to a mobile phone number of the target talent resume, and the like.
As can be seen from the above embodiments, in the resume searching method provided in the embodiments of the present application, a resume screening instruction described for a target job is received; sending a resume screening request aiming at the target position description to a server; receiving talent resume matched with the target position description and returned by the server; the processing mode is that the first talent keywords of the target position description and the second talent keywords of the plurality of talent resumes to be screened are matched according to the synonym dictionary, and the talent resume matched with the target position description is automatically determined according to the matching result; therefore, the recall rate and the recall rate of the resume search results can be effectively improved.
In the above embodiment, a resume searching method is provided, and correspondingly, the application also provides a resume searching device. The device corresponds to the embodiment of the method described above.
Eighth embodiment
Please refer to fig. 9, which is a schematic diagram of an embodiment of a resume search device of the present application. Since the apparatus embodiments are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
The application additionally provides a resume search device comprising:
an instruction receiving unit 901, configured to receive a resume screening instruction for a target job description;
a request sending unit 902, configured to send a resume screening request for the target job description to a server;
the talent resume receiving unit 903 is configured to receive a talent resume that is returned by the server and matches the target job description;
the talent resume matched with the target job description is determined by the following method:
the server determines second talent keywords of talent resume to be screened, which are matched with the first talent keywords described by the target position, according to a pre-generated synonym dictionary; and taking the talent resume corresponding to the matched second talent keyword as the talent resume matched with the target job description.
Ninth embodiment
Please refer to fig. 10, which is a schematic diagram of an embodiment of an electronic device of the present application. Since the apparatus embodiments are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
An electronic device of the present embodiment includes: a processor 1001 and a memory 1002; the memory is used for storing a program for realizing a resume searching method, and after the device is electrified and the program of the resume searching method is run by the processor, the following steps are executed: receiving resume screening instructions aiming at target position descriptions; sending a resume screening request aiming at the target position description to a server; receiving talent resume matched with the target position description and returned by the server; the talent resume matched with the target job description is determined by the following method: the server determines second talent keywords of talent resume to be screened, which are matched with the first talent keywords described by the target position, according to a pre-generated synonym dictionary; and taking the talent resume corresponding to the matched second talent keyword as the talent resume matched with the target job description.
Tenth embodiment
The embodiment of the application also provides a resume search system, as shown in fig. 11, which includes the resume search device 1101 and the resume search device 1102 on the client side described in the fifth embodiment. The resume search device 1101 is typically disposed on a server, but is not limited to a server, and may be any device capable of implementing the resume search method; the resume search device 1102 is typically disposed in a terminal device such as a mobile communication device, a personal computer, a PAD, an iPad, etc.
For example, the resume search device 1102 is deployed on a smart phone, and is capable of receiving resume screening instructions for target job descriptions; sending a resume screening request aiming at the target position description to a server; receiving talent resume matched with the target position description and returned by the server; the resume searching device 1101 is deployed on a server, and receives a talent resume screening request aiming at target position description sent by a client; determining a first talent keyword of the target position description; determining second talent keywords of a plurality of talent resume to be screened; determining a second talent keyword matched with the first talent keyword according to a pre-generated synonym dictionary; and returning the talent resume corresponding to the matched second talent keyword to the client.
As can be seen from the above embodiments, in the resume search system provided in the embodiments of the present application, a talent resume screening request for a target job description sent by a client is received; determining a first talent keyword of the target position description; determining second talent keywords of a plurality of talent resume to be screened; determining a second talent keyword matched with the first talent keyword according to a pre-generated synonym dictionary; the talent resume corresponding to the matched second talent keyword is returned to the client; the processing mode is that the first talent keywords of the target position description and the second talent keywords of the plurality of talent resumes to be screened are matched according to the synonym dictionary, and the talent resume matched with the target position description is automatically determined according to the matching result; therefore, the recall rate and the recall rate of the resume search results can be effectively improved.
In the above embodiment, a synonym dictionary construction method is provided, and correspondingly, a resume delivery method is also provided. The method corresponds to the embodiment of the method described above.
Eleventh embodiment
Please refer to fig. 12, which is a schematic diagram illustrating an embodiment of a resume delivery method of the present application. Since this method embodiment is based on the method embodiment of the first embodiment, the description of the relevant parts is relatively simple, and the relevant parts are referred to in the description of the method embodiment of the first embodiment.
The application additionally provides a resume delivery method, which comprises the following steps:
step S1201: and receiving a resume delivery request aiming at the target talent resume and sent by the client.
According to the method, the target talent resume is automatically delivered to the proper job description, and the first talent keyword of the job description to be delivered, which is matched with the second talent keyword of the target talent resume, is determined according to the pre-generated synonym dictionary, so that the full rate and the accuracy rate of resume delivery are improved.
The client described in the present application includes, but is not limited to, a mobile communication device, namely: the mobile phone or the intelligent mobile phone also comprises terminal equipment such as a personal computer, a PAD, an iPad and the like.
Step S1203: determining first talent keywords of a plurality of job descriptions to be delivered; and determining a second talent keyword of the target talent resume.
According to the method provided by the implementation of the application, the Natural Language Processing (NLP) technology (such as a keyword extraction algorithm) can be utilized to extract the talent keywords from the position descriptions to be delivered, and the talent keywords are used as the first talent keywords; and the talent keywords extracted from the target talent resume are used as second talent keywords. The talent keywords may originate from a dictionary in the recruitment domain.
In one example, the step of determining the first talent capable keyword of the job description to be delivered may include the following sub-steps: 1) Acquiring talent resume which is successfully recruited and corresponds to the job description to be delivered; 2) And taking the talent keywords of the talent resume successfully recruited as the first talent keywords.
Step S1205: and determining the first talent keyword matched with the second talent keyword according to a pre-generated synonym dictionary.
The pre-generated synonym dictionary can be manually marked, and the synonym dictionary can be automatically built and updated according to recruitment data.
In one example, the method further comprises the steps of: 1) Determining recruitment data; 2) And constructing a synonym dictionary according to the recruitment data.
1) Recruitment data is determined.
The recruitment data includes, but is not limited to: resume delivery behavior data, interview behavior data.
The resume delivery behavior data comprises behavior data that a user delivers personal resume to a job description through a mailbox or a resume submitting webpage. In this embodiment, the resume delivery behavior data is obtained from a mailbox server and a web server.
The interview behavioral data includes behavioral data formed at the time of interview. In this embodiment, the interview behavior data is formed from interview records.
2) And constructing a synonym dictionary according to the recruitment data.
The method for automatically constructing and updating the pre-generated synonym dictionary can be referred to the related description of the first embodiment, and will not be repeated here.
Further, the method may further comprise the steps of: and updating the synonym dictionary according to the newly added recruitment data.
After determining the talent keywords of the to-be-delivered position descriptions matched with the talent keywords of the target talent resume, the position descriptions corresponding to the matched (with the same or similar semantics) first talent keywords can be used as the position descriptions matched with the target talent resume, and the association relationship between the two can be automatically constructed.
Step S1207: and delivering the target talent resume to the job description corresponding to the matched first talent keyword.
As can be seen from the above embodiments, in the resume delivery method provided in the embodiments of the present application, a resume delivery request for a target talent resume sent by a client is received; determining first talent keywords of a plurality of job descriptions to be delivered; determining a second talent keyword of the target talent resume; determining the first talent keyword matched with the second talent keyword according to a pre-generated synonym dictionary; delivering the target talent resume to a job description corresponding to the matched first talent keyword; the processing mode is that the first talent keywords of the plurality of to-be-delivered job descriptions and the second talent keywords of the target talent resume are matched according to the synonym dictionary, and the job descriptions matched with the target talent resume are automatically determined according to the matching result; therefore, the overall rate and the accuracy rate of resume delivery can be effectively improved.
In the above embodiment, a resume delivery method is provided, and correspondingly, the application also provides a resume delivery device. The device corresponds to the embodiment of the method described above.
Twelfth embodiment
Please refer to fig. 13, which is a schematic diagram of an embodiment of the resume delivery device of the present application. Since the apparatus embodiments are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
The application additionally provides a resume delivery device comprising:
a request receiving unit 1301, configured to receive a resume delivery request for a target talent resume sent by a client;
a first talent keyword determining unit 1302, configured to determine first talent keywords of a plurality of job descriptions to be delivered;
a second talent keyword determining unit 1303, configured to determine a second talent keyword of the target talent resume;
a talent keyword matching unit 1304 configured to determine, according to a pre-generated synonym dictionary, the first talent keyword that matches the second talent keyword;
and the resume delivery unit 1305 is used for delivering the target talent resume to the job description corresponding to the matched first talent keyword.
Thirteenth embodiment
Please refer to fig. 14, which is a schematic diagram of an embodiment of an electronic device of the present application. Since the apparatus embodiments are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
An electronic device of the present embodiment includes: a processor 1401 and a memory 1402; the memory is used for storing a program for realizing a resume delivery method, and after the device is electrified and the program of the resume delivery method is run by the processor, the following steps are executed: receiving a resume delivery request aiming at a target talent resume and sent by a client; determining first talent keywords of a plurality of job descriptions to be delivered; determining a second talent keyword of the target talent resume; determining the first talent keyword matched with the second talent keyword according to a pre-generated synonym dictionary; and delivering the target talent resume to the job description corresponding to the matched first talent keyword.
Fourteenth embodiment
The embodiment of the application also provides a resume delivery system, as shown in fig. 15, which includes the resume delivery device 1501 and the resume delivery device 1502 on the client side described in the above embodiment. The resume search device 1501 is typically disposed in a server, but is not limited to a server, and may be any device capable of implementing the resume delivery method; the resume delivery device 1502 is typically deployed in a mobile communication device, a personal computer, a PAD, an iPad, and other terminal devices.
For example, the resume delivery device 1502 is deployed on a smart phone, and is capable of sending a resume delivery request for a target talent resume to the resume delivery device 1501; the resume delivery device 1501 is deployed on a server, and receives a resume delivery request for a target talent resume sent by a client; determining first talent keywords of a plurality of job descriptions to be delivered; determining a second talent keyword of the target talent resume; determining the first talent keyword matched with the second talent keyword according to a pre-generated synonym dictionary; and delivering the target talent resume to the job description corresponding to the matched first talent keyword.
As can be seen from the above embodiments, in the resume delivery system provided in the embodiments of the present application, a resume delivery request for a target talent resume sent by a client is received; determining first talent keywords of a plurality of job descriptions to be delivered; determining a second talent keyword of the target talent resume; determining the first talent keyword matched with the second talent keyword according to a pre-generated synonym dictionary; delivering the target talent resume to a job description corresponding to the matched first talent keyword; the processing mode is that the first talent keywords of the plurality of to-be-delivered job descriptions and the second talent keywords of the target talent resume are matched according to the synonym dictionary, and the job descriptions matched with the target talent resume are automatically determined according to the matching result; therefore, the overall rate and the accuracy rate of resume delivery can be effectively improved.
While the preferred embodiment has been described, it is not intended to limit the invention thereto, and any person skilled in the art may make variations and modifications without departing from the spirit and scope of the present invention, so that the scope of the present invention shall be defined by the claims of the present application.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
1. Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer readable media, as defined herein, does not include non-transitory computer readable media (transmission media), such as modulated data signals and carrier waves.
2. It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

