CN112182383B - Recommendation method and device for second post and computer equipment - Google Patents
Recommendation method and device for second post and computer equipment Download PDFInfo
- Publication number
- CN112182383B CN112182383B CN202011044951.0A CN202011044951A CN112182383B CN 112182383 B CN112182383 B CN 112182383B CN 202011044951 A CN202011044951 A CN 202011044951A CN 112182383 B CN112182383 B CN 112182383B
- Authority
- CN
- China
- Prior art keywords
- post
- information
- job seeker
- posts
- resume
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012216 screening Methods 0.000 claims abstract description 34
- 239000013598 vector Substances 0.000 claims description 48
- 230000006870 function Effects 0.000 claims description 43
- 238000004422 calculation algorithm Methods 0.000 claims description 24
- 238000013527 convolutional neural network Methods 0.000 claims description 24
- 238000004364 calculation method Methods 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 238000012512 characterization method Methods 0.000 claims description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000008859 change Effects 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000012217 deletion Methods 0.000 description 4
- 230000037430 deletion Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000012886 linear function Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000007115 recruitment Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
- G06Q10/1053—Employment or hiring
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of artificial intelligence, and provides a second post recommending method, a second post recommending device and computer equipment, wherein the second post recommending method comprises the following steps: extracting resume information in the resume of the job seeker; extracting the post information of the first post, comparing the post information of the first post with post information in a post database, and screening according to preset rules to obtain a plurality of related posts; calculating the grading value of the job seeker at each relevant post; and screening out the relevant posts with the grading values larger than the preset threshold value as second posts, and recommending the second posts to job seekers. The invention has the beneficial effects that: through obtaining resume information and personal detail information of the job seeker, a plurality of corresponding relevant posts are selected, and corresponding second posts are provided for the job seeker through the scoring value of the job seeker at each post, so that the efficiency of screening the second posts by the job seeker is improved, and the job seeker can quickly and accurately find the second posts different from the current first posts.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a second post recommending method, a second post recommending device and computer equipment.
Background
With the continuous development of internet technology, more and more job seekers choose to seek proper work through the internet, when job seekers have a need of changing work positions, the existing technical scheme only recommends other positions similar to the current position of the job seekers, and the recommending mode is too simple, rough and not based on resume information of the job seekers, and only recommends based on the current position, personal information of the job seekers is ignored, related information of the job seekers is not fully utilized, and recommending accuracy and intelligence are low, so that a recommending method for the second position is needed.
Disclosure of Invention
The invention mainly aims to provide a second post recommending method, a second post recommending device and computer equipment, and aims to solve the problem that the accuracy and the intelligence of recommending the second post are low.
The invention provides a second post recommending method, which comprises the following steps:
extracting resume information in the resume of the job seeker; the resume information comprises post information and personal detail information of a first post of the job seeker, wherein the first post is a post of the job seeker which is currently engaged in, and the first post and the second post are different posts;
Extracting the post information of the first post, comparing the post information of the first post with post information in a post database, and screening according to a preset rule to obtain a plurality of relevant posts;
inputting the resume information and the post information of the related posts into a pre-trained post matching model to obtain the matching degree of the resume information and each related post in the related posts;
calculating the scoring value of the job seeker at each relevant post according to the matching degree and the skill weight information corresponding to each relevant post;
and screening out the relevant posts with the grading values larger than a preset threshold value as the second posts, and recommending the second posts to the job seeker.
Further, the step of calculating the score value of the job seeker at each relevant post according to the matching degree and the weight corresponding to each relevant post includes:
acquiring the working time, the certificate information, the incumbent information and the working skills of the job seeker at the first post according to the resume information and the post information of the first post;
according to the formula Calculating the capability of each working skill of the job seeker; wherein F (xi) represents a function of the ability of the job seeker's ith work skills as a function of the time of the practitioner,>a derivative function representing the ability of the ith work skill as a function of the time of day, g (xi) representing the ability to calculate the ith work skill from the credential information and the incumbent information, t representing the time of day of the first station;
according to the formulaCalculating a scoring value at the relevant post; wherein G (n) represents the grading value of the relevant post, m is the matching degree, and wi is the weight parameter corresponding to the ith working skill.
Further, the step of extracting the post information of the first post, comparing the post information of the first post with post information in a post database, and screening to obtain a plurality of relevant posts according to a preset rule includes:
extracting first keywords from post information of a first post by using a preset text ordering algorithm, and extracting second keywords from post information of a post database;
vectorizing the first keyword and the second keyword by using a preset word vector database to obtain a first feature vector and a second feature vector;
Calculating the similarity of the first feature vector and the second feature vector by using a preset similarity algorithm;
and screening the positions corresponding to the position information with the similarity larger than the preset similarity value as the relevant positions.
Further, before the step of inputting the resume information and the post information of the plurality of related posts into a pre-trained post matching model to obtain the matching degree of the resume information and each of the plurality of related posts, the method further includes:
acquiring a plurality of resume from a resume information base, extracting corresponding resume information, acquiring post information of a current post corresponding to each resume from the extracted resume information, and carrying out characteristic processing on the post information of the current post and the extracted resume information;
inputting the information after the characterization treatment into a convolutional neural network model for training;
after the convolutional neural network model converges, a preliminary job matching model is obtained;
calculating a loss value of the preliminary job matching model;
judging whether the loss value is lower than a loss preset value or not;
if the loss value is lower than the loss preset value, the preliminary job matching model is considered as the job matching model;
And if the loss value is not lower than the loss preset value, adjusting parameters of the convolutional neural network model, and continuing training the convolutional neural network model until the loss value of the trained preliminary position matching model is lower than the loss preset value.
Further, the step of selecting the relevant post with the grading value greater than the predetermined threshold as the second post and recommending the second post to the job seeker includes:
screening out the relevant posts with the grading values larger than a preset threshold value as the second posts;
acquiring the intention post of the job seeker in the resume information;
judging whether the intention post belongs to the second post or not;
if yes, judging that the intention post is the matching post of the job seeker, and sending the matching post to the job seeker after marking.
Further, after the step of selecting the relevant post with the score value greater than the predetermined threshold as the second post and recommending the second post to the job seeker, the method further includes:
acquiring a target post selected from the second post by the job seeker;
recommending the resume of the job seeker and the scoring value corresponding to the target post to the company where the target post is located.
The invention also provides a recommending device of the second post, which comprises:
the resume information extraction module is used for extracting resume information in the resume of the job seeker; the resume information comprises post information and personal detail information of a first post of the job seeker, wherein the first post is a post of the job seeker which is currently engaged in, and the first post and the second post are different posts;
the post information extraction module is used for extracting post information of the first post, comparing the post information of the first post with post information in a post database, and screening according to preset rules to obtain a plurality of relevant posts;
the input module is used for inputting the resume information and the post information of the related posts into a post matching model to obtain the matching degree of the resume information and each related post in the related posts;
the scoring value calculation module is used for calculating the scoring value of the job seeker at each relevant post according to the matching degree and the skill weight information corresponding to each relevant post;
and the screening module is used for screening out the relevant posts with the grading values larger than a preset threshold value as the second posts, and recommending the second posts to the job seeker.
Further, the scoring value calculating module includes:
the working skill information acquisition sub-module is used for acquiring the working time, the certificate information, the incumbent information and the working skill of the job seeker in the first post according to the resume information and the post information of the first post;
capability calculation submodule for calculating a capability according to a formulaCalculating the capability of each working skill of the job seeker; wherein F (xi) represents a function of the ability of the job seeker's ith work skills as a function of the time of the practitioner,>a derivative function representing the ability of the ith work skill as a function of the time of day, g (xi) representing the ability to calculate the ith work skill from the credential information and the incumbent information, t representing the time of day of the first station;
a scoring value calculation sub-module for calculating a scoring value according to the formulaCalculating a scoring value at the relevant post; wherein G (n) represents the grading value of the relevant post, m is the matching degree, and wi is the weight parameter corresponding to the ith working skill.
The invention also provides a computer device comprising a memory storing a computer program and a processor implementing the steps of any of the methods described above when the processor executes the computer program.
The application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of any of the preceding claims.
The application has the beneficial effects that: through obtaining resume information and personal detail information of the job seeker, a plurality of corresponding relevant posts are selected, and corresponding second posts are provided for the job seeker through the scoring value of the job seeker at each post, so that the efficiency of screening the second posts by the job seeker is improved, and the job seeker can quickly and accurately find the second posts different from the current first posts.
Drawings
FIG. 1 is a flow chart of a second post recommendation method according to an embodiment of the present application;
FIG. 2 is a schematic block diagram of a second post recommending apparatus according to an embodiment of the present application;
fig. 3 is a schematic block diagram of a computer device according to an embodiment of the present application.
The achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that, in the embodiments of the present invention, all directional indicators (such as up, down, left, right, front, and back) are merely used to explain the relative positional relationship, movement conditions, and the like between the components in a specific posture (as shown in the drawings), if the specific posture is changed, the directional indicators correspondingly change, and the connection may be a direct connection or an indirect connection.
The term "and/or" is herein merely an association relation describing an associated object, meaning that there may be three relations, e.g., a and B, may represent: a exists alone, A and B exist together, and B exists alone.
Furthermore, descriptions such as those referred to as "first," "second," and the like, are provided for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implying an order of magnitude of the indicated technical features in the present disclosure. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not within the scope of protection claimed in the present invention.
Referring to fig. 1, the present invention proposes a second post recommending method, including:
s1: extracting resume information in the resume of the job seeker; the resume information comprises post information and personal detail information of a first post of the job seeker, wherein the first post is a post of the job seeker which is currently engaged in, and the first post and the second post are different posts;
s2: extracting the post information of the first post, comparing the post information of the first post with post information in a post database, and screening according to a preset rule to obtain a plurality of relevant posts;
s3: inputting the resume information and the post information of the related posts into a pre-trained post matching model to obtain the matching degree of the resume information and each related post in the related posts;
s4: calculating the scoring value of the job seeker at each relevant post according to the matching degree and the skill weight information corresponding to each relevant post;
s5: and screening out the relevant posts with the grading values larger than a preset threshold value as the second posts, and recommending the second posts to the job seeker.
The resume information in the resume of the job seeker is obtained as described in the above step S1, and the resume may include information such as the name, the school, the work experience (including the work time, the job title, the work content, etc.), the project name, the project role, the project work description, the desired salary, the desired work place, etc. The extraction mode can be to identify the resume of the job seeker by a deep learning technology; the method comprises the steps of carrying out text analysis on the context of the resume through combining a knowledge graph and an LSTM model, finding information points, carrying out information content standardization to correct nonstandard and ambiguous resume contents, and correcting resume information through processing modes of duplication removal, punctuation deletion, unified languages, deletion of irrelevant words and sentences and the like, wherein the irrelevant words and sentences comprise greetings, adjectives and the like.
As described in the above step S2, the post information of the first post is then extracted, that is, the post that the job seeker is currently engaged in, the working content of the job seeker can be analyzed from the post information of the first post, and the degree of correlation between the post and the first post in the post database is then calculated based on the post information of the first post, which may be any preset similarity algorithm, for example, WMD algorithm (word mover' S distance), simhash algorithm, cosine similarity algorithm, preferably: the formula is adopted: Calculating the degree of correlation between the first post and other posts, wherein X represents a feature set in post information of the first post, Y represents a feature set of post information of other posts, wherein the closer the calculated value is to 1, the higher the degree of correlation between the first post and the post is, and the closer the calculated value is to 0, the lower the degree of correlation between the first post and the post is. A correlation threshold may then be set and the relevant posts that are greater than the correlation threshold may be filtered out.
As described in step S3, since each post has different requirements for different skills, further analysis and calculation are required for the content in the resume information, and the analysis and calculation process may be performed through a pre-trained post matching model, where the post matching model is based on the skills and years included in the resume information of the job seeker, and the job posts (which may include a plurality of job posts) of the job seeker are trained, which is equivalent to the requirement of the relevant post for different skills, the post information and resume information of the relevant post are input into the post matching model, so that the degree of matching with the job seeker based on the resume information with each relevant post can be obtained, and the higher the degree of matching is generally considered, the more relevant the resume information of the job seeker is related to the relevant post.
As described in the above step S4, since the skills of the job seeker and the requirements of each skill are different in the aspect of the company, a weight may be set for each skill based on the requirements of the company on the relevant posts, the score value of the job seeker on each relevant post based on resume information may be calculated, the score value may be presented to the job seeker, or the calculation formulas of the weights may be presented to the job seeker together, and the job seeker may be provided with a screening judgment or the like, or the score value may be presented to the company for the company to select a suitable job seeker. The specific calculation formula can beWherein->Wherein F (xi) represents a function of the ability of the job seeker's ith work skills as a function of the change in time of the job, n represents the total number of work skills, xi represents the ith work skills, m is the degree of matching,/>A derivative function representing the variation of the ability of the ith work skill with the time of the work, t representing the time of the work of the first post, g (xi) representing the ability to be embodied from other aspects, such as various certificates, involved items, etc., wi representing the weight of the different ith work skill in that post, and w1+w2+ … +wn=1.
As described in step S5 above, the relevant post that is greater than the predetermined threshold is selected as the second post, the predetermined threshold is a preset value, and may be adjusted according to the actual situation later, and then the second post that is greater than the predetermined threshold is sent to the job seeker, so that the job seeker who wants to walk can be helped to recommend the ideal post, so that the job seeker cannot deviate too much from the original post, and the job seeker can continue to compete with the job after the job change.
In one embodiment, the step S4 of calculating the score value of the job seeker at each relevant post according to the matching degree and the weight corresponding to each relevant post includes:
s401: acquiring the working time, the certificate information, the incumbent information and the working skills of the job seeker at the first post according to the resume information and the post information of the first post;
s402: according to the formulaCalculating the capability of each working skill of the job seeker; wherein F (xi) represents a function of the ability of the job seeker's ith work skills as a function of the time of the practitioner,>a derivative function representing the ability of the ith work skill as a function of the time of day, g (xi) representing the ability to calculate the ith work skill from the credential information and the incumbent information, t representing the time of day of the first station;
s403: according to the formulaCalculating a scoring value at the relevant post; wherein G (n) represents the grading value of the relevant post, m is the matching degree, wi is the weight parameter corresponding to the ith working skill, and n represents the number of the working skills.
As described in the above step S401, the resume information generally includes the time of employment, the certificate information, the on-job information and the skill information of each job of the job seeker at the first post, and then the information is complemented and perfected according to the post information of the first post, where the certificate information is related to the first post and the second post, and the certificate information not related to the first post and the second post can be ignored.
As described in the above step S402, the formula is passedThe ability of each working skill of the job seeker is calculated, and it should be noted that, since different working skills of the job seeker have different growth degrees within the same working time according to different working contents, for example, the job is also programmed, big data is made, blockchain is made, popularization is made, after-sales is made, and the like, in different fields, the working skills have different growth degrees, so that the function of the ability of the corresponding working skill along with the working time is obtained according to the first post information, namely, the derivative function of the ability of the ith working skill along with the change of the working time is improved>The differential function may be set by itself or may be a linear function or another function according to the change of the ability of the ith skill in the course of time. In addition, because different job seekers have different growth degrees, the capabilities can be reflected from certificate information and incumbent information, a function g (xi) can be set for calculation, the function g (xi) comprises the capabilities corresponding to various certificates, and then the capabilities of the ith skill are obtained by adding the two functions.
As described in step S403, the ability of each work skill is calculated through F (xi), then multiplied by the weight wi, and then accumulated and multiplied by the matching degree m to obtain the scoring value G (n) of the job seeker at the second post, where the matching degree is different between two posts, and the scoring value G (n) of the relevant post can be obtained by multiplying the matching degree as a coefficient.
In one embodiment, the step S2 of extracting the post information of the first post, comparing the post information of the first post with post information in a post database, and screening to obtain a plurality of relevant posts according to a preset rule includes:
s201: extracting first keywords from post information of a first post by using a preset text ordering algorithm, and extracting second keywords from post information of a post database;
s202: vectorizing the first keyword and the second keyword by using a preset word vector database to obtain a first feature vector and a second feature vector;
s203: calculating the similarity between the first feature vector and the second feature vector by using a preset similarity algorithm;
s204: and taking the post corresponding to the post information with the similarity larger than the preset similarity value as the relevant post.
As described in the above steps S201-S204, the preset text ranking algorithm may be a TextRank algorithm, which is modified from a google' S web page importance ranking algorithm PageRank algorithm, and is capable of extracting keywords and keyword groups of a given text, and extracting keywords and sentences of the text by using an automatic extraction method. The first keyword and the second keyword are entity words and relationship words, for example: mastering programming languages, engaging in financial work, applying eclipse, processing accounting transactions, and the like. Vectorization is performed by using professional keywords as an example, vectorization is performed on the professional requirement in the position, and the fields corresponding to the professional requirement in the position are as follows: automation, economics, computer and the like, searching a word vector corresponding to the field in a preset word vector database, and taking the word vector as a vectorized result; for example: the "professional requirements" for a recruitment position are: and searching a word of the computer in a preset word vector database, and acquiring an n-dimensional vector corresponding to the computer as a vectorization result of the professional requirement. If the professional requirement is: and (3) automatically, economically and computer, searching three words of 'automatically, economically and computer' and corresponding word vectors thereof in a preset word vector database, wherein the three word vectors are used as vectorization results of 'professional requirements' in the text. Then re-use the formula Calculating the similarity of the first feature vector and the second feature vector, wherein the closer the calculated similarity is to 1, the more the first feature vector and the second feature vector are representedSimilarly, a more approaching 0 means that the first feature vector is less similar to the second feature vector. Then a specific preset similarity value is preset, and the corresponding positions in the position database which is larger than the preset similarity value are screened out and marked as related positions.
In one embodiment, before the step S3 of inputting the resume information and the post information of the plurality of related posts into a post matching model to obtain the matching degree between the resume information and each of the plurality of related posts, the method further includes:
s211: acquiring a plurality of resume from a resume information base, extracting corresponding resume information, acquiring post information of a current post corresponding to each resume from the extracted resume information, and carrying out characteristic processing on the post information of the current post and the extracted resume information;
s212: inputting the information after the characterization treatment into a convolutional neural network model for training;
s213: and after the convolutional neural network model is converged, obtaining a preliminary job matching model.
As described in the above steps S211-S213, in this embodiment, the job position and resume data are first prepared, the post information and resume information of the first post may be characterized by training a trained transducer model, and then the characterized data are input into a convolutional neural network for model training, and when the training times reach the set requirements, the convolutional neural network model is converged, so as to train a preliminary job position matching model. After training is completed, any position can be input into the preliminary position matching model to carry out position matching, the preliminary position matching model returns whether the position is matched or not, and the number of information points in each position matching is larger, and the matching degree of each information point is larger.
S214: calculating a loss value of the preliminary job matching model;
s215: judging whether the loss value is lower than a loss preset value or not;
s216: if the loss value is lower than the loss preset value, the preliminary job matching model is considered as the job matching model;
s217: and if the loss value is not lower than the loss preset value, adjusting parameters of the convolutional neural network model, and continuing training the convolutional neural network model until the loss value of the trained preliminary position matching model is lower than the loss preset value.
As described in the above steps S214-S217, by the formulaCalculating a loss value of the preliminary job matching model, wherein S is the loss value, A i Representing the ith calculated value calculated by the preliminary job matching model, B i Is equal to A i And the corresponding ith predicted value, n represents the number of data. Judging whether the loss is lower than a loss preset value or not, wherein the loss preset value is a set value, and if the loss is lower than the loss preset value, determining the preliminary job matching model as the job matching model; and if the loss value is not lower than the loss preset value, adjusting parameters of the convolutional neural network model, and continuing training the convolutional neural network until a preliminary job matching model with the loss value lower than the loss preset value is obtained. Thereby improving the accuracy of the model.
In one embodiment, the step S5 of selecting the relevant post with the score value greater than the predetermined threshold as the second post and recommending the second post to the job seeker includes:
s501: screening out the relevant posts with the grading values larger than a preset threshold value as the second posts;
s502: acquiring the intention post of the job seeker in the resume information;
s503: judging whether the intention post belongs to the second post or not;
S504: if yes, judging that the intention post is the matching post of the job seeker, and sending the intention post to the job seeker in the form of the matching post.
As described in the above steps S501-S504, the intention post of the job seeker in the resume information is obtained, which may be obtained by semantic recognition after the resume information is obtained, and then the intention post is detected to be in the second post which is not screened, if yes, the company related to the intention post may be pushed to the job seeker in advance, so that the job seeker may select his own intention according to his own situation and is suitable for his own company. The matching post is sent to the job seeker in a form of the matching post, which is different from the recommended form of other second posts, for example, the matching post can be specially marked and then sent to the job seeker, or the matching post can be sent to the job seeker first and then the other second posts are sent to the job seeker, and it should be understood that the sending in the form of the matching post is to enable the job seeker to quickly distinguish from the second posts, and the specific form is not limited.
In one embodiment, after step S5, the step of selecting the relevant post with the score value greater than the predetermined threshold as the second post, recommending the second post to the job seeker further includes:
S601: acquiring a target post selected from the second post by the job seeker;
s602: recommending the resume of the job seeker and the scoring value corresponding to the target post to the company where the target post is located.
As described in the above steps S601-S602, after a plurality of second posts are selected for the job seeker, if the job seeker is interested in the selected second posts, the target post selected by the job seeker is received, and at this time, the resume and the score value of the job seeker can be sent to the company where the target post is located, so that the company can learn about the job seeker.
Referring to fig. 2, the present invention further provides a second post recommending apparatus, including:
the resume information extraction module 10 is used for extracting resume information in the resume of the job seeker; the resume information comprises post information and personal detail information of a first post of the job seeker, wherein the first post is a post of the job seeker which is currently engaged in, and the first post and the second post are different posts;
the post information extraction module 20 is configured to extract post information of the first post, compare the post information of the first post with post information in a post database, and screen to obtain a plurality of relevant posts according to a preset rule;
The input module 30 is configured to input the resume information and post information of the relevant posts into a post matching model, so as to obtain a matching degree of the resume information and each relevant post of the relevant posts;
a scoring value calculating module 40, configured to calculate a scoring value of the job seeker at each relevant post according to the matching degree and the skill weight information corresponding to each relevant post;
and the screening module 50 is configured to screen the relevant post with the score value greater than the predetermined threshold as the second post, and recommend the second post to the job seeker.
Resume information in the resume of the job seeker is obtained, and the resume can comprise information such as names, academies, working experiences (including working time, job title, working content and the like), project names, project roles, project work descriptions, expected salary, expected work places and the like of the job seeker. The extraction mode can be to identify the resume of the job seeker by a deep learning technology; the method comprises the steps of carrying out text analysis on the context of the resume through combining a knowledge graph and an LSTM model, finding information points, carrying out information content standardization to correct nonstandard and ambiguous resume contents, and correcting resume information through processing modes of duplication removal, punctuation deletion, unified languages, deletion of irrelevant words and sentences and the like, wherein the irrelevant words and sentences comprise greetings, adjectives and the like.
Then extracting the position information of the first position, i.e. the position the job seeker is currently engaged in, analyzing the working content of the job seeker from the position information of the first position, calculating the degree of correlation between the position in the position database and the first position based on the skill required by the first position, and calculating the degree of correlation between the position in the position database and the first position based on the position information of the first position in any preset similarity algorithm, such as WMD algorithm (word mover's distancece), simhash algorithm, cosine similarity-based algorithm, preferably: the formula is adopted:calculating the degree of correlation between the first post and other posts, wherein X represents a feature set in post information of the first post, Y represents a feature set of post information of other posts, wherein the closer the calculated value is to 1, the higher the degree of correlation between the first post and the post is, and the closer the calculated value is to 0, the lower the degree of correlation between the first post and the post is. A correlation threshold may then be set and the relevant posts that are greater than the correlation threshold may be filtered out.
Because each post has different requirements on different working skills, further analysis and calculation are needed to be carried out on the content in resume information, the analysis and calculation process can be carried out through a pre-trained post matching model, the post matching model is formed by training the posts (including a plurality of working posts) of the job seeker based on the skills and years contained in resume information of the job seeker, the post information and resume information of the relevant post can be input into the post matching model based on the requirements of the relevant post on different skills, and the degree of matching with the job seeker based on resume information and each relevant post can be obtained, wherein the higher the degree of matching is generally considered, the more relevant the resume information of the job seeker is related to the relevant post.
Because the skills of the company on the job seeker and the requirements on each skill are different, a weight can be set for each skill based on the requirements of the company on the relevant posts, the score value of the job seeker on each relevant post based on resume information is calculated, the score value can be presented to the job seeker, the calculation formulas of the weights can be presented to the job seeker together, the job seeker can carry out screening judgment and the like, the score value can be presented to the company, and the company can select the proper job seeker. The specific calculation formula can beWherein->Wherein F (xi) represents a function of the ability of the job seeker's ith work skills as a function of the change in time of the job, n represents the total number of work skills, xi represents the ith work skills, m is the degree of matching,/>A derivative function representing the variation of the ability of the ith work skill with the time of the work, t representing the time of the work of the first post, g (xi) representing the ability to be embodied from other aspects, such as various certificates, involved items, etc., wi representing the weight of the different ith work skill in that post, and w1+w2+ … +wn=1.
The relevant posts larger than the preset threshold are selected as the second posts, the preset threshold is a preset value, the follow-up operation can also be adjusted according to actual conditions, and then the second posts larger than the preset threshold are sent to job seekers, so that the job seekers who want to turn can be helped to recommend ideal posts, the ideal posts cannot deviate too much from the original posts, and the job seekers can continue to compete after the job change work.
In one embodiment, the scoring value calculation module 40 includes:
the working skill information acquisition sub-module is used for acquiring the working time, the certificate information, the incumbent information and the working skill of the job seeker in the first post according to the resume information and the post information of the first post;
capability calculation submodule for calculating a capability according to a formulaCalculating the capability of each working skill of the job seeker; wherein F (xi) represents a function of the ability of the job seeker's ith work skills as a function of the time of the practitioner,>the ability to represent the ith work skill as a function of the time of the practitionerA derivative function of the equation, g (xi) representing the ability to calculate the ith work skill from the credential information and the incumbent information, t representing the time of day of the first post;
a scoring value calculation sub-module for calculating a scoring value according to the formulaCalculating a scoring value at the relevant post; wherein G (n) represents the grading value of the relevant post, m is the matching degree, wi is the weight parameter corresponding to the ith working skill, and n represents the number of the working skills.
The resume information generally comprises the working time of the job seeker at the first post, the certificate information, the job information and the work skill information, and then the information is complemented and perfected according to the post information of the first post, wherein the certificate information is related to the first post and the second post, and the certificate information which is not related to the first post and the second post can be ignored.
By the formulaThe ability of each working skill of the job seeker is calculated, and it should be noted that, since different working skills of the job seeker have different growth degrees within the same time of the job according to different working contents, for example, the job is programmed, big data is made, blockchain is made, popularization is made, after-sales is made, and the like, in different fields, the working skills have different growth degrees, thus the function of the ability of the corresponding working skill along with the time of the job is obtained according to the first post information, namely, the derivative function of the ability of the ith working skill along with the time of the job is changedThe differential function may be set by itself or may be a linear function or another function according to the change of the ability of the ith skill in the course of time. In addition, byDifferent job seekers have different growth degrees, and the capabilities can be reflected from certificate information and job information, so that a function g (xi) can be set for calculation, the function g (xi) comprises the capabilities corresponding to various certificates, and then the capabilities of the ith skill are obtained by adding the two capabilities.
The ability of each working skill is calculated through F (xi), then the weight wi is multiplied, then the matching degree m is accumulated and multiplied to obtain the scoring value G (n) of the job seeker in the second position, of course, different matching degrees exist between the two different positions, and the matching degree can be used as a coefficient to multiply to obtain the scoring value G (n) of the relevant position.
In one embodiment, the post information extraction module 20 includes:
the first keyword extraction sub-module is used for respectively extracting first keywords from post information of a first post by using a preset text ordering algorithm and extracting second keywords from post information of a post database;
the vectorization sub-module is used for vectorizing the first keyword and the second keyword by using a preset word vector database to obtain a first feature vector and a second feature vector;
a similarity calculation submodule, configured to calculate a similarity between the first feature vector and the second feature vector by using a preset similarity algorithm;
and the related post screening sub-module is used for screening posts with similarity larger than a preset similarity value as the related posts.
The preset text ranking algorithm can be a TextRank algorithm, is improved by a webpage importance ranking algorithm Pagerank algorithm of google, and can extract keywords and keyword groups of a given text and extract key sentences of the text by using a removable automatic abstract method. The first keyword and the second keyword are entity words and relationship words, for example: mastering programming languages, engaging in financial work, applying eclipse, processing accounting transactions, and the like. Vectorizing professional keywords as an example, vectorizing the professional requirement in the position, and corresponding words according to the professional requirement in the position Segments such as: automation, economics, computer and the like, searching a word vector corresponding to the field in a preset word vector database, and taking the word vector as a vectorized result; for example: the "professional requirements" for a recruitment position are: and searching a word of the computer in a preset word vector database, and acquiring an n-dimensional vector corresponding to the computer as a vectorization result of the professional requirement. If the professional requirement is: and (3) automatically, economically and computer, searching three words of 'automatically, economically and computer' and corresponding word vectors thereof in a preset word vector database, wherein the three word vectors are used as vectorization results of 'professional requirements' in the text. Then re-use the formula And calculating the similarity of the first feature vector and the second feature vector, wherein when the calculated similarity is more similar to 1, the more similar the first feature vector and the second feature vector are, the more similar to 0, the more dissimilar the first feature vector and the second feature vector are. Then a specific preset similarity value is preset, and the corresponding positions in the position database which is larger than the preset similarity value are screened out and marked as related positions.
In one embodiment, the recommending means of the second post further comprises:
the characteristic processing module is used for acquiring a plurality of resume from the resume information base, extracting corresponding resume information, acquiring the post information of the current post corresponding to each resume from the extracted resume information, and carrying out characteristic processing on the post information of the current post and the extracted resume information;
the training module is used for inputting the information after the characterization processing into the convolutional neural network model for training;
and the convergence module is used for obtaining a preliminary job matching model after the convolutional neural network model converges.
In the embodiment, the post and resume data are prepared first, the post information and resume information of the first post can be characterized by training a trained Transformer model, the characterized data are input into a convolutional neural network for model training, and when the training times reach the set requirements, the convolutional neural network model is converged, so that a preliminary post matching model is trained. After training is completed, any position can be input into the preliminary position matching model to carry out position matching, the preliminary position matching model returns whether the position is matched or not, and the number of information points in each position matching is larger, and the matching degree of each information point is larger.
The loss value calculation module is used for calculating the loss value of the preliminary position matching model;
the loss value judging module is used for judging whether the loss value is lower than a loss preset value or not;
the identification module is used for identifying the preliminary job matching model as the job matching model if the loss value is lower than the loss preset value;
and the parameter adjustment module is used for adjusting parameters of the convolutional neural network model if the loss value is not lower than the loss preset value, and continuing training the convolutional neural network model until the loss value of the trained preliminary job matching model is lower than the loss preset value.
By the formulaCalculating a loss value of the preliminary job matching model, wherein S is the loss value, A i Representing the ith calculated value calculated by the preliminary job matching model, B i Is equal to A i And the corresponding ith predicted value, n represents the number of data. Judging whether the loss is lower than a loss preset value or not, wherein the loss preset value is a set value, and if the loss is lower than the loss preset value, determining the preliminary job matching model as the job matching model; if the loss is not lower than the loss preset value, adjusting parameters of the convolutional neural network model, and continuing training the convolutional neural network until obtaining The loss value is lower than a preliminary job matching model of the loss preset value. Thereby improving the accuracy of the model. />
In one embodiment, the screening module 50 includes:
the screening submodule is used for screening out the relevant posts with the grading values larger than a preset threshold value as the second posts;
the intention post acquisition sub-module is used for acquiring the intention post of the job seeker in the resume information;
the intention post judging submodule is used for judging whether the intention post belongs to the second post or not;
and the matching post judging sub-module is used for judging that the intention post is the matching post of the job seeker if the intention post is the matching post, and sending the intention post to the job seeker in the form of the matching post.
The method for acquiring the intention post of the job seeker in the resume information can be realized by semantic recognition after the resume information is acquired, then detecting that the intention post is in a second post which is not screened, and if so, pushing a company related to the intention post for the job seeker in advance, so that the job seeker can select own intention according to own conditions and is suitable for own company. The matching post is sent to the job seeker in a form of the matching post, which is different from the recommended form of other second posts, for example, the matching post can be specially marked and then sent to the job seeker, or the matching post can be sent to the job seeker first and then the other second posts are sent to the job seeker, and it should be understood that the sending in the form of the matching post is to enable the job seeker to quickly distinguish from the second posts, and the specific form is not limited.
In one embodiment, the recommending means of the second post further comprises:
the target post acquisition module is used for acquiring a target post selected from the second post by the job seeker;
and the company recommending module is used for recommending the scoring values corresponding to the job seeker resume and the target position to the company where the target position is located.
After a plurality of second posts are selected for the job seeker, if the job seeker is interested in the selected second posts, the target posts selected by the job seeker are received, and at the moment, the resume and the scoring values of the job seeker can be sent to the company where the target posts are located, so that the company can know the job seeker.
The application has the beneficial effects that: through obtaining resume information and personal detail information of the job seeker, a plurality of corresponding relevant posts are selected, and corresponding second posts are provided for the job seeker through the scoring value of the job seeker at each post, so that the efficiency of screening the second posts by the job seeker is improved, and the job seeker can quickly and accurately find the second posts different from the current first posts.
Referring to fig. 3, in an embodiment of the present application, there is further provided a computer device, which may be a server, and an internal structure thereof may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing various post information and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, may implement the second post recommendation method according to any of the embodiments described above.
It will be appreciated by those skilled in the art that the architecture shown in fig. 3 is merely a block diagram of a portion of the architecture in connection with the present inventive arrangements and is not intended to limit the computer devices to which the present inventive arrangements are applicable.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor can implement the second post recommendation method according to any of the above embodiments.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by hardware associated with a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided by the present application and used in embodiments may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (8)
1. A method for recommending a second post, comprising:
extracting resume information in the resume of the job seeker; the resume information comprises post information and personal detail information of a first post of the job seeker, wherein the first post is a post of the job seeker which is currently engaged in, and the first post and the second post are different posts;
Extracting the post information of the first post, comparing the post information of the first post with post information in a post database, and screening according to a preset rule to obtain a plurality of relevant posts;
inputting the resume information and the post information of the related posts into a pre-trained post matching model to obtain the matching degree of the resume information and each related post in the related posts;
calculating the scoring value of the job seeker at each relevant post according to the matching degree and the skill weight information corresponding to each relevant post;
screening out the relevant posts with the grading values larger than a preset threshold value as the second posts, and recommending the second posts to the job seeker;
the step of calculating the scoring value of the job seeker at each relevant post according to the matching degree and the weight corresponding to each relevant post comprises the following steps:
acquiring the working time, the certificate information, the incumbent information and the working skills of the job seeker at the first post according to the resume information and the post information of the first post;
according to the formula Calculating the capability of each working skill of the job seeker; wherein F (xi) represents a function of the ability of the job seeker's ith work skills as a function of the time of the practitioner,>a derivative function representing the ability of the ith work skill as a function of the time of day, g (xi) representing the ability to calculate the ith work skill from the credential information and the incumbent information, t representing the time of day of the first station;
according to the formulaCalculating a scoring value at the relevant post; wherein G (n) represents the grading value of the relevant post, m is the matching degree, wi is the weight parameter corresponding to the ith working skill, and n represents the number of the working skills.
2. The method of recommending a second station according to claim 1, wherein the step of extracting the station information of the first station, comparing the station information of the first station with the station information in the station database, and screening to obtain a plurality of relevant stations according to a preset rule comprises:
extracting first keywords from the post information of the first post and extracting second keywords from the post information of the post database by using a preset text ordering algorithm;
Vectorizing the first keyword and the second keyword by using a preset word vector database to obtain a first feature vector and a second feature vector;
calculating the similarity between the first feature vector and the second feature vector by using a preset similarity algorithm;
and taking the post corresponding to the post information with the similarity larger than the preset similarity value as the relevant post.
3. The method for recommending a second post according to claim 1, wherein before the step of inputting the resume information and the post information of the plurality of related posts into a pre-trained post matching model to obtain a matching degree of the resume information and each of the plurality of related posts, further comprising:
acquiring a plurality of resume from a resume information base, extracting corresponding resume information, acquiring post information of a current post corresponding to each resume from the extracted resume information, and carrying out characteristic processing on the post information of the current post and the extracted resume information;
inputting the information after the characterization treatment into a convolutional neural network model for training;
after the convolutional neural network model converges, a preliminary job matching model is obtained;
Calculating a loss value of the preliminary job matching model;
judging whether the loss value is lower than a loss preset value or not;
if the loss value is lower than the loss preset value, the preliminary job matching model is considered as the job matching model;
and if the loss value is not lower than the loss preset value, adjusting parameters of the convolutional neural network model, and continuing training the convolutional neural network model until the loss value of the trained preliminary job matching model is lower than the loss preset value.
4. The method of recommending a second post according to claim 1, wherein said step of screening out the relevant post having a score value greater than a predetermined threshold as the second post, recommending the second post to the job seeker comprises:
screening out the relevant posts with the grading values larger than a preset threshold value as the second posts;
acquiring the intention post of the job seeker in the resume information;
judging whether the intention post belongs to the second post or not;
if yes, judging that the intention post is the matching post of the job seeker, and sending the matching post to the job seeker after marking.
5. The method of recommending a second post according to claim 1, wherein said step of screening out said relevant post having a score value greater than a predetermined threshold as said second post, recommending said second post to said job seeker further comprises:
acquiring a target post selected from the second post by the job seeker;
recommending the resume of the job seeker and the scoring value corresponding to the target post to the company where the target post is located.
6. A recommendation device for a second station, comprising:
the resume information extraction module is used for extracting resume information in the resume of the job seeker; the resume information comprises post information and personal detail information of a first post of the job seeker, wherein the first post is a post of the job seeker which is currently engaged in, and the first post and the second post are different posts;
the post information extraction module is used for extracting post information of the first post, comparing the post information of the first post with post information in a post database, and screening according to preset rules to obtain a plurality of relevant posts;
the input module is used for inputting the resume information and the post information of the related posts into a post matching model to obtain the matching degree of the resume information and each related post in the related posts;
The scoring value calculation module is used for calculating the scoring value of the job seeker at each relevant post according to the matching degree and the skill weight information corresponding to each relevant post;
the screening module is used for screening out the relevant posts with the grading values larger than a preset threshold value as the second posts, and recommending the second posts to the job seeker;
the scoring value calculation module includes:
the working skill information acquisition sub-module is used for acquiring the working time, the certificate information, the incumbent information and the working skill of the job seeker in the first post according to the resume information and the post information of the first post;
capability calculation submodule for calculating a capability according to a formulaCalculating the capability of each working skill of the job seeker; wherein F (xi) represents a function of the ability of the job seeker's ith work skills as a function of the time of the practitioner,>a derivative function representing the ability of the ith work skill as a function of the time of day, g (xi) representing the ability to calculate the ith work skill from the certification information and the incumbent information, t representing the time of day of the first post;
a scoring value calculation sub-module for calculating a scoring value according to the formula Calculating a scoring value at the relevant post; wherein G (n) represents the grading value of the relevant post, m is the matching degree, wi is the weight parameter corresponding to the ith working skill, and n represents the number of the working skills.
7. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011044951.0A CN112182383B (en) | 2020-09-28 | 2020-09-28 | Recommendation method and device for second post and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011044951.0A CN112182383B (en) | 2020-09-28 | 2020-09-28 | Recommendation method and device for second post and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112182383A CN112182383A (en) | 2021-01-05 |
| CN112182383B true CN112182383B (en) | 2023-11-14 |
Family
ID=73946795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011044951.0A Active CN112182383B (en) | 2020-09-28 | 2020-09-28 | Recommendation method and device for second post and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112182383B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239283B (en) * | 2021-07-09 | 2021-09-28 | 国能大渡河大数据服务有限公司 | Multi-dimension-based post matching degree calculation method and system |
| CN113657496B (en) * | 2021-08-17 | 2023-08-18 | 深圳平安智汇企业信息管理有限公司 | Information matching method, device, equipment and medium based on similarity matching model |
| CN114663042B (en) * | 2022-02-11 | 2023-04-21 | 北京斗米优聘科技发展有限公司 | Smart phone call recruitment method and device, electronic equipment and storage medium |
| CN114168819B (en) * | 2022-02-14 | 2022-07-12 | 北京大学 | Post matching method and device based on graph neural network |
| CN114358657B (en) * | 2022-03-09 | 2022-08-12 | 北京大学 | Post recommendation method and device based on model fusion |
| CN114925287B (en) * | 2022-07-22 | 2022-11-18 | 天津大学 | Intelligent knowledge management system and method based on big data |
| CN115526590B (en) * | 2022-09-16 | 2023-08-04 | 深圳今日人才信息科技有限公司 | Efficient person post matching and re-pushing method combining expert knowledge and algorithm |
| CN117473251A (en) * | 2023-10-10 | 2024-01-30 | 北京华普亿方科技集团股份有限公司 | User job-seeking intention analysis method and system based on big data |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022723A (en) * | 2016-05-19 | 2016-10-12 | 中国传媒大学 | Personalized recommendation method of employment information |
| CN107590133A (en) * | 2017-10-24 | 2018-01-16 | 武汉理工大学 | The method and system that position vacant based on semanteme matches with job seeker resume |
| CN108021673A (en) * | 2017-12-06 | 2018-05-11 | 北京拉勾科技有限公司 | A kind of user interest model generation method, position recommend method and computing device |
| CN109831531A (en) * | 2019-03-15 | 2019-05-31 | 河北冀联人力资源服务集团有限公司 | Job seeker resume method for pushing and device and task method for pushing and device |
| CN110298598A (en) * | 2019-07-03 | 2019-10-01 | 广东倍智测聘网络科技股份有限公司 | A kind of matching process, personnel and post matching device and the electronic equipment of personnel and post |
| CN110874714A (en) * | 2018-08-31 | 2020-03-10 | 阿里巴巴集团控股有限公司 | Data matching method and device |
| CN111708929A (en) * | 2020-06-17 | 2020-09-25 | 北京字节跳动网络技术有限公司 | Information searching method and device, electronic equipment and storage medium |
-
2020
- 2020-09-28 CN CN202011044951.0A patent/CN112182383B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022723A (en) * | 2016-05-19 | 2016-10-12 | 中国传媒大学 | Personalized recommendation method of employment information |
| CN107590133A (en) * | 2017-10-24 | 2018-01-16 | 武汉理工大学 | The method and system that position vacant based on semanteme matches with job seeker resume |
| CN108021673A (en) * | 2017-12-06 | 2018-05-11 | 北京拉勾科技有限公司 | A kind of user interest model generation method, position recommend method and computing device |
| CN110874714A (en) * | 2018-08-31 | 2020-03-10 | 阿里巴巴集团控股有限公司 | Data matching method and device |
| CN109831531A (en) * | 2019-03-15 | 2019-05-31 | 河北冀联人力资源服务集团有限公司 | Job seeker resume method for pushing and device and task method for pushing and device |
| CN110298598A (en) * | 2019-07-03 | 2019-10-01 | 广东倍智测聘网络科技股份有限公司 | A kind of matching process, personnel and post matching device and the electronic equipment of personnel and post |
| CN111708929A (en) * | 2020-06-17 | 2020-09-25 | 北京字节跳动网络技术有限公司 | Information searching method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112182383A (en) | 2021-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112182383B (en) | Recommendation method and device for second post and computer equipment | |
| CN111708873B (en) | Intelligent question-answering method, intelligent question-answering device, computer equipment and storage medium | |
| CN110427563B (en) | Professional field system cold start recommendation method based on knowledge graph | |
| CN110377730B (en) | Case-by-case classification method, apparatus, computer device, and storage medium | |
| CN107168954B (en) | Text keyword generation method and device, electronic equipment and readable storage medium | |
| US20180165370A1 (en) | Methods and systems for object recognition | |
| CN109582704B (en) | Recruitment information and the matched method of job seeker resume | |
| CN111538908A (en) | Search ranking method and device, computer equipment and storage medium | |
| CN112347340B (en) | Information searching method, device and computer equipment | |
| CN110413961B (en) | Method and device for text scoring based on classification model and computer equipment | |
| CN111259113B (en) | Text matching method, text matching device, computer readable storage medium and computer equipment | |
| CN112163079B (en) | Intelligent dialogue method and system based on reading understanding model | |
| CN110717041B (en) | Case retrieval method and system | |
| CN112200153B (en) | Person post matching method, device and equipment based on history matching result | |
| CN112823345A (en) | Ranking image search results using machine learning models | |
| CN116401464B (en) | Professional user portrait construction method, device, equipment and storage medium | |
| CN109948154B (en) | Character acquisition and relationship recommendation system and method based on mailbox names | |
| CN110569419A (en) | question-answering system optimization method and device, computer equipment and storage medium | |
| CN112434217A (en) | Position information recommendation method, system, computer equipment and storage medium | |
| US11409814B2 (en) | Systems and methods for crawling web pages and parsing relevant information stored in web pages | |
| CN106570196B (en) | Video program searching method and device | |
| CN113902354B (en) | Travel evaluation data processing method and device and computer equipment | |
| CN116383366A (en) | Response information determining method, electronic equipment and storage medium | |
| KR102609616B1 (en) | Method and apparatus for image processing, electronic device and computer readable storage medium | |
| CN112989022B (en) | Intelligent virtual text selection method and device and computer equipment |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210224 Address after: 518000 room 64, 3 / F, building 364B, Jingui building, 68 Puti Road, Fubao community, Fubao street, Futian District, Shenzhen City, Guangdong Province Applicant after: Shenzhen Pingan Zhihui Enterprise Information Management Co.,Ltd. Address before: No.1411-14158, main tower of shipping center, No.59 Linhai Avenue, Nanshan street, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong 518000 Applicant before: Ping An digital information technology (Shenzhen) Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |