CN111339285A - BP neural network-based enterprise resume screening method and system - Google Patents
BP neural network-based enterprise resume screening method and system Download PDFInfo
- Publication number
- CN111339285A CN111339285A CN202010100084.1A CN202010100084A CN111339285A CN 111339285 A CN111339285 A CN 111339285A CN 202010100084 A CN202010100084 A CN 202010100084A CN 111339285 A CN111339285 A CN 111339285A
- Authority
- CN
- China
- Prior art keywords
- resume
- job
- neural network
- keyword set
- layer
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
- G06Q10/1053—Employment or hiring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/107—Computer-aided management of electronic mailing [e-mailing]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Computer Hardware Design (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an enterprise resume screening method and system based on a BP neural network, wherein the method comprises the following steps: setting a plurality of first keywords to form a first keyword set according to the post requirements; extracting second keywords in the job-seeking resume, and calculating the similarity between a second keyword set consisting of the second keywords and the first keyword set; extracting personal basic information and a personal mailbox address of a job seeker in a job seeker resume with similarity higher than a preset similarity threshold, and sending a standard resume to a personal mailbox of the job seeker, wherein the standard resume comprises a capability survey questionnaire; receiving the fed back standard resume, distributing an initial weight value to each ability index, and setting a score for each ability mastery degree; establishing a three-layer BP neural network model; training the three-layer BP neural network model; and screening the standard resume which is not manually screened by adopting the trained three-layer BP neural network model. The method and the device have the advantages that the obtained information is more accurate, and the accuracy of resume screening is higher.
Description
Technical Field
The invention relates to the technical field of data processing. More specifically, the invention relates to an enterprise resume screening method and system based on a BP neural network.
Background
With the continuous development of internet technology, the talent recruitment mode of receiving the resume of application through the e-mail is continuously favored by each recruiter. At present, a recruiter generally publishes a recruiting mailbox for receiving an application resume in a released recruiting inspiring, so that the recruiter can directly send a resume mail to a recruiting mailbox according to the recruiting mailbox published by a recruiting unit, then the recruiter manually screens the resume mails received in the recruiting mailbox, and the excellent application resume screened from the recruiting mailbox is forwarded to an actual employment department.
However, the process of manually screening resumes by recruiters is time-consuming and mental, so some programs for automatically screening resumes have appeared in the market, for example, a program for screening resumes by extracting keywords in resumes and calculating similarity to the demand of recruiting positions is adopted, but the program can only perform quantitative screening, that is, only can judge whether job seekers have the capacity required by positions, but cannot judge the mastery degree of the capacity required by the positions, so that the screening accuracy of resumes is limited.
Disclosure of Invention
An object of the present invention is to solve at least the above problems and to provide at least the advantages described later.
To achieve these objects and other advantages in accordance with the present invention, there is provided an enterprise resume screening method based on a BP neural network, comprising:
setting a plurality of first keywords to form a first keyword set according to the post requirements;
extracting second keywords in the job hunting resume, calculating the similarity between a second keyword set consisting of the second keywords in the job hunting resume and the first keyword set, and selecting the job hunting resume with the similarity higher than a preset similarity threshold;
extracting personal basic information and a personal mailbox address of a job seeker in a job hunting resume with similarity higher than a preset similarity threshold, respectively archiving the personal basic information and the personal mailbox address, and then sending a standard resume to a personal mailbox of the job seeker, wherein the standard resume comprises a capacity survey questionnaire, each question in the capacity survey questionnaire relates to a capacity index, and a plurality of answers are set for each question to respectively correspond to different capacity mastery degrees;
receiving the fed back standard resume, distributing an initial weight value to each ability index, and setting a score for each ability mastery degree;
establishing a three-layer BP neural network model, setting the neuron number of an input layer according to the capacity index number, taking the score of each capacity mastery degree as input data of each neuron of the input layer, setting a unique neuron of an output layer, outputting a preset value a by the output layer if the recruitment requirement is met, and outputting a preset value b by the output layer if the recruitment requirement is not met;
training the three-layer BP neural network model by adopting the manually screened M standard resumes meeting the recruitment requirement and the N standard resumes not meeting the recruitment requirement as training samples until the qualification rate of the standard resumes screened by the three-layer BP neural network model reaches a preset value;
and screening the standard resume which is not manually screened by adopting the trained three-layer BP neural network model.