Claims (21)

1. A resume search method, comprising:
receiving a talent resume screening request aiming at target position description and sent by a client;
determining a first talent keyword of the target position description; determining second talent keywords of a plurality of talent resume to be screened;
determining a second talent keyword matched with the first talent keyword according to a pre-generated synonym dictionary;
the talent resume corresponding to the matched second talent keyword is returned to the client;
the synonym dictionary is generated by the following steps: determining recruitment data, wherein the recruitment data comprises resume delivery behavior data and interview behavior data; according to resume delivery behavior data and interview behavior data, determining association relations among talent resume, job description and interview records; and determining the synonym relation among the talent resume, the job description and the talent keywords corresponding to the interview records according to the association relation.
2. The method as recited in claim 1, further comprising:
and capturing the talent resume to be screened from the mailbox server and/or the webpage server according to the identification of the target job description.
3. The method of claim 1, wherein the step of determining the position of the substrate comprises,
the recruitment data includes resume delivery behavior data;
the determining recruitment data includes:
and capturing the resume delivery behavior data from the mailbox server and/or the webpage server.
4. The method of claim 1, wherein the step of determining the position of the substrate comprises,
the recruitment data includes interview data;
the determining recruitment data includes:
generating the interview behavior data according to the interview record.
5. The method of claim 1, wherein the step of determining the position of the substrate comprises,
determining the synonym relation among the talent resume, the job description and the face test record corresponding to each talent keyword according to the association relation, wherein the synonym relation comprises the following steps:
determining a talent keyword pair between the talent resume, the job description and the interview record;
and determining the word pairs with the synonym relationship according to the occurrence times of the word pairs.
6. The method of claim 1, wherein the determining the first talent capable keyword of the target job description comprises:
acquiring talent resume which is successfully recruited and corresponds to the target position description;
and taking the talent keywords of the talent resume successfully recruited as the first talent keywords.
7. A resume search method, comprising:
receiving resume screening instructions aiming at target position descriptions;
sending a resume screening request aiming at the target position description to a server;
receiving talent resume matched with the target position description and returned by the server;
the talent resume matched with the target job description is determined by the following method:
the server determines second talent keywords of talent resume to be screened, which are matched with the first talent keywords described by the target position, according to a pre-generated synonym dictionary; the talent resume corresponding to the matched second talent keyword is used as the talent resume matched with the target position description; the synonym dictionary is generated in the following way: determining recruitment data, wherein the recruitment data comprises resume delivery behavior data and interview behavior data; according to resume delivery behavior data and interview behavior data, determining association relations among talent resume, job description and interview records; and determining the synonym relation among the talent resume, the job description and the talent keywords corresponding to the interview records according to the association relation.
8. A resume search device, comprising:
the request receiving unit is used for receiving talent resume screening requests aiming at target position descriptions and sent by the client;
the first talent keyword determining unit is used for determining a first talent keyword of the target position description;
the second talent keyword determining unit is used for determining second talent keywords of the plurality of talent resumes to be screened;
the talent keyword matching unit is used for determining a second talent keyword matched with the first talent keyword according to a pre-generated synonym dictionary;
the talent resume returning unit is used for returning talent resume corresponding to the matched second talent keyword to the client;
the synonym dictionary is generated by the following steps: determining recruitment data, wherein the recruitment data comprises resume delivery behavior data and interview behavior data; according to resume delivery behavior data and interview behavior data, determining association relations among talent resume, job description and interview records; and determining the synonym relation among the talent resume, the job description and the talent keywords corresponding to the interview records according to the association relation.
9. A resume search device, comprising:
the instruction receiving unit is used for receiving resume screening instructions aiming at target position descriptions;
the request sending unit is used for sending a resume screening request aiming at the target position description to a server;
the talent resume receiving unit is used for receiving talent resume matched with the target position description and returned by the server;
the talent resume matched with the target job description is determined by the following method:
the server determines second talent keywords of talent resume to be screened, which are matched with the first talent keywords described by the target position, according to a pre-generated synonym dictionary; the talent resume corresponding to the matched second talent keyword is used as the talent resume matched with the target position description; the synonym dictionary is generated in the following way: determining recruitment data, wherein the recruitment data comprises resume delivery behavior data and interview behavior data; according to resume delivery behavior data and interview behavior data, determining association relations among talent resume, job description and interview records; and determining the synonym relation among the talent resume, the job description and the talent keywords corresponding to the interview records according to the association relation.
10. A resume search system, comprising:
the resume search device according to claim 8 above, and the resume search device according to claim 9 above.
11. A resume delivery method, comprising:
receiving a resume delivery request aiming at a target talent resume and sent by a client;
determining first talent keywords of a plurality of job descriptions to be delivered; determining a second talent keyword of the target talent resume;
determining the first talent keyword matched with the second talent keyword according to a pre-generated synonym dictionary;
delivering the target talent resume to a job description corresponding to the matched first talent keyword;
the synonym dictionary is generated by the following steps: determining recruitment data, wherein the recruitment data comprises resume delivery behavior data and interview behavior data; according to resume delivery behavior data and interview behavior data, determining association relations among talent resume, job description and interview records; and determining the synonym relation among the talent resume, the job description and the talent keywords corresponding to the interview records according to the association relation.
