CN116862166A - Post matching method, device, equipment and computer storage medium - Google Patents
Post matching method, device, equipment and computer storage medium Download PDFInfo
- Publication number
- CN116862166A CN116862166A CN202310813554.2A CN202310813554A CN116862166A CN 116862166 A CN116862166 A CN 116862166A CN 202310813554 A CN202310813554 A CN 202310813554A CN 116862166 A CN116862166 A CN 116862166A
- Authority
- CN
- China
- Prior art keywords
- post
- job seeker
- information
- matching
- features
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000013210 evaluation model Methods 0.000 claims abstract description 19
- 230000006399 behavior Effects 0.000 claims description 33
- 238000004891 communication Methods 0.000 claims description 28
- 238000000605 extraction Methods 0.000 claims description 27
- 238000004590 computer program Methods 0.000 claims description 11
- 230000000694 effects Effects 0.000 claims description 7
- 230000007115 recruitment Effects 0.000 abstract description 17
- 238000013473 artificial intelligence Methods 0.000 description 14
- 238000012545 processing Methods 0.000 description 7
- 238000012549 training Methods 0.000 description 7
- 239000000284 extract Substances 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 230000002452 interceptive effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000009877 rendering Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063112—Skill-based matching of a person or a group to a task
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a post matching method, a post matching device, post matching equipment and a computer storage medium, and relates to the technical field of computers and Internet. The method comprises the following steps: acquiring post information of a post to be recruited; extracting post features from post information to generate post images; acquiring resume information and job hunting behavior information of a job seeker; extracting the features of the job seeker from resume information and job seeker behavior information, and generating a job seeker portrait; calculating the similarity of the post portrait and the job seeker portrait and matching description information based on the matching result evaluation model; aiming at a plurality of job seekers, the post images, the job seeker images, the similarity and the matching description information are respectively displayed according to the sequence of the similarity from high to low. Therefore, the post matching can be rapidly and accurately realized, and the picture, text, image, similarity and matching description information of the post and the job seeker can be intuitively displayed, so that recruitment efficiency and recruitment quality are improved.
Description
Technical Field
The embodiment of the application relates to the technical fields of computers and the Internet, in particular to a post matching method, a post matching device, post matching equipment and a computer storage medium.
Background
Currently, in each industry, enterprises often have a need for recruiters to recruit quality talents that match the posts. However, in the current recruitment mode, it is necessary to rely heavily on the recruiter to view the resume of the resume delivery person and then manually screen candidates that meet the conditions.
The inventors found that in the process of implementing the present application, recruiters need to screen numerous resumes, and the writing level and quality of the resume are uneven, so that it is difficult for recruiters to screen candidates matched with posts from the numerous resume quickly and accurately.
Therefore, how to make recruiters quickly and accurately screen candidates matched with posts from numerous resumes becomes a technical problem to be solved.
Disclosure of Invention
The embodiment of the application provides a post matching method, a post matching device, post matching equipment and a computer storage medium, which can be used for rapidly and accurately screening candidates matched with posts from a plurality of resumes, thereby improving recruitment efficiency and recruitment quality. The technical scheme is as follows:
in a first aspect, an embodiment of the present application provides a post matching method, where the method includes:
Acquiring post information of a post to be recruited;
extracting post features from the post information to generate a post image; the post portraits are used for representing expected employee portraits of at least two levels meeting post requirements through images and texts;
acquiring resume information and job hunting behavior information of a job seeker;
extracting the features of the job seekers from the resume information and the job seeker behavior information, and generating the images of the job seekers; the job seeker portrait is represented by graphics and texts;
calculating the similarity and matching description information of the post image and the job seeker image based on the matching result evaluation model;
aiming at a plurality of job seekers, the post images, the job seeker images, the similarity and the matching description information are respectively displayed according to the sequence of the similarity from high to low.
Optionally, the extracting the post feature from the post information to generate a post portrait may include:
extracting a first looks characteristic from the post information, wherein the first looks characteristic comprises one or more of an age characteristic, a height characteristic, a gender characteristic, an academic characteristic, a native place characteristic and an interest characteristic;
extracting first capability features from the post information, wherein the first capability features comprise one or more of professional skill features, language skill features and communication skill features;
Obtaining the emergency degree corresponding to the post information, wherein the emergency degree is as follows: emergency, generally urgent or not;
generating at least two levels of desired employee images, represented by graphics, that meet the post requirements based on an intelligent AI persona generation model, the first physiognomic feature, the first competency feature, and the degree of urgency; the hierarchy includes at least: highest matching level, lowest matching level.
Optionally, the extracting the job seeker feature from the job seeker resume information and the job seeker behavior information to generate a job seeker portrait may include:
extracting second looks characteristic from resume information of the job seeker, wherein the second looks characteristic comprises one or more of resume photo, age characteristic, height characteristic, sex characteristic, learning characteristic, native characteristic and hobby characteristic;
extracting second capability features from the job seeker resume information, wherein the second capability features comprise one or more of professional skill features, language skill features and communication skill features;
extracting a third capability feature from the job hunting behavior information, the third capability feature comprising: one or more of the collection times of the enterprise, the active communication times of the enterprise, the resume delivery times, the active communication times of the job seeker, the online activity of the job seeker and the online active time interval of the job seeker;
And generating a job seeker portrait represented by graphics based on the intelligent AI persona generation model, the second phase feature, the second capability feature and the third capability feature.
Optionally, the calculating the similarity between the post image and the job seeker image and the matching description information based on the matching result evaluation model may include:
calculating a first similarity of the image of the post portrait and the image of the job seeker portrait based on the matching result evaluation model, and calculating a second similarity of the text description of the post portrait and the text description of the job seeker portrait;
calculating the similarity of the post image and the job seeker image based on the first similarity and the second similarity;
generating an image comparison theory based on the image of the post portrait, the image of the job seeker portrait and the first similarity;
generating a text comparison conclusion based on the text description of the post portrait, the text description of the job seeker portrait and the second similarity;
and generating matching description information of the post image and the job seeker image by comparing the image comparison theory with the text comparison conclusion.
Optionally, the matching description information includes: matching item description information, unmatched item description information, job seeker potential level information and resume authenticity information.
In a second aspect, an embodiment of the present application further provides a post matching device, where the device includes:
the first acquisition module is used for acquiring post information of a post to be recruited;
the first extraction module is used for extracting post features from post information and generating post images; the post portraits are used for representing expected employee portraits of at least two levels meeting the post requirements through graphics and texts;
the second acquisition module is used for acquiring resume information and job hunting behavior information of the job seeker;
the second extraction module is used for extracting the features of the job seeker from the resume information and the job seeker behavior information and generating a job seeker portrait; the job seeker portrait is represented by graphics and texts;
the matching module is used for calculating the similarity between the post image and the job seeker image and matching description information based on the matching result evaluation model;
the display module is used for respectively displaying the post image, the job seeker image, the similarity and the matching description information according to the sequence of the similarity from high to low for a plurality of job seekers.
Optionally, the first extraction module includes:
the first extraction unit is used for extracting first looks characteristics from the post information, wherein the first looks characteristics comprise one or more of age characteristics, height characteristics, gender characteristics, learning characteristics, native characteristics and hobby characteristics;
the second extraction unit is used for extracting first capability features from the post information, wherein the first capability features comprise one or more of professional skill features, language skill features and communication skill features;
the first obtaining unit is used for obtaining the emergency degree corresponding to the post information, and the emergency degree is as follows: emergency, generally urgent or not;
a first generating unit, configured to generate at least two levels of desired employee images that are represented by graphics and texts and meet the post requirements, based on an intelligent AI personage generation model, the first looks feature, the first ability feature, and the degree of urgency; the hierarchy includes at least: highest matching level, lowest matching level.
Optionally, the second extraction module includes:
the third extraction unit is used for extracting second looks features from resume information of the job seeker, wherein the second looks features comprise one or more of resume photos, age features, height features, gender features, learning features, native features and interest features;
A fourth extraction unit, configured to extract a second capability feature from the job seeker resume information, where the second capability feature includes one or more of a professional skill feature, a language skill feature, and a communication skill feature;
a fifth extraction unit, configured to extract a third capability feature from the job hunting behavior information, where the third capability feature includes: one or more of the collection times of the enterprise, the active communication times of the enterprise, the resume delivery times, the active communication times of the job seeker, the online activity of the job seeker and the online active time interval of the job seeker;
and the second generation unit is used for generating a job seeker portrait represented by graphics and texts based on the intelligent AI personage generation model, the second phase feature, the second capability feature and the third capability feature.
Optionally, the matching module may include:
a first calculation unit for calculating a first similarity of an image of the post portrait and an image of the job seeker portrait based on a matching result evaluation model, and calculating a second similarity of a word description of the post portrait and a word description of the job seeker portrait;
the second calculating unit is used for calculating the similarity between the post image and the job seeker image based on the first similarity and the second similarity;
A third generation unit, configured to generate an image comparison theory based on the image of the post portrait, the image of the job seeker portrait, and the first similarity;
a fourth generation unit, configured to generate a text comparison conclusion based on the text description of the post portrait, the text description of the job seeker portrait, and the second similarity;
and a fifth generating unit, configured to generate matching description information of the post image and the job seeker image according to the image comparison theory and the text comparison conclusion.
Optionally, the matching description information includes: matching item description information, unmatched item description information, job seeker potential level information and resume authenticity information.
In a third aspect, embodiments of the present application also provide a computer device comprising a processor and a memory, the memory having stored therein a computer program, the computer program being loaded and executed by the processor to implement a method as described in any of the first aspects above.
In a fourth aspect, embodiments of the present application also provide a computer readable storage medium having a computer program stored therein, the computer program being loaded and executed by a processor to implement a method as described in any of the first aspects above.
The technical scheme provided by the embodiment of the application can have the following beneficial effects:
the application provides a new post matching scheme, which comprises the steps of firstly acquiring post information of a post to be recruited, extracting post characteristics from the post information, and generating a post image. The post portrait is used for representing expected employee portraits of at least two levels meeting post requirements through graphics. And the resume information and the job-seeking behavior information of the job seeker can be obtained, and then the characteristics of the job seeker are extracted from the resume information and the job-seeking behavior information of the job seeker, so that the image of the job seeker is generated. The job seeker portrait is represented by graphics. And then, based on the matching result evaluation model, calculating the similarity between the post portrait and the job seeker portrait and the matching description information. And, for a plurality of job seekers, the post portrait, the job seeker portrait, the similarity and the matching description information are respectively displayed according to the sequence of the similarity from high to low. Therefore, the post matching can be quickly and accurately realized, and the picture, text, image, similarity and matching description information of the post and the job seeker can be intuitively displayed, and the recruiter can quickly determine the candidate through the picture, the similarity and the matching description information, so that the recruitment efficiency and the recruitment quality are improved.
Drawings
FIG. 1 is a flow chart of a post matching method provided by one embodiment of the application;
FIG. 2 is a flow chart of generating a post representation provided by one embodiment of the present application;
FIG. 3 is a flow chart of generating job applicant representations provided by one embodiment of the present application;
FIG. 4 is a block diagram of a post matching device provided by one embodiment of the present application;
fig. 5 is a block diagram of a computer device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings.
In each industry, enterprises often have a need for recruiters to recruit to quality talents that match the job. However, in the current recruitment mode, it is necessary to rely heavily on the recruiter to view the resume of the resume delivery person and then manually screen candidates that meet the conditions.
The inventors found that in the process of implementing the present application, recruiters need to screen numerous resumes, and the writing level and quality of the resume are uneven, so that it is difficult for recruiters to screen candidates matched with posts from the numerous resume quickly and accurately.
Therefore, how to make recruiters quickly and accurately screen candidates matched with posts from numerous resumes becomes a technical problem to be solved.
In order to solve the technical problems, the application provides a novel post matching scheme. The project firstly acquires the post information of the post to be recruited, and extracts the post characteristics from the post information to generate the post portrait. The post portrait is used for representing expected employee portraits of at least two levels meeting post requirements through graphics. And the resume information and the job-seeking behavior information of the job seeker can be obtained, and then the characteristics of the job seeker are extracted from the resume information and the job-seeking behavior information of the job seeker, so that the image of the job seeker is generated. The job seeker portrait is represented by graphics. And then, based on the matching result evaluation model, calculating the similarity between the post portrait and the job seeker portrait and the matching description information. And, for a plurality of job seekers, the post portrait, the job seeker portrait, the similarity and the matching description information are respectively displayed according to the sequence of the similarity from high to low.
Therefore, the post matching can be quickly and accurately realized, and the picture, text, image, similarity and matching description information of the post and the job seeker can be intuitively displayed, and the recruiter can quickly determine the candidate through the picture, the similarity and the matching description information, so that the recruitment efficiency and the recruitment quality are improved.
The post matching method provided by the embodiment of the application is described in detail below with reference to fig. 1 to 3.
FIG. 1 is a flow chart of a post matching method provided by one embodiment of the application. Referring to fig. 1, the post matching method provided by the embodiment of the application may include the following steps:
s101: acquiring post information of a post to be recruited;
in one implementation, the post information of the post to be recruited can intelligently identify the recruitment manuscript of the human entity and extract the needed key post information therefrom; in another mode, an interactive interface for filling specific requirements can be provided for the personnel units, the interactive interface can provide filling templates for the personnel units, and the personnel units only need to fill relevant skill requirement information, salary information and the like in corresponding template items.
Of course, the staff of the human entity can also add filling items (such as model human entity can add height items and weight items) or delete filling items (such as express human entity can delete academic items) on the interactive interface according to the self requirement. That is, the interactive interface supports custom settings with human units.
It is to be appreciated that the post information for the recruitment post can include: one or more of age information, height information, gender information, learning information, native place information, interest information, professional skill information, language skill information, communication skill information, and the like, which are not limited thereto, and are not illustrated herein.
S102: extracting post features from post information to generate post images; the post portrait is used for representing expected employee portraits of at least two levels meeting post requirements through graphics and texts;
FIG. 2 is a flow chart of generating a post representation provided by one embodiment of the present application. Referring to fig. 2, a post image may be generated by:
s201: extracting first looks characteristic from post information, wherein the first looks characteristic comprises one or more of age characteristic, height characteristic, sex characteristic, academic characteristic, native characteristic and hobby characteristic;
it will be appreciated that personnel having high demands on the physical characteristics, such as model personnel, actors or etiquette personnel, may formulate conditions in the post information that meet personnel requirements. The computer device may then extract this information from the post information to obtain a first phase feature.
It is noted that the first phase feature may be represented by a feature vector, for example, first phase feature= (age feature, height feature, gender feature) = (2, 1). Wherein, the age is in the interval of [20, 30), the age characteristic value is 2; the age is in the interval of [30, 40), the age characteristic value is 3; etc. The height is in the interval of (1.55-1.6), and the height characteristic value is 1; height is in the interval of [ 1.6-1.65), the height characteristic value is 2, and the like; the sex is female and the sex characteristic is 1, and the sex is male and the sex characteristic is 2.
S202: extracting first capability features from post information, wherein the first capability features comprise one or more of professional skill features, language skill features and communication skill features;
similarly, a person may also set forth specific skill requirements. The computer device may then extract skill requirements from the post information to obtain a first capability feature.
It should be noted that the first capability feature may also be represented by a feature vector, for example, first capability feature= (professional skill feature, language skill feature) = (3, 2). Wherein, the professional skill is at the primary level, and the value of the professional skill characteristic is 1; the professional skill is at a medium level, and the value of the professional skill characteristic is 2; the professional skill is in a high level, and the value of the professional skill characteristic is 3; etc. The language skill is in English four levels, and the language skill characteristic value is 1; the language skill is in English six-level, and the language skill characteristic value is 2; etc.
The foregoing is merely illustrative, and the job site big data may be specifically cleaned and segmented, and then reasonable features and feature values may be formulated, which are not specifically described herein.
S203: obtaining emergency degree corresponding to the post information, wherein the emergency degree is as follows: emergency, generally urgent or not;
It can be appreciated that for recruitment requirements of the urgent employment category, the computer device can obtain the urgency corresponding to the post information after identifying the urgent employment keyword or the time-to-job requirement.
The recruiter can also correct the error according to specific requirements and report error information if the computer equipment recognizes the error of the emergency degree.
S204: generating at least two levels of expected employee images which are expressed by graphics and texts and meet the position requirements based on the intelligent AI personage generation model, the first looks feature, the first ability feature and the emergency degree; the hierarchy includes at least: highest matching level, lowest matching level.
It will be appreciated that the first topographical feature, the first competency feature, and the degree of urgency may all be represented by relatively vivid images. For example, an emergency may be highlighted with three exclamation marks, a professional skill feature may be shown with a bar graph showing the type of ability and corresponding level, and a female at an age of [20, 30) may be shown with a girl graph of puberty. Of course, there may also be corresponding textual descriptions.
The intelligent AI character generating model is trained by a large amount of sample data, and the training data comprises the looks characteristic, the ability characteristic and other descriptive characteristics (such as emergency degree) and the image-text results corresponding to the characteristics.
Specifically, training the intelligent AI character generation model may employ deep learning algorithms, such as generating countermeasure networks (GANs) and Variational Automatic Encoders (VAEs). To calculate a large amount of data through these algorithms to generate a realistic, feature-specific character image or text description.
Among these, generating a countermeasure network (GANs) is a model composed of a generator and a arbiter. The generator is responsible for generating an image or text description of the person, while the arbiter is responsible for determining whether the generated result is authentic or counterfeit. By countering, the generator gradually increases the quality of the generated results to fool the arbiter. This manner of training of the competition and feedback loops may help the generator learn the distribution characteristics of the sample data to generate realistic character features.
Variational Automatic Encoders (VAEs) are a model of generation based on probabilistic models. It maps the input feature vector to a distribution in a potential space by learning the distribution features of the sample data and samples it from it to generate new character features. The VAEs training process includes maximizing the likelihood of the data and minimizing the KL divergence of the potential space to ensure that the results generated accurately reflect the characteristics of the sample data.
In addition to GANs and VAEs, there are other algorithms for generating model training, such as autoregressive models (e.g., recurrent neural networks and transformer models), which are not illustrated herein.
S103: acquiring resume information and job hunting behavior information of a job seeker;
it is to be appreciated that job hunting behavior information can include: one or more of enterprise collection times, enterprise active communication times, resume delivery times, job seekers active communication times, job seekers online activity time interval. Of course, not limited thereto.
The capacity condition of the job seeker can be reflected from the side based on the job seeker behavior information, namely, the job seeker behavior information can evaluate the capacity of the job seeker more accurately in an objective aspect, and the job seeker is not limited to subjective evaluation of the capacity of the job seeker, so that the post matching result is more accurate.
S104: extracting the features of the job seeker from resume information and job seeker behavior information, and generating a job seeker portrait; the job seeker portrait is represented by graphics and texts;
FIG. 3 is a flow chart of generating job applicant representations provided by one embodiment of the present application. Referring to FIG. 3, a job applicant representation may be generated by:
S301: extracting second looks characteristic from resume information of job seekers, wherein the second looks characteristic comprises one or more of resume photo, age characteristic, height characteristic, gender characteristic, school characteristic, native characteristic and interest characteristic;
it is to be appreciated that the computer device can extract a feature of the looks about the job applicant from the job applicant resume as a second feature of looks based on the job applicant resume information, wherein the second feature of looks includes one or more of a resume photo, an age feature, a height feature, a gender feature, a calendar feature, a native feature, a hobby feature. Of course, not limited thereto.
The method for obtaining the value of the second phase feature corresponds to the method for obtaining the value of the first phase feature, which is not described herein.
S302: extracting second capability features from the job seeker resume information, wherein the second capability features comprise one or more of professional skill features, language skill features and communication skill features;
it will be appreciated that the job seeker will often write their own competency in the job seeker's resume, such as professional skills, language skills, communication skills, etc., and the computer device can automatically recognize this information to obtain a second competency feature.
The method for obtaining the value of the second capability feature corresponds to the method for obtaining the value of the first capability feature, which is not described herein.
S303: extracting a third capability feature from job hunting behavior information, wherein the third capability feature comprises: one or more of the collection times of the enterprise, the active communication times of the enterprise, the resume delivery times, the active communication times of the job seeker, the online activity of the job seeker and the online active time interval of the job seeker;
it will be appreciated that job hunting information is not the subjective statement of the job seeker, but rather is the actual actions of the job seeker after putting the resume, and whether the market approves the job seeker, which is an objectively manifestation of the job seeker's ability. That is, the capacity of the job seeker can be reflected from the side based on the job seeker behavior information, the job seeker behavior information can evaluate the capacity of the job seeker more accurately in an objective aspect, and the job seeker is not limited to subjective evaluation of the job seeker on the capacity, so that the post matching result can be more accurate.
S304: and generating a job seeker portrait represented by graphics based on the intelligent AI persona generation model, the second feature, the second capability feature and the third capability feature.
It will be appreciated that the second aspect feature, the second capability feature, and the third capability feature may all be represented by relatively vivid images. And, there may also be corresponding textual descriptions for the respective images.
The intelligent AI character generating model is obtained through training a large amount of sample data, wherein the training data comprises looks characteristics, capability characteristics and other descriptive characteristics, and image-text results corresponding to the characteristics. The intelligent AI persona generation model may be the same model as the one mentioned above, and the algorithm that trains the model is not described here in detail.
S105: calculating the similarity of the post portrait and the job seeker portrait and matching description information based on the matching result evaluation model;
the step S105 may specifically include the following steps:
s1051: calculating a first similarity of the image of the post picture and the image of the job seeker picture based on the matching result evaluation model, and calculating a second similarity of the text description of the post picture and the text description of the job seeker picture;
in S1051, a matching result evaluation model may be used to evaluate the similarity between the post representation and the job applicant representation. First, the image of the post portraits may be compared with the image of the job applicant portraits to calculate a first similarity therebetween. This may be achieved by image processing techniques and similarity measurement methods, such as calculating Structural Similarity (SSIM), peak signal-to-noise ratio (PSNR), etc. between them.
Meanwhile, the text description of the post picture and the text description of the job seeker picture can be compared, and the second similarity between the post picture and the job seeker picture can be calculated. This may be accomplished using natural language processing techniques, such as computing word vector similarity, cosine similarity, etc. between them.
S1052: calculating the similarity of the post portrait and the job seeker portrait based on the first similarity and the second similarity;
in S1052, the overall similarity between the post portrait and the job applicant portrait can be calculated using the first similarity and the second similarity calculated in S1051. This may be achieved by defining a weighting function to weight combine the two similarities to obtain a composite similarity score. The weight selection can be adjusted according to specific application scenes and requirements.
S1053: generating an image comparison theory based on the image of the post image, the image of the job seeker image and the first similarity;
in S1053, the image of the post image, the image of the job seeker image, and the first similarity calculated in S1051 may be used to generate a conclusion of the image comparison. It may be determined whether the two images are similar or matched based on a threshold of similarity. For example, if the first similarity is above a set threshold, then the two images may be judged to be similar or matching, otherwise they are not considered to be similar or matching.
S1054: generating a text comparison conclusion based on the text description of the post image, the text description of the job seeker image and the second similarity;
in S1054, the text description of the post image, the text description of the job seeker image, and the second similarity calculated in S1051 may be used to generate a conclusion of the text comparison. By comparing the similarity of the two text descriptions, the degree of text matching between the post portrayal and the job seeker portrayal can be evaluated.
Based on the threshold of the second similarity, it may be determined whether the two textual descriptions are similar or match. If the second similarity is higher than the set threshold, indicating a higher similarity between the textual descriptions, the post portraits and job applicant portraits may be considered to be better matched textually. Conversely, if the second similarity is below the threshold, indicating less similarity between the textual descriptions may mean that the post representation and job applicant representation differ significantly in terms of keywords or descriptions
S1055: and (5) generating matching description information of the post portrait and the job seeker portrait by comparing the image comparison conclusion with the text comparison conclusion.
In S1055, the image comparison conclusion and the text comparison conclusion can be combined to generate matching description information of the post portrait and the job seeker portrait. By comprehensively considering similarity evaluation of two aspects of images and characters, a comprehensive matching conclusion can be obtained.
If the image comparison and the text comparison indicate that the post portrait and the job seeker portrait have higher similarity, the matching description information can be obtained to have higher matching degree on the images and the texts, and the potential matching opportunity is provided. If one aspect of the comparison theory is higher and the other aspect of the comparison theory is lower, the matching description information can be obtained to have higher matching degree in one aspect, but a certain difference exists in the other aspect.
And combining the conclusion of image comparison and text comparison, and generating matching description information for describing the matching degree and similarity between the post portrait and the job seeker portrait. This matching description information can be provided to recruiters, human resources departments, or candidates as decision and reference bases to assist them in assessing the degree of matching between posts and candidates.
S106: aiming at a plurality of job seekers, the post images, the job seeker images, the similarity and the matching description information are respectively displayed according to the sequence of the similarity from high to low.
Wherein, the matching description information may include: matching item description information, unmatched item description information, job seeker potential level information and resume authenticity information. Of course, not limited thereto.
Specifically, for multiple job seekers, according to the sequence of the similarity from high to low, the post portrait, the job seeker portrait, the similarity and the matching description information can be displayed to help screening and matching of candidates. Specific examples may be:
job seeker 1:
post portrayal and job seeker portrayal: the image of the post picture and the image of job seeker 1 are presented for comparison and visual comparison.
Similarity: the similarity score between the display post portrait and the job seeker 1 portrait can be in a numerical value or a percentage form.
Matching description information: the description information generated according to the result of the image and text comparison has high matching degree, for example, the image and text matching degree and strong matching potential.
Job seeker 2:
post portrayal and job seeker portrayal: the image of the post picture and the image of job seeker 2 are presented for comparison and visual comparison.
Similarity: the similarity score between the display post portrait and the job seeker 2 portrait can be in a numerical value or a percentage form.
Matching description information: the description information generated according to the result of the image and text comparison is, for example, high in matching degree on the image, but some differences exist in text description.
Job seeker 3:
post portrayal and job seeker portrayal: the image of the post picture and the image of job seeker 3 are presented for comparison and visual comparison.
Similarity: the similarity score between the display post portrait and the job seeker 3 portrait can be in a numerical value or a percentage form.
Matching description information: descriptive information generated from the result of the image and text comparison, for example, has a high degree of matching in text description, but some differences exist in the image.
Job seeker 4:
post portrayal and job seeker portrayal: the image of the post picture and the image of job seeker 4 are presented for comparison and visual comparison.
Similarity: the similarity score between the display post image and the job seeker 4 image can be in a numerical value or a percentage form.
Matching description information: the description information generated according to the result of the image and text comparison has a relatively low matching degree, for example, a relatively large difference in image and text description.
In this way, recruiters or human resource department references can be provided to assist them in multiple job seekers
Therefore, by the post matching scheme provided by the application, the post information of the post to be recruited can be acquired first, and the post characteristics are extracted from the post information to generate the post image. The post portrait is used for representing expected employee portraits of at least two levels meeting post requirements through graphics. And the resume information and the job-seeking behavior information of the job seeker can be obtained, and then the characteristics of the job seeker are extracted from the resume information and the job-seeking behavior information of the job seeker, so that the image of the job seeker is generated. The job seeker portrait is represented by graphics. And then, based on the matching result evaluation model, calculating the similarity between the post portrait and the job seeker portrait and the matching description information. And, for a plurality of job seekers, the post portrait, the job seeker portrait, the similarity and the matching description information are respectively displayed according to the sequence of the similarity from high to low. Therefore, the post matching can be quickly and accurately realized, and the picture, text, image, similarity and matching description information of the post and the job seeker can be intuitively displayed, and the recruiter can quickly determine the candidate through the picture, the similarity and the matching description information, so that the recruitment efficiency and the recruitment quality are improved.
