Human resource management method and device based on artificial intelligence

Abstract

The invention relates to the technical field of human resources, in particular to a human resource management method based on artificial intelligence, and the method comprises the steps: receiving resume data of an applicant, analyzing the resume data through a natural language processing technology, and extracting keywords related to positions from the resume data to determine corresponding key information; calling a pre-linked external data source, and verifying the authenticity of the resume data providing information based on the external data source; and after verification succeeds, scoring the key information and the resume data by using a scoring model to obtain corresponding scoring data, and arranging interviews according to the scoring data. The recruitment efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of human resources, and in particular to a human resources management method and device based on artificial intelligence. Background Art

[0002] With the development of information technology, human resource management faces new challenges. Traditional recruitment processes usually rely on manual screening of resumes and arranging interviews, which are not only time-consuming and labor-intensive, but also susceptible to personal bias. Especially in the resume screening stage, due to information asymmetry, some applicants may exaggerate their work experience or skill level, or even provide false information.

[0003] However, due to the lack of effective verification methods, companies find it difficult to quickly and accurately identify the authenticity of applicants, which leads to increased recruitment costs and even selection errors, affecting the stability of the team and the progress of the project, thereby affecting the efficiency of recruitment. Summary of the invention

[0004] In order to improve the efficiency of recruitment, the present application provides a human resource management method and device based on artificial intelligence.

[0005] In the first aspect, the present application provides a human resources management method based on artificial intelligence, which adopts the following technical solutions:

[0006] A human resource management method based on artificial intelligence includes: receiving resume data of an applicant, parsing the resume data through natural language processing technology, and extracting keywords related to the position from the resume data to determine corresponding key information; calling a pre-linked external data source, and verifying the authenticity of information provided by the resume data based on the external data source; after successful verification, using a scoring model to score the key information and resume data, obtaining corresponding scoring data, and arranging interviews based on the scoring data.

[0007] By adopting the above technical solutions, resumes can be automatically parsed and keywords can be extracted through natural language processing technology, reducing the manual screening workload of human resource management personnel. The authenticity of information can be automatically verified through external data sources, reducing the time of manual verification. The scoring model can be used to quickly screen out qualified applicants and shorten the screening cycle. From resume reception, parsing, verification to scoring and interview arrangement, the entire process is automated to improve the efficiency of the overall recruitment process.

[0008] Optionally, in the process of verifying the authenticity of the information provided by the resume data based on the external data source, the method also includes: retrieving the corresponding key information, using the key information as a query parameter, and obtaining corresponding relevant information by calling the external data source through an API; comparing the relevant information obtained from the external data source with the key information in the resume to generate a corresponding verification report; and feeding back the verification report to the human resources management personnel to determine whether it is authentic.

[0009] By adopting the above technical solution, in the process of verifying the authenticity of information provided by resume data based on external data sources, by retrieving key information and using it as query parameters, the external data source is called through the API to obtain relevant information, and then the obtained information is compared with the key information in the resume to generate a verification report, and the verification report is fed back to the human resources management personnel to determine the authenticity of the information. The automation and accuracy of information verification can be improved, the time and errors of manual operations can be reduced, the authenticity and reliability of applicant information can be ensured, and the efficiency and quality of recruitment can be improved.

[0010] Optionally, in the process of feeding back the verification report to the human resources management personnel and determining whether it is authentic, the method also includes: obtaining the human resources management personnel to evaluate the verification report and give a corresponding authenticity score, wherein the more consistent the information in the verification report, the higher the corresponding authenticity score; calling the corresponding authenticity threshold, and comparing the authenticity score with the authenticity threshold; if the authenticity score is greater than the authenticity threshold, it is determined to be authentic.

[0011] By adopting the above technical solution, in the process of feeding back the verification report to the human resources management personnel and determining the authenticity of the information, the authenticity score given by the human resources management personnel for evaluating the verification report is obtained, and the score is compared with the preset authenticity threshold. If the authenticity score is higher than the threshold, the information is determined to be authentic; the objectivity and accuracy of information verification are improved through quantitative evaluation, ensuring that only information that has been strictly verified can enter the next recruitment process, thereby improving the reliability and efficiency of recruitment.

[0012] Optionally, for the application of the scoring model, the method also includes: collecting historical recruitment data, the historical recruitment data including the recruitment resume data, interview evaluation results, and final recruitment or non-recruitment of hired employees, extracting keywords related to the position from the recruitment resume data, and encoding and standardizing them, and defining labels based on whether the employees are finally hired or not; using the historical recruitment data to train the machine learning model, evaluating the performance of the machine learning model through cross-validation, and using the test data set in the historical recruitment data to evaluate the performance of the model, and adjusting the hyperparameters of the machine learning model; determining the trained machine learning model as the corresponding scoring model, and deploying the scoring model into the human resources management system.

[0013] By adopting the above technical solution, the trained model is determined as a scoring model and deployed to the human resources management system. Through a data-driven approach, the accuracy and reliability of the scoring model are improved, thereby optimizing the recruitment process and improving recruitment efficiency and quality.

[0014] Optionally, in the process of obtaining the corresponding scoring data, the method also includes: determining specific recruitment requirements for job recruitment, associating the specific recruitment requirements with a scoring model, and adjusting the scoring criteria corresponding to the scoring model based on the specific recruitment requirements, wherein the specific recruitment requirements include necessary skills, years of work experience, and specific industry background; extracting the applicant's work experience from the resume, and inputting the work experience into the scoring model for scoring, wherein the work experience includes work unit, position, job responsibilities, and time in office; obtaining the score data corresponding to the work experience based on the scoring criteria of the scoring model, and determining the corresponding scoring data based on all the score data, wherein the work unit, position, job responsibilities, and time in office all have corresponding score data.

[0015] By adopting the above technical solution, in the process of obtaining the corresponding scoring data, by determining the specific requirements of the job recruitment and associating them with the scoring model, adjusting the scoring criteria based on the recruitment requirements, extracting the applicant's work experience and inputting it into the scoring model for scoring, and finally obtaining the work experience score data based on the scoring criteria, and summarizing and determining the total scoring data, it can be ensured that the scoring model can accurately evaluate the applicant's work experience according to the specific job requirements, thereby improving the accuracy and efficiency of recruitment.

[0016] Optionally, after determining the applicant corresponding to the recruitment, the method also includes: collecting the applicant's personal information based on resume data, wherein the personal information includes skills, past work experience, educational background, etc.; obtaining the applicant's personality characteristic information through questionnaires, psychological assessments, and behavioral analysis; retrieving the specific needs corresponding to all teams, wherein the specific needs include required skill combinations, personality types, and team sizes; performing team matching based on the specific needs, the personal information, and the personality characteristic information to determine the appropriate team corresponding to the applicant.

[0017] By adopting the above technical solution, through comprehensive analysis of the applicants' personal information (skills, work experience, educational background) and personality characteristics, combined with the specific needs of the team (skill combination, personality type, size), accurate team matching is achieved, ensuring that the applicants can best integrate into and contribute to the target team, thereby improving the overall effectiveness and collaboration efficiency of the team.

[0018] Optionally, the method also includes: retrieving specific recruitment requirements for job recruitment, and determining corresponding skill points that need to be trained based on the specific recruitment requirements; creating a virtual environment based on all the skill points that need to be trained based on a 3D modeling tool, and the virtual environment includes a workplace, equipment, tools, etc.; recording the corresponding operation data of the applicant in the virtual environment, and generating a corresponding operation report score, and feeding back the operation report score to the human resources management personnel.

[0019] By adopting the above technical solution, by retrieving the specific recruitment requirements of the position and determining the skill points required for training, a virtual environment containing workplaces, equipment and tools is created based on 3D modeling tools, allowing applicants to operate in it and record their behavioral data, and generate operation report scores. This is used as a basis for evaluating the applicants' actual operational capabilities and skill matching, and ultimately these scores are fed back to human resources management personnel to assist in making more objective and accurate recruitment decisions.

[0020] In a second aspect, the present application provides a human resources management device based on artificial intelligence, which adopts the following technical solution:

[0021] A human resources management device based on artificial intelligence, comprising:

[0022] Key information determination module: Receive the resume data of the applicant, parse the resume data through natural language processing technology, and extract keywords related to the position from the resume data to determine the corresponding key information;

[0023] A verification model, which retrieves a pre-linked external data source and verifies the authenticity of information provided by the resume data based on the external data source;

[0024] The scoring data acquisition module, after successful verification, uses the scoring model to score the key information and resume data to obtain corresponding scoring data and arrange interviews based on the scoring data.

[0025] In a third aspect, the present application provides a human resources management method based on artificial intelligence, which adopts the following technical solutions:

[0026] A human resource management method based on artificial intelligence comprises a processor in which a program of any one of the above-mentioned human resource management methods based on artificial intelligence is running.

[0027] In a fourth aspect, the present application provides a storage medium, which adopts the following technical solution:

[0028] A storage medium storing a program of any one of the above-mentioned methods for human resource management based on artificial intelligence.

[0029] In summary, the present application includes at least one of the following beneficial technical effects:

[0030] Automated processing: Reduce the workload of manual resume screening and improve screening efficiency.

[0031] Information verification: ensure the authenticity of information and reduce recruitment risks.

[0032] Scoring model: objectively evaluate candidates and improve interview quality and success rate.

[0033] Full process optimization: Automating the entire process from resume receipt to interview arrangement to improve overall recruitment efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 The present invention is a flowchart of a human resource management method based on artificial intelligence according to an exemplary embodiment.

[0035] Figure 2 It is a structural block diagram of a human resource management method and device based on artificial intelligence according to an exemplary embodiment. DETAILED DESCRIPTION

[0036] Embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings.

[0037] In the description of this specification, the description with reference to the terms "certain embodiments", "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0038] The present application embodiment discloses a human resource management method based on artificial intelligence, referring to Figure 1 ,include:

[0039] S100, receiving the resume data of the applicant, parsing the resume data by natural language processing technology, and extracting keywords related to the position from the resume data to determine corresponding key information.

[0040] Typically, applicants submit their resumes or cover letters via email, online application forms, or by directly uploading files; these documents may contain the applicant's basic information (such as name, contact information), educational background, work experience, skill certificates, etc.

[0041] Among them, natural language processing (NLP) technology is used to analyze the content of applicants' resumes. NLP technology can help the system understand the semantics in the text, thereby identifying words and phrases that are closely related to the job requirements. For example, if you are recruiting a software engineer, the system may look for words such as "programming", "Java", and "Python". By automatically identifying and extracting important information from resumes, the workload of HR in manually screening resumes is reduced, and the accuracy and efficiency of screening are improved.

[0042] S110, calling a pre-linked external data source, and verifying the authenticity of information provided by the resume data based on the external data source.

[0043] Among them, the information provided by the applicant is compared with external data sources such as third-party databases or social media platforms to verify whether the experience, qualifications or other statements mentioned in the resume are authentic. This may include educational background verification, contacting former employers to confirm work experience, etc., to ensure that the candidates finally hired have real qualifications and experience.

[0044] S120, after successful verification, use the scoring model to score the key information and resume data, obtain the corresponding scoring data, and arrange the interview according to the scoring data.

[0045] Among them, once the applicant's information passes the authenticity verification, the system will use a pre-set scoring model to quantitatively evaluate the applicant's suitability; this model may consider various factors, such as skill matching, length of experience, education level, etc., and assign corresponding scores; finally, based on the score, it will decide whether to invite the applicant to participate in further interviews; support the decision-making process through objective data, reduce the impact of subjective bias, and help HR quickly identify the most promising candidates.

[0046] It should be noted here that in the embodiment of the present application, the scoring model is trained in advance, and the specific training process and the process of applying the human resource management system of the present application include:

[0047] S1201, collect historical recruitment data, extract keywords related to the position from the recruitment resume data, encode and standardize them, and define labels based on whether the recruitment is finally accepted or not.

[0048] Among them, historical recruitment data includes the resume data of hired employees, interview evaluation results, and final hiring or not. It is further specified as the resume of hired employees (including but not limited to educational background, work experience, skill certificates, etc.); evaluation results generated during the interview process (such as the interviewer's evaluation and score, etc.); and the final decision record on whether to hire.

[0049] In addition, key information related to the position (such as professional skills, work experience, etc.) is extracted from the resume, and this information is encoded (i.e., non-numerical information is converted into numerical form) and standardized (to make different types of features comparable); through encoding and standardization, machine learning algorithms can better understand and process input data, thereby improving the effectiveness of model training.

[0050] It should be pointed out here that a label is assigned to each piece of data based on the final hiring result (i.e., whether hired) marked in the historical recruitment data; for example, the label for hired is the positive class (usually 1), and the label for unhired is the negative class (usually 0).

[0051] S1202, train the machine learning model using historical recruitment data, evaluate the performance of the machine learning model through cross-validation, evaluate the performance of the model using a test data set in the historical recruitment data, and adjust the hyperparameters of the machine learning model.

[0052] Among them, historical recruitment data with labels is used to train machine learning models, which usually includes selecting a suitable algorithm (such as logistic regression, random forest, neural network, etc.), and then dividing the data into training sets and validation sets, training the model on the training set, and evaluating the performance of the model on the validation set.

[0053] In addition, cross-validation techniques are used to evaluate the generalization ability of the model, that is, the performance of the model on unseen data. This usually means dividing the data into several parts, taking turns to use one part as test data and the rest as training data. After completing the initial training, a specially reserved test data set is used to evaluate the performance of the model, and the hyperparameters of the model (such as learning rate, regularization coefficient, etc.) are adjusted as needed. Adjusting the hyperparameters can help optimize the performance of the model and make it more effective in practical applications.

[0054] S1203, determining the trained machine learning model as the corresponding scoring model, and deploying the scoring model into the human resource management system.

[0055] Once the model is fully trained and reaches satisfactory performance indicators, it can be determined as a scoring model and integrated into the existing human resource management system. In this way, when new resume data enters the system, the model can automatically score it.

[0056] By applying the trained scoring model to the human resources management system, the automated scoring process not only improves work efficiency, but also reduces the possibility of human errors, allowing the human resources department to handle large amounts of job applications more efficiently.

[0057] In the process of authenticity verification, the method also includes:

[0058] S111, retrieve corresponding key information, use the key information as a query parameter, and call an external data source through an API to obtain corresponding related information.

[0059] First, the system will identify and extract keywords or key information related to the position in the resume, which may include educational background, work experience, professional skills certification, etc.; for example, if the resume mentions that the applicant has a degree from a certain university, then the "university name" and "degree type" will become key information; thereby ensuring that the system can accurately capture important data points that need to be verified for subsequent verification operations.

[0060] Next, the system will use the key information extracted previously as query conditions and access external data sources (such as China Higher Education Student Information and Career Center, LinkedIn, industry certification agency databases, etc.) through API interfaces. These data sources contain real information that can be verified, such as academic certification, work experience, etc. By using the authoritative information provided by external data sources, it is possible to effectively verify whether the information provided by the applicant is accurate, which increases the professionalism and reliability of the verification process.

[0061] S112, comparing the relevant information obtained from the external data source with the key information in the resume to generate a corresponding verification report.

[0062] The system compares the information obtained from the external data source with the corresponding key information in the applicant's resume to check whether there are inconsistencies between the two; for example, if the applicant claims that he or she graduated from a certain university, but the external data source does not find relevant records, then there may be a discrepancy in the information.

[0063] In addition, based on the comparison results, the system will generate a detailed verification report, which will list all the checked items and their consistency; if there are any discrepancies, they will also be clearly pointed out in the report; the verification report can provide HR with an objective basis to help them make more informed decisions.

[0064] S113, feed back the verification report to the human resources management personnel and determine whether it is authentic.

[0065] Finally, the system will send the verification report to the human resources management personnel for review. HR can judge whether the information provided by the applicant is true and reliable based on the information in the report, and decide whether to continue the recruitment process, such as arranging interviews, etc. This can ensure that HR can make decisions based on accurate information, while also strengthening the integrity culture within the company.

[0066] It should be pointed out here that in the process of determining whether it is true, the following steps are also carried out:

[0067] S1131, obtaining the corresponding authenticity score given by the human resources management personnel after evaluating the verification report.

[0068] Among them, the more consistent the information in the verification report, the higher the corresponding authenticity score; after receiving the verification report, the human resources management personnel will review the information in the report and give an authenticity score based on the consistency of the information. This score may be based on a combination of multiple standards, such as the consistency of educational background, work experience, professional skills, etc.; through professional evaluation of HR, the accuracy of the verification report can be ensured, and the authenticity score can be made more authoritative.

[0069] S1132, retrieve the corresponding authenticity threshold, and compare the authenticity score with the authenticity threshold.

[0070] Among them, an authenticity threshold is preset in the system. This threshold is used to distinguish whether the information is authentic enough. The comparison between the authenticity score and the authenticity threshold is a simple numerical comparison process, that is, to see whether the authenticity score reaches the preset threshold standard; by setting the threshold, it can help companies formulate unified evaluation standards, ensure that all applicants are treated with the same standards, and avoid deviations caused by subjective judgment.

[0071] S1133: If the authenticity score is greater than the authenticity threshold, it is determined to be authentic.

[0072] Among them, if after comparison, the authenticity score is higher than the preset authenticity threshold, then the system will determine that the information provided by the applicant is true, and such applicants can continue to the next step of the recruitment process; thereby effectively screening out applicants who meet the company's standards and reducing the recruitment risks caused by false information.

[0073] In the embodiment of the present application, in the process of obtaining the corresponding scoring data, the method further includes:

[0074] S121, determining specific recruitment requirements for the position recruitment, associating the specific recruitment requirements with the scoring model, and adjusting the scoring criteria corresponding to the scoring model based on the specific recruitment requirements.

[0075] First of all, the HR or recruitment team needs to clarify the specific requirements of this recruitment, which may include: Necessary skills: skills that applicants must master, such as programming languages, design software operations, etc.; Years of work experience: the minimum number of years of work experience an applicant should have; Specific industry background: applicants should have work experience in a specific industry.

[0076] Then, the above specific recruitment requirements are converted into scoring criteria in the scoring model. This step involves converting specific requirements into variables in the model and setting corresponding weights. For example, if the recruitment requirements particularly emphasize the importance of a certain skill, then the weight of this skill in the scoring model should be higher.

[0077] According to the specific recruitment requirements, adjust the weight of each scoring criterion in the scoring model; for example, if a skill is crucial to the position, then the scoring model should give this skill a higher weight; by adjusting the scoring criteria, you can ensure that the scoring model is more in line with actual recruitment needs and make the scoring results more reasonable.

[0078] S122, extracting the applicant's work experience from the resume, and inputting the work experience into the scoring model for scoring.

[0079] Among them, information related to the applicant's work experience is extracted from the applicant's resume, including but not limited to: work unit: the name of the company where the applicant has worked or is working; position: the specific position the applicant holds in the company; job responsibilities: the applicant's main work content and responsibilities; working time: the duration of the applicant's work in the position. The extracted applicant's work experience information is input into the scoring model with adjusted scoring criteria, and the scoring model will calculate a score based on the preset scoring criteria.

[0080] S123, obtaining score data corresponding to the work experience based on the scoring standard of the scoring model, and determining corresponding scoring data based on all the score data.

[0081] Among them, the scoring model will score each item of the applicant's work experience (such as work unit, position, job responsibilities, and time in office) according to the scoring criteria and output the score data; these score data provide the applicant's ability reflection in different aspects, helping HR to fully understand the applicant's situation.

[0082] Then, all individual scores are aggregated to obtain a comprehensive score data, which reflects the overall suitability of the applicant for the job. The comprehensive score data provides HR with an intuitive basis for ranking applicants, helping them to select the most suitable candidates for interview or recruitment from among many candidates.

[0083] By executing steps S121 to S123, the entire scoring process is not only highly automated, but also can ensure the objectivity and accuracy of the scoring, thereby improving the efficiency and effectiveness of human resource management.

[0084] After determining the applicants corresponding to the recruitment, the method further includes:

[0085] S124, collecting the applicant's personal information based on the resume data, and obtaining the applicant's personality characteristics information through questionnaire surveys, psychological assessments, and behavioral analysis.

[0086] Among them, key personal information is extracted from resume data. This information includes but is not limited to the applicant's skills and expertise (such as programming language proficiency, project management experience, etc.), past work experience (including position, company, work content and achievements, etc.) and educational background (education, major, graduation school, etc.); after collecting basic personal information, we can further use questionnaires, psychological assessments (such as MBTI, DISC, etc.) and behavioral analysis (such as performance in interviews, past work cases, etc.) to gain a deeper understanding of the applicant's personality characteristics, work style, values ​​and interpersonal skills.

[0087] Based on the personality traits and work style of the candidates, work tasks and resources can be allocated more effectively, improving the overall efficiency of the team.

[0088] S125, retrieve the specific needs corresponding to all teams.

[0089] Among them, by obtaining the specific needs of each team, including but not limited to the required skill combination (i.e. the skill areas that the team currently lacks or hopes to enhance), personality type (personality traits favored by team culture and atmosphere) and team size (current number of team members and future expansion plans); by clarifying the specific needs of the team, it can be ensured that the recruited candidates can directly meet the actual needs of the team.

[0090] S126, performing team matching based on specific needs, personal information and personality characteristics information to determine the appropriate team for the applicant.

[0091] Match candidates with their most suitable teams to ensure that each candidate can play a role in the most suitable team, thereby improving the overall effectiveness and collaboration efficiency of the team.

[0092] In addition, during the interview phase, the following steps are also carried out:

[0093] S127, retrieve specific recruitment requirements for the position recruitment, and determine corresponding skill points that need to be trained based on the specific recruitment requirements.

[0094] First, obtain specific job description documents from the company's internal system or recruitment platform. These documents usually list the basic requirements, scope of responsibilities, and technical and soft skills required for the position; next, analyze the above information and identify all the skills related to the position. For example, for a mechanical engineer position, it may be necessary to master CAD software operation, understand material science, have project management experience, etc.; based on the analysis results, further clarify which skills are required for applicants, which are optional, and which can be quickly improved through training. This step will help to establish a highly targeted training plan later.

[0095] S128, creating a virtual environment based on all the skill points that need to be trained based on a 3D modeling tool.

[0096] Among them, professional 3D modeling software (such as Unity, Unreal Engine, etc.) is used to build a three-dimensional model that simulates the real working environment. This includes but is not limited to office layout, production line, laboratory, etc.; add corresponding equipment, tools and other elements in the virtual environment to make it as close to the real working conditions as possible. For example, if you are training mechanical engineers, you can add the virtual interface of CAD design software, simulated machine tools, etc.; according to the skill point list, set a series of tasks in the virtual environment, which are designed to test the relevant skill level of the applicant.

[0097] By simulating real-life work situations, applicants can demonstrate their abilities in a safe and controllable environment, while helping employers assess whether applicants are suitable for the position.

[0098] S129, record the operation data of the applicant in the virtual environment, generate a corresponding operation report score, and feed back the operation report score to the human resources management personnel

[0099] When candidates perform tasks in a virtual environment, the system automatically records their every action, including the time to complete the task, the number of errors, the decision-making process, etc. Based on the collected data, the system evaluates the candidates' performance through preset scoring criteria and gives a comprehensive score. The scoring results are summarized in an easy-to-understand report format with specific feedback attached. Finally, this report is sent to the human resources department responsible for recruitment as an important reference for evaluating the candidates' abilities and making hiring decisions.

[0100] The present application also discloses a human resource management device based on artificial intelligence, please refer to Figure 2 , the devices include but are not limited to:

[0101] Key information determination module 200: Receive the resume data of the applicant, parse the resume data by natural language processing technology, and extract keywords related to the position from the resume data to determine the corresponding key information;

[0102] Verification model 210, calling a pre-linked external data source, and verifying the authenticity of information provided by the resume data based on the external data source;

[0103] The scoring data acquisition module 220, after successful verification, uses the scoring model to score the key information and resume data to obtain corresponding scoring data and arrange interviews based on the scoring data.

[0104] Furthermore, the device includes but is not limited to:

[0105] The key information retrieval module is used to retrieve the corresponding key information, use the key information as a query parameter, and call the external data source through the API to obtain the corresponding relevant information;

[0106] The comparison module is used to compare the relevant information obtained from the external data source with the key information in the resume and generate a corresponding verification report;

[0107] The authenticity determination module feeds back the verification report to the human resources management personnel and uses it to determine whether it is authentic.

[0108] Furthermore, the device includes but is not limited to:

[0109] The authenticity score acquisition module is used to obtain the corresponding authenticity score given by the human resources management personnel for evaluating the verification report. The more consistent the information in the verification report, the higher the corresponding authenticity score;

[0110] The authenticity comparison module retrieves the corresponding authenticity threshold value and compares the authenticity score with the authenticity threshold value;

[0111] If the authenticity score is greater than the authenticity threshold, it is determined to be authentic.

[0112] Furthermore, the device includes but is not limited to:

[0113] The historical recruitment data collection module is used to collect historical recruitment data, which includes the resume data of hired employees, interview evaluation results, and whether they were finally hired or not. Keywords related to the position are extracted from the resume data, coded and standardized, and labels are defined based on whether they were finally hired or not.

[0114] A training module, which is used to train the machine learning model using the historical recruitment data, evaluate the performance of the machine learning model through cross-validation, evaluate the performance of the model using a test data set in the historical recruitment data, and adjust the hyperparameters of the machine learning model;

[0115] The scoring model determination module uses the trained machine learning model to determine the corresponding scoring model and deploys the scoring model into the human resource management system.

[0116] Furthermore, the device includes but is not limited to:

[0117] The module for determining specific recruitment requirements is used to determine the specific recruitment requirements for job recruitment, associate the specific recruitment requirements with the scoring model, and adjust the scoring criteria corresponding to the scoring model based on the specific recruitment requirements. The specific recruitment requirements include necessary skills, years of work experience, and specific industry background;

[0118] The scoring module extracts the applicant's work experience from the resume and inputs the work experience into the scoring model for scoring. The work experience includes the work unit, position, job responsibilities, and working time.

[0119] The score data acquisition module is used to obtain the score data corresponding to the work experience based on the scoring criteria of the scoring model, and determine the corresponding scoring data based on all the score data, wherein the work unit, position, job responsibilities, and working time all have corresponding score data.

[0120] Furthermore, the device includes but is not limited to:

[0121] The personal information collection module is used to collect the applicant's personal information based on resume data, where the personal information includes skills, past work experience, educational background, etc.;

[0122] The personality characteristics information acquisition module is used to obtain the personality characteristics information of applicants through questionnaire surveys, psychological assessments, and behavioral analysis;

[0123] The specific requirements retrieval module is used to retrieve the specific requirements corresponding to all teams, where the specific requirements include the required skill combination, personality type, and team size;

[0124] The matching team determination module matches teams based on specific needs, personal information, and personality characteristics to determine the matching team corresponding to the applicant.

[0125] Furthermore, the device includes but is not limited to:

[0126] The module for determining the skill points to be trained retrieves the specific recruitment requirements for the job and determines the corresponding skill points to be trained based on the specific recruitment requirements;

[0127] The virtual environment creation module is based on 3D modeling tools and all the skills that need to be trained to create a virtual environment, including workplaces, equipment, tools, etc.

[0128] The operation report score generation module records the operation data of the applicant in the virtual environment, which is used to generate the corresponding operation report score and feed back the operation report score to the human resources management personnel.

[0129] An embodiment of the present application also discloses a human resource management method based on artificial intelligence, including a processor, in which a program of any one of the above-mentioned human resource management methods based on artificial intelligence is running.

[0130] An embodiment of the present application also discloses a storage medium storing a program of any one of the above-mentioned human resource management methods based on artificial intelligence.

[0131] The effects of the above technical solutions are summarized as follows:

[0132] Automatically parse resumes and extract keywords through natural language processing technology, reducing the manual screening workload of human resource management personnel; automatically verify the authenticity of resume information using external data sources, reducing the time of manual verification and lowering the error rate; use scoring models to quickly screen out qualified applicants and shorten the screening cycle; automate the entire process from resume receipt, parsing, verification to scoring and interview scheduling to improve the efficiency of the recruitment process.

[0133] Improve the objectivity and accuracy of information verification through quantitative evaluation, and ensure the authenticity and reliability of applicant information; improve the accuracy and reliability of scoring through the scoring model trained by the machine learning model, and optimize the recruitment process; ensure that the scoring model can accurately evaluate the applicant's work experience according to specific job requirements and improve recruitment accuracy.

[0134] By comprehensively analyzing the applicants' information and personality traits and combining them with team needs, we can achieve accurate team matching and improve team effectiveness. Through operational tests in a virtual environment, we can evaluate the applicants' actual operational capabilities and skill matching, and assist in making more objective recruitment decisions.

[0135] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A human resource management method based on artificial intelligence, characterized in that: include: Receiving resume data of an applicant, parsing the resume data using natural language processing technology, and extracting keywords related to the position from the resume data to determine corresponding key information; Retrieving a pre-linked external data source, and verifying the authenticity of information provided by the resume data based on the external data source; After successful verification, the key information and resume data are scored using a scoring model, corresponding scoring data is obtained, and an interview is arranged based on the scoring data.

2. The human resource management method based on artificial intelligence according to claim 1, characterized in that: In the process of verifying the authenticity of the information provided by the resume data based on the external data source, the method further includes: Retrieve the corresponding key information, use the key information as a query parameter, and call the external data source through an API to obtain corresponding relevant information; Comparing the relevant information obtained from the external data source with the key information in the resume to generate a corresponding verification report; Feedback the verification report to the human resources management personnel to determine whether it is authentic.

3. The human resource management method based on artificial intelligence according to claim 2 is characterized in that: In the process of feeding back the verification report to the human resources management personnel and determining whether it is true, the method further includes: Obtaining a corresponding authenticity score given by a human resources manager to evaluate the verification report, wherein the more consistent the information in the verification report is, the higher the corresponding authenticity score is; Retrieving a corresponding authenticity threshold, and comparing the authenticity score with the authenticity threshold; If the authenticity score is greater than the authenticity threshold, it is determined to be authentic.

4. The human resource management method based on artificial intelligence according to claim 1, characterized in that: For application of the scoring model, the method further includes: Collect historical recruitment data, including the resume data, interview evaluation results, and final recruitment of hired employees, extract keywords related to the position from the resume data, encode and standardize them, and define labels based on whether the employees were finally hired or not; Train the machine learning model using historical recruitment data, evaluate the performance of the machine learning model through cross-validation, evaluate the performance of the model using a test dataset from the historical recruitment data, and adjust the hyperparameters of the machine learning model; The trained machine learning model is determined as the corresponding scoring model, and the scoring model is deployed in the human resources management system.

5. The human resource management method based on artificial intelligence according to claim 4 is characterized in that: In the process of obtaining the corresponding scoring data, the method further includes: Determine specific recruitment requirements for the job recruitment, associate the specific recruitment requirements with the scoring model, and adjust the scoring criteria corresponding to the scoring model based on the specific recruitment requirements, the specific recruitment requirements including necessary skills, years of work experience, and specific industry background; Extracting the applicant's work experience from the resume, and inputting the work experience into a scoring model for scoring, wherein the work experience includes work unit, position, job responsibilities, and working time; The scoring model obtains score data corresponding to the work experience based on the scoring criteria, and determines corresponding score data based on all the score data, wherein the work unit, position, job responsibilities, and working time all have corresponding score data.

6. The human resource management method based on artificial intelligence according to claim 1 is characterized in that: After determining the applicants corresponding to the recruitment, the method further includes: Collect applicants’ personal information based on resume data, including skills, past work experience, educational background, etc.; Obtaining information on the personality characteristics of the applicant through questionnaires, psychological assessments, and behavioral analysis; Retrieve specific requirements for all teams, including required skill sets, personality types, and team size; Team matching is performed based on the specific needs, the personal information and the personality characteristic information to determine the suitable team for the applicant.

7. The human resource management method based on artificial intelligence according to claim 1 is characterized in that: The method also includes: Retrieving specific recruitment requirements for job recruitment, and determining corresponding skills points to be trained based on the specific recruitment requirements; Creating a virtual environment based on all the skill points to be trained based on a 3D modeling tool, wherein the virtual environment includes a workplace, equipment, tools, etc.; The operation data of the applicant in the virtual environment is recorded, and a corresponding operation report score is generated, and the operation report score is fed back to the human resources management personnel.

8. A human resource management device based on artificial intelligence, characterized in that: include: Key information determination module: Receive the resume data of the applicant, parse the resume data through natural language processing technology, and extract keywords related to the position from the resume data to determine the corresponding key information; A verification model, which retrieves a pre-linked external data source and verifies the authenticity of information provided by the resume data based on the external data source; The scoring data acquisition module, after successful verification, uses the scoring model to score the key information and resume data to obtain corresponding scoring data and arrange interviews based on the scoring data.

9. A human resource management method based on artificial intelligence, characterized in that: It comprises a processor, in which a program of the human resource management method based on artificial intelligence as described in any one of claims 1 to 7 is run.

10. A storage medium, characterized in that: A program storing the human resource management method based on artificial intelligence as described in any one of claims 1 to 7 is provided.

Images