12. A resume delivery device, comprising:
the request receiving unit is used for receiving a resume delivery request aiming at the target talent resume, which is sent by the client;
the first talent keyword determining unit is used for determining first talent keywords of the plurality of job descriptions to be delivered;
a second talent keyword determining unit, configured to determine a second talent keyword of the target talent resume;
a talent keyword matching unit, configured to determine, according to a pre-generated synonym dictionary, the first talent keyword that matches the second talent keyword;
the resume delivery unit is used for delivering the target talent resume to the job description corresponding to the matched first talent keyword;
the synonym dictionary is generated by the following steps: determining recruitment data, wherein the recruitment data comprises resume delivery behavior data and interview behavior data; according to resume delivery behavior data and interview behavior data, determining association relations among talent resume, job description and interview records; and determining the synonym relation among the talent resume, the job description and the talent keywords corresponding to the interview records according to the association relation.
13. A resume delivery system, comprising:
the resume delivery apparatus of claim 12, and a resume delivery request means;
the resume delivery request device is used for sending a resume delivery request aiming at the target talent resume to the resume delivery device.
14. A synonym dictionary construction method, comprising:
acquiring the association relationship between talent resume, job description and interview record according to recruitment data;
extracting talent keywords from the talent resume, the job description and the interview record;
and determining the synonym relation between the talent resume, the job description and the talent keywords corresponding to the interview records according to the association relation.
15. The method of claim 14, wherein the step of providing the first information comprises,
determining the synonym relationship between the talent resume, the job description and the talent keywords corresponding to the interview records according to the association relationship, wherein the synonym relationship comprises the following steps:
determining a talent keyword word pair between the talent resume, the job description and the interview record;
and determining the word pairs with the synonym relationship according to the occurrence times of the word pairs.
16. The method of claim 14, wherein the step of providing the first information comprises,
extracting talent keywords from the job description includes:
acquiring talent resume which is successfully recruited and corresponds to the job description;
and taking the talent resume talent keywords as the talent keywords of the job description.
17. The method of claim 14, wherein the extracting talent keywords from the talent resume, job description, and interview record comprises:
and extracting keywords contained in the recruitment domain dictionary from the talent resume, the job description and the interview record through a keyword extraction algorithm, wherein the keywords are used as talent keywords corresponding to the talent resume, the job description and the interview record.
18. A synonym dictionary construction device, comprising:
the association relation acquisition unit is used for acquiring association relations among talent resume, job description and interview record according to recruitment data;
the talent keyword extraction unit is used for extracting talent keywords from the talent resume, the job description and the interview record;
and the synonym relation determining unit is used for determining the synonym relation between the talent resume, the job description and the talent keywords corresponding to the interview records according to the association relation.
19. An electronic device, comprising:
a processor; and
a memory for storing a program for implementing the synonym dictionary construction method, the apparatus being powered on and executing the program of the synonym dictionary construction method by the processor, and performing the steps of: acquiring the association relationship between talent resume, job description and interview record according to recruitment data; extracting talent keywords from the talent resume, the job description and the interview record; and determining the synonym relation between the talent resume, the job description and the talent keywords corresponding to the interview records according to the association relation.
20. An electronic device, comprising:
a processor; and
and the memory is used for storing a program for realizing the resume searching method, and after the device is electrified and runs the program of the resume searching method through the processor, the following steps are executed: receiving a talent resume screening request aiming at target position description and sent by a client; determining a first talent keyword of the target position description; determining second talent keywords of a plurality of talent resume to be screened; determining a second talent keyword matched with the first talent keyword according to a pre-generated synonym dictionary; the talent resume corresponding to the matched second talent keyword is returned to the client;
The synonym dictionary is generated by the following steps: determining recruitment data, wherein the recruitment data comprises resume delivery behavior data and interview behavior data; according to resume delivery behavior data and interview behavior data, determining association relations among talent resume, job description and interview records; and determining the synonym relation among the talent resume, the job description and the talent keywords corresponding to the interview records according to the association relation.
21. An electronic device, comprising:
a processor; and
the memory is used for storing a program for realizing the resume delivery method, and after the device is electrified and the program of the resume delivery method is run by the processor, the following steps are executed: receiving a resume delivery request aiming at a target talent resume and sent by a client; determining first talent keywords of a plurality of job descriptions to be delivered; determining a second talent keyword of the target talent resume; determining the first talent keyword matched with the second talent keyword according to a pre-generated synonym dictionary; delivering the target talent resume to a job description corresponding to the matched first talent keyword;
The synonym dictionary is generated by the following steps: determining recruitment data, wherein the recruitment data comprises resume delivery behavior data and interview behavior data; according to resume delivery behavior data and interview behavior data, determining association relations among talent resume, job description and interview records; and determining the synonym relation among the talent resume, the job description and the talent keywords corresponding to the interview records according to the association relation.
CN201811075813.1A 2018-09-14 2018-09-14 Resume searching/delivering method, device and system and electronic equipment Active CN110909120B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811075813.1A CN110909120B (en) 2018-09-14 2018-09-14 Resume searching/delivering method, device and system and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811075813.1A CN110909120B (en) 2018-09-14 2018-09-14 Resume searching/delivering method, device and system and electronic equipment

Publications (2)

Publication Number Publication Date
CN110909120A CN110909120A (en) 2020-03-24
CN110909120B true CN110909120B (en) 2023-05-02

Family

ID=69812461

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811075813.1A Active CN110909120B (en) 2018-09-14 2018-09-14 Resume searching/delivering method, device and system and electronic equipment

Country Status (1)

Country Link
CN (1) CN110909120B (en)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111598462B (en) * 2020-05-19 2022-07-12 厦门大学 Resume screening method for campus recruitment
CN111815258A (en) * 2020-06-01 2020-10-23 五八到家有限公司 Human resource matching method, device, equipment and storage medium
CN112559726A (en) * 2020-12-22 2021-03-26 深圳市易博天下科技有限公司 Resume information filtering method, model training method, device, equipment and medium
CN113191436A (en) * 2021-05-07 2021-07-30 广州博士信息技术研究院有限公司 Talent image tag identification method and system and cloud platform
CN114943517A (en) * 2022-05-27 2022-08-26 深圳市君润众乐企业管理咨询有限公司 Electronic recruitment matching method and system based on Internet of things and storage medium
JP7358678B1 (en) * 2023-08-16 2023-10-10 株式会社ビズリーチ Search support system, search support method and program
CN118379034B (en) * 2024-06-20 2024-10-11 广东南粤锦程数字科技有限公司 Intelligent recruitment method based on artificial intelligence and related device

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101576916A (en) * 2009-06-18 2009-11-11 清华大学 Method and device for obtaining synonyms
CN103198083A (en) * 2011-09-29 2013-07-10 波音公司 System and method for identifying a qualified candidate
CN105893641A (en) * 2016-07-01 2016-08-24 中国传媒大学 Job recommending method
CN106408249A (en) * 2016-08-31 2017-02-15 五八同城信息技术有限公司 Resume and position matching method and device
CN106569807A (en) * 2016-06-30 2017-04-19 伯禄(上海)商务咨询有限公司 Application of automatic matching method to network job-hunting and recruitment platform
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
CN107967256A (en) * 2017-11-14 2018-04-27 北京拉勾科技有限公司 Term weighing prediction model generation method, position recommend method and computing device

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8117024B2 (en) * 2008-05-01 2012-02-14 My Perfect Gig, Inc. System and method for automatically processing candidate resumes and job specifications expressed in natural language into a normalized form using frequency analysis
US20150269526A1 (en) * 2014-03-18 2015-09-24 Nxmoov Llc Method and system for matching a jobseeker and a job provider

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101576916A (en) * 2009-06-18 2009-11-11 清华大学 Method and device for obtaining synonyms
CN103198083A (en) * 2011-09-29 2013-07-10 波音公司 System and method for identifying a qualified candidate
CN106569807A (en) * 2016-06-30 2017-04-19 伯禄(上海)商务咨询有限公司 Application of automatic matching method to network job-hunting and recruitment platform
CN105893641A (en) * 2016-07-01 2016-08-24 中国传媒大学 Job recommending method
CN106408249A (en) * 2016-08-31 2017-02-15 五八同城信息技术有限公司 Resume and position matching method and device
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
CN107967256A (en) * 2017-11-14 2018-04-27 北京拉勾科技有限公司 Term weighing prediction model generation method, position recommend method and computing device

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
张俊峰 ; 魏瑞斌 ; .国内招聘类网站的数据类岗位人才需求特征挖掘.情报杂志.2018,(06),全文. *
陈玫 ; 蒙祖强 ; .面向医学知识的中文分词词典设计与实现.大众科技.2010,(11),全文. *

Also Published As

Publication number Publication date
CN110909120A (en) 2020-03-24

Similar Documents

Publication Publication Date Title
CN110909120B (en) Resume searching/delivering method, device and system and electronic equipment
CN109885773B (en) Personalized article recommendation method, system, medium and equipment
US11514235B2 (en) Information extraction from open-ended schema-less tables
US10896214B2 (en) Artificial intelligence based-document processing
CN106649818B (en) Application search intention identification method and device, application search method and server
US12026194B1 (en) Query modification based on non-textual resource context
US8073877B2 (en) Scalable semi-structured named entity detection
US8892554B2 (en) Automatic word-cloud generation
CN111753198A (en) Information recommendation method and device, electronic equipment and readable storage medium
CN109508458B (en) Legal entity identification method and device
US20090112830A1 (en) System and methods for searching images in presentations
CN110147425B (en) Keyword extraction method and device, computer equipment and storage medium
CN110968684A (en) Information processing method, device, equipment and storage medium
US20140379719A1 (en) System and method for tagging and searching documents
US11640420B2 (en) System and method for automatic summarization of content with event based analysis
CN111737443B (en) Answer text processing method and device and key text determining method
US9779363B1 (en) Disambiguating personal names
CN107368489B (en) Information data processing method and device
US20190197184A1 (en) Constructing content based on multi-sentence compression of source content
WO2015084404A1 (en) Matching of an input document to documents in a document collection
Alexandridis et al. A knowledge-based deep learning architecture for aspect-based sentiment analysis
CN109271624A (en) A kind of target word determines method, apparatus and storage medium
US20230290168A1 (en) Selecting files for intensive text extraction
CN110399431A (en) A kind of incidence relation construction method, device and equipment
CN115328945A (en) Data asset retrieval method, electronic device and computer-readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant