Recruitment talent portrait generation method and system based on multi-dimensional information

Abstract

The invention is suitable for the technical field of recruitment portraits, and provides a recruitment talent portrait generation method and system based on multi-dimensional information, and the method comprises the following steps: collecting the resume information of candidates; performing data cleaning and data conversion on the resume information; performing feature extraction, analyzing candidate online behavior data based on a natural language processing technology, and extracting behavior patterns and interest points; performing model training and evaluation based on historical resume data to obtain a talent portrait model; the resume information, the behavior modes and the interest points of the candidates are input into a talent portrait model, candidate portraits are obtained, and the candidate portraits comprise skill ability evaluation, occupational development potential and culture adaptation degree; and providing personalized vocational development suggestions and post matching recommendations according to the candidate portraits. According to the method, through feature extraction and machine learning model training, a detailed talent portrait is generated, the scientificity of recruitment decision making is improved, suitable candidates are rapidly identified, and vocational suggestions are provided for the candidates.

Description

Technical Field

[0001] The present invention relates to the technical field of recruitment portraits, and in particular to a method and system for generating recruitment talent portraits based on multi-dimensional information. Background Art

[0002] Existing recruitment talent profile generation solutions mainly rely on resume screening and interview evaluation. These methods usually rely on subjective judgment and are difficult to comprehensively and objectively evaluate the comprehensive ability and matching degree of candidates. Some advanced systems use basic data analysis and automation tools, but the integration and in-depth analysis of multi-dimensional data are still insufficient.

[0003] The main defects currently exist: 1. Insufficient data integration: Existing systems may not be able to effectively integrate all relevant information of candidates, such as online behavioral data and diverse skill certificates. 2. High subjectivity: Traditional methods rely on subjective judgment, which affects the accuracy of talent matching and recruitment decisions. 3. Limited data processing: Many systems fail to fully utilize machine learning technology for in-depth data analysis, which limits the accuracy of talent portraits and the scientific nature of decision support. 4. Insufficient personalization: Current systems are generally unable to provide personalized career advice and development paths, and fail to effectively meet the career development needs of candidates. Therefore, it is necessary to provide a method and system for generating recruitment talent portraits based on multi-dimensional information to solve the above problems. Summary of the invention

[0004] In view of the deficiencies in the prior art, the purpose of the present invention is to provide a method and system for generating recruitment talent portraits based on multi-dimensional information to solve the problems existing in the above-mentioned background technology.

[0005] The present invention is implemented as follows: a method for generating a recruitment talent portrait based on multi-dimensional information, the method comprising the following steps:

[0006] Collecting candidate resume information, including basic personal information, target job position, work experience, educational background, skill certificates, and online behavior data;

[0007] Perform data cleaning and data conversion on resume information;

[0008] Perform feature extraction and analyze candidate online behavior data based on natural language processing technology to extract behavior patterns and points of interest;

[0009] Train and evaluate the model based on historical resume data to obtain a talent portrait model;

[0010] Input the candidate's resume information, behavior patterns and interests into the talent portrait model to obtain the candidate portrait, which includes skill ability assessment, career development potential and cultural adaptability;

[0011] Provide personalized career development advice and job matching recommendations based on candidate profiles.

[0012] As a further solution of the present invention: the steps of data cleaning and data conversion of resume information specifically include:

[0013] Processing missing values ​​and outliers on resume information, and performing data standardization and normalization. The missing value processing includes filling strategy and deletion strategy, and the outlier processing includes identifying anomalies and processing anomalies;

[0014] Converting unstructured data into structured data specifically includes format standardization and data type conversion. The format standardization includes date format and text encoding unification, and the data type conversion includes numerical conversion and text conversion.

[0015] As a further solution of the present invention: the step of performing feature extraction specifically includes:

[0016] Conducting business relevance analysis, including job requirement matching and candidate historical performance;

[0017] Performing feature importance evaluation, wherein the feature importance evaluation includes weight calculation and contribution analysis;

[0018] Analyze online behavior data, including activity analysis and interactive behavior analysis.

[0019] As a further solution of the present invention: the step of training and evaluating the model based on the historical resume data to obtain the talent portrait model specifically includes:

[0020] Build a training data set based on historical resume data, obtain training set and validation set, and perform data annotation;

[0021] Performing model training based on machine learning algorithms, including classification algorithms, regression analysis, and cluster analysis algorithms;

[0022] The accuracy, recall and F1 score indicators were used to evaluate the model performance and to cross-validate the talent profile model.

[0023] As a further solution of the present invention: the step of providing personalized career development suggestions and job matching recommendations based on the candidate portrait specifically includes:

[0024] Recruitment recommendations are made based on candidate profiles. Recommendation algorithms include collaborative filtering and content recommendation to optimize recommendation results.

[0025] Get career development path planning, including job promotion paths and skills improvement suggestions;

[0026] Collect user feedback information, analyze and apply it.

[0027] Another object of the present invention is to provide a recruitment talent portrait generation system based on multi-dimensional information, the system comprising:

[0028] A resume information collection module is used to collect the candidate's resume information, which includes basic personal information, target professional position, work experience, educational background, skill certificates and online behavior data;

[0029] Data cleaning and conversion module, used for data cleaning and data conversion of resume information;

[0030] Data feature extraction module, used for feature extraction, analyzing candidate online behavior data based on natural language processing technology, and extracting behavior patterns and points of interest;

[0031] The talent portrait model module is used to train and evaluate the model based on historical resume data to obtain a talent portrait model;

[0032] The candidate portrait module is used to input the candidate's resume information, behavior patterns and interests into the talent portrait model to obtain the candidate portrait, which includes skill ability assessment, career development potential and cultural adaptability;

[0033] The job matching recommendation module is used to provide personalized career development suggestions and job matching recommendations based on candidate portraits.

[0034] As a further solution of the present invention: the data cleaning conversion module includes:

[0035] A data cleaning unit, used to process missing values ​​and outliers in resume information, and to standardize and normalize data. The missing value processing includes filling strategy and deletion strategy, and the outlier processing includes identifying anomalies and processing anomalies.

[0036] The data conversion unit is used to convert unstructured data into structured data, specifically including format standardization and data type conversion. The format standardization includes date format and text encoding unification, and the data type conversion includes numerical conversion and text conversion.

[0037] As a further solution of the present invention: the data feature extraction module includes:

[0038] A relevance analysis unit, used to perform business relevance analysis, wherein the business relevance analysis includes job requirement matching and candidate historical performance;

[0039] A feature evaluation unit, used to perform feature importance evaluation, wherein the feature importance evaluation includes weight calculation and contribution analysis;

[0040] The behavior data analysis unit is used to analyze online behavior data, including activity analysis and interactive behavior analysis.

[0041] As a further solution of the present invention: the talent portrait model module includes:

[0042] The training data set unit is used to construct a training data set based on historical resume data, obtain a training set and a validation set, and perform data annotation;

[0043] A model training unit, used to perform model training based on a machine learning algorithm, wherein the machine learning algorithm includes a classification algorithm, a regression analysis algorithm, and a cluster analysis algorithm;

[0044] The model evaluation and verification unit is used to evaluate model performance using accuracy, recall, and F1 score indicators, and to cross-validate the talent profile model.

[0045] As a further solution of the present invention: the job matching recommendation module includes:

[0046] Recruitment recommendation unit, used to make recruitment recommendations based on candidate profiles. Recommendation algorithms include collaborative filtering and content recommendation to optimize recommendation results.

[0047] Career development planning unit, used to obtain career development path planning, including job promotion paths and skill improvement suggestions;

[0048] The user feedback unit is used to collect user feedback information, analyze and apply the user feedback information.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] The present invention analyzes the online behavior data of candidates based on natural language processing technology, extracts behavior patterns and points of interest from them; trains and evaluates the model based on historical resume data to obtain a talent portrait model; inputs the candidate's resume information, behavior patterns and points of interest into the talent portrait model to obtain a candidate portrait; and finally provides personalized career development suggestions and job matching recommendations based on the candidate portrait. In this way, the present invention can automatically generate detailed talent portraits to improve the scientific nature of recruitment decisions, quickly identify suitable candidates, and provide career advice to candidates. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is a flowchart of a method for generating recruitment talent portraits based on multi-dimensional information.

[0052] Figure 2 This is a flowchart for data cleaning in a recruitment talent portrait generation method based on multi-dimensional information.

[0053] Figure 3 This is a flowchart for feature extraction in a recruitment talent portrait generation method based on multi-dimensional information.

[0054] Figure 4 The present invention is a flowchart of obtaining a talent portrait model in a recruitment talent portrait generation method based on multi-dimensional information.

[0055] Figure 5 A flowchart for providing career development suggestions in a recruitment talent profile generation method based on multi-dimensional information.

[0056] Figure 6 This is a structural diagram of a recruitment talent portrait generation system based on multi-dimensional information. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0058] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0059] like Figure 1 As shown, an embodiment of the present invention provides a method for generating a recruitment talent portrait based on multi-dimensional information, and the method includes the following steps:

[0060] S100, collecting the candidate's resume information, the resume information including basic personal information, target professional position, work experience, educational background, skill certificates and online behavior data;

[0061] S200, data cleaning and data conversion of resume information;

[0062] S300 performs feature extraction and analyzes the candidate’s online behavior data based on natural language processing technology to extract behavior patterns and points of interest;

[0063] S400, trains and evaluates the model based on historical resume data to obtain a talent portrait model;

[0064] S500: Input the candidate's resume information, behavior patterns and interests into the talent portrait model to obtain the candidate portrait, which includes skill ability assessment, career development potential and cultural adaptability;

[0065] S600 provides personalized career development advice and job matching recommendations based on candidate profiles.

[0066] In the embodiment of the present invention, it is first necessary to collect the resume information of the candidate, and the resume information includes personal basic information, target professional position, work experience, educational background, skill certificate and online behavior data, wherein the resume information is captured through the resume API interface, and the online behavior data is obtained through the social media data source, and then the resume information needs to be cleaned and converted, and then feature extraction is performed, and keyword extraction and classification technology are used to identify the candidate's skills and mark the corresponding level, and the candidate's online behavior data is analyzed based on natural language processing technology to extract behavior patterns and points of interest. In addition, when applying the embodiment of the present invention, it is necessary to train and evaluate the model based on historical resume data in advance to obtain a talent portrait model, where a suitable model (such as random forest, support vector machine, deep learning model) needs to be selected, and cross-validation is performed after training to ensure generalization ability. Then the candidate's resume information, behavior pattern and points of interest are input into the talent portrait model to obtain a candidate portrait, which includes skill ability assessment, career development potential and cultural adaptability; the candidate portrait can be visualized, specifically in the form of charts, radar charts, etc., to show the portrait to the recruiter for easy understanding and analysis. Finally, we will provide personalized career development suggestions and job matching recommendations based on the candidate portrait, such as suitable positions, suggestions for further improving skills, etc.; this provides a scientific basis for recruitment decisions and valuable guidance for candidates' career planning.

[0067] like Figure 2 As shown, as a preferred embodiment of the present invention, the steps of data cleaning and data conversion of resume information specifically include:

[0068] S201, processing missing values ​​and outliers on resume information, and performing data standardization and normalization;

[0069] S202, converting unstructured data into structured data, specifically including format standardization and data type conversion.

[0070] In the embodiment of the present invention, data cleaning is performed on the resume information, and data cleaning includes missing value processing and outlier processing, and data standardization and normalization are performed. The missing value processing includes filling strategy and deletion strategy, and the outlier processing includes identifying anomalies and processing anomalies. Then, the unstructured data needs to be converted into structured data, which specifically includes format standardization and data type conversion. The format standardization includes date format and text encoding unification, and the data type conversion includes numerical conversion and text conversion.

[0071] like Figure 3 As shown, as a preferred embodiment of the present invention, the step of performing feature extraction specifically includes:

[0072] S301, performing business relevance analysis, wherein the business relevance analysis includes job requirement matching and candidate historical performance;

[0073] S302, performing feature importance evaluation, wherein the feature importance evaluation includes weight calculation and contribution analysis;

[0074] S303, analyzing the online behavior data, specifically including activity analysis and interactive behavior analysis.

[0075] In an embodiment of the present invention, during feature selection, text feature extraction and keyword extraction are performed, and then a business relevance analysis is required, the business relevance analysis includes job requirement matching and candidate historical performance; and a feature importance evaluation is required, the feature importance evaluation includes weight calculation and contribution analysis; finally, the online behavior data is analyzed, specifically including activity analysis and interactive behavior analysis.

[0076] like Figure 4 As shown, as a preferred embodiment of the present invention, the steps of training and evaluating the model based on the historical resume data to obtain the talent portrait model specifically include:

[0077] S401, constructing a training data set based on historical resume data, obtaining a training set and a validation set, and performing data annotation;

[0078] S402, performing model training based on a machine learning algorithm, wherein the machine learning algorithm includes a classification algorithm, a regression analysis algorithm, and a cluster analysis algorithm;

[0079] S403, use accuracy, recall and F1 score indicators to evaluate model performance and cross-validate the talent profile model.

[0080] In the embodiment of the present invention, the data labeling includes manual labeling and automatic labeling.

[0081] like Figure 5As shown, as a preferred embodiment of the present invention, the step of providing personalized career development suggestions and job matching recommendations based on candidate portraits specifically includes:

[0082] S601, recruiting recommendations based on candidate profiles, using collaborative filtering and content recommendation algorithms to optimize recommendation results;

[0083] S602, obtain career development path planning, including job promotion path and skill improvement suggestions;

[0084] S603: Collect user feedback information, analyze and apply the user feedback information.

[0085] In the embodiment of the present invention, the optimization of the recommendation results includes sorting strategy and diversity improvement.

[0086] like Figure 6 As shown, an embodiment of the present invention further provides a recruitment talent portrait generation system based on multi-dimensional information, the system comprising:

[0087] The resume information collection module 100 is used to collect the candidate's resume information, which includes basic personal information, target professional position, work experience, educational background, skill certificates and online behavior data;

[0088] The data cleaning and conversion module 200 is used to perform data cleaning and data conversion on resume information;

[0089] A data feature extraction module 300 is used to perform feature extraction, analyze the candidate's online behavior data based on natural language processing technology, and extract behavior patterns and points of interest therefrom;

[0090] The talent portrait model module 400 is used to perform model training and evaluation based on historical resume data to obtain a talent portrait model;

[0091] The candidate portrait module 500 is used to input the candidate's resume information, behavior patterns and interests into the talent portrait model to obtain a candidate portrait, which includes skill ability assessment, career development potential and cultural adaptability;

[0092] The job matching recommendation module 600 is used to provide personalized career development suggestions and job matching recommendations based on the candidate profile.

[0093] As a preferred embodiment of the present invention, the data cleaning conversion module 500 includes:

[0094] A data cleaning unit, used to process missing values ​​and outliers in resume information, and to standardize and normalize data. The missing value processing includes filling strategy and deletion strategy, and the outlier processing includes identifying anomalies and processing anomalies.

[0095] The data conversion unit is used to convert unstructured data into structured data, specifically including format standardization and data type conversion. The format standardization includes date format and text encoding unification, and the data type conversion includes numerical conversion and text conversion.

[0096] As a preferred embodiment of the present invention, the data feature extraction module 300 includes:

[0097] A relevance analysis unit, used to perform business relevance analysis, wherein the business relevance analysis includes job requirement matching and candidate historical performance;

[0098] A feature evaluation unit, used to perform feature importance evaluation, wherein the feature importance evaluation includes weight calculation and contribution analysis;

[0099] The behavior data analysis unit is used to analyze online behavior data, including activity analysis and interactive behavior analysis.

[0100] As a preferred embodiment of the present invention, the talent portrait model module 400 includes:

[0101] The training data set unit is used to construct a training data set based on historical resume data, obtain a training set and a validation set, and perform data annotation;

[0102] A model training unit, used to perform model training based on a machine learning algorithm, wherein the machine learning algorithm includes a classification algorithm, a regression analysis algorithm, and a cluster analysis algorithm;

[0103] The model evaluation and verification unit is used to evaluate model performance using accuracy, recall, and F1 score indicators, and to cross-validate the talent profile model.

[0104] As a preferred embodiment of the present invention, the job matching recommendation module 600 includes:

[0105] Recruitment recommendation unit, used to make recruitment recommendations based on candidate profiles. Recommendation algorithms include collaborative filtering and content recommendation to optimize recommendation results.

[0106] Career development planning unit, used to obtain career development path planning, including job promotion paths and skill improvement suggestions;

[0107] The user feedback unit is used to collect user feedback information, analyze and apply the user feedback information.

[0108] The embodiments of the present invention strictly abide by the laws and regulations of the country and region on data protection and privacy, formulate and publish a clear privacy policy, and clearly inform users of the collection, use, sharing and protection measures of their data. Before collecting user data, clearly inform users of the purpose of the data and obtain their explicit consent.

[0109] The above only describes in detail the preferred embodiments of the present invention, which is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0110] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0111] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0112] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the disclosure in the specification and examples. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A method for generating a recruitment talent portrait based on multi-dimensional information, characterized in that: The method comprises the following steps: Collecting candidate resume information, including basic personal information, target job position, work experience, educational background, skill certificates, and online behavior data; Perform data cleaning and data conversion on resume information; Perform feature extraction and analyze candidate online behavior data based on natural language processing technology to extract behavior patterns and points of interest; Train and evaluate the model based on historical resume data to obtain a talent portrait model; Input the candidate's resume information, behavior patterns and interests into the talent portrait model to obtain the candidate portrait, which includes skill ability assessment, career development potential and cultural adaptability; Provide personalized career development advice and job matching recommendations based on candidate profiles.

2. The method for generating a recruitment talent portrait based on multi-dimensional information according to claim 1, characterized in that: The steps of data cleaning and data conversion of resume information specifically include: Processing missing values ​​and outliers on resume information, and performing data standardization and normalization. The missing value processing includes filling strategy and deletion strategy, and the outlier processing includes identifying anomalies and processing anomalies; Converting unstructured data into structured data specifically includes format standardization and data type conversion. The format standardization includes date format and text encoding unification, and the data type conversion includes numerical conversion and text conversion.

3. The method for generating a recruitment talent portrait based on multi-dimensional information according to claim 1, characterized in that: The step of performing feature extraction specifically includes: Conducting business relevance analysis, including job requirement matching and candidate historical performance; Performing feature importance evaluation, wherein the feature importance evaluation includes weight calculation and contribution analysis; Analyze online behavior data, including activity analysis and interactive behavior analysis.

4. The method for generating a recruitment talent portrait based on multi-dimensional information according to claim 1, characterized in that: The steps of training and evaluating the model based on the historical resume data to obtain the talent portrait model specifically include: Build a training data set based on historical resume data, obtain training set and validation set, and perform data annotation; Performing model training based on machine learning algorithms, including classification algorithms, regression analysis, and cluster analysis algorithms; The accuracy, recall and F1 score indicators were used to evaluate the model performance and to cross-validate the talent profile model.

5. The method for generating a recruitment talent portrait based on multi-dimensional information according to claim 1, characterized in that: The steps of providing personalized career development suggestions and job matching recommendations based on candidate portraits specifically include: Recruitment recommendations are made based on candidate profiles. Recommendation algorithms include collaborative filtering and content recommendation to optimize recommendation results. Get career development path planning, including job promotion paths and skills improvement suggestions; Collect user feedback information, analyze and apply it.

6. A recruitment talent portrait generation system based on multi-dimensional information, characterized in that: The system comprises: A resume information collection module is used to collect the candidate's resume information, which includes basic personal information, target professional position, work experience, educational background, skill certificates and online behavior data; Data cleaning and conversion module, used for data cleaning and data conversion of resume information; Data feature extraction module, used for feature extraction, analyzing candidate online behavior data based on natural language processing technology, and extracting behavior patterns and points of interest; The talent portrait model module is used to train and evaluate the model based on historical resume data to obtain a talent portrait model; The candidate portrait module is used to input the candidate's resume information, behavior patterns and interests into the talent portrait model to obtain the candidate portrait, which includes skill ability assessment, career development potential and cultural adaptability; The job matching recommendation module is used to provide personalized career development suggestions and job matching recommendations based on candidate portraits.

7. The recruitment talent portrait generation system based on multi-dimensional information according to claim 6 is characterized in that: The data cleaning conversion module includes: A data cleaning unit, used to process missing values ​​and outliers in resume information, and to standardize and normalize data. The missing value processing includes filling strategy and deletion strategy, and the outlier processing includes identifying anomalies and processing anomalies. The data conversion unit is used to convert unstructured data into structured data, specifically including format standardization and data type conversion. The format standardization includes date format and text encoding unification, and the data type conversion includes numerical conversion and text conversion.

8. The recruitment talent portrait generation system based on multi-dimensional information according to claim 6 is characterized in that: The data feature extraction module comprises: A relevance analysis unit, used to perform business relevance analysis, wherein the business relevance analysis includes job requirement matching and candidate historical performance; A feature evaluation unit, used to perform feature importance evaluation, wherein the feature importance evaluation includes weight calculation and contribution analysis; The behavior data analysis unit is used to analyze online behavior data, including activity analysis and interactive behavior analysis.

9. The recruitment talent portrait generation system based on multi-dimensional information according to claim 6 is characterized in that: The talent portrait model module includes: The training data set unit is used to construct a training data set based on historical resume data, obtain a training set and a validation set, and perform data annotation; A model training unit, used to perform model training based on a machine learning algorithm, wherein the machine learning algorithm includes a classification algorithm, a regression analysis algorithm, and a cluster analysis algorithm; The model evaluation and verification unit is used to evaluate model performance using accuracy, recall, and F1 score indicators, and to cross-validate the talent profile model.

10. The recruitment talent portrait generation system based on multi-dimensional information according to claim 6 is characterized in that: The job matching recommendation module includes: Recruitment recommendation unit, used to make recruitment recommendations based on candidate profiles. Recommendation algorithms include collaborative filtering and content recommendation to optimize recommendation results. Career development planning unit, used to obtain career development path planning, including job promotion paths and skill improvement suggestions; The user feedback unit is used to collect user feedback information, analyze and apply the user feedback information.

Images