In a second aspect, an embodiment of the present application further provides a post matching device, referring to fig. 4, fig. 4 is a block diagram of a post matching device provided in an embodiment of the present application, where the device may include:
a first obtaining module 401, configured to obtain post information of a post to be recruited;
a first extraction module 402, configured to extract a post feature from post information, and generate a post image; the post portrait is used for representing expected employee portraits of at least two levels meeting post requirements through graphics and texts;
a second obtaining module 403, configured to obtain resume information and job hunting behavior information of the job seeker;
the second extraction module 404 is configured to extract features of the job seeker from resume information and job seeker behavior information, and generate a job seeker portrait; the job seeker portrait is represented by graphics and texts;
the matching module 405 is configured to calculate, based on the matching result evaluation model, similarity between the post portrait and the job seeker portrait and matching description information;
the display module 406 is configured to display the post portrait, the job seeker portrait, the similarity and the matching description information for the job seeker according to the order of the similarity from high to low.
By applying the post matching device provided by the application, the post information of the post to be recruited can be acquired first, and the post characteristics are extracted from the post information to generate the post portrait. The post portrait is used for representing expected employee portraits of at least two levels meeting post requirements through graphics. And the resume information and the job-seeking behavior information of the job seeker can be obtained, and then the characteristics of the job seeker are extracted from the resume information and the job-seeking behavior information of the job seeker, so that the image of the job seeker is generated. The job seeker portrait is represented by graphics. And then, based on the matching result evaluation model, calculating the similarity between the post portrait and the job seeker portrait and the matching description information. And, for a plurality of job seekers, the post portrait, the job seeker portrait, the similarity and the matching description information are respectively displayed according to the sequence of the similarity from high to low. Therefore, the post matching can be quickly and accurately realized, and the picture, text, image, similarity and matching description information of the post and the job seeker can be intuitively displayed, and the recruiter can quickly determine the candidate through the picture, the similarity and the matching description information, so that the recruitment efficiency and the recruitment quality are improved.
Optionally, the first extraction module 402 includes:
the first extraction unit is used for extracting first looks characteristics from post information, wherein the first looks characteristics comprise one or more of age characteristics, height characteristics, gender characteristics, school characteristics, penetration characteristics and interest characteristics;
the second extraction unit is used for extracting first capability features from post information, wherein the first capability features comprise one or more of professional skill features, language skill features and communication skill features;
the first acquisition unit is used for acquiring the emergency degree corresponding to the post information, and the emergency degree is: emergency, generally urgent or not;
the first generation unit is used for generating at least two levels of expected employee images which are expressed by using graphics and texts and meet the post requirements based on the intelligent AI personage generation model, the first looks characteristic, the first capability characteristic and the emergency degree; the hierarchy includes at least: highest matching level, lowest matching level.
Optionally, the second extraction module 404 includes:
the third extraction unit is used for extracting second looks characteristic from resume information of job seekers, wherein the second looks characteristic comprises one or more of resume photos, age characteristics, height characteristics, gender characteristics, learning characteristics, native characteristics and hobby characteristics;
A fourth extraction unit, configured to extract a second capability feature from resume information of the job seeker, where the second capability feature includes one or more of a professional skill feature, a language skill feature, and a communication skill feature;
a fifth extraction unit, configured to extract a third capability feature from job hunting behavior information, where the third capability feature includes: one or more of the collection times of the enterprise, the active communication times of the enterprise, the resume delivery times, the active communication times of the job seeker, the online activity of the job seeker and the online active time interval of the job seeker;
and the second generation unit is used for generating a job seeker portrait represented by graphics and texts based on the intelligent AI persona generation model, the second looks feature, the second capability feature and the third capability feature.
Optionally, the matching module 405 may include:
the first computing unit is used for computing a first similarity between the image of the post picture and the image of the job seeker picture based on the matching result evaluation model, and computing a second similarity between the word description of the post picture and the word description of the job seeker picture;
the second calculation unit is used for calculating the similarity between the post portrait and the job seeker portrait based on the first similarity and the second similarity;
The third generation unit is used for generating an image comparison theory based on the image of the post image, the image of the job seeker image and the first similarity;
a fourth generating unit, configured to generate a text comparison conclusion based on the text description of the post image, the text description of the job seeker image, and the second similarity;
and the fifth generation unit is used for comparing the image comparison conclusion with the text comparison conclusion to generate matching description information of the post portrait and the job seeker portrait.
Optionally, the matching description information includes: matching item description information, unmatched item description information, job seeker potential level information and resume authenticity information.
In a third aspect, an embodiment of the present application further provides a computer device, referring to fig. 5, and fig. 5 is a block diagram of a computer device according to an embodiment of the present application. The computer device comprises a processor 501 and a memory 502, the memory 502 having stored therein a computer program that is loaded and executed by the processor 501 to implement the method according to any of the first aspects.
Processor 501 may include one or more processing cores, such as a 4-core processor, a 17-core processor, etc. The processor 501 may be implemented in at least one hardware form of DSP (Digital Signal Processing ), FPGA (Field Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array ). The processor 501 may also include a main processor and a coprocessor, the main processor being a processor for processing data in an awake state, also referred to as a CPU (Central Processing Unit ); a coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 501 may be integrated with a GPU for use in connection with rendering and rendering of content to be displayed by the display screen. In some embodiments, the processor 501 may also include an AI (Artificial Intelligence ) processor for processing computing operations related to machine learning.
Memory 502 may include one or more computer-readable storage media, which may be tangible and non-transitory. Memory 502 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in memory 502 stores a computer program that is loaded and executed by processor 501 to implement the live interaction method performed by the terminal or the live interaction method performed by the server.
Those skilled in the art will appreciate that the architecture shown in fig. 5 is not limiting of a computer device and may include more or fewer components than shown, or may combine certain components, or employ a different arrangement of components.
It should be noted that, in the apparatus provided in the foregoing embodiment, when implementing the functions thereof, only the division of the foregoing functional modules is used as an example, in practical application, the foregoing functional allocation may be implemented by different functional modules, that is, the internal structure of the device is divided into different functional modules, so as to implement all or part of the functions described above. In addition, the apparatus and the method embodiments provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the apparatus and the method embodiments are detailed in the method embodiments and are not repeated herein.
In an exemplary embodiment, there is also provided a computer readable storage medium having stored therein a computer program which, when executed by a processor, implements the method of any of the above first aspects.
Alternatively, the computer-readable storage medium may include: ROM (Read-Only Memory), RAM (Random Access Memory ), SSD (Solid State Drives, solid state disk), or optical disk, etc. The random access memory may include, among other things, reRAM (Resistance Random Access Memory, resistive random access memory) and DRAM (Dynamic Random Access Memory ).
In an exemplary embodiment, a computer program product is also provided, the computer program product comprising computer instructions stored in a computer readable storage medium. And the processor of the computer equipment reads the computer instructions from the computer readable storage medium, and executes the computer instructions to enable the computer equipment to execute the live interaction method executed by the terminal or the live interaction method executed by the server.
It should be understood that references herein to "a plurality" are to two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. In addition, the step numbers described herein are merely exemplary of one possible execution sequence among steps, and in some other embodiments, the steps may be executed out of the order of numbers, such as two differently numbered steps being executed simultaneously, or two differently numbered steps being executed in an order opposite to that shown, which is not limiting. The foregoing embodiments may also be combined arbitrarily, and a combination scheme will not be described herein.
The foregoing description of the exemplary embodiments of the application is not intended to limit the application to the particular embodiments disclosed, but on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the application.
Claims (10)
1. A post matching method, the method comprising:
Acquiring post information of a post to be recruited;
extracting post features from the post information to generate a post image; the post portraits are used for representing expected employee portraits of at least two levels meeting post requirements through images and texts;
acquiring resume information and job hunting behavior information of a job seeker;
extracting the features of the job seekers from the resume information and the job seeker behavior information, and generating the images of the job seekers; the job seeker portrait is represented by graphics and texts;
calculating the similarity and matching description information of the post image and the job seeker image based on the matching result evaluation model;
aiming at a plurality of job seekers, the post images, the job seeker images, the similarity and the matching description information are respectively displayed according to the sequence of the similarity from high to low.
2. The method of claim 1, wherein extracting post features from the post information to generate a post representation comprises:
extracting a first looks characteristic from the post information, wherein the first looks characteristic comprises one or more of an age characteristic, a height characteristic, a gender characteristic, an academic characteristic, a native place characteristic and an interest characteristic;
Extracting first capability features from the post information, wherein the first capability features comprise one or more of professional skill features, language skill features and communication skill features;
obtaining the emergency degree corresponding to the post information, wherein the emergency degree is as follows: emergency, generally urgent or not;
generating at least two levels of desired employee images, represented by graphics, that meet the post requirements based on an intelligent AI persona generation model, the first physiognomic feature, the first competency feature, and the degree of urgency; the hierarchy includes at least: highest matching level, lowest matching level.
3. The method of claim 2, wherein extracting job seeker features from the job seeker resume information and job seeker behavior information to generate a job seeker portrait comprises:
extracting second looks characteristic from resume information of the job seeker, wherein the second looks characteristic comprises one or more of resume photo, age characteristic, height characteristic, sex characteristic, learning characteristic, native characteristic and hobby characteristic;
extracting second capability features from the job seeker resume information, wherein the second capability features comprise one or more of professional skill features, language skill features and communication skill features;
Extracting a third capability feature from the job hunting behavior information, the third capability feature comprising: one or more of the collection times of the enterprise, the active communication times of the enterprise, the resume delivery times, the active communication times of the job seeker, the online activity of the job seeker and the online active time interval of the job seeker;
and generating a job seeker portrait represented by graphics based on the intelligent AI persona generation model, the second phase feature, the second capability feature and the third capability feature.
4. The method of claim 3, wherein the computing similarity and matching description information of the post image and the job seeker image based on the matching result evaluation model comprises:
calculating a first similarity of the image of the post portrait and the image of the job seeker portrait based on the matching result evaluation model, and calculating a second similarity of the text description of the post portrait and the text description of the job seeker portrait;
calculating the similarity of the post image and the job seeker image based on the first similarity and the second similarity;
generating an image comparison theory based on the image of the post portrait, the image of the job seeker portrait and the first similarity;
Generating a text comparison conclusion based on the text description of the post portrait, the text description of the job seeker portrait and the second similarity;
and generating matching description information of the post image and the job seeker image by comparing the image comparison theory with the text comparison conclusion.
5. The method of claim 4, wherein the matching description information comprises: matching item description information, unmatched item description information, job seeker potential level information and resume authenticity information.
6. A post matching device, the device comprising:
the first acquisition module is used for acquiring post information of a post to be recruited;
the first extraction module is used for extracting post features from post information and generating post images; the post portraits are used for representing expected employee portraits of at least two levels meeting the post requirements through graphics and texts;
the second acquisition module is used for acquiring resume information and job hunting behavior information of the job seeker;
the second extraction module is used for extracting the features of the job seeker from the resume information and the job seeker behavior information and generating a job seeker portrait; the job seeker portrait is represented by graphics and texts;
The matching module is used for calculating the similarity between the post image and the job seeker image and matching description information based on the matching result evaluation model;
the display module is used for respectively displaying the post image, the job seeker image, the similarity and the matching description information according to the sequence of the similarity from high to low for a plurality of job seekers.
7. The apparatus of claim 6, wherein the first extraction module comprises:
the first extraction unit is used for extracting first looks characteristics from the post information, wherein the first looks characteristics comprise one or more of age characteristics, height characteristics, gender characteristics, learning characteristics, native characteristics and hobby characteristics;
the second extraction unit is used for extracting first capability features from the post information, wherein the first capability features comprise one or more of professional skill features, language skill features and communication skill features;
the first obtaining unit is used for obtaining the emergency degree corresponding to the post information, and the emergency degree is as follows: emergency, generally urgent or not;
a first generating unit, configured to generate at least two levels of desired employee images that are represented by graphics and texts and meet the post requirements, based on an intelligent AI personage generation model, the first looks feature, the first ability feature, and the degree of urgency; the hierarchy includes at least: highest matching level, lowest matching level.
8. The apparatus of claim 7, wherein the second extraction module comprises:
the third extraction unit is used for extracting second looks features from resume information of the job seeker, wherein the second looks features comprise one or more of resume photos, age features, height features, gender features, learning features, native features and interest features;
a fourth extraction unit, configured to extract a second capability feature from the job seeker resume information, where the second capability feature includes one or more of a professional skill feature, a language skill feature, and a communication skill feature;
a fifth extraction unit, configured to extract a third capability feature from the job hunting behavior information, where the third capability feature includes: one or more of the collection times of the enterprise, the active communication times of the enterprise, the resume delivery times, the active communication times of the job seeker, the online activity of the job seeker and the online active time interval of the job seeker;
and the second generation unit is used for generating a job seeker portrait represented by graphics and texts based on the intelligent AI personage generation model, the second phase feature, the second capability feature and the third capability feature.
9. A computer device comprising a processor and a memory, the memory having stored therein a computer program that is loaded and executed by the processor to implement the method of any of claims 1 to 5.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program, which is loaded and executed by a processor to implement the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310813554.2A CN116862166A (en) | 2023-07-04 | 2023-07-04 | Post matching method, device, equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310813554.2A CN116862166A (en) | 2023-07-04 | 2023-07-04 | Post matching method, device, equipment and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116862166A true CN116862166A (en) | 2023-10-10 |
Family
ID=88222810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310813554.2A Pending CN116862166A (en) | 2023-07-04 | 2023-07-04 | Post matching method, device, equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116862166A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117689354A (en) * | 2024-02-04 | 2024-03-12 | 芯知科技(江苏)有限公司 | Intelligent processing method and platform for recruitment information based on cloud service |
| CN117787939A (en) * | 2024-02-23 | 2024-03-29 | 武汉厚溥数字科技有限公司 | Enterprise intelligent matching method and device and electronic equipment |
-
2023
- 2023-07-04 CN CN202310813554.2A patent/CN116862166A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117689354A (en) * | 2024-02-04 | 2024-03-12 | 芯知科技(江苏)有限公司 | Intelligent processing method and platform for recruitment information based on cloud service |
| CN117689354B (en) * | 2024-02-04 | 2024-04-19 | 芯知科技(江苏)有限公司 | Intelligent processing method and platform for recruitment information based on cloud service |
| CN117787939A (en) * | 2024-02-23 | 2024-03-29 | 武汉厚溥数字科技有限公司 | Enterprise intelligent matching method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107851097B (en) | Data analysis system, data analysis method, data analysis program, and storage medium | |
| CN116862166A (en) | Post matching method, device, equipment and computer storage medium | |
| CN111723784B (en) | Risk video identification method and device and electronic equipment | |
| CN114020929A (en) | Intelligent education system platform design method based on course knowledge graph | |
| CN112231554B (en) | Search recommended word generation method and device, storage medium and computer equipment | |
| CN112699283A (en) | Test paper generation method and device | |
| CN110458600A (en) | Portrait model training method, device, computer equipment and storage medium | |
| CN112206541A (en) | Game plug-in identification method and device, storage medium and computer equipment | |
| EP3977392A1 (en) | Method for training a discriminator | |
| Zhang et al. | Research on student Big Data portrait method based on improved K-means algorithm | |
| CN115757112A (en) | Test subset construction method based on variation analysis and related equipment | |
| JP6178480B1 (en) | DATA ANALYSIS SYSTEM, ITS CONTROL METHOD, PROGRAM, AND RECORDING MEDIUM | |
| CN112070662B (en) | Evaluation method and device of face changing model, electronic equipment and storage medium | |
| CN114443838A (en) | Image construction method, device, server and storage medium | |
| CN113919983A (en) | Test question portrait method, device, electronic equipment and storage medium | |
| Ramos et al. | A Facial Expression Emotion Detection using Gabor Filter and Principal Component Analysis to identify Teaching Pedagogy | |
| Kanchana et al. | Analysis of social media images to predict user personality assessment | |
| Wu et al. | Evaluation of student's 3D modeling capability based on model completeness and usage pattern in K-12 classrooms | |
| CN117725191B (en) | Guide information generation method and device of large language model and electronic equipment | |
| Siddiqui et al. | Predicting the Student Performance via Machine Leaning Techniques | |
| CN110750620A (en) | Group decision capability assessment method and device | |
| CN111259138A (en) | Tax field short text emotion classification method and device | |
| US20220237531A1 (en) | Method of matching employers with job seekers including emotion recognition | |
| CN109815212A (en) | A kind of intelligent data base construction method, apparatus and system | |
| CN114237460B (en) | Label display method, device, terminal, storage medium and computer program product |
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 |