Job seeker quality grade determination method and device, equipment, medium and program product

Abstract

The invention discloses a job seeker quality grade determination method and device, equipment, a medium and a program product, and the method comprises the steps: carrying out the preprocessing of a target resume of a target job seeker, and obtaining a preprocessed target resume; target key information is extracted from the preprocessed target resume, and target character traits of the target job seeker are determined from the preprocessed target resume; determining target matching information of the target job seeker and the target recruitment post according to the information of the target recruitment post and the preprocessed target resume; performing semantic analysis on the preprocessed target resume to obtain target semantic analysis result information; and inputting the target key information, the target character traits, the target matching information and the target semantic analysis result information into a pre-trained target quality grade classification model to obtain the quality grade of the target job seeker output by the target quality grade classification model. According to the job seeker quality grade determination method, the accuracy, objectivity and comprehensiveness of the determined quality grade are improved.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to a method, device, equipment, medium and program product for determining the quality level of job seekers. Background Art

[0002] With the rapid development of Internet technology and information technology, job seekers can apply for jobs by submitting resumes online. In order to improve recruitment efficiency, employers need to screen out qualified job seekers based on the resumes submitted by job seekers and information about recruitment positions, and determine the quality level of job seekers.

[0003] Currently, the resumes of qualified job seekers can be screened based on the resumes and information about the recruitment positions, and information such as work experience and educational background in these resumes can be counted. Based on the statistical information, the quality level of the job seekers can be determined according to experience.

[0004] However, in the above method, since the quality level of job seekers is determined based on experience, it is impossible to accurately evaluate the quality of job seekers based on statistical information, so that the accuracy of the determined quality level of job seekers is low. Summary of the invention

[0005] The present invention provides a method, device, equipment, medium and program product for determining the quality grade of job seekers, so as to solve the technical problem of low accuracy of the quality grade determination method in the related art.

[0006] According to one aspect of the present invention, there is provided a method for determining the quality level of a job applicant, comprising:

[0007] Preprocessing the target resume of the target job seeker to obtain a preprocessed target resume;

[0008] Extracting target key information from the preprocessed target resume, and determining target personality traits of the target job seeker from the preprocessed target resume;

[0009] Determining target matching information between the target job applicant and the target job according to the information of the target job and the pre-processed target resume;

[0010] Performing semantic analysis on the preprocessed target resume to obtain target semantic analysis result information;

[0011] The target key information, the target personality traits, the target matching information and the target semantic analysis result information are input into a pre-trained target quality grade classification model to obtain the quality grade of the target job seeker output by the target quality grade classification model.

[0012] According to another aspect of the present invention, there is provided a device for determining the quality level of job seekers, comprising:

[0013] A preprocessing module is used to preprocess the target resume of the target job seeker to obtain the preprocessed target resume;

[0014] A first determination module is used to extract target key information from the pre-processed target resume and determine the target personality traits of the target job seeker from the pre-processed target resume;

[0015] A second determination module determines target matching information between the target job seeker and the target job according to information of the target job and the pre-processed target resume;

[0016] A semantic analysis module, used for performing semantic analysis on the preprocessed target resume to obtain target semantic analysis result information;

[0017] The third determination module is used to input the target key information, the target personality traits, the target matching information and the target semantic analysis result information into a pre-trained target quality grade classification model to obtain the quality grade of the target job seeker output by the target quality grade classification model.

[0018] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0019] at least one processor; and

[0020] a memory communicatively connected to the at least one processor; wherein,

[0021] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for determining the quality level of job applicants described in any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program is used to enable a processor to implement the method for determining the quality level of job seekers described in any embodiment of the present invention when executed.

[0023] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method for determining the quality level of job applicants according to any embodiment of the present invention is implemented.

[0024] The technical solution of the embodiment of the present invention includes: preprocessing the target resume of the target job seeker to obtain a preprocessed target resume; extracting target key information from the preprocessed target resume, and determining the target personality traits of the target job seeker from the preprocessed target resume; determining the target matching information between the target job seeker and the target recruitment position based on the information of the target recruitment position and the preprocessed target resume; performing semantic analysis on the preprocessed target resume to obtain target semantic analysis result information; inputting the target key information, target personality traits, target matching information and target semantic analysis result information into a pre-trained target quality grade classification model to obtain the quality grade of the target job seeker output by the target quality grade classification model. The method for determining the quality grade of job seekers can, on the one hand, comprehensively determine the quality grade of target job seekers from multiple dimensions, including key information dimensions in target resumes, personality traits dimensions of target job seekers, matching dimensions between target job seekers and target recruitment positions, and overall dimensions of target resumes, thereby deeply mining the information of target job seekers and avoiding ignoring potential traits of target job seekers, thereby improving the accuracy, objectivity, and comprehensiveness of the determined quality grade; on the other hand, pre-processing the target resume before executing subsequent steps can improve the efficiency of the method for determining the quality grade of job seekers and further improve the accuracy of the determined quality grade.

[0025] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 is a flow chart of a method for determining the quality level of job seekers provided by an embodiment of the present invention;

[0028] Figure 2 is a flow chart of another method for determining the quality level of job seekers provided by an embodiment of the present invention;

[0029] Figure 3 is a block diagram of the execution process of another method for determining the quality level of job seekers provided by an embodiment of the present invention;

[0030] Figure 4 is a flow chart of another method for determining the quality level of job seekers provided by an embodiment of the present invention;

[0031] Figure 5 It is a structural schematic diagram of a device for determining the quality level of job seekers provided by an embodiment of the present invention;

[0032] Figure 6 It is a structural schematic diagram of an electronic device for implementing the method for determining the quality level of job seekers according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the term "comprising" and any variation thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the embodiments of the present invention all comply with the relevant provisions of national laws and regulations.

[0035] Figure 1 1 is a flow chart of a method for determining the quality level of a job applicant provided by an embodiment of the present invention. This embodiment can be applied to a scenario in which the quality level of a job applicant is determined based on the job applicant's resume and information about the job position. The method can be executed by a job applicant quality level determination device, which can be implemented in the form of hardware and / or software. The job applicant quality level determination device can be configured in an electronic device, such as a computer device. Figure 1 As shown, the method includes the following steps 101 to 105.

[0036] Step 101: pre-processing the target resume of the target job seeker to obtain the pre-processed target resume.

[0037] The target job seeker in this embodiment refers to the job seeker whose quality level is to be determined, and can be any job seeker applying for the target job position. The target job position is a job posted by the recruiter. In this embodiment, there is no restriction on the type of the target job position, for example, it can be a job position in the Internet industry, such as programmers, product managers, etc., or it can be a job position in the manufacturing industry, such as project supervisors, audit risk control, etc.

[0038] In this embodiment, the target resume of the target job seeker can be obtained through multiple channels. For example, it can be obtained through a recruitment platform, obtained through an email, obtained through an instant messaging software, etc. This embodiment does not limit the format of the target resume. For example, the format of the target resume can be a portable document format (PDF), an online form, a picture, a document (doc, docx), and docx, etc. This implementation method is not limited to resumes in a specific format, which enhances the flexibility and wide application of the method for determining the quality level of job seekers.

[0039] The target resume in this embodiment may include information such as the name, educational background, work experience and skills of the target job seeker.

[0040] The preprocessing in this embodiment may include at least one of the following: text cleaning and text normalization. The text cleaning in this embodiment includes removing special characters and punctuation marks, etc. The text normalization in this embodiment includes unifying upper and lower case, extracting stems, etc. After preprocessing the target resume, a preprocessed target resume is obtained.

[0041] The subsequent steps of this embodiment are implemented based on the preprocessed target resume. Since the preprocessed target resume is a resume after text cleaning and text normalization, the efficiency and accuracy of the job seeker quality level determination method provided in this embodiment can be improved by performing subsequent steps based on the preprocessed target resume.

[0042] This embodiment introduces natural language processing (NLP) technologies such as stem extraction when preprocessing the target resume, so that the information extraction of the target resume after preprocessing is more accurate.

[0043] Step 102: Extract target key information from the pre-processed target resume, and determine the target personality traits of the target job seeker from the pre-processed target resume.

[0044] This embodiment can extract target key information from the preprocessed target resume through at least the following two implementation methods.

[0045] In one implementation, the target key information can be extracted from the preprocessed target resume in the following manner: the preprocessed target resume is input into a pre-trained key information extraction model to obtain the target key information output by the key information extraction model. The target key information includes at least one of the following: the target job seeker's educational background, work experience, and skills.

[0046] Optionally, the key information extraction model in this embodiment may be a model trained based on NLP technology. Exemplarily, the key information extraction model may be a named entity recognition (NER) model.

[0047] The key information extraction model in this embodiment can extract the target key information from the target resume after preprocessing. The extracted target key information can be an educational background that meets the predefined educational background, work experience that meets the predefined work experience, and skills that meet the predefined skills. For example, assuming that the key information is more than 5 years of work experience and a master's degree, the trained key information extraction model can extract at least a part of the key information from the resume with the key information. Assuming that the work experience in the target resume after preprocessing is 3 years and the degree is a master's degree, the target key information extracted in this embodiment is a master's degree.

[0048] In another implementation method, the target key information can be extracted from the preprocessed target resume in the following manner: establish a key information database, which includes multiple key information; based on the key information database, determine the target key information that matches the key information in the key information database from the preprocessed target resume.

[0049] This embodiment can determine the target personality traits of the target job seeker from the preprocessed target resume in at least two implementation methods as follows. The personality traits in this embodiment are used to characterize the psychological characteristics of the job seeker during the work process. Exemplarily, the personality traits in this embodiment can be high work enthusiasm, strong work stress resistance, strong work responsibility, etc.

[0050] In one implementation, the preprocessed target resume may be input into a pre-trained personality trait analysis model to obtain the target personality trait output by the personality trait analysis model.

[0051] In another implementation, personality keywords corresponding to each personality trait may be pre-established. Then, target personality keywords are extracted from the pre-processed target resume. The target personality keywords are matched with the personality keywords corresponding to each personality trait, and the personality trait with the highest matching degree is determined as the target personality trait.

[0052] In step 102, the significance of determining the target personality traits of the target job seeker is that, when determining the quality level of the job seeker, in addition to considering the target key information in the target resume, the personality traits and potential value of the target job seeker are also considered, so as to facilitate the comprehensive determination of the quality level.

[0053] Step 103: Determine target matching information between the target job seeker and the target job according to the information of the target job and the pre-processed target resume.

[0054] Optionally, the information of the target recruitment position in this embodiment may include: required skills, experience requirements, work location, certificate requirements, etc.

[0055] In one implementation, step 103 includes the following steps 1031 to 1034 .

[0056] Step 1031: Determine a first keyword list from the information of the target recruitment position.

[0057] The first keyword table includes each first field and the value of each first field.

[0058] Optionally, the first field in this embodiment may include: required skills, experience requirements, work location, age and gender, certificates and certifications, etc. The values ​​of each first field are extracted from the information of the target recruitment position to form a first keyword table.

[0059] Step 1032: Determine a second keyword list from the preprocessed target resume.

[0060] The second keyword table includes each second field and the value of each second field.

[0061] Optionally, the second field in this embodiment may include: acquired skills, project experience, desired work location, age and gender, certificates and certifications, etc. The values ​​of each second field are extracted from the pre-processed target resume to form a second keyword table.

[0062] Step 1033: For each first field, determine the second field corresponding to the first field from the second keyword table, and determine a matching relationship between the value of the first field and the value of the second field corresponding to the first field.

[0063] In this embodiment, a mapping relationship between the first field and the second field may be pre-established. For example, required skills correspond to mastered skills, experience requirements correspond to project experience, and work location corresponds to expected work location. In step 1033, for each first field, based on the mapping relationship, the second field corresponding to the first field may be determined from the second keyword table, and a matching relationship between the value of the first field and the value of the second field corresponding to the first field may be determined.

[0064] Step 1034: Determine target matching information between target job seekers and target recruitment positions based on the matching relationships corresponding to all first fields.

[0065] In step 1034, all matching relationships corresponding to the first fields are combined and processed to obtain target matching information of target job seekers and target recruitment positions.

[0066] Exemplarily, the target matching information may include: the matching relationship between required skills and mastered skills is: complete match, the matching relationship between experience requirements and project experience is: partial match, the matching relationship between work location and expected work location is: no match, the matching relationship between age and gender and age and gender is: other, and the matching relationship between certificates and certifications and certificates and certifications is: other.

[0067] In another implementation, the target matching information may be determined based on the text similarity between the information of the target recruitment position and the preprocessed target resume.

[0068] Step 104: Perform semantic analysis on the preprocessed target resume to obtain target semantic analysis result information.

[0069] In this embodiment, in order to improve the accuracy of the determined quality level, semantic analysis can also be performed on the pre-processed target resume to obtain target semantic analysis result information for subsequent determination of the quality level of the target job seeker. The target semantic analysis result information in this embodiment is information obtained after in-depth understanding and analysis of the entire pre-processed target resume.

[0070] In this embodiment, semantic analysis can be performed on the preprocessed target resume based on NLP technology to obtain target semantic analysis result information.

[0071] Step 105: Input the target key information, target personality traits, target matching information and target semantic analysis result information into a pre-trained target quality grade classification model to obtain the quality grade of the target job seeker output by the target quality grade classification model.

[0072] This embodiment can determine the quality grade of the target job seeker based on the trained target quality grade classification model. Input the target key information, target personality traits, target matching information and target semantic analysis result information into the pre-trained target quality grade classification model to obtain the quality grade of the target job seeker output by the target quality grade classification model.

[0073] The quality level in this embodiment can be expressed by text, for example, the highest quality level, high quality level, medium quality level, low quality level, etc. The quality level in this embodiment can also be expressed by numbers or letters, for example, the quality levels are A, B, C and D, etc. The quality level actually mapped to each letter can be predetermined. In this embodiment, the higher the quality level, the more the target job seeker meets the requirements of the target recruitment position.

[0074] It can be seen that this embodiment can comprehensively determine the quality level of the target job seeker from multiple dimensions, including the key information dimension in the target resume, the personality trait dimension of the target job seeker, the matching dimension between the target job seeker and the target job position, and the overall dimension of the target resume, so as to achieve in-depth mining of the target job seeker's information and avoid ignoring the target job seeker's potential traits, thereby improving the accuracy, comprehensiveness and objectivity of the determined quality level. Based on the determined accurate, comprehensive and objective quality level, the job seeker who best meets the job position can be quickly screened out later, thereby improving recruitment efficiency and improving recruitment quality.

[0075] Optionally, in order to further improve the accuracy of the determined quality grade, so as to further improve the recruitment efficiency and quality, in this embodiment, the target quality grade classification model can be updated and trained in the following manner to achieve dynamic optimization of the target quality grade classification model: obtaining at least one target resume with feedback information among multiple target resumes; updating and training the target quality grade classification model based on at least one target resume with feedback information to obtain a new target quality grade classification model. The feedback information in this embodiment can be the recruiter's true evaluation or feedback on the quality grade of the target resume. Exemplarily, the feedback information can be a high quality grade, a very accurate quality grade evaluation, or a very inaccurate quality grade evaluation.

[0076] In actual implementation, a feedback interface can be provided to the recruiter, and the recruiter fills in the feedback information for the target resume in the feedback interface. At least one target resume with feedback information is regularly obtained from multiple target resumes; the target quality grade classification model is updated and trained according to the at least one target resume with feedback information to obtain a new target quality grade classification model.

[0077] The method for determining the quality grade of job seekers provided in this embodiment includes: preprocessing a target resume of a target job seeker to obtain a preprocessed target resume; extracting target key information from the preprocessed target resume, and determining the target personality traits of the target job seeker from the preprocessed target resume; determining target matching information between the target job seeker and the target recruitment position based on information of the target recruitment position and the preprocessed target resume; performing semantic analysis on the preprocessed target resume to obtain target semantic analysis result information; inputting the target key information, target personality traits, target matching information and target semantic analysis result information into a pre-trained target quality grade classification model to obtain the quality grade of the target job seeker output by the target quality grade classification model. The method for determining the quality grade of job seekers can, on the one hand, comprehensively determine the quality grade of target job seekers from multiple dimensions, including key information dimensions in target resumes, personality traits dimensions of target job seekers, matching dimensions between target job seekers and target recruitment positions, and overall dimensions of target resumes, thereby deeply mining the information of target job seekers and avoiding ignoring potential traits of target job seekers, thereby improving the accuracy, objectivity, and comprehensiveness of the determined quality grade; on the other hand, pre-processing the target resume before executing subsequent steps can improve the efficiency of the method for determining the quality grade of job seekers and further improve the accuracy of the determined quality grade.

[0078] Figure 2 is a flow chart of another method for determining the quality level of job seekers provided by an embodiment of the present invention. The method for determining the quality level of job seekers provided by this embodiment, Figure 1 Based on the illustrated embodiment and various optional implementations, the implementation of step 105 is described in detail. Figure 2 As shown, the method for determining the quality level of job applicants provided in this embodiment includes the following steps 201 to 209.

[0079] Step 201: pre-processing the target resume of the target job seeker to obtain the pre-processed target resume.

[0080] Step 202: extract target key information from the pre-processed target resume, and determine the target personality traits of the target job seeker from the pre-processed target resume.

[0081] Step 203: Determine target matching information between the target job seeker and the target job according to the information of the target job and the pre-processed target resume.

[0082] Step 204: Perform semantic analysis on the preprocessed target resume to obtain target semantic analysis result information.

[0083] The implementation process and technical principle of step 201 and step 101, step 202 and step 102, step 203 and step 103, and step 204 and step 104 are similar, and will not be repeated here.

[0084] In this embodiment, in order to further improve the accuracy of the determined quality level and increase the processing speed of the target quality level classification model, the target key information, the target personality traits and the target matching information may be converted into feature vectors.

[0085] Step 205: convert the target key information to obtain target key information features.

[0086] Optionally, the target key information may be converted based on a vector model to obtain target key information features. The target key information features in this embodiment may be vectors or matrices.

[0087] Step 206: Convert the target personality traits to obtain target personality trait characteristics.

[0088] Optionally, the target personality trait may be converted based on One-Hot encoding to obtain the target personality trait feature. The target personality trait feature in this embodiment may be a vector or a matrix.

[0089] Step 207: convert the target matching information to obtain target matching information features.

[0090] Optionally, the target matching information may be converted based on one-hot encoding to obtain target matching information features.

[0091] Based on the example in step 1034, it is assumed that the target matching information includes: the matching relationship between the required skills and the acquired skills is: complete match, the matching relationship between the experience requirements and the project experience is: partial match, the matching relationship between the work location and the expected work location is: mismatch, the matching relationship between age and gender and age and gender is: other, and the matching relationship between certificates and certifications and certificates and certifications is: other. Assume that the label of safe matching is 3, the label of partial matching is 2, the label of mismatch is 1, and the label of others indicates that there is no match, and its label is 0. Then the target matching information feature corresponding to the target matching information is 32100.

[0092] Step 208: Concatenate the target key information feature, the first weight corresponding to the target key information feature, the target personality trait feature, the second weight corresponding to the target personality trait feature, the target matching information feature, and the third weight corresponding to the target matching information feature to obtain the target input feature.

[0093] Among them, the first weight, the third weight and the second weight decrease in sequence, and are all numbers greater than 0.

[0094] In this embodiment, in order to further improve the accuracy of the determined quality level, corresponding weights are set for different dimensions. Among them, the key information dimension has the largest weight, the target job seeker and the target job position matching dimension has the second largest weight, and the target job seeker's personality trait dimension has the smallest weight. This is because when considering job seekers from the perspective of the recruiter, the key information dimension is the most important, the job seeker and the job position matching dimension is the second, and the personality trait dimension is relatively less important. Therefore, the weights corresponding to the various dimensions in this embodiment also meet the actual recruitment needs.

[0095] Exemplarily, the first weight may be 2, the second weight may be 0.5, and the third weight may be 1.

[0096] The splicing in this embodiment refers to connecting these information together to form an overall vector or matrix, and the spliced ​​result is called the target input feature.

[0097] Step 209: Input the target input features and the target semantic analysis result information into the target quality grade classification model to obtain the quality grade of the target job seeker output by the target quality grade classification model.

[0098] In one implementation, the target semantic analysis result is text. In this implementation, the semantic analysis result can be converted into a semantic vector. Then, the target input features and the semantic vector are input into a target quality grade classification model to obtain the quality grade of the target job seeker output by the target quality grade classification model.

[0099] In another implementation, the target semantic analysis result is in vector form, and the target input features and target semantic analysis result information can be directly input into the target quality grade classification model.

[0100] After receiving the target input features and the target semantic analysis result information, the target quality grade classification model can weight the target key information features based on the first weight, weight the target personality trait features based on the second weight, and weight the target matching information features based on the third weight, so as to further improve the accuracy of the determined quality grade.

[0101] Figure 3 FIG. 1 is a block diagram of another method for determining the quality level of job seekers provided by an embodiment of the present invention. Figure 3As shown, this embodiment obtains the target resume in the format of PDF, online form or picture. After that, preprocessing such as data cleaning is performed to obtain the preprocessed target resume. After that, the target key information is extracted from the preprocessed target resume, and the target personality traits of the target job seeker are determined from the preprocessed target resume. According to the information of the target recruitment position and the preprocessed target resume, the target matching information between the target job seeker and the target recruitment position is determined. The preprocessed target resume is semantically analyzed to obtain the target semantic analysis result information. After that, step 205 is executed to obtain the target key information features, step 206 is executed to obtain the target personality trait features, and step 207 is executed to obtain the target matching information features. Feature embedding is performed on these three features and their corresponding weights to obtain the target input features. The target input features and the target semantic analysis result information are input into the target quality grade classification model to obtain the quality grade of the target job seeker output by the target quality grade classification model.

[0102] Furthermore, the target quality grade classification model can be updated and trained based on the feedback from the employer to continuously improve the prediction accuracy of the target quality grade classification model.

[0103] The method for determining the quality grade of job seekers provided in this embodiment converts the target key information to obtain the target key information feature, converts the target personality trait to obtain the target personality trait feature, converts the target matching information to obtain the target matching information feature, splices the target key information feature, the first weight corresponding to the target key information feature, the target personality trait feature, the second weight corresponding to the target personality trait feature, the target matching information feature, and the third weight corresponding to the target matching information feature to obtain the target input feature, wherein the first weight, the third weight, and the second weight decrease in sequence and are all numbers greater than 0, and inputs the target input feature and the target semantic analysis result information into the target quality grade classification model to obtain the quality grade of the target job seeker output by the target quality grade classification model. On the one hand, it is realized that the target key information, the target personality trait, and the target matching information can be converted into corresponding feature vectors respectively, thereby improving the processing speed of the target quality grade classification model, and further improving the efficiency of the method for determining the quality grade of job seekers. On the other hand, by splicing the first weight corresponding to the target key information feature, the second weight corresponding to the target personality trait feature, and the third weight corresponding to the target matching information feature and inputting them into the target quality grade classification model, the accuracy of the determined quality grade is further improved.

[0104] Figure 4 Flowchart of another method for determining the quality level of job seekers provided by an embodiment of the present invention. Figure 1 and Figure 2Based on the illustrated embodiment and various optional implementations, the training process of the target quality grade classification model is described in detail. For simplicity, only the training process of the target quality grade classification model is shown in this embodiment. The method for determining the quality grade of job seekers provided in this embodiment also includes the following steps.

[0105] Step 401: pre-process the training resumes of the training job seekers in the training set to obtain pre-processed training resumes.

[0106] It should be noted that, in step 401, training resumes in various formats may be collected, not limited to a specific type of resume, so as to enhance the applicability and extensiveness of the method for determining the quality level of job applicants.

[0107] Step 402: extract key training information from the pre-processed training resume, and determine the training personality traits of the training job seeker from the pre-processed training resume.

[0108] Step 403: Determine the training matching information between the training job seeker and the training recruitment position according to the information of the training recruitment position and the pre-processed training resume.

[0109] Step 404: Perform semantic analysis on the preprocessed training resume to obtain training semantic analysis result information.

[0110] The difference between step 401 and step 101, step 402 and step 102, step 403 and step 103, and step 404 and step 104 is that the objects of processing are different: in this embodiment, the above processing is performed on the training resume, while Figure 1 In the illustrated embodiment, the above processing is performed on the target resume, and the rest of the implementation process and technical principles are similar and will not be described in detail here.

[0111] Step 405: Perform supervised training on the initial quality grade classification model according to the training key information, training personality traits, training matching information, training semantic analysis result information and calibration data of the training resume to obtain a target quality grade classification model.

[0112] The training process in this embodiment is a supervised training process. Input the training key information, training personality traits, training matching information, and training semantic analysis result information into the initial quality grade classification model to obtain the model output result. According to the model output result and the calibration data, the stochastic gradient descent algorithm is used to calculate the loss function. Update the parameters of the initial quality grade classification model with the loss function to obtain a new initial quality grade classification model. Return to execute the step of "inputting the training key information, training personality traits, training matching information, and training semantic analysis result information into the initial quality grade classification model to obtain the model output result" until the iteration termination condition is met. The new initial quality grade classification model at this time is determined as the target quality grade classification model.

[0113] Furthermore, during the training process, an implementation method similar to steps 205 to 209 may also be adopted: converting the training key information to obtain training key information features; converting the training personality traits to obtain training personality trait features; converting the training matching information to obtain training matching information features; concatenating the training key information features, the first weights corresponding to the training key information features, the training personality trait features, the second weights corresponding to the training personality trait features, the training matching information features, and the third weights corresponding to the training matching information features to obtain training input features; and performing supervised training on the initial quality grade classification model based on the training input features, the training semantic analysis result information, and the calibration data of the training resume to obtain a target quality grade classification model.

[0114] The method for determining the quality level of job seekers provided in this embodiment pre-processes the training resume during the training process to obtain the pre-processed training resume, and then performs subsequent steps based on the pre-processed training resume, thereby improving the training efficiency and the accuracy of the trained target quality level classification model. At the same time, based on the training process, the trained target quality level classification model can comprehensively determine the quality level of job seekers from multiple dimensions, including the key information dimension in the resume, the personality trait dimension of the job seeker, the matching dimension between the job seeker and the recruitment position, and the overall dimension of the resume, so as to realize in-depth mining of the target job seeker's information and avoid ignoring the job seeker's potential characteristics, thereby improving the accuracy, objectivity and comprehensiveness of the determined quality level.

[0115] Figure 5 Schematic diagram of a device for determining the quality level of job seekers provided by an embodiment of the present invention. Figure 5 As shown, the device for determining the quality level of job applicants provided in this embodiment includes the following modules: a preprocessing module 51 , a first determining module 52 , a second determining module 53 , a semantic analysis module 54 and a third determining module 55 .

[0116] The preprocessing module 51 is used to preprocess the target resume of the target job seeker to obtain the preprocessed target resume.

[0117] The first determination module 52 is used to extract target key information from the pre-processed target resume and determine the target personality traits of the target job seeker from the pre-processed target resume.

[0118] The second determination module 53 determines target matching information between the target job seeker and the target job according to the information of the target job and the pre-processed target resume.

[0119] The semantic analysis module 54 is used to perform semantic analysis on the preprocessed target resume to obtain target semantic analysis result information.

[0120] The third determination module 55 is used to input the target key information, the target personality traits, the target matching information and the target semantic analysis result information into a pre-trained target quality grade classification model to obtain the quality grade of the target job seeker output by the target quality grade classification model.

[0121] In one embodiment, the third determination module 55 is specifically used to: convert the target key information to obtain target key information features; convert the target personality traits to obtain the target personality trait features; convert the target matching information to obtain target matching information features; concatenate the target key information features, the first weight corresponding to the target key information features, the target personality trait features, the second weight corresponding to the target personality trait features, the target matching information features and the third weight corresponding to the target matching information features to obtain target input features, wherein the first weight, the third weight and the second weight decrease in sequence and are all numbers greater than 0; input the target input features and the target semantic analysis result information into the target quality grade classification model to obtain the quality grade of the target job seeker output by the target quality grade classification model.

[0122] In one embodiment, the second determination module 53 is specifically used to: determine a first keyword table from the information of the target recruitment position, wherein the first keyword table includes each first field and the value of each first field; determine a second keyword table from the preprocessed target resume, wherein the second keyword table includes each second field and the value of each second field; for each first field, determine the second field corresponding to the first field from the second keyword table, and determine the matching relationship between the value of the first field and the value of the second field corresponding to the first field; determine the target matching information of the target job seeker and the target recruitment position based on the matching relationships corresponding to all the first fields.

[0123] In one embodiment, the device also includes a training module, which is used to perform the following operations: preprocessing the training resumes of training job applicants in the training set to obtain preprocessed training resumes; extracting training key information from the preprocessed training resumes, and determining the training personality traits of the training job applicants from the preprocessed training resumes; determining the training matching information between the training job applicants and the training recruitment positions based on the information of the training recruitment positions and the preprocessed training resumes; performing semantic analysis on the preprocessed training resumes to obtain training semantic analysis result information; performing supervised training on the initial quality grade classification model based on the training key information, the training personality traits, the training matching information, the training semantic analysis result information and the calibration data of the training resume to obtain the target quality grade classification model.

[0124] In one embodiment, the device further includes an acquisition module and an update training module.

[0125] The acquisition module is used to acquire at least one target resume with feedback information among the multiple target resumes.

[0126] An update training module is used to update and train the target quality grade classification model according to the at least one fed-back target resume and the feedback information to obtain a new target quality grade classification model.

[0127] In one embodiment, in the aspect of extracting target key information from the preprocessed target resume, the first determination module 52 is specifically used to: input the preprocessed target resume into a pre-trained key information extraction model to obtain the target key information output by the key information extraction model. The target key information includes at least one of the following: the educational background, work experience and skills of the target job seeker.

[0128] The device for determining the quality grade of job applicants provided in the embodiment of the present invention can execute the method for determining the quality grade of job applicants provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0129] Figure 6 1 is a schematic diagram of the structure of an electronic device that implements the method for determining the quality level of job seekers of an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0130] like Figure 6 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0131] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0132] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the job applicant quality level determination method.

[0133] In some embodiments, the method for determining the quality level of job applicants may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for determining the quality level of job applicants described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the method for determining the quality level of job applicants in any other appropriate manner (e.g., by means of firmware).

[0134] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0135] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0136] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0137] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0138] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0139] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0140] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the method for determining the quality level of job applicants provided in any embodiment of the present invention.

[0141] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0142] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0143] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining the quality level of job seekers, characterized in that: include: Preprocessing the target resume of the target job seeker to obtain a preprocessed target resume; Extracting target key information from the preprocessed target resume, and determining target personality traits of the target job seeker from the preprocessed target resume; Determining target matching information between the target job applicant and the target job according to the information of the target job and the pre-processed target resume; Performing semantic analysis on the preprocessed target resume to obtain target semantic analysis result information; The target key information, the target personality traits, the target matching information and the target semantic analysis result information are input into a pre-trained target quality grade classification model to obtain the quality grade of the target job seeker output by the target quality grade classification model.

2. The method according to claim 1, characterized in that The step of inputting the target key information, the target personality traits, the target matching information and the target semantic analysis result information into a pre-trained target quality grade classification model to obtain the quality grade of the target job seeker output by the target quality grade classification model comprises: Converting the target key information to obtain target key information features; Converting the target personality traits to obtain the target personality trait characteristics; Converting the target matching information to obtain target matching information features; The target key information feature, the first weight corresponding to the target key information feature, the target personality trait feature, the second weight corresponding to the target personality trait feature, the target matching information feature, and the third weight corresponding to the target matching information feature are concatenated to obtain a target input feature; wherein the first weight, the third weight, and the second weight decrease in sequence and are all numbers greater than 0; The target input features and the target semantic analysis result information are input into the target quality grade classification model to obtain the quality grade of the target job seeker output by the target quality grade classification model.

3. The method according to claim 1, characterized in that Determining target matching information between the target job seeker and the target job according to the information of the target job and the pre-processed target resume includes: Determine a first keyword table from the information of the target recruitment position; wherein the first keyword table includes each first field and the value of each first field; Determine a second keyword table from the preprocessed target resume; wherein the second keyword table includes each second field and each value of the second field; For each of the first fields, determine the second field corresponding to the first field from the second keyword table, and determine a matching relationship between the value of the first field and the value of the second field corresponding to the first field; According to the matching relationships corresponding to all the first fields, target matching information between the target job seeker and the target recruitment position is determined.

4. The method according to any one of claims 1 to 3, characterized in that: The target quality grade classification model is trained in the following way: Preprocessing the training resumes of the training job seekers in the training set to obtain preprocessed training resumes; Extracting key training information from the pre-processed training resume, and determining the training personality traits of the training job seeker from the pre-processed training resume; Determining training matching information between the training job seeker and the training recruitment position according to the information of the training recruitment position and the pre-processed training resume; Performing semantic analysis on the preprocessed training resume to obtain training semantic analysis result information; The initial quality grade classification model is supervisedly trained according to the training key information, the training personality traits, the training matching information, the training semantic analysis result information and the calibration data of the training resume to obtain the target quality grade classification model.

5. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Obtain at least one target resume with feedback information from among the plurality of target resumes; The target quality grade classification model is updated and trained according to the at least one fed-back target resume and the feedback information to obtain a new target quality grade classification model.

6. The method according to any one of claims 1 to 3, characterized in that: The step of extracting target key information from the preprocessed target resume includes: The preprocessed target resume is input into a pre-trained key information extraction model to obtain the target key information output by the key information extraction model; wherein the target key information includes at least one of the following: the educational background, work experience and skills of the target job seeker.

7. A device for determining the quality level of job seekers, characterized in that: include: A preprocessing module is used to preprocess the target resume of the target job seeker to obtain the preprocessed target resume; A first determination module is used to extract target key information from the pre-processed target resume and determine the target personality traits of the target job seeker from the pre-processed target resume; A second determination module determines target matching information between the target job seeker and the target job according to information of the target job and the pre-processed target resume; A semantic analysis module, used for performing semantic analysis on the preprocessed target resume to obtain target semantic analysis result information; The third determination module is used to input the target key information, the target personality traits, the target matching information and the target semantic analysis result information into a pre-trained target quality grade classification model to obtain the quality grade of the target job seeker output by the target quality grade classification model.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so as to enable the at least one processor to perform the method for determining the quality level of job applicants according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is used to enable a processor to implement the method for determining the quality level of job applicants according to any one of claims 1 to 6 when executed.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the method for determining the quality level of job applicants according to any one of claims 1 to 6.

Images