Mechanism personnel adding method, device and equipment and medium

Abstract

The invention belongs to the field of artificial intelligence, and relates to an institution staff adding method, which comprises the following steps: acquiring staff adding demand information of a target institution and target data of an initial candidate object; determining candidate objects from the initial candidate objects on the basis of the personnel increase demand information, the target data and a preset reference portrait; based on the target data of the candidate object, adopting a preset question and answer model to generate a target interview question of the candidate object so as to obtain reply data of the candidate object for the target interview question; scoring the reply data by adopting a preset scoring model to obtain a scoring result of the candidate object; and on the basis of the scoring result, selecting an object to be subjected to personnel addition from the candidate objects. The invention further provides a device, equipment and a medium. In addition, the invention also relates to a block chain technology, and the added personnel demand information and the target data can be stored in a block chain. According to the invention, the mechanism personnel increasing efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and medium for recruiting personnel for an organization. Background Art

[0002] In the insurance industry, the sustainable development and market competitiveness of insurance companies largely rely on the construction and expansion of their workforce, especially the recruitment of sales and service teams. In the traditional recruitment process of insurance companies, the recruitment interview stage occupies a pivotal position. However, this stage generally has many challenges and shortcomings.

[0003] Specifically, the traditional recruitment interview process relies on steps such as manual resume screening, interview scheduling, and face-to-face communication. These steps are not only time-consuming but also inefficient. In addition, due to factors such as differences in interviewers' subjective judgments and insufficient standardization of interview questions, the recruitment process lacks sufficient personalization and intelligence, making it difficult to accurately match the talent needs of insurance companies for different positions. In summary, there is an urgent need for a method that can solve the problems of the traditional recruitment interview process, such as being time-consuming and labor-intensive, lacking personalization and intelligence, and low recruitment efficiency. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a method, device, equipment and medium for recruiting employees for an organization, so as to solve the problems of the existing recruitment interview process being time-consuming and labor-intensive, lacking in personalization and intelligence, and having low recruitment efficiency.

[0005] In order to solve the above technical problems, the present application embodiment provides a method for recruiting new employees, which adopts the following technical solutions:

[0006] Obtain the target organization's recruitment demand information and the target data of the initial candidates; determine the candidates from the initial candidates based on the recruitment demand information, the target data of the initial candidates and the preset reference portraits; based on the target data of the candidates, use a preset question-answering model to generate target interview questions for the candidates to obtain the candidates' response data to the target interview questions; use a preset scoring model to score the response data to obtain the scoring results for the candidates; and select candidates to be recruited from the candidates based on the scoring results.

[0007] Furthermore, before the step of determining the candidate from the initial candidate based on the recruitment demand information, the target data of the initial candidate and the preset reference portrait, the method further includes:

[0008] Obtain the personal data of the target object; classify the target object according to the preset classification strategy and personal data to obtain the classification result; use the preset feature extraction algorithm to extract the feature information of the target object from the personal data; determine the feature weight of the feature information based on the preset weight allocation strategy; construct a portrait framework of the target object based on the classification result, feature information and feature weight; fill the portrait framework based on the personal data to obtain a preset reference portrait.

[0009] Furthermore, based on the recruitment demand information, the target data of the initial candidate objects and the preset reference portrait, the step of determining the candidate objects from the initial candidate objects specifically includes:

[0010] Based on the recruitment demand information and the target data of the initial candidate objects, the screening conditions are determined; the target initial candidate objects that meet the screening conditions are screened out from the initial candidate objects; the feature vector of the target data of the target initial candidate objects is extracted, and based on the feature vector, a detailed portrait of the target initial candidate objects is constructed; the detailed portrait and the reference portrait are matched for similarity to obtain a similarity matching result; based on the similarity matching result, the target initial candidate objects are screened to obtain screened candidate objects.

[0011] Further, based on the target data of the candidate, the step of using a preset question-answering model to generate target interview questions for the candidate specifically includes:

[0012] Obtain the job description information of the target position applied for by the candidate; extract the education background information and work experience information from the target data of the candidate; integrate the education background information, work experience information and job description information according to a preset data format to obtain model input data; use a preset question-answering model to analyze and process the model input data to generate interview questions; use a preset question quality assessment algorithm to screen the interview questions to obtain target interview questions.

[0013] Furthermore, the step of using a preset scoring model to score the response data and obtain the scoring results of the candidate objects specifically includes:

[0014] Extract the response features of the response data; input the response features into a preset scoring model to obtain a preliminary score for the candidate; obtain a preset scoring standard, and calibrate the preliminary score according to the scoring standard to obtain a corrected target score; output the target score as the scoring result for the candidate.

[0015] Further, based on the scoring results, the step of selecting the candidates to be recruited from the candidates specifically includes:

[0016] Obtain reference scores of candidate objects; obtain reference weights of reference scores, and obtain target weights of target scores; perform weighted operations on reference scores, reference weights, target scores, and target weights to obtain weighted average scores of candidate objects; and select candidates for recruitment from among the candidate objects based on the weighted average scores.

[0017] Furthermore, after the step of selecting the candidate to be recruited from the candidate based on the scoring result, the following steps are specifically included:

[0018] Obtain historical staff data of the target organization; use a preset association rule mining algorithm to mine association rules between the attribute characteristics of target employees and their career development paths from the historical staff data; extract attribute feature vectors of the target data of the target employees to be recruited; based on the association rules and attribute feature vectors, determine the target career development path from the career development paths; based on the target career development path, generate a career development reference for the target employees to be recruited.

[0019] In order to solve the above technical problems, the embodiment of the present application also provides an organization recruitment device, which adopts the following technical solutions:

[0020] An acquisition module is used to obtain the target organization's recruitment demand information and target data of initial candidates;

[0021] A determination module, for determining a candidate from the initial candidate based on recruitment demand information, target data of the initial candidate, and a preset reference profile;

[0022] A question generation module is used to generate target interview questions for the candidate based on the target data of the candidate and using a preset question-answering model to obtain the candidate's answer data for the target interview questions;

[0023] A scoring module is used to score the response data using a preset scoring model to obtain a scoring result for the candidate object;

[0024] The selection module is used to select candidates to be recruited from the candidate objects based on the scoring results.

[0025] In order to solve the above technical problems, an embodiment of the present application also provides a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the above-mentioned method for recruiting personnel are implemented.

[0026] In order to solve the above technical problems, an embodiment of the present application also provides a computer-readable storage medium, which stores computer-readable instructions. The computer-readable instructions can be executed by at least one processor to enable at least one processor to perform the steps of the above-mentioned institutional recruitment method.

[0027] Compared with the prior art, the embodiment of the present application mainly has the following beneficial effects: by obtaining the target organization's recruitment demand information and the target data of the initial candidate, the accurate grasp of the recruitment demand and the preliminary screening of the candidate are realized, and the time cost of manually screening resumes is effectively reduced. Secondly, based on the preset reference portrait, the candidate that meets the job requirements can be quickly determined from the initial candidate. This process not only improves the accuracy of the screening, but also makes the recruitment process more personalized and intelligent. Furthermore, the preset question-and-answer model is used to generate the target interview questions, and the answer data of the candidate is collected. This process not only realizes the combination of standardization and personalization of the interview questions, but also improves the pertinence and efficiency of the interview. Finally, the answer data is scored by the preset scoring model, and the performance of the candidate can be objectively and impartially evaluated, thereby ensuring that the selected object to be recruited meets the actual needs of the target organization and improving the efficiency of the organization's recruitment. In summary, the technical solution realizes the comprehensive optimization of the recruitment interview process through intelligent and standardized processing means, which not only improves the recruitment efficiency, but also ensures the recruitment quality, so that the target organization can efficiently conduct interviews and recruitment processes. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0029] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0030] Figure 2 It is a flowchart of a method for recruiting members of an organization provided by this application;

[0031] Figure 3 It is a structural schematic diagram of an institutional recruitment device provided by the present application;

[0032] Figure 4 It is a structural schematic diagram of a computer device provided by this application. DETAILED DESCRIPTION

[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0034] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0035] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0036] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0037] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0038] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0039] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0040] It should be noted that the organization recruitment method provided in the embodiment of the present application is generally executed by a server, and accordingly, the organization recruitment device is generally set in the server.

[0041] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0042] Continue to refer Figure 2 , showing a flow chart of an embodiment of the method for increasing staff of an organization according to the present application. The method for increasing staff of an organization comprises the following steps:

[0043] Step S201, obtaining the target organization's recruitment demand information and target data of initial candidate objects.

[0044] In this embodiment, the electronic device (eg Figure 1 The server shown in the figure) can obtain the recruitment demand information through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0045] The target organization refers to the organization that needs to recruit new employees. For example, a large insurance company plans to expand its sales team, and the insurance company is the target organization.

[0046] Among them, the recruitment demand information refers to the specific requirements for new employees proposed by the target organization. It can include the type of position, quantity, required skills, etc. It is used to guide the subsequent screening and matching process. For example, the recruitment demand information may include "recruiting 5 sales managers with more than 3 years of insurance sales experience."

[0047] The initial candidates refer to the set of candidates that meet the basic requirements after preliminary screening. These candidates may come from various channels such as recruitment websites and internal recommendations. For example, the candidates among 100 resumes obtained from a recruitment website are the initial candidates.

[0048] The target data of the initial candidate refers to the personal information provided by the initial candidate, such as resume, self-introduction, etc. It can be used for subsequent analysis and evaluation. For example, the candidate's educational background, work experience, professional skills, etc.

[0049] Step S202, determining a candidate object from the initial candidate objects based on the recruitment demand information, the target data of the initial candidate objects, and a preset reference portrait.

[0050] The reference profile refers to an ideal employee image constructed based on the characteristics of outstanding employees of the target organization. It is used to match with the candidate. For example, the reference profile may include characteristics such as "having 5 years of insurance sales experience, good at communication, and excellent performance".

[0051] Among them, candidates refer to candidates who meet the recruitment requirements and are more closely matched with the reference profile after further screening. For example, 20 qualified candidates are screened out of 100 initial candidates.

[0052] Step S203, based on the target data of the candidate, using a preset question-answering model, generates target interview questions for the candidate to obtain the candidate's answer data for the target interview questions.

[0053] Among them, the target data of the candidate refers to the more detailed information provided by the candidate during the screening process, which is used to generate interview questions and evaluate responses. For example, the candidate's specific work experience, project experience, professional skills certificates, etc.

[0054] The question-answering model refers to an algorithmic model based on machine learning that is used to generate interview questions based on the target data of the candidate. For example, the question-answering model can generate professional questions related to the position based on the candidate's work experience.

[0055] Among them, target interview questions refer to specific questions used in interviews that are generated by the question-answering model based on the target data of the candidate. These questions are designed to assess the candidate's professional ability, work experience, and overall quality. For example, "Please describe how you successfully completed a sales task in your past job."

[0056] The response data refers to the answers given by the candidate to the target interview questions, which are used to evaluate the candidate's ability and fit. For example, the candidate's description and explanation of the above sales task.

[0057] Step S204: Use a preset scoring model to score the response data to obtain a scoring result for the candidate object.

[0058] The scoring model refers to a mathematical model that quantitatively evaluates the candidate's response data based on preset algorithms and rules. The model extracts response features from the response data and uses these features to comprehensively score the candidate's response quality, professional ability, and adaptability. For example, the scoring model can be a neural network-based scoring model that learns and extracts key features from responses by training a large amount of historical interview data, and then accurately scores new response data.

[0059] The scoring result refers to the score obtained by evaluating the response data using a preset scoring model, which is used to quantify the candidate's performance. For example, the score is given based on the quality of the candidate's answer and the degree of match with the job requirements.

[0060] Step S205: selecting candidates to be recruited from the candidate candidates based on the scoring results.

[0061] Among them, the candidates to be recruited refer to the candidates who are selected from the candidates based on the scoring results and are the final recruitment targets. For example, 5 candidates with the highest scores are selected from 20 candidates.

[0062] The embodiment of the present application can achieve accurate grasp of recruitment needs and preliminary screening of candidates by obtaining the target organization's recruitment demand information and the target data of the initial candidates, effectively reducing the time cost of manually screening resumes. Secondly, based on the preset reference portrait, it is possible to quickly determine the candidate that meets the job requirements from the initial candidates. This process not only improves the accuracy of screening, but also makes the recruitment process more personalized and intelligent. Furthermore, the preset question-and-answer model is used to generate target interview questions, and the answer data of the candidates are collected. This process not only realizes the combination of standardization and personalization of interview questions, but also improves the pertinence and efficiency of the interview. Finally, the answer data is scored by the preset scoring model, and the performance of the candidates can be objectively and impartially evaluated, thereby ensuring that the selected candidates meet the actual needs of the target organization and improving the efficiency of the organization's recruitment. In summary, this technical solution realizes the comprehensive optimization of the recruitment interview process through intelligent and standardized processing means, which not only improves the recruitment efficiency, but also ensures the recruitment quality, so that the target organization can efficiently conduct interviews and recruitment processes.

[0063] In some optional implementations of this embodiment, in step 202, before determining a candidate from the initial candidate based on the recruitment demand information, the target data of the initial candidate, and the preset reference portrait, the following steps are specifically included:

[0064] Obtain the personal data of the target object; classify the target object according to the preset classification strategy and personal data to obtain the classification result; use the preset feature extraction algorithm to extract the feature information of the target object from the personal data; determine the feature weight of the feature information based on the preset weight allocation strategy; construct a portrait framework of the target object based on the classification result, feature information and feature weight; fill the portrait framework based on the personal data to obtain a preset reference portrait.

[0065] Among them, the target objects refer to the employees within the target organization. By obtaining the personal data of these employees, a reference portrait is constructed.

[0066] Personal data refers to personal information provided by the target, including but not limited to education background, work experience, skill level, etc. It can be used to build profiles and assessments.

[0067] The classification strategy refers to the method of classifying the target objects according to the preset standards and rules. For example, the target objects are classified into three categories: "junior", "intermediate" and "senior" according to their years of work experience.

[0068] The classification result refers to the result obtained after classifying the target object according to the classification strategy. For example, a candidate (target object) is classified as a "mid-level" salesperson.

[0069] The feature extraction algorithm refers to an algorithm that extracts information related to the characteristics of the target object from personal data. For example, key information related to sales targets can be extracted from the work experience of the target object.

[0070] The characteristic information of the target object refers to the information obtained through the feature extraction algorithm and used to describe the characteristics of the target object, such as the sales performance and communication ability of the candidate.

[0071] Among them, the weight allocation strategy refers to the method of assigning different weights to feature information according to its importance and relevance. For example, for sales personnel, sales performance and communication skills may be given higher weights.

[0072] The feature weight refers to the weight value assigned to the feature information according to the weight allocation strategy. For example, the weight of sales performance is 0.5, and the weight of communication ability is 0.3.

[0073] The portrait framework refers to a model framework that is constructed based on classification results and feature weights and is used to describe the characteristics of the target object. For example, a portrait framework that includes features such as sales performance, communication skills, and work experience.

[0074] In one example, first, the personal information of the target object can be collected through legal means, including but not limited to age, gender, occupation, hobbies, consumption habits, etc. Next, the target object is classified according to the preset classification strategy (such as classification based on occupation and age group) in combination with personal data to obtain the classification result. Next, the preset feature extraction algorithm (such as decision tree and random forest in machine learning algorithm) is used to extract the characteristic information of the target object from the personal data, such as consumption preference, social activity, etc. Then, based on the preset weight allocation strategy (such as the importance of the feature information, the relevance to the target object portrait, etc.), the feature weight of each feature information is determined. Then, the classification result, feature information and feature weight are combined to construct the portrait framework of the target object. Finally, based on the personal data, the portrait framework is filled to obtain the preset reference portrait. The reference portrait can comprehensively and accurately reflect the characteristics of the target object.

[0075] The embodiment of the present application can realize the construction of an accurate portrait of the target object by systematically processing the personal data of the target object. First, the preset classification strategy ensures that the target object can be reasonably classified, providing a basic framework for subsequent portrait construction. Then, the preset feature extraction algorithm is used to deeply mine the key information in the personal data, and these feature information can fully reflect the characteristics of the target object. The weight distribution strategy further improves the accuracy of portrait construction, and ensures the rationality and importance of each feature in the portrait by assigning reasonable weights to different feature information. Finally, the portrait framework constructed by combining the classification results, feature information and feature weights, and using personal data for filling, a preset reference portrait is obtained. This reference portrait is not only comprehensive and accurate, but also can be flexibly applied to different scenarios.

[0076] In some optional implementations of this embodiment, step S202, based on the recruitment demand information, the target data of the initial candidate objects, and the preset reference portrait, determines the candidate objects from the initial candidate objects, and specifically includes the following steps:

[0077] Based on the recruitment demand information and the target data of the initial candidate objects, the screening conditions are determined; the target initial candidate objects that meet the screening conditions are screened out from the initial candidate objects; the feature vector of the target data of the target initial candidate objects is extracted, and based on the feature vector, a detailed portrait of the target initial candidate objects is constructed; the detailed portrait and the reference portrait are matched for similarity to obtain a similarity matching result; based on the similarity matching result, the target initial candidate objects are screened to obtain screened candidate objects.

[0078] Among them, screening conditions refer to the conditions set for screening candidates based on recruitment demand information and reference profiles. For example, candidates are required to have more than 3 years of sales experience and excellent performance.

[0079] The feature vector refers to the conversion of the target data of the target initial candidate object into a vector form for subsequent analysis and calculation.

[0080] Among them, a detailed profile refers to a profile that is constructed based on the target data and feature vector of the candidate and contains more detailed information. For example, a detailed profile that contains information such as the candidate's specific work experience, project experience, and professional skills.

[0081] In one example, the target organization needs to recruit a back-end development engineer with Java development experience. First, the recruitment demand information can be extracted based on the job description, such as skill requirements (Java, Spring Boot), work experience (more than 3 years), etc. Then, the target data of the initial candidates is obtained from the resume database, including educational background, work experience, skill certificates, etc. Next, set the screening conditions, such as the degree must be a bachelor's degree or above, and have Java project experience, etc., to filter out the target initial candidates who meet the conditions from the initial candidates. Subsequently, the machine learning algorithm is used to extract the feature vector of the target data and construct a detailed portrait, such as technical ability, project experience, communication ability and other dimensions. At the same time, a reference portrait is constructed based on historical excellent employee data. The similarity between the detailed portrait and the reference portrait is calculated by cosine similarity, and candidates with a similarity higher than the threshold are selected for further interviews, which significantly improves the accuracy and efficiency of recruitment.

[0082] The embodiment of the present application can achieve preliminary and accurate screening of candidates by combining the recruitment demand information with the target data of the initial candidates and carefully setting the screening conditions. On this basis, the target data feature vector of the target initial candidate is further extracted, and a detailed portrait is constructed accordingly. This step greatly enriches the personalized information of the candidate and provides a solid foundation for subsequent matching. By matching the detailed portrait with the reference portrait for similarity, this solution can quantitatively evaluate the degree of fit between the candidate and the job requirements, ensuring the objectivity and accuracy of the screening process. Finally, based on the screening of similarity matching results, it is possible to efficiently identify candidates that are highly matched with the job requirements, which not only improves recruitment efficiency, but also effectively reduces the risk of mismatching, bringing significant optimization effects to the human resource management of the target organization.

[0083] In some optional implementations of this embodiment, step S203, based on the target data of the candidate, uses a preset question-answering model to generate target interview questions for the candidate, specifically including the following steps:

[0084] Obtain the job description information of the target position applied for by the candidate; extract the education background information and work experience information from the target data of the candidate; integrate the education background information, work experience information and job description information according to a preset data format to obtain model input data; use a preset question-answering model to analyze and process the model input data to generate interview questions; use a preset question quality assessment algorithm to screen the interview questions to obtain target interview questions.

[0085] The job description information refers to a detailed description of the target job, including job responsibilities, job requirements, etc. For example, the job description information of a sales manager may include "responsible for formulating sales strategies and achieving sales targets" and so on.

[0086] The data format refers to integrating the educational background information, work experience information, and job description information into a format that can be recognized by the question-answering model. For example, the information is integrated into JSON or XML format.

[0087] Among them, the question quality assessment algorithm is used to evaluate whether the generated interview questions meet the preset standards. For example, whether the assessment questions are relevant to the job description information and whether they are helpful in evaluating the candidate's ability.

[0088] In one example, the target organization needs to recruit a software development engineer, and the job description information includes programming language requirements (such as Java, Python), project development experience, teamwork ability, etc. The target data of the candidate includes his educational background (such as computer science major, master's degree), work experience (such as having participated in multiple large-scale software development projects and serving as a core development role), etc. The job description information, educational background information and work experience information can be integrated in a preset data format (such as JSON format) to form model input data. Then, a pre-trained question-answering model (such as a BERT model) is used to analyze and process the model input data to generate interview questions that are highly relevant to the job description and the candidate's background, such as "Please describe the biggest challenges you encountered in Java project development and solutions", "How to effectively coordinate project progress and team members' work in a team", etc. The interview questions are screened through a preset question quality assessment algorithm (such as semantic similarity calculation based on natural language processing technology, question complexity assessment, etc.), and repeated, ambiguous and overly simple questions are removed to obtain the target interview questions.

[0089] The embodiment of the present application can realize a comprehensive analysis of the target position applied by the candidate through intelligent means. By accurately extracting the educational background and work experience information of the candidate and integrating it with the job description information, structured model input data is formed, which provides a solid foundation for subsequent analysis. The model input data is deeply analyzed and processed using a preset question-and-answer model, which can automatically generate interview questions that are highly relevant to the candidate's background and job requirements, ensuring the pertinence and relevance of the questions. At the same time, the interview questions are screened through a preset question quality assessment algorithm, effectively removing repeated, vague, and low-quality questions, further improving the quality and effectiveness of the interview questions. This technical solution not only improves the generation efficiency of interview questions, but also reduces the subjectivity and uncertainty when designing questions manually, which helps to improve the accuracy and efficiency of recruitment.

[0090] In some optional implementations of this embodiment, step S204, using a preset scoring model to score the response data to obtain a scoring result for the candidate object, specifically includes the following steps:

[0091] Extract the response features of the response data; input the response features into a preset scoring model to obtain a preliminary score for the candidate; obtain a preset scoring standard, and calibrate the preliminary score according to the scoring standard to obtain a corrected target score; output the target score as the scoring result for the candidate.

[0092] The answer features refer to the key information related to the evaluation extracted from the answer data, for example, the description of sales strategy and goals extracted from the candidate's answer.

[0093] The preliminary score refers to the score obtained by using the scoring model to make a preliminary assessment of the response characteristics. For example, the preliminary score is given based on the quality of the candidate's answer and the degree of match with the job requirements.

[0094] Among them, the scoring criteria are used to calibrate the preliminary scoring and ensure that the scoring results are objective and fair. For example, the scoring criteria are formulated based on historical data and industry standards.

[0095] Among them, the target score refers to the final score result after correction of the scoring criteria.

[0096] In one example, key features can be extracted from the interview response data of the candidate, such as the fluency of language expression, the accuracy of professional knowledge, the logic of answering questions, the stability of emotional control, etc. These features can be quantified through natural language processing technology (such as text segmentation, sentiment analysis, keyword extraction, etc.). The extracted response features are input into the preset scoring model. The scoring model can be built based on a machine learning algorithm (such as support vector machine, random forest, neural network, etc.), and by training a large amount of historical interview data, it can automatically give a preliminary score based on the response features. Obtain a preset scoring standard, which can be customized according to different recruitment needs and job characteristics, including the weight distribution of each response feature, the scoring range, the scoring level, etc. According to the scoring standard, the preliminary score is corrected to eliminate the possible deviation of the scoring model and obtain a more objective and accurate corrected target score.

[0097] The embodiments of the present application can significantly improve the accuracy and objectivity of candidate scoring through a refined data processing process. First, the extraction of reply features can accurately capture the key information in the reply data, providing strong support for subsequent scoring. Secondly, the application of the preset scoring model realizes the automatic generation of preliminary scores and improves the scoring efficiency. Furthermore, the preliminary scores are corrected in combination with the preset scoring criteria to ensure the fairness and consistency of the scores, and effectively avoid the subjectivity and uncertainty of manual scoring. Finally, the output target score is used as the scoring result of the candidate, which not only reflects the true level of the candidate, but also provides a reliable basis for subsequent decision-making.

[0098] In some optional implementations of this embodiment, step S205, selecting a candidate to be recruited from the candidate objects based on the scoring result, may specifically include the following steps:

[0099] Obtain reference scores of candidate objects; obtain reference weights of reference scores, and obtain target weights of target scores; perform weighted operations on reference scores, reference weights, target scores, and target weights to obtain weighted average scores of candidate objects; and select candidates for recruitment from among the candidate objects based on the weighted average scores.

[0100] The reference score refers to the interview score of the candidate obtained from other interview terminals, for example, the score given by multiple interviewers after interview evaluation of the candidate and submitted through the interview terminal.

[0101] The reference weight is the weight value assigned to the reference score, which is used to consider its influence in the weighted calculation. For example, the weight assigned to the reference score based on its importance and relevance.

[0102] The target weight is the weight value assigned to the target score, which is used to consider its influence in the weighted operation. For example, the weight assigned to the target score is based on the importance and relevance of the current evaluation.

[0103] Among them, the weighted average score refers to the average score obtained by weighted calculation of the reference score, reference weight, target score and target weight.

[0104] In one example, the human resources department or recruitment experts can give a preliminary score based on the candidate's resume, educational background, work experience and other basic information. According to the recruitment needs of the target organization and the characteristics of the position, set the weight of the reference score, such as 0.4. Use the preset scoring model to score the response data to obtain the target score of the candidate. Similarly, according to the recruitment needs of the target organization and the characteristics of the position, set the weight of the target score, such as 0.6. Multiply the reference score and target score of each candidate by the corresponding weights to obtain the weighted reference score and target score. Add the weighted reference score and target score to obtain the weighted average score of the candidate. Sort the candidates according to the weighted average score. Select the candidate with a higher weighted average score as the candidate to be recruited and enter the subsequent recruitment process.

[0105] The embodiment of the present application can achieve a comprehensive and accurate quantification of the capabilities of the candidates by introducing a dual-dimensional evaluation system of reference score and target score, and cleverly integrating the reference weight and target weight. Based on this quantitative scoring result, the candidates to be recruited can be selected more scientifically and fairly, effectively improving the accuracy and efficiency of talent selection.

[0106] In some optional implementations of this embodiment, after selecting the candidate to be recruited from the candidate objects based on the scoring result in step S205, the following steps may be specifically included:

[0107] Obtain historical staff data of the target organization; use a preset association rule mining algorithm to mine association rules between the attribute characteristics of target employees and their career development paths from the historical staff data; extract attribute feature vectors of the target data of the target employees to be recruited; based on the association rules and attribute feature vectors, determine the target career development path from the career development paths; based on the target career development path, generate a career development reference for the target employees to be recruited.

[0108] Among them, historical employee data refers to the personal information and work performance data of the target organization’s past employees, which is used to mine association rules and career development paths. For example, the employee data and performance records of a sales team of an insurance company in the past five years.

[0109] Among them, the association rule mining algorithm refers to the algorithm that mines the association relationship between variables from a large amount of data. For example, mining the association rules between the attribute characteristics of the target employee and the career development path from historical employee data.

[0110] Among them, attribute characteristics refer to attribute information that describes the characteristics of the target employee, such as age, education, work experience, etc. For example, the age and education of the target employee are attribute characteristics.

[0111] Among them, association rules refer to rules that describe the association relationship between variables obtained through association rule mining algorithms. For example, "employees with more than 5 years of sales experience and excellent performance are more likely to be promoted to sales managers" is an association rule.

[0112] The attribute feature vector refers to the conversion of employee attribute features into vector form for subsequent analysis and calculation. For example, the attribute features such as employee age, education, and work experience are converted into a vector containing multiple values.

[0113] The target career development path refers to the career development path determined for the candidate to be recruited based on the association rules and attribute feature vectors, for example, the career development path from sales consultant to sales manager determined for the candidate to be recruited.

[0114] Among them, career development reference refers to the career development suggestions and plans provided to the candidates for recruitment based on the target career development path.

[0115] In one example, historical staff data can be exported from the human resources information system of the target organization, including basic staff information (such as gender, age, education, major, etc.), work performance (such as performance evaluation, project participation, etc.), promotion records, etc. Then, the Apriori algorithm is used as the preset association rule mining algorithm to process the historical staff data and mine the association rules between staff attribute characteristics and career development paths. For example, it is found that employees who "graduated from 985 / 211 universities and have matching majors" are more likely to get promotion opportunities within three years after joining the company. Next, the basic information and work performance of the objects to be recruited (such as newly recruited graduates) are collected, and their attribute feature vectors are extracted, such as education, major, entry performance, etc. Then, the attribute feature vectors of the objects to be recruited are matched with the mined association rules, and the career development path that best matches their attribute characteristics is calculated, that is, the target career development path. Finally, based on the target career development path and combined with the company's internal job setting and promotion mechanism, a personalized career development reference is generated for the recruits, including short-term goals (such as improving professional skills, participating in specific projects), medium-term goals (such as obtaining promotion opportunities, assuming more responsibilities) and long-term goals (such as becoming a department head, industry expert, etc.).

[0116] The embodiment of the present application can reveal the intrinsic connection between employee attribute characteristics and career development paths by deeply mining the historical employee data of the target organization and using advanced association rule mining algorithms. By accurately extracting the attribute feature vectors of the objects to be recruited and matching them with the mined association rules, it is possible to personalize and predict and determine their target career development paths. This innovative method not only provides a scientific and reasonable career development blueprint for the objects to be recruited, but also significantly enhances the pertinence and effectiveness of career development planning. With the help of this career development reference, the objects to be recruited can more clearly understand their own development paths and clarify their career goals, thereby effectively improving their personal professional qualities and accelerating their personal growth process. At the same time, the technical solution also provides strong support for the talent training and career development management of the target organization, and helps to build a more complete and efficient human resources management system.

[0117] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned recruitment demand information and target data, the above-mentioned recruitment demand information and target data can also be stored in a node of a blockchain.

[0118] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0119] The embodiments of the present application can build and optimize related models and networks based on artificial intelligence technology, such as question-answering models, scoring models, etc. Among them, artificial intelligence (AI) models are the crystallization of theory and practice that simulate the decision-making process of human intelligence through algorithms and data analysis to solve complex problems, predict future trends, or realize automated tasks. These models use a large amount of historical data and real-time information, and are trained and optimized through a specific algorithm framework to achieve efficient, accurate and reliable performance.

[0120] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0121] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0122] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a device for recruiting personnel in an organization. Figure 2Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0123] like Figure 3 As shown, the organization recruitment device 400 of this embodiment includes: an acquisition module 401, a determination module 402, a question generation module 403, a scoring module 404 and a selection module 405.

[0124] in:

[0125] The acquisition module 401 is used to acquire the recruitment demand information of the target organization and the target data of the initial candidate objects;

[0126] A determination module 402 is used to determine a candidate object from the initial candidate objects based on the recruitment demand information, the target data of the initial candidate objects, and a preset reference portrait;

[0127] The question generation module 403 is used to generate target interview questions for the candidate based on the target data of the candidate and using a preset question-answering model to obtain the candidate's answer data for the target interview questions;

[0128] Scoring module 404, used to score the response data using a preset scoring model to obtain a scoring result for the candidate object;

[0129] The selection module 405 is used to select a candidate to be recruited from the candidate objects based on the scoring result.

[0130] The embodiment of the present application can achieve accurate grasp of recruitment needs and preliminary screening of candidates by obtaining the target organization's recruitment demand information and the target data of the initial candidates, effectively reducing the time cost of manually screening resumes. Secondly, based on the preset reference portrait, it is possible to quickly determine the candidate that meets the job requirements from the initial candidates. This process not only improves the accuracy of screening, but also makes the recruitment process more personalized and intelligent. Furthermore, the preset question-and-answer model is used to generate target interview questions, and the answer data of the candidates are collected. This process not only realizes the combination of standardization and personalization of interview questions, but also improves the pertinence and efficiency of the interview. Finally, the answer data is scored by the preset scoring model, and the performance of the candidates can be objectively and impartially evaluated, thereby ensuring that the selected candidates meet the actual needs of the target organization and improving the efficiency of the organization's recruitment. In summary, this technical solution realizes the comprehensive optimization of the recruitment interview process through intelligent and standardized processing means, which not only improves the recruitment efficiency, but also ensures the recruitment quality, so that the target organization can efficiently conduct interviews and recruitment processes.

[0131] In one embodiment, the determination module 402 includes:

[0132] The condition determination submodule is used to determine the screening conditions based on the recruitment demand information and the target data of the initial candidates;

[0133] A first screening submodule is used to screen out target initial candidate objects that meet the screening conditions from the initial candidate objects;

[0134] A construction submodule is used to extract a feature vector of target data of a target initial candidate object, and to construct a detailed portrait of the target initial candidate object based on the feature vector;

[0135] The matching submodule is used to perform similarity matching between the detailed portrait and the reference portrait to obtain a similarity matching result;

[0136] The second screening submodule is used to screen the target initial candidate objects based on the similarity matching result to obtain screened candidate objects.

[0137] The embodiment of the present application can achieve preliminary and accurate screening of candidates by combining the recruitment demand information with the target data of the initial candidates and carefully setting the screening conditions. On this basis, the target data feature vector of the target initial candidate is further extracted, and a detailed portrait is constructed accordingly. This step greatly enriches the personalized information of the candidate and provides a solid foundation for subsequent matching. By matching the detailed portrait with the reference portrait for similarity, this solution can quantitatively evaluate the degree of fit between the candidate and the job requirements, ensuring the objectivity and accuracy of the screening process. Finally, based on the screening of similarity matching results, it is possible to efficiently identify candidates that are highly matched with the job requirements, which not only improves recruitment efficiency, but also effectively reduces the risk of mismatching, bringing significant optimization effects to the human resource management of the target organization.

[0138] In one embodiment, the question generation module 403 includes:

[0139] A description information acquisition submodule is used to obtain the job description information of the target position applied by the candidate;

[0140] An information extraction submodule is used to extract educational background information and work experience information from the target data of the candidate;

[0141] The integration submodule is used to integrate the educational background information, work experience information and job description information according to the preset data format to obtain the model input data;

[0142] The analysis submodule is used to use a preset question-answering model to analyze and process the model input data and generate interview questions;

[0143] The third screening submodule is used to screen the interview questions using a preset question quality assessment algorithm to obtain target interview questions.

[0144] The embodiment of the present application can realize a comprehensive analysis of the target position applied by the candidate through intelligent means. By accurately extracting the educational background and work experience information of the candidate and integrating it with the job description information, structured model input data is formed, which provides a solid foundation for subsequent analysis. The model input data is deeply analyzed and processed using a preset question-and-answer model, which can automatically generate interview questions that are highly relevant to the candidate's background and job requirements, ensuring the pertinence and relevance of the questions. At the same time, the interview questions are screened through a preset question quality assessment algorithm, effectively removing repeated, vague, and low-quality questions, further improving the quality and effectiveness of the interview questions. This technical solution not only improves the generation efficiency of interview questions, but also reduces the subjectivity and uncertainty when designing questions manually, which helps to improve the accuracy and efficiency of recruitment.

[0145] In one embodiment, the scoring module 404 includes:

[0146] A feature extraction submodule, used to extract reply features of reply data;

[0147] An input submodule, used to input the response features into a preset scoring model to obtain a preliminary score for the candidate;

[0148] The standard acquisition submodule is used to obtain the preset scoring standard, and correct the preliminary score according to the scoring standard to obtain the corrected target score; and output the target score as the scoring result of the candidate object.

[0149] The embodiments of the present application can significantly improve the accuracy and objectivity of candidate scoring through a refined data processing process. First, the extraction of reply features can accurately capture the key information in the reply data, providing strong support for subsequent scoring. Secondly, the application of the preset scoring model realizes the automatic generation of preliminary scores and improves the scoring efficiency. Furthermore, the preliminary scores are corrected in combination with the preset scoring criteria to ensure the fairness and consistency of the scores, and effectively avoid the subjectivity and uncertainty of manual scoring. Finally, the output target score is used as the scoring result of the candidate, which not only reflects the true level of the candidate, but also provides a reliable basis for subsequent decision-making.

[0150] In one embodiment, the selection module 405 includes:

[0151] The score acquisition submodule is used to obtain the reference score of the candidate object;

[0152] The weight acquisition submodule is used to obtain the reference weight of the reference score and the target weight of the target score;

[0153] The weighting submodule is used to perform weighted operations on the reference score, reference weight, target score and target weight to obtain the weighted average score of the candidate object;

[0154] The selection submodule is used to select candidates for recruitment from the candidate objects based on the weighted average score.

[0155] The embodiment of the present application can achieve a comprehensive and accurate quantification of the capabilities of the candidates by introducing a dual-dimensional evaluation system of reference score and target score, and cleverly integrating the reference weight and target weight. Based on this quantitative scoring result, the candidates to be recruited can be selected more scientifically and fairly, effectively improving the accuracy and efficiency of talent selection.

[0156] In one embodiment, the organization recruitment device 400 further includes:

[0157] A data acquisition module, used to acquire personal data of the target object;

[0158] A classification module is used to classify the target object according to the preset classification strategy and personal data to obtain the classification result;

[0159] An information extraction module, used to extract feature information of a target object from personal data using a preset feature extraction algorithm;

[0160] A weight determination module, used to determine the feature weight of feature information based on a preset weight allocation strategy;

[0161] A construction module is used to construct a portrait framework of the target object based on the classification results, feature information and feature weights;

[0162] The filling module is used to fill the portrait framework based on personal data to obtain a preset reference portrait.

[0163] The embodiment of the present application can realize the construction of an accurate portrait of the target object by systematically processing the personal data of the target object. First, the preset classification strategy ensures that the target object can be reasonably classified, providing a basic framework for subsequent portrait construction. Then, the preset feature extraction algorithm is used to deeply mine the key information in the personal data, and these feature information can fully reflect the characteristics of the target object. The weight distribution strategy further improves the accuracy of portrait construction, and ensures the rationality and importance of each feature in the portrait by assigning reasonable weights to different feature information. Finally, the portrait framework constructed by combining the classification results, feature information and feature weights, and using personal data for filling, a preset reference portrait is obtained. This reference portrait is not only comprehensive and accurate, but also can be flexibly applied to different scenarios.

[0164] In one embodiment, the organization recruitment device 400 may further include:

[0165] An employee data acquisition module is used to acquire historical employee data of a target organization;

[0166] A mining module is used to mine the association rules between the attribute characteristics of target employees and their career development paths from historical employee data using a preset association rule mining algorithm;

[0167] A vector extraction module is used to extract attribute feature vectors of target data of the object to be recruited;

[0168] A path determination module, used for determining a target career development path from career development paths based on association rules and attribute feature vectors;

[0169] The reference generation module is used to generate career development references for candidates to be recruited based on the target career development path.

[0170] The embodiment of the present application can reveal the intrinsic connection between employee attribute characteristics and career development paths by deeply mining the historical employee data of the target organization and using advanced association rule mining algorithms. By accurately extracting the attribute feature vectors of the objects to be recruited and matching them with the mined association rules, it is possible to personalize and predict and determine their target career development paths. This innovative method not only provides a scientific and reasonable career development blueprint for the objects to be recruited, but also significantly enhances the pertinence and effectiveness of career development planning. With the help of this career development reference, the objects to be recruited can more clearly understand their own development paths and clarify their career goals, thereby effectively improving their personal professional qualities and accelerating their personal growth process. At the same time, the technical solution also provides strong support for the talent training and career development management of the target organization, and helps to build a more complete and efficient human resources management system.

[0171] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0172] The computer device 6 includes a memory 61, a processor 62, and a network interface 63 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 6 having a memory 61, a processor 62, and a network interface 63, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASIC), programmable gate arrays (FPGA), digital signal processors (DSP), embedded devices, etc.

[0173] Computer devices can be computing devices such as desktop computers, notebooks, PDAs, and cloud servers. Computer devices can interact with users through keyboards, mice, remote controls, touch pads, or voice control devices.

[0174] The memory 61 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 61 can be an internal storage unit of the computer device 6, such as a hard disk or memory of the computer device 6. In other embodiments, the memory 61 can also be an external storage device of the computer device 6, such as a plug-in hard disk equipped on the computer device 6, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 61 can also include both the internal storage unit of the computer device 6 and its external storage device. In this embodiment, the memory 61 is generally used to store the operating system and various application software installed on the computer device 6, such as computer-readable instructions of the organization recruitment method, etc. In addition, the memory 61 can also be used to temporarily store various types of data that have been output or are to be output.

[0175] The processor 62 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 62 is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is used to run computer-readable instructions stored in the memory 61 or process data, such as computer-readable instructions for running the organization recruitment method.

[0176] The network interface 63 may include a wireless network interface or a wired network interface, and the network interface 63 is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0177] The embodiment of the present application can achieve accurate grasp of recruitment needs and preliminary screening of candidates by obtaining the target organization's recruitment demand information and the target data of the initial candidates, effectively reducing the time cost of manually screening resumes. Secondly, based on the preset reference portrait, it is possible to quickly determine the candidate that meets the job requirements from the initial candidates. This process not only improves the accuracy of screening, but also makes the recruitment process more personalized and intelligent. Furthermore, the preset question-and-answer model is used to generate target interview questions, and the answer data of the candidates are collected. This process not only realizes the combination of standardization and personalization of interview questions, but also improves the pertinence and efficiency of the interview. Finally, the answer data is scored by the preset scoring model, and the performance of the candidates can be objectively and impartially evaluated, thereby ensuring that the selected candidates meet the actual needs of the target organization and improving the efficiency of the organization's recruitment. In summary, this technical solution realizes the comprehensive optimization of the recruitment interview process through intelligent and standardized processing means, which not only improves the recruitment efficiency, but also ensures the recruitment quality, so that the target organization can efficiently conduct interviews and recruitment processes.

[0178] The present application also provides another embodiment, namely, providing a computer-readable storage medium, which stores computer-readable instructions. The computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the above-mentioned method for increasing the number of employees in an organization.

[0179] The embodiment of the present application can achieve accurate grasp of recruitment needs and preliminary screening of candidates by obtaining the target organization's recruitment demand information and the target data of the initial candidate, effectively reducing the time cost of manually screening resumes. Secondly, based on the preset reference portrait, it is possible to quickly determine the candidate that meets the job requirements from the initial candidate. This process not only improves the accuracy of screening, but also makes the recruitment process more personalized and intelligent. Furthermore, the preset question-and-answer model is used to generate target interview questions, and the answer data of the candidate is collected. This process not only realizes the combination of standardization and personalization of interview questions, but also improves the pertinence and efficiency of the interview. Finally, the answer data is scored by the preset scoring model, and the performance of the candidate can be objectively and impartially evaluated, thereby ensuring that the selected object to be recruited meets the actual needs of the target organization and improving the efficiency of the organization's recruitment. In summary, the technical solution realizes the comprehensive optimization of the recruitment interview process through intelligent and standardized processing means, which not only improves the recruitment efficiency, but also ensures the recruitment quality, so that the target organization can efficiently conduct interviews and recruitment processes.

[0180] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods of each embodiment of the present application.

[0181] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for recruiting new employees, characterized in that: The steps include: Obtain the target organization's recruitment demand information and target data of initial candidates; Determine a candidate object from the initial candidate objects based on the recruitment demand information, the target data of the initial candidate objects, and a preset reference portrait; Based on the target data of the candidate, using a preset question-answering model, generating target interview questions for the candidate to obtain answer data of the candidate to the target interview questions; Using a preset scoring model to score the response data, and obtaining a scoring result for the candidate object; Based on the scoring result, a candidate to be recruited is selected from the candidate objects.

2. The method according to claim 1, characterized in that Before the step of determining a candidate object from the initial candidate objects based on the recruitment demand information, the target data of the initial candidate objects, and a preset reference portrait, the method further includes: Obtaining personal data of the target person; Classify the target object according to a preset classification strategy and the