Preferably, the method for extracting the second keyword in the job resume comprises the following steps: and segmenting the job-seeking resume to obtain a job-seeking resume vocabulary set, and selecting i vocabularies with the minimum hash value in the job-seeking resume vocabulary set as second keywords of the job-seeking resume.
Preferably, the method for calculating the similarity between the second keyword set and the first keyword set includes: and comparing the second keyword set with the first keyword set, counting the number of the first keywords appearing in the second keyword set, and calculating the percentage of the number of the first keywords appearing in the second keyword set in the total vocabulary of the first keyword set and the second keyword set.
Preferably, the number of hidden layer neurons of the three-layer BP neural network model is obtained by kolmogorov theorem, and the hidden layer transfer function is a hardlim function.
The invention also provides an enterprise resume screening system based on the BP neural network, which comprises the following steps:
the post requirement acquisition module is used for setting a plurality of first keywords to form a first keyword set according to the post requirement;
the resume primary selection module is used for extracting second keywords in the job-seeking resume, calculating the similarity between a second keyword set consisting of the second keywords in the job-seeking resume and the first keyword set, and selecting the job-seeking resume with the similarity higher than a preset similarity threshold;
the standard resume sending module is used for extracting personal basic information and a personal mailbox address of a job seeker in a job hunting resume with similarity higher than a preset similarity threshold, respectively archiving the personal basic information and the personal mailbox address, and then sending a standard resume to a personal mailbox of the job seeker, wherein the standard resume comprises a capacity survey questionnaire, each question in the capacity survey questionnaire relates to a capacity index, and a plurality of answers are set for each question respectively corresponding to different capacity mastery degrees;
the standard resume receiving module is used for receiving the fed back standard resumes, distributing an initial weight value to each ability index and setting a score for each ability mastery degree;
the BP neural network module is used for establishing a three-layer BP neural network model, setting the number of neurons in an input layer according to the number of capability indexes, taking the score of each capability mastery degree as input data of each neuron in the input layer, setting a unique neuron in an output layer, outputting a preset value a by the output layer if the recruitment requirement is met, and outputting a preset value b by the output layer if the recruitment requirement is not met;
the training module is used for training the three-layer BP neural network model by adopting the manually screened M standard resumes meeting the recruitment requirement and the N standard resumes not meeting the recruitment requirement as training samples until the qualification rate of the standard resumes screened by the three-layer BP neural network model reaches a preset value
And the resume refining module is used for screening the standard resumes which are not manually screened by adopting the trained three-layer BP neural network model.
Preferably, the method for extracting the second keyword in the job-seeking resume in the resume initial selection module comprises the following steps: and segmenting the job-seeking resume to obtain a job-seeking resume vocabulary set, and selecting i vocabularies with the minimum hash value in the job-seeking resume vocabulary set as second keywords of the job-seeking resume.
Preferably, the method for calculating the similarity between the second keyword set and the first keyword set in the resume initial selection module includes: and comparing the second keyword set with the first keyword set, counting the number of the first keywords appearing in the second keyword set, and calculating the percentage of the number of the first keywords appearing in the second keyword set in the total vocabulary of the first keyword set and the second keyword set.
Preferably, the number of hidden layer neurons of the three-layer BP neural network model in the BP neural network module is obtained by kolmogorov theorem, and the hidden layer transfer function is a hardlim function.
The present invention also provides an electronic device, comprising: the system comprises at least one processor and a memory communicatively connected with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to cause the at least one processor to execute the enterprise resume screening method.
The invention also provides a storage medium, which stores a computer program, and when the program is executed by a processor, the method for screening the enterprise resume is realized.
The invention at least comprises the following beneficial effects: the job seeker meeting the post requirement is obtained through the first resume screening, the ability mastering degree of the job seeker meeting the post requirement can be obtained through the second resume screening, and compared with the existing resume screening method, the method provided by the invention is more accurate in information obtained and higher in accuracy of resume screening.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention.
Drawings
FIG. 1 is a flow chart of a method for screening enterprise resumes according to the present invention;
fig. 2 is a schematic structural diagram of the enterprise resume screening system according to the present invention.
Detailed Description
The present invention is further described in detail below with reference to the attached drawings so that those skilled in the art can implement the invention by referring to the description text.
It should be noted that in the description of the present invention, the terms "lateral", "longitudinal", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
As shown in fig. 1, the present invention provides an enterprise resume screening method based on a BP neural network, which includes:
s101, setting a plurality of first keywords to form a first keyword set according to the post requirements;
the first keyword can be provided by the employing unit, so that the first keyword can be closer to the actual recruitment requirement of the employing unit, and the accuracy of resume screening can be higher. If no useless person unit can be provided, the keyword can be extracted from the existing recruitment position requirement of the same or similar position, for example, the position requirement of a JAVA engineer of a certain company is ' computer related professional and past academic records, Java development work experience for more than 1 year, Restful API, HTTP protocol and the like are familiar, Java is mastered, J2ee related technology and system architecture are familiar, development of mainstream Web frameworks such as Spring and the like is mastered, MySQL, sqlserver and mongodb one or more databases are familiar, configuration, maintenance and performance optimization are familiar, large Internet project development experience is preferred ', the position requirement of a JAVA engineer of another company is ' profound and past academic records, computer related professional, JAVA basic knowledge is mastered, technical frameworks such as Spring, Spring boot, Spring MVC, Mybatis and the like are familiar with relational databases such as SQL, Oracle databases, corresponding database optimization and SQL learning, reading and writing and separating, the common post requirement key words of two JAVA engineers are 'computer related specialty, Spring, MySQL, MongoDB, database', which are generalized and can not accurately capture the actual recruitment requirement of a human unit.
S102, extracting second keywords in the job hunting resume, calculating the similarity between a second keyword set consisting of the second keywords in the job hunting resume and the first keyword set, and selecting the job hunting resume with the similarity higher than a preset similarity threshold;
the method for extracting the second keyword in the job searching resume comprises the following steps: the method comprises the steps of segmenting a job-hunting resume to obtain a job-hunting resume vocabulary set, selecting i vocabularies with the minimum hash value in the job-hunting resume vocabulary set as second keywords of the job-hunting resume, wherein the I vocabularies are large in vocabulary amount in a common job-hunting resume, if the I vocabularies are compared with the first keywords one by one, the calculated amount is large, dimension reduction processing is carried out on the vocabularies of the job-hunting resume by using a minimum hash value algorithm to obtain the second keyword set, and the calculated amount can be reduced under the condition that the similarity between information contained in the job-hunting resume and the first keywords is not changed.
The similarity calculation method of the second keyword set and the first keyword set comprises the following steps: and comparing the second keyword set with the first keyword set, counting the number of the first keywords appearing in the second keyword set, and calculating the percentage of the number of the first keywords appearing in the second keyword set in the total vocabulary of the first keyword set and the second keyword set.
S103, extracting personal basic information and a personal mailbox address of a job seeker in a job hunting resume with similarity higher than a preset similarity threshold, respectively archiving the personal basic information and the personal mailbox address, and then sending a standard resume to a personal mailbox of the job seeker, wherein the standard resume comprises a capacity survey questionnaire, each question in the capacity survey questionnaire relates to a capacity index, and a plurality of answers are set for each question respectively corresponding to different capacity mastery degrees;
the competency survey questionnaire is a test question compiled by a person unit according to actual requirements, and because the job hunting resume self-compiled by the job seeker has various layouts and contents, the test question cannot completely correspond to the requirement of a recruitment post of the person unit, and the person unit cannot see the actual competency level of the job seeker from the job hunting resume, so that the test question of the competency survey questionnaire can properly and deeply examine the competency index to observe the specific competency mastering degree of the job seeker, such as English test question for examining the English degree of the job seeker, programming knowledge test question for examining whether the programming base of the job seeker is real, mathematics test question for examining the logical thinking ability of the job seeker and the like, and some psychological problems and interpersonal relationship processing problems can be set.
The answer time of the standard resume is preferably controlled within a certain range, and after the standard resume is sent to the personal mailbox of the job seeker, the person using unit cannot control the answer time, so that the standard resume is preferably sent to the personal mailbox of the job seeker and hung on the person using unit official network, and thus, a timing tool can be attached to the standard resume.
S104, receiving the fed back standard resume, distributing an initial weight value to each ability index, and setting a score for each ability mastery degree;
the initial weight value of each capability index is distributed by a human unit, the sum of the weight values of all the capability indexes is 1, and the specific distribution scheme is determined according to the attention degree of the human unit to the capability indexes. When the score is set for each ability mastery degree, some objective questions only have a unique correct option, so the correct option can be set to have a score of 1, the incorrect option can be set to have a score of 0, and some subjective questions have no unique correct option, so the score can be set to be 1, 2 or 3 according to the adaptation degree of the answer, and the like.
The standard resume receiving feedback here can set a cutoff time to avoid inefficient work caused by extended recruitment time.
S105, establishing a three-layer BP neural network model, setting the number of neurons in an input layer according to the number of capability indexes, taking the score of each capability mastery degree as input data of each neuron in the input layer, setting a unique neuron in an output layer, outputting a preset value a by the output layer if the recruitment requirement is met, and outputting a preset value b by the output layer if the recruitment requirement is not met;
the number of hidden layer neurons of the three-layer BP neural network model is obtained by the kolmogorov theorem, the hidden layer transfer function is a hardlim function, and the kolmogorov theorem and the hardlim function are both in the prior art and are not described herein again.
S106, training the three-layer BP neural network model by adopting the manually screened M standard resumes meeting the recruitment requirement and the N standard resumes not meeting the recruitment requirement as training samples until the qualification rate of the standard resumes screened by the three-layer BP neural network model reaches a preset value;
and S107, screening the standard resume which is not manually screened by adopting the trained three-layer BP neural network model.
In the embodiment, the job seeker meeting the post requirement is obtained through the first resume screening, the ability mastering degree of the job seeker meeting the post requirement can be obtained through the second resume screening, and compared with the conventional resume screening method, the method provided by the invention has the advantages that the obtained information is more accurate, and the accuracy of resume screening is higher.
As shown in fig. 2, the present invention further provides an enterprise resume screening system based on a BP neural network, which includes:
the post requirement acquisition module is used for setting a plurality of first keywords to form a first keyword set according to the post requirement;
the resume primary selection module is used for extracting second keywords in the job-seeking resume, calculating the similarity between a second keyword set consisting of the second keywords in the job-seeking resume and the first keyword set, and selecting the job-seeking resume with the similarity higher than a preset similarity threshold;
the method for extracting the second keyword in the job-seeking resume in the resume initial selection module comprises the following steps: and segmenting the job-seeking resume to obtain a job-seeking resume vocabulary set, and selecting i vocabularies with the minimum hash value in the job-seeking resume vocabulary set as second keywords of the job-seeking resume.
The similarity calculation method of the second keyword set and the first keyword set in the resume initial selection module comprises the following steps: and comparing the second keyword set with the first keyword set, counting the number of the first keywords appearing in the second keyword set, and calculating the percentage of the number of the first keywords appearing in the second keyword set in the total vocabulary of the first keyword set and the second keyword set.
The standard resume sending module is used for extracting personal basic information and a personal mailbox address of a job seeker in a job hunting resume with similarity higher than a preset similarity threshold, respectively archiving the personal basic information and the personal mailbox address, and then sending a standard resume to a personal mailbox of the job seeker, wherein the standard resume comprises a capacity survey questionnaire, each question in the capacity survey questionnaire relates to a capacity index, and a plurality of answers are set for each question respectively corresponding to different capacity mastery degrees;
the standard resume receiving module is used for receiving the fed back standard resumes, distributing an initial weight value to each ability index and setting a score for each ability mastery degree;
the BP neural network module is used for establishing a three-layer BP neural network model, setting the number of neurons in an input layer according to the number of capability indexes, taking the score of each capability mastery degree as input data of each neuron in the input layer, setting a unique neuron in an output layer, outputting a preset value a by the output layer if the recruitment requirement is met, and outputting a preset value b by the output layer if the recruitment requirement is not met;
the number of hidden layer neurons of a three-layer BP neural network model in the BP neural network module is obtained by kolmogorov theorem, and a hidden layer transfer function is a hardlim function.
The training module is used for training the three-layer BP neural network model by adopting the manually screened M standard resumes meeting the recruitment requirement and the N standard resumes not meeting the recruitment requirement as training samples until the qualification rate of the standard resumes screened by the three-layer BP neural network model reaches a preset value
And the resume refining module is used for screening the standard resumes which are not manually screened by adopting the trained three-layer BP neural network model.
The present invention also provides an electronic device, comprising: the system comprises at least one processor and a memory communicatively connected with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to cause the at least one processor to execute the enterprise resume screening method.
The invention also provides a storage medium, which stores a computer program, and when the program is executed by a processor, the method for screening the enterprise resume is realized.
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable in various fields of endeavor to which the invention pertains, and further modifications may readily be made by those skilled in the art, it being understood that the invention is not limited to the details shown and described herein without departing from the general concept defined by the appended claims and their equivalents.
Claims (10)
1. The enterprise resume screening method based on the BP neural network is characterized by comprising the following steps:
setting a plurality of first keywords to form a first keyword set according to the post requirements;
extracting second keywords in the job hunting resume, calculating the similarity between a second keyword set consisting of the second keywords in the job hunting resume and the first keyword set, and selecting the job hunting resume with the similarity higher than a preset similarity threshold;
extracting personal basic information and a personal mailbox address of a job seeker in a job hunting resume with similarity higher than a preset similarity threshold, respectively archiving the personal basic information and the personal mailbox address, and then sending a standard resume to a personal mailbox of the job seeker, wherein the standard resume comprises a capacity survey questionnaire, each question in the capacity survey questionnaire relates to a capacity index, and a plurality of answers are set for each question to respectively correspond to different capacity mastery degrees;
receiving the fed back standard resume, distributing an initial weight value to each ability index, and setting a score for each ability mastery degree;
establishing a three-layer BP neural network model, setting the neuron number of an input layer according to the capacity index number, taking the score of each capacity mastery degree as input data of each neuron of the input layer, setting a unique neuron of an output layer, outputting a preset value a by the output layer if the recruitment requirement is met, and outputting a preset value b by the output layer if the recruitment requirement is not met;
training the three-layer BP neural network model by adopting the manually screened M standard resumes meeting the recruitment requirement and the N standard resumes not meeting the recruitment requirement as training samples until the qualification rate of the standard resumes screened by the three-layer BP neural network model reaches a preset value;
and screening the standard resume which is not manually screened by adopting the trained three-layer BP neural network model.
2. The method for screening resumes of enterprises based on the BP neural network as claimed in claim 1, wherein the method for extracting the second keyword in the job-seeking resume comprises: and segmenting the job-seeking resume to obtain a job-seeking resume vocabulary set, and selecting i vocabularies with the minimum hash value in the job-seeking resume vocabulary set as second keywords of the job-seeking resume.
3. The method for screening resumes of enterprises based on the BP neural network as claimed in claim 1, wherein the method for calculating the similarity between the second keyword set and the first keyword set comprises: and comparing the second keyword set with the first keyword set, counting the number of the first keywords appearing in the second keyword set, and calculating the percentage of the number of the first keywords appearing in the second keyword set in the total vocabulary of the first keyword set and the second keyword set.
4. The enterprise resume screening method based on the BP neural network as claimed in claim 1, wherein the number of hidden layer neurons of the three-layer BP neural network model is obtained by kolmogorov theorem, and the hidden layer transfer function is hardlim function.
5. An enterprise resume screening system based on a BP neural network is characterized by comprising:
the post requirement acquisition module is used for setting a plurality of first keywords to form a first keyword set according to the post requirement;
the resume primary selection module is used for extracting second keywords in the job-seeking resume, calculating the similarity between a second keyword set consisting of the second keywords in the job-seeking resume and the first keyword set, and selecting the job-seeking resume with the similarity higher than a preset similarity threshold;
the standard resume sending module is used for extracting personal basic information and a personal mailbox address of a job seeker in a job hunting resume with similarity higher than a preset similarity threshold, respectively archiving the personal basic information and the personal mailbox address, and then sending a standard resume to a personal mailbox of the job seeker, wherein the standard resume comprises a capacity survey questionnaire, each question in the capacity survey questionnaire relates to a capacity index, and a plurality of answers are set for each question respectively corresponding to different capacity mastery degrees;
the standard resume receiving module is used for receiving the fed back standard resumes, distributing an initial weight value to each ability index and setting a score for each ability mastery degree;
the BP neural network module is used for establishing a three-layer BP neural network model, setting the number of neurons in an input layer according to the number of capability indexes, taking the score of each capability mastery degree as input data of each neuron in the input layer, setting a unique neuron in an output layer, outputting a preset value a by the output layer if the recruitment requirement is met, and outputting a preset value b by the output layer if the recruitment requirement is not met;
the training module is used for training the three-layer BP neural network model by adopting the manually screened M standard resumes meeting the recruitment requirement and the N standard resumes not meeting the recruitment requirement as training samples until the qualification rate of the standard resumes screened by the three-layer BP neural network model reaches a preset value
And the resume refining module is used for screening the standard resumes which are not manually screened by adopting the trained three-layer BP neural network model.
6. The system of claim 5, wherein the method for extracting the second keyword from the job-seeking resume in the resume initiative module comprises: and segmenting the job-seeking resume to obtain a job-seeking resume vocabulary set, and selecting i vocabularies with the minimum hash value in the job-seeking resume vocabulary set as second keywords of the job-seeking resume.
7. The enterprise resume screening system based on the BP neural network as claimed in claim 5, wherein the similarity calculation method of the second keyword set and the first keyword set in the resume primary selection module comprises: and comparing the second keyword set with the first keyword set, counting the number of the first keywords appearing in the second keyword set, and calculating the percentage of the number of the first keywords appearing in the second keyword set in the total vocabulary of the first keyword set and the second keyword set.
8. The enterprise resume screening system based on the BP neural network as claimed in claim 5, wherein the number of hidden layer neurons of the three-layer BP neural network model in the BP neural network module is obtained by kolmogorov theorem, and the hidden layer transfer function is hardlim function.
9. An electronic device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method of any of claims 1-4.
10. Storage medium on which a computer program is stored which, when being executed by a processor, carries out the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010100084.1A CN111339285B (en) | 2020-02-18 | 2020-02-18 | BP neural network-based enterprise resume screening method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010100084.1A CN111339285B (en) | 2020-02-18 | 2020-02-18 | BP neural network-based enterprise resume screening method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111339285A true CN111339285A (en) | 2020-06-26 |
| CN111339285B CN111339285B (en) | 2023-05-26 |
Family
ID=71185439
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010100084.1A Active CN111339285B (en) | 2020-02-18 | 2020-02-18 | BP neural network-based enterprise resume screening method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111339285B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111768175A (en) * | 2020-06-28 | 2020-10-13 | 龙马智芯（珠海横琴）科技有限公司 | Resume screening method and device, screening equipment and readable storage medium |
| CN113641794A (en) * | 2021-08-17 | 2021-11-12 | 中国民生银行股份有限公司 | Resume text evaluation method and device and server |
| CN114529105A (en) * | 2022-03-24 | 2022-05-24 | 江苏真鹿科技有限公司 | Engine crankshaft high-temperature performance analysis processing method based on BP neural network |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103634420A (en) * | 2013-11-22 | 2014-03-12 | 北京极客优才科技有限公司 | Resume e-mail screening system and method |
| US20190102704A1 (en) * | 2017-10-02 | 2019-04-04 | Wei Liu | Machine learning systems for ranking job candidate resumes |
| CN109635288A (en) * | 2018-11-29 | 2019-04-16 | 东莞理工学院 | A kind of resume abstracting method based on deep neural network |
| CN109978510A (en) * | 2019-04-02 | 2019-07-05 | 北京网聘咨询有限公司 | Campus recruiting management system and method |
| US20190220824A1 (en) * | 2018-01-12 | 2019-07-18 | Wei Liu | Machine learning systems for matching job candidate resumes with job requirements |
| CN110263818A (en) * | 2019-05-24 | 2019-09-20 | 平安科技（深圳）有限公司 | Method, apparatus, terminal and the computer readable storage medium of resume selection |
| US20190317966A1 (en) * | 2018-04-12 | 2019-10-17 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for talent-post matching and computer readable storage medium |
-
2020
- 2020-02-18 CN CN202010100084.1A patent/CN111339285B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103634420A (en) * | 2013-11-22 | 2014-03-12 | 北京极客优才科技有限公司 | Resume e-mail screening system and method |
| US20190102704A1 (en) * | 2017-10-02 | 2019-04-04 | Wei Liu | Machine learning systems for ranking job candidate resumes |
| US20190220824A1 (en) * | 2018-01-12 | 2019-07-18 | Wei Liu | Machine learning systems for matching job candidate resumes with job requirements |
| US20190317966A1 (en) * | 2018-04-12 | 2019-10-17 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for talent-post matching and computer readable storage medium |
| CN109635288A (en) * | 2018-11-29 | 2019-04-16 | 东莞理工学院 | A kind of resume abstracting method based on deep neural network |
| CN109978510A (en) * | 2019-04-02 | 2019-07-05 | 北京网聘咨询有限公司 | Campus recruiting management system and method |
| CN110263818A (en) * | 2019-05-24 | 2019-09-20 | 平安科技（深圳）有限公司 | Method, apparatus, terminal and the computer readable storage medium of resume selection |
Non-Patent Citations (1)
| Title |
|---|
| 张开智等: "基于BP神经网络的应聘人员与岗位匹配度模型设计与应用", 《电子世界》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111768175A (en) * | 2020-06-28 | 2020-10-13 | 龙马智芯（珠海横琴）科技有限公司 | Resume screening method and device, screening equipment and readable storage medium |
| CN111768175B (en) * | 2020-06-28 | 2021-04-23 | 龙马智芯（珠海横琴）科技有限公司 | Resume screening method and device, screening equipment and readable storage medium |
| CN113641794A (en) * | 2021-08-17 | 2021-11-12 | 中国民生银行股份有限公司 | Resume text evaluation method and device and server |
| CN114529105A (en) * | 2022-03-24 | 2022-05-24 | 江苏真鹿科技有限公司 | Engine crankshaft high-temperature performance analysis processing method based on BP neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111339285B (en) | 2023-05-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kurtz | Value-added and student growth percentile models: What drives differences in estimated classroom effects? | |
| Alblawi et al. | Big data and learning analytics in higher education: Demystifying variety, acquisition, storage, NLP and analytics | |
| US11238394B2 (en) | Assessment-based qualified candidate delivery | |
| US11232380B2 (en) | Mapping assessment results to levels of experience | |
| CN111339285A (en) | BP neural network-based enterprise resume screening method and system | |
| US20200311112A1 (en) | Semantic matching of search terms to results | |
| US20150026083A1 (en) | Generating Connection Map for Intelligent Connections in Enterprises | |
| US11205144B2 (en) | Assessment-based opportunity exploration | |
| CN107391547A (en) | A kind of manpower object data matching process and system | |
| US20200210957A1 (en) | Classification of job titles via machine learning | |
| Georgieff et al. | Artificial intelligence and employment: new cross-country evidence | |
| US20150248648A1 (en) | Scoring model methods and apparatus | |
| US20140122360A1 (en) | Scoring model methods and apparatus | |
| CN111192024A (en) | Method and device for matching human posts based on reinforcement learning | |
| US20200302397A1 (en) | Screening-based opportunity enrichment | |
| US20200311683A1 (en) | Similarity-based sequencing of skills | |
| CN113656687B (en) | Teacher portrait construction method based on teaching and research data | |
| US20190042646A1 (en) | Methods and system for estimating job and career transition capabilities of candidates in a database | |
| Aydoğdu | Educational data mining studies in Turkey: A systematic review | |
| Ali et al. | Prediction MOOC’s for student by using machine learning methods | |
| US20200364275A1 (en) | Characterizing international orientation | |
| US20200311684A1 (en) | Skills-based talent packaging | |
| Ekka | Research methodology and data analysis in humanities & social sciences | |
| US20150248645A1 (en) | Scoring model methods and apparatus | |
| CN114328667A (en) | Construction and system of university department portrait model based on employment data |
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 |