CN107480582A - The detection method and device of resume validity - Google Patents

The detection method and device of resume validity Download PDF

Info

Publication number
CN107480582A
CN107480582A CN201710510236.3A CN201710510236A CN107480582A CN 107480582 A CN107480582 A CN 107480582A CN 201710510236 A CN201710510236 A CN 201710510236A CN 107480582 A CN107480582 A CN 107480582A
Authority
CN
China
Prior art keywords
image
applicant
validity
resume
feature vector
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201710510236.3A
Other languages
Chinese (zh)
Inventor
郭方清
吕庆春
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.)
Beijing 58 Information Technology Co Ltd
Original Assignee
Beijing 58 Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing 58 Information Technology Co Ltd filed Critical Beijing 58 Information Technology Co Ltd
Priority to CN201710510236.3A priority Critical patent/CN107480582A/en
Publication of CN107480582A publication Critical patent/CN107480582A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/178—Human faces, e.g. facial parts, sketches or expressions estimating age from face image; using age information for improving recognition

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Library & Information Science (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • General Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Image Processing (AREA)

Abstract

The embodiment of the present invention provides a kind of detection method and device of resume validity, and this method includes：Applicant's image is obtained, and the fisrt feature information of applicant is extracted from the resume of applicant；Using pre-set image identification technology, the image validity of applicant's image is determined, and the second feature information of applicant is extracted from applicant's image；According to fisrt feature information, second feature information and image validity, the validity of the resume of applicant is determined.For improving detection efficiency and the degree of accuracy of resume validity.

Description

The detection method and device of resume validity
Technical field
The present embodiments relate to information service field, more particularly to a kind of detection method and dress of resume validity Put.
Background technology
With the development of network technology, increasing applicant's selection delivers resume by network, and recruitment side passes through net Network is collected into a large amount of resumes, and the resume to being collected into carries out artificial screening, meets the applicant of positions demand to select and enters Row interview.
However, many false resumes would generally be included in the resume that recruitment side is received by network, answering in false resume The person's of engaging image is usually Vitua limage, and Vitua limage is usually network character image, for example, star image, cartoon image etc..For The false resume of rejecting, it usually needs manually screened, for example, after staff opens resume, judge that applicant's image is No is real image, if it is not, resume then is defined as into false resume, and abandons the false resume.
But the detection by manually carrying out resume validity needs to consume more manpower, and detection speed is slower, enters And it is less efficient to cause resume validity to detect.
The content of the invention
The embodiment of the present invention provides a kind of resume detection method and device, improves the efficiency and standard of the detection of resume validity Exactness.
In a first aspect, the embodiment of the present invention provides a kind of detection method of resume validity, including：
Applicant's image is obtained, and the fisrt feature information of the applicant is extracted from the resume of the applicant；
Using pre-set image identification technology, the image validity of applicant's image is determined, and is schemed from the applicant The second feature information of the applicant is extracted as in；
According to the fisrt feature information, the second feature information and described image validity, the applicant is determined Resume validity.
It is described to utilize pre-set image identification technology in a kind of possible embodiment, determine applicant's image Image validity, including：
Obtain default standard faces characteristic vector；
The first face feature vector is extracted in applicant's image；
Obtain the first similarity of first face feature vector and the standard faces characteristic vector；
According to first similarity, the image validity of applicant's image is determined.
It is described to utilize pre-set image identification technology in alternatively possible embodiment, determine applicant's image Image validity, including：
Obtain default standard faces characteristic vector；
The first face feature vector is extracted in applicant's image；
Obtain the first similarity of first face feature vector and the standard faces characteristic vector；
Applicant's image is matched with the image in pre-set image storehouse, obtain applicant's image with it is described The similarity of each image in pre-set image storehouse；
In applicant's image and the pre-set image storehouse maximum similarity is determined in the similarity of each image；
According to first similarity and the maximum similarity, the image validity of applicant's image is determined.
In alternatively possible embodiment, comprised at least in the fisrt feature information and the second feature information The sex of applicant；The second feature information that the applicant is extracted from applicant's image, including：
The first face feature vector is extracted in applicant's image；
Obtain default standard male face feature vector and default standard women face feature vector；
Obtain the second similarity of first face feature vector and the standard male face feature vector and described The third phase of first face feature vector and the standard women face feature vector is seemingly spent；
According to second similarity and the third phase like spending, it is determined that the applicant extracted from applicant's image Sex.
In alternatively possible embodiment, comprised at least in the fisrt feature information and the second feature information The age bracket of applicant；The second feature information that the applicant is extracted from applicant's image, including：
The first face feature vector is extracted in applicant's image；
Obtain face feature vector corresponding to multiple default age brackets；
Obtain the phase between first face feature vector face feature vector corresponding with each default age bracket Like degree；
According to the phase between first face feature vector face feature vector corresponding with each default age bracket Like degree, the age bracket of applicant extracted from applicant's image is determined in the default age bracket.
In alternatively possible embodiment, the validity of the resume for determining the applicant, including：
The fisrt feature information and the second feature information are contrasted, obtains applicant's image and the resume Matching degree；
According to the image validity of applicant's image and the matching degree, determine the applicant resume it is true Degree.
In alternatively possible embodiment, the image validity according to applicant's image and the matching Degree, the validity of the resume of the applicant is determined, including：
Obtain the second weighted value corresponding to the first weighted value corresponding to image validity and matching degree；
According to described image validity, first weighted value, the matching degree and second weighted value, institute is determined State the validity of the resume of applicant.
In alternatively possible embodiment, after the validity of the resume for determining the applicant, in addition to：
Obtain default resume validity threshold value；
Abandon the resume that resume validity is less than the default resume validity threshold value.
In alternatively possible embodiment, after the image validity for determining applicant's image, also wrap Include：
Obtain pre-set image validity threshold value；
When the image validity of applicant's image is less than the pre-set image validity threshold value, the application is prompted Person resubmits applicant's image.
Second aspect, the embodiment of the present invention provide a kind of detection means of resume validity, including the first acquisition module, the One extraction module, the first determining module, the second extraction module and the second determining module, wherein,
The acquisition module is used for, and obtains applicant's image；
First extraction module is used for, and the fisrt feature letter of the applicant is extracted from the resume of the applicant Breath；
First determining module is used for, and using pre-set image identification technology, determines that the image of applicant's image is true Solidity；
Second extraction module is used for, and the second feature letter of the applicant is extracted from applicant's image Breath；
Second determining module is used for, according to the fisrt feature information, the second feature information and described image Validity, determine the validity of the resume of the applicant.
In a kind of possible embodiment, first determining module is specifically used for：
Obtain default standard faces characteristic vector；
The first face feature vector is extracted in applicant's image；
Obtain the first similarity of first face feature vector and the standard faces characteristic vector；
According to first similarity, the image validity of applicant's image is determined.
In alternatively possible embodiment, first determining module is specifically used for：
Obtain default standard faces characteristic vector；
The first face feature vector is extracted in applicant's image；
Obtain the first similarity of first face feature vector and the standard faces characteristic vector；
Applicant's image is matched with the image in pre-set image storehouse, obtain applicant's image with it is described The similarity of each image in pre-set image storehouse；
In applicant's image and the pre-set image storehouse maximum similarity is determined in the similarity of each image；
According to first similarity and the maximum similarity, the image validity of applicant's image is determined.
In alternatively possible embodiment, comprised at least in the fisrt feature information and the second feature information The sex of applicant；Second extraction module is specifically used for：
The first face feature vector is extracted in applicant's image；
Obtain default standard male face feature vector and default standard women face feature vector；
Obtain the second similarity of first face feature vector and the standard male face feature vector and described The third phase of first face feature vector and the standard women face feature vector is seemingly spent；
According to second similarity and the third phase like spending, it is determined that the applicant extracted from applicant's image Sex.
In alternatively possible embodiment, comprised at least in the fisrt feature information and the second feature information The age bracket of applicant；Second extraction module is specifically used for：
The first face feature vector is extracted in applicant's image；
Obtain face feature vector corresponding to multiple default age brackets；
Obtain the phase between first face feature vector face feature vector corresponding with each default age bracket Like degree；
According to the phase between first face feature vector face feature vector corresponding with each default age bracket Like degree, the age bracket of applicant extracted from applicant's image is determined in the default age bracket.
In alternatively possible embodiment, second determining module includes comparison unit and determining unit, wherein,
The comparison unit is used for, and contrasts the fisrt feature information and the second feature information, obtains the application The matching degree of person's image and the resume；
The determining unit is used for, according to the image validity of applicant's image and the matching degree, it is determined that described The validity of the resume of applicant.
In alternatively possible embodiment, the determining unit is specifically used for：
Obtain the second weighted value corresponding to the first weighted value corresponding to image validity and matching degree；
According to described image validity, first weighted value, the matching degree and second weighted value, institute is determined State the validity of the resume of applicant.
In alternatively possible embodiment, described device also includes the second acquisition module and discard module, wherein,
Second acquisition module is used for, determined in second determining module applicant resume validity it Afterwards, default resume validity threshold value is obtained；
The discard module is used for, and abandons the resume that resume validity is less than the default resume validity threshold value.
In alternatively possible embodiment, described device also includes reminding module, wherein,
Second acquisition module is used for, and the image validity of applicant's image is determined in second determining module Afterwards, pre-set image validity threshold value is obtained；
The reminding module is used for, when the image validity of applicant's image is less than the pre-set image validity threshold During value, the applicant is prompted to resubmit applicant's image.
Resume detection method and device provided in an embodiment of the present invention, applicant's image is obtained, and from the resume of applicant In extract the fisrt feature information of applicant, using pre-set image identification technology, determine the image validity of applicant's image, And the second feature information of applicant is extracted from applicant's image, according to fisrt feature information, second feature information and figure Picture validity, determine the validity of the resume of applicant.Wherein, the image validity of applicant's image is used to reflect that applicant schemes Seem it is no be real facial image, the matching degree of applicant's image and resume is used to reflect the letter that applicant fills in resume Whether breath or applicant's image are true, and then can accurately determine the validity of resume, and said process need not be participated in manually, Can batch the detection for carrying out resume automatic identification and validity, and then improve to the efficiency of resume validity detection and accurate Degree.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are this hairs Some bright embodiments, for those of ordinary skill in the art, without having to pay creative labor, can be with Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the application scenarios schematic diagram of the detection method of resume validity provided in an embodiment of the present invention；
Fig. 2 is the schematic flow sheet of the detection method of resume validity provided in an embodiment of the present invention；
Fig. 3 is the schematic flow sheet one of determination image validity method provided in an embodiment of the present invention；
Fig. 4 is the schematic flow sheet two of determination image validity method provided in an embodiment of the present invention；
Fig. 5 is the structural representation one of the detection means of resume validity provided in an embodiment of the present invention；
Fig. 6 is the structural representation two of the detection means of resume validity provided in an embodiment of the present invention.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is Part of the embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Fig. 1 is the application scenarios schematic diagram of the detection method of resume validity provided in an embodiment of the present invention.Refer to figure 1, including client 101 and server 102.Optionally, client 101 can be installed on mobile phone, apparatus such as computer.Applicant can To deliver resume to recruitment side by client 101, then the server 102 managed by recruitment side is carried out to the resume being collected into Processing.Wherein, the essential information of applicant's image and applicant are comprised at least in the resume of delivery, such as the name of applicant, Sex etc..
After the resume that server 102 receives the transmission of client 101, resume can be stored in resume storehouse, taken Business device 102 can also be analyzed applicant's image in resume and applicant's information, to determine the validity of resume；Enter One step, the resume in resume storehouse can also be ranked up or be screened according to the validity of each resume in resume storehouse. In the application, the validity of resume according to the applicant's image and applicant's information in resume, can be determined, without manually to letter The authenticity screening gone through, and then the degree of accuracy to the detection of resume validity is improved, simultaneously, it is possible to achieve the automatic detection of batch And resume is screened, improve treatment effeciency and the degree of accuracy of resume.
In actual applications, the detection method of resume validity provided in an embodiment of the present invention can also be set applied to terminal Standby, the terminal device can be collected into the resume of applicant by the mode such as scan or take pictures, and utilize terminal device local afterwards The standard information storehouse of setting, detect the image validity and resume validity of applicant, so as to realize resume authenticity it is automatic, Batch detection and screening.
Below, by specific embodiment, the technical scheme shown in the application is described in detail.It should be noted that Several specific embodiments can be combined with each other below, for same or analogous content, no longer carry out in various embodiments Repeat.
Fig. 2 is the schematic flow sheet of the detection method of resume validity provided in an embodiment of the present invention.Fig. 2 is referred to, should Method can include：
S201, applicant's image is obtained, and the fisrt feature information of applicant is extracted from the resume of applicant.
The executive agent of the embodiment of the present invention is the detection means of resume validity, and the detection means of the resume validity can To set in the server.Optionally, the detection means of resume validity can be realized by software, or, resume validity Detection means can be implemented in combination with by software and hardware.
Optionally, the detection means of resume validity can be performed shown in Fig. 2 embodiments after a resume is received Technical scheme, can also periodically or the technical scheme shown in the parallel execution Fig. 2 embodiments of batch, with resume storehouse The resume not detected is detected, and is not especially limited at the time of the embodiment of the present invention is to carrying out resume detection.
Optionally, the resume of applicant can be any one resume that applicant uploads, and the resume of applicant can also For any one resume not detected in resume storehouse.
Optionally, the fisrt feature information of applicant can be the sex of applicant, age etc. of applicant, actually should During, the fisrt feature information can be set according to being actually needed, the embodiment of the present invention is not especially limited to this.
Optionally, the resume of applicant can be that applicant is generated by the application program in client, for example, installation Resume template can be provided to applicant in the application program of client, after applicant fills in corresponding information in resume template Resume can be generated.In that case, position of the information of applicant in resume is fixed that accordingly, resume is true The detection means of degree can be according to applicant's image in resume position, in resume obtain applicant's image, according to application Position of the characteristic information of person in resume, the fisrt feature information of applicant is obtained in resume.
Optionally, the resume of applicant can also be what applicant was uploaded by client, for example, the resume of applicant can Think word document, PDF document, picture etc..In that case, the detection means of resume validity can be to the letter of applicant Go through and carry out Text region or semantic analysis, believed with extracting the fisrt feature of applicant's image and applicant in the resume of applicant Breath.
S202, using pre-set image identification technology, determine the image validity of applicant's image.
In embodiments of the present invention, the image validity of applicant's image is used to indicate whether applicant's image is real Facial image, the embodiment of the present invention can carry out recognition of face to applicant's image using face recognition technology, can also utilize Other image recognition technologys detect whether applicant's image is real facial image.
It should be noted that in the embodiment shown in Fig. 3-Fig. 4, the side of the image validity to obtaining applicant's image Method is described in detail, and is no longer repeated herein.
S203, the second feature information for extracting from applicant's image applicant.
Optionally, second feature information can be the sex of applicant, age etc. of applicant.
Specifically, when second feature information includes the sex of applicant, can be according to following manner in applicant's image The sex of middle extraction applicant：The first face feature vector is extracted in applicant's image；Obtain default standard male face Characteristic vector and default standard women face feature vector；Obtain the first face feature vector and standard male face characteristic to The second similarity and the first face feature vector of amount are with the third phase of standard women face feature vector like degree；According to second Similarity and third phase determine applicant's sex corresponding to applicant's image like spending.
Optionally, standard male face feature vector includes the essential characteristic of male's face, can be to multiple male's samples This face carries out extraction feature, obtains the characteristic vector of each male's sample face, and to the feature of multiple male's sample faces Vector carries out integration processing, obtains standard male's face feature vector.Standard women face feature vector includes women face Essential characteristic, extraction feature can be carried out to multiple women sample faces, obtain the characteristic vector of each women sample face, And integration processing is carried out to the characteristic vector of multiple women sample faces, obtain standard women face feature vector.
Optionally, the first distance between the first face feature vector and standard male's face feature vector can be obtained, And according to the first distance, the second similarity is obtained, wherein, first apart from smaller, and the second similarity is bigger.Optionally, can obtain Take the second distance between the first face feature vector and standard women face feature vector, and according to second distance, obtain the Three similarities, wherein, second distance is smaller, and third phase is bigger like spending.Optionally, if the second similarity is more than third phase and seemingly spent, It is male that applicant's sex corresponding to applicant's image, which can then be determined,, can be with if the second similarity is less than third phase like spending It is women to determine applicant's sex corresponding to applicant's image.
Specifically, when second feature information includes the age bracket of applicant, can be schemed according to following manner in applicant The age bracket of applicant is extracted as in：The first face feature vector is extracted in applicant's image；Obtain multiple default age brackets Corresponding face feature vector；Obtain the first face feature vector face feature vector corresponding with each default age bracket it Between similarity；According to similar between the first face feature vector face feature vector corresponding with each default age bracket Degree, the age bracket of applicant extracted from applicant's image is determined in default age bracket.
Optionally, face feature vector corresponding to each default age bracket includes the people of the user of the default age bracket The essential characteristic of face, multiple sample faces that age bracket can be preset to this carry out extraction feature, obtain each sample face Characteristic vector, and integration processing is carried out to the characteristic vector of multiple sample faces, it is special to obtain face corresponding to the default age bracket Sign vector.
Optionally, the first face feature vector can be obtained and preset age bracket to the face feature vector of one with each The distance between, and according to the first face feature vector and each default age bracket between the face feature vector of one Distance, the similarity between the first face feature vector face feature vector corresponding with each default age bracket is obtained, will Default age bracket corresponding with the first face feature vector similarity highest face feature vector is defined as from applicant's image The age bracket of the applicant of middle extraction.
Specifically, when both the sex including applicant also includes age bracket to second feature information, can be according to above-mentioned two Kind mode is incorporated in the sex and age segment information that applicant is extracted in applicant's image.
S204, according to fisrt feature information, second feature information and described image validity, determine the resume of applicant Validity.
Specifically, contrast fisrt feature information and second feature information, obtain the matching degree of applicant's image and resume, root According to the image validity and matching degree of applicant's image, the validity of the resume of applicant is determined.
Optionally, the applicant's image and answering in resume that the matching degree of applicant's image and resume is used to indicate in resume Uniformity between the information for the person of engaging.That is, the matching degree of applicant's image and resume is higher, the validity of resume is also got over It is high.
Optionally, the second weighted value corresponding to the first weighted value corresponding to image validity and matching degree, root can be obtained According to the validity of applicant's image, the first weighted value, matching degree and the second weighted value, the validity of resume is determined.
Optionally, according to equation below one, the validity P of the resume is determined：
P=α1×P1+α2×P2Formula one；
Wherein, α1For the first weighted value, P corresponding to image validity1For image validity, α2For corresponding to matching degree Two weighted values, P2For the matching degree of applicant's image and resume.
For example, when applicant's image is real facial image, then the image validity of applicant's image can be with For 1, when applicant's image and real facial image are closer to, then the image validity of applicant's image can be 0.8； When applicant's image is landscape image, cartoon image, then the image validity of applicant's image can be 0.
For example, it is assumed that α1For 0.5, α2For 0.5, it is further assumed that the image validity P of applicant's image in resume 11For 0.8, The matching degree of applicant's image and resume in resume 1 is 0.9, then the validity P=0.5*0.8+0.5*0.9=of resume 1 0.85。
Further, the embodiment of the present invention can be ranked up or Screening Treatment according to P size to resume.Work as P<N, N During to preset resume validity threshold value, the resume is abandoned.Or work as P<When N, N are default resume validity threshold value, application is prompted Person resubmits the true picture of applicant.
Resume detection method provided in an embodiment of the present invention, applicant's image is obtained, and extracted from the resume of applicant Go out the fisrt feature information of applicant, using pre-set image identification technology, determine the image validity of applicant's image, and from should The second feature information of applicant is extracted in the person's of engaging image, it is true according to fisrt feature information, second feature information and image Degree, determine the validity of the resume of applicant.Wherein, the image validity of applicant's image is used for whether reflecting applicant's image For real facial image, the matching degree of applicant's image and resume is used for the information or answer for reflecting that applicant fills in resume Whether the person's of engaging image is true, and then can accurately determine the validity of resume, and said process can be criticized without manually participating in The detection for carrying out resume automatic identification and validity of amount, and then improve the efficiency to the detection of resume validity and the degree of accuracy.
On the basis of any one above-mentioned embodiment, optionally, can be determined by following feasible implementation should The image validity (S202 in embodiment illustrated in fig. 2) of the person's of engaging image, specifically, referring to the embodiment shown in Fig. 3-Fig. 4.
Fig. 3 is the schematic flow sheet one of determination image validity method provided in an embodiment of the present invention.Fig. 3 is referred to, should Method can include：
S301, obtain default standard faces characteristic vector.
Default standard faces characteristic vector includes the essential characteristic of face, optionally, can be to multiple sample faces Middle extraction feature, the characteristic vector of each sample face is obtained, and integration processing is carried out to the characteristic vector of multiple sample faces, Obtain standard faces characteristic vector.The mark face feature vector can be multidimensional, for example, 200 dimensions, 300 dimensions etc., wherein, The characteristic value of each latitude in standard faces characteristic vector can indicate a feature in face.In practical application mistake Cheng Zhong, the latitude that standard faces characteristic vector can be set according to being actually needed.
For example, the contour curve of face is generally elliptical, ellipse is generally had between the face and background in image Edge line, therefore, default standard faces characteristic vector includes being used to indicate the feature of the edge line.For another example face On eyes, nose, the shape of face it is approximately fixed, and the relative position of these organs is more fixed, therefore, default standard Face feature vector includes being used for the feature for indicating organ shape and relative position.
S302, the first face feature vector is extracted in applicant's image.
Optionally, the characteristic type that can be indicated according to the latitude of standard faces characteristic vector and each latitude, is being answered The first face feature vector is extracted in the person's of engaging image.
Optionally, the latitude of the first face feature vector is identical with the latitude of standard faces characteristic vector, and the first face The characteristic type of each feature instruction, the feature class of feature corresponding with standard faces characteristic vector instruction in characteristic vector Type is identical, for example, first in standard faces characteristic vector feature indicates face contour line, then in the first face feature vector First feature also indicate that facial contour line.
S303, the first similarity for obtaining the first face feature vector and standard faces characteristic vector.
Optionally, the distance between the first face feature vector and standard faces characteristic vector can be obtained, according to first The distance between face feature vector and standard faces characteristic vector, determine the first face feature vector and standard faces feature to First similarity of amount.The distance between first face feature vector and standard faces characteristic vector are smaller, and the first similarity is got over It is high.
S304, according to the first similarity, determine the validity of applicant's image.
Optionally, the first similarity is higher, and the validity of applicant's image is also higher.First similarity and applicant's image Validity between can have default corresponding relation, accordingly, can according to the first phase Sihe the default corresponding relation, it is determined that The validity of applicant's image.In actual application, the default corresponding relation can be set according to being actually needed.
In the embodiment shown in fig. 3, by extracting the first face feature vector in applicant's image, and will be the first Face characteristic vector is compared with default standard faces characteristic vector, can accurately obtain the validity of applicant's image.
Fig. 4 is the schematic flow sheet two of determination image validity method provided in an embodiment of the present invention.Fig. 4 is referred to, should Method can include：
S401, obtain default standard faces characteristic vector.
S402, the first face feature vector is extracted in applicant's image.
S403, the first similarity for obtaining the first face feature vector and standard faces characteristic vector.
It should be noted that S401-S403 implementation procedure may refer to S301-S303, no longer repeated herein.
S404, applicant's image matched with the image in pre-set image storehouse, obtain applicant's image and default figure As the similarity of each image in storehouse.
Optionally, the image in pre-set image storehouse includes network character image, for example, network character image can be star Image etc..
Optionally, can obtain the characteristic vector of each image in pre-set image storehouse, and according to the first face characteristic to The characteristic vector of each image in amount and image library, obtain applicant's image in pre-set image storehouse each image it is similar Degree.
S405, determine maximum similarity in the similarity of each image in applicant's image and pre-set image storehouse.
Maximum similarity is applicant's image and similarity maximum in the similarity of each image in pre-set image storehouse.
S406, according to the first similarity and maximum similarity, determine the validity of applicant's image.
Optionally, the first similarity is higher, and the validity of applicant's image is also higher.Maximum similarity is higher, applicant The validity of image is lower.
In the embodiment shown in fig. 4, after the validity of applicant's image is obtained, whether applicant's image is also judged For network character image, so, the validity of applicant's image further can be accurately determined.
On the basis of any one above-mentioned embodiment, optionally, the resume in resume detection means obtains resume storehouse After validity, the resume in resume storehouse can also be ranked up according to validity, so, staff can easily exist The higher resume of validity is obtained in resume storehouse.
It should be noted that in actual application, when resume exists for the application program in client according to applicant , accordingly, can be right when applicant uploads applicant's image in resume template during the information generation filled in resume template The validity for the image that applicant uploads is detected, if the validity for the image that detection applicant uploads is true less than default resume During solidity threshold value, prompting message can be generated, so that applicant uploads more real applicant's image.Certainly, if applicant Applicant's information is first filled in, it is rear to upload applicant's image, then after applicant uploads applicant's image, applicant can be filled in Information and applicant's image matched, to determine the matching degree of applicant's fill message and applicant's image, if matching degree Less than preset matching degree, then applicant is prompted to correct applicant's information or applicant's image；Should if applicant first uploads The person's of engaging image, after fill in applicant's information, then after applicant fills in applicant's information, the information that applicant can be filled in and Applicant's image is matched, and to determine the matching degree of applicant's fill message and applicant's image, is preset if matching degree is less than Matching degree, then applicant is prompted to correct applicant's information or applicant's image.
Optionally, when applicant resume be resume storehouse in resume when, it is determined that applicant resume validity it Afterwards, default resume validity threshold value can also be obtained, and abandons the resume that resume validity is less than default resume validity threshold value. So, quickly the resume in resume storehouse can be screened.
Optionally, when applicant resume for user in the resume that client is submitted when, it is determined that the figure of applicant's image As after validity, pre-set image validity threshold value can also be obtained, when the image validity of applicant's image is less than default figure During as validity threshold value, applicant is prompted to resubmit applicant's image.In this manner it is ensured that it is submitted to the resume in resume storehouse For the higher resume of validity.
Fig. 5 is the structural representation one of the detection means of resume validity provided in an embodiment of the present invention.Refer to Fig. 5, Including the first acquisition module 11, the first extraction module 12, the first determining module 13, the second extraction module 14 and the second determining module 15, wherein,
The acquisition module 11 is used for, and obtains applicant's image；
First extraction module 12 is used for, and the fisrt feature of the applicant is extracted from the resume of the applicant Information；
First determining module 13 is used for, and using pre-set image identification technology, determines the image of applicant's image Validity；
Second extraction module 14 is used for, and the second feature letter of the applicant is extracted from applicant's image Breath；
Second determining module 15 is used for, according to the fisrt feature information, the second feature information and the figure Picture validity, determine the validity of the resume of the applicant.
The detection means of resume validity provided in an embodiment of the present invention can perform the skill shown in above method embodiment Art scheme, its realization principle and beneficial effect are similar, are no longer repeated herein.
In a kind of possible embodiment, first determining module 13 is specifically used for：
Obtain default standard faces characteristic vector；
The first face feature vector is extracted in applicant's image；
Obtain the first similarity of first face feature vector and the standard faces characteristic vector；
According to first similarity, the image validity of applicant's image is determined.
In alternatively possible embodiment, first determining module 13 is specifically used for：
Obtain default standard faces characteristic vector；
The first face feature vector is extracted in applicant's image；
Obtain the first similarity of first face feature vector and the standard faces characteristic vector；
Applicant's image is matched with the image in pre-set image storehouse, obtain applicant's image with it is described The similarity of each image in pre-set image storehouse；
In applicant's image and the pre-set image storehouse maximum similarity is determined in the similarity of each image；
According to first similarity and the maximum similarity, the image validity of applicant's image is determined.
In alternatively possible embodiment, comprised at least in the fisrt feature information and the second feature information The sex of applicant；Second extraction module 14 is specifically used for：
The first face feature vector is extracted in applicant's image；
Obtain default standard male face feature vector and default standard women face feature vector；
Obtain the second similarity of first face feature vector and the standard male face feature vector and described The third phase of first face feature vector and the standard women face feature vector is seemingly spent；
According to second similarity and the third phase like spending, it is determined that the applicant extracted from applicant's image Sex.
In alternatively possible embodiment, comprised at least in the fisrt feature information and the second feature information The age bracket of applicant；Second extraction module 14 is specifically used for：
The first face feature vector is extracted in applicant's image；
Obtain face feature vector corresponding to multiple default age brackets；
Obtain the phase between first face feature vector face feature vector corresponding with each default age bracket Like degree；
According to the phase between first face feature vector face feature vector corresponding with each default age bracket Like degree, the age bracket of applicant extracted from applicant's image is determined in the default age bracket.
Fig. 6 is the structural representation two of the detection means of resume validity provided in an embodiment of the present invention.Real shown in Fig. 5 On the basis of applying example, Fig. 6 is referred to, second determining module 15 includes comparison unit 151 and determining unit 152, wherein,
The comparison unit 151 is used for, and contrasts the fisrt feature information and the second feature information, obtains described answer The matching degree of the person's of engaging image and the resume；
The determining unit 152 is used for, and according to the image validity of applicant's image and the matching degree, determines institute State the validity of the resume of applicant.
In alternatively possible embodiment, the determining unit 152 is specifically used for：
Obtain the second weighted value corresponding to the first weighted value corresponding to image validity and matching degree；
According to described image validity, first weighted value, the matching degree and second weighted value, institute is determined State the validity of the resume of applicant.
In alternatively possible embodiment, described device also includes the second acquisition module 16 and discard module 17, its In,
Second acquisition module 16 is used for, determined in second determining module 15 applicant resume it is true After degree, default resume validity threshold value is obtained；
The discard module 17 is used for, and abandons the resume that resume validity is less than the default resume validity threshold value.
In alternatively possible embodiment, described device also includes reminding module 18, wherein,
Second acquisition module 16 is used for, and determines that the image of applicant's image is true in second determining module 15 After solidity, pre-set image validity threshold value is obtained；
The reminding module 18 is used for, when the image validity of applicant's image is less than the pre-set image validity During threshold value, the applicant is prompted to resubmit applicant's image.
The detection means of resume validity provided in an embodiment of the present invention can perform the skill shown in above method embodiment Art scheme, its realization principle and beneficial effect are similar, are no longer repeated herein.
One of ordinary skill in the art will appreciate that：Realizing all or part of step of above-mentioned each method embodiment can lead to The related hardware of programmed instruction is crossed to complete.Foregoing program can be stored in a computer read/write memory medium.The journey Sequence upon execution, execution the step of including above-mentioned each method embodiment；And foregoing storage medium includes：ROM, RAM, magnetic disc or Person's CD etc. is various can be with the medium of store program codes.
Finally it should be noted that：Various embodiments above is only illustrating the technical scheme of the embodiment of the present invention, rather than to it Limitation；Although the embodiment of the present invention is described in detail with reference to foregoing embodiments, one of ordinary skill in the art It should be understood that：It can still modify to the technical scheme described in foregoing embodiments, either to which part or All technical characteristic carries out equivalent substitution；And these modifications or replacement, the essence of appropriate technical solution is departed from this hair The scope of bright embodiment scheme.

Claims (10)

  1. A kind of 1. detection method of resume validity, it is characterised in that including：
    Applicant's image is obtained, and the fisrt feature information of the applicant is extracted from the resume of the applicant；
    Using pre-set image identification technology, the image validity of applicant's image is determined, and from applicant's image Extract the second feature information of the applicant；
    According to the fisrt feature information, the second feature information and described image validity, the letter of the applicant is determined The validity gone through.
  2. 2. according to the method for claim 1, it is characterised in that it is described to utilize pre-set image identification technology, it is determined that described should The image validity of the person's of engaging image, including：
    Obtain default standard faces characteristic vector；
    The first face feature vector is extracted in applicant's image；
    Obtain the first similarity of first face feature vector and the standard faces characteristic vector；
    According to first similarity, the image validity of applicant's image is determined.
  3. 3. according to the method for claim 1, it is characterised in that it is described to utilize pre-set image identification technology, it is determined that described should The image validity of the person's of engaging image, including：
    Obtain default standard faces characteristic vector；
    The first face feature vector is extracted in applicant's image；
    Obtain the first similarity of first face feature vector and the standard faces characteristic vector；
    Applicant's image is matched with the image in pre-set image storehouse, applicant's image is obtained and is preset with described The similarity of each image in image library；
    In applicant's image and the pre-set image storehouse maximum similarity is determined in the similarity of each image；
    According to first similarity and the maximum similarity, the image validity of applicant's image is determined.
  4. 4. according to the method for claim 1, it is characterised in that in the fisrt feature information and the second feature information Including at least the sex of applicant；The second feature information that the applicant is extracted from applicant's image, bag Include：
    The first face feature vector is extracted in applicant's image；
    Obtain default standard male face feature vector and default standard women face feature vector；
    Obtain the second similarity and described first of first face feature vector and the standard male face feature vector The third phase of face feature vector and the standard women face feature vector is seemingly spent；
    According to second similarity and the third phase like spending, it is determined that the property of the applicant extracted from applicant's image Not.
  5. 5. according to the method for claim 1, it is characterised in that in the fisrt feature information and the second feature information Including at least the age bracket of applicant；The second feature information that the applicant is extracted from applicant's image, Including：
    The first face feature vector is extracted in applicant's image；
    Obtain face feature vector corresponding to multiple default age brackets；
    Obtain the similarity between first face feature vector face feature vector corresponding with each default age bracket；
    According to the similarity between first face feature vector face feature vector corresponding with each default age bracket, The age bracket of applicant extracted from applicant's image is determined in the default age bracket.
  6. 6. according to the method for claim 1, it is characterised in that the validity of the resume for determining the applicant, bag Include：
    The fisrt feature information and the second feature information are contrasted, obtains the matching of applicant's image and the resume Degree；
    According to the image validity of applicant's image and the matching degree, the validity of the resume of the applicant is determined.
  7. 7. according to the method for claim 6, it is characterised in that the image validity according to applicant's image and The matching degree, the validity of the resume of the applicant is determined, including：
    Obtain the second weighted value corresponding to the first weighted value corresponding to image validity and matching degree；
    According to described image validity, first weighted value, the matching degree and second weighted value, it is determined that described should The validity of the resume for the person of engaging.
  8. 8. according to the method described in claim any one of 1-7, it is characterised in that the resume for determining the applicant it is true After solidity, in addition to：
    Obtain default resume validity threshold value；
    Abandon the resume that resume validity is less than the default resume validity threshold value.
  9. 9. according to the method described in claim any one of 1-7, it is characterised in that the image for determining applicant's image After validity, in addition to：
    Obtain pre-set image validity threshold value；
    When the image validity of applicant's image is less than the pre-set image validity threshold value, applicant's weight is prompted It is new to submit applicant's image.
  10. 10. a kind of detection means of resume validity, it is characterised in that including the first acquisition module, the first extraction module, first Determining module, the second extraction module and the second determining module, wherein,
    The acquisition module is used for, and obtains applicant's image；
    First extraction module is used for, and the fisrt feature information of the applicant is extracted from the resume of the applicant；
    First determining module is used for, and using pre-set image identification technology, determines the image validity of applicant's image；
    Second extraction module is used for, and the second feature information of the applicant is extracted from applicant's image；
    Second determining module is used for, true according to the fisrt feature information, the second feature information and described image Degree, determine the validity of the resume of the applicant.
CN201710510236.3A 2017-06-28 2017-06-28 The detection method and device of resume validity Pending CN107480582A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710510236.3A CN107480582A (en) 2017-06-28 2017-06-28 The detection method and device of resume validity

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710510236.3A CN107480582A (en) 2017-06-28 2017-06-28 The detection method and device of resume validity

Publications (1)

Publication Number Publication Date
CN107480582A true CN107480582A (en) 2017-12-15

Family

ID=60595442

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710510236.3A Pending CN107480582A (en) 2017-06-28 2017-06-28 The detection method and device of resume validity

Country Status (1)

Country Link
CN (1) CN107480582A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108985707A (en) * 2018-06-11 2018-12-11 安徽引航科技有限公司 A kind of method of quick judgement resume content authenticity

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102799276A (en) * 2012-07-18 2012-11-28 上海量明科技发展有限公司 Method, client and system for avatar icon age conversion in instant messaging
CN103699691A (en) * 2014-01-10 2014-04-02 五八同城信息技术有限公司 Method for generating image fingerprint and method for searching similar image based on same
CN104680131A (en) * 2015-01-29 2015-06-03 深圳云天励飞技术有限公司 Identity authentication method based on identity certificate information and human face multi-feature recognition
CN105095833B (en) * 2014-05-08 2019-03-15 中国科学院声学研究所 For the network establishing method of recognition of face, recognition methods and system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102799276A (en) * 2012-07-18 2012-11-28 上海量明科技发展有限公司 Method, client and system for avatar icon age conversion in instant messaging
CN103699691A (en) * 2014-01-10 2014-04-02 五八同城信息技术有限公司 Method for generating image fingerprint and method for searching similar image based on same
CN105095833B (en) * 2014-05-08 2019-03-15 中国科学院声学研究所 For the network establishing method of recognition of face, recognition methods and system
CN104680131A (en) * 2015-01-29 2015-06-03 深圳云天励飞技术有限公司 Identity authentication method based on identity certificate information and human face multi-feature recognition

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108985707A (en) * 2018-06-11 2018-12-11 安徽引航科技有限公司 A kind of method of quick judgement resume content authenticity
CN108985707B (en) * 2018-06-11 2021-08-10 安徽引航科技有限公司 Method for rapidly judging authenticity of resume content

Similar Documents

Publication Publication Date Title
US20200151310A1 (en) Method and apparatus for identity authentication
CN111444908A (en) Image recognition method, device, terminal and storage medium
CN109410026A (en) Identity identifying method, device, equipment and storage medium based on recognition of face
JP2019519844A (en) Image quality evaluation of documents
US11367310B2 (en) Method and apparatus for identity verification, electronic device, computer program, and storage medium
CN107093066A (en) Service implementation method and device
CN111738357B (en) Junk picture identification method, device and equipment
CN110348444A (en) Wrong topic collection method, device and equipment based on deep learning
CN102508606A (en) Method and system for subdividing belonged groups of users by face recognition and setting corresponding functions of mobile handsets
CN110245573B (en) Sign-in method and device based on face recognition and terminal equipment
CN113111880B (en) Certificate image correction method, device, electronic equipment and storage medium
CN110348346A (en) A kind of bill classification recognition methods and system
CN110969154A (en) Text recognition method and device, computer equipment and storage medium
CN113763249A (en) Text image super-resolution reconstruction method and related equipment thereof
CN105631404B (en) The method and device that photo is clustered
CN113379713B (en) Certificate image detection method and device
CN114005019B (en) Method for identifying flip image and related equipment thereof
CN109145720A (en) A kind of face identification method and device
CN111177622A (en) Webpage rendering method and device based on machine learning and computer equipment
CN107480582A (en) The detection method and device of resume validity
US20240048842A1 (en) Assisted image capturing methods and apparatuses for pets
CN112419257A (en) Method and device for detecting definition of text recorded video, computer equipment and storage medium
CN107169093B (en) target image acquisition method and device
CN108509828A (en) A kind of face identification method and face identification device
CN112861836B (en) Text image processing method, text and card image quality evaluation method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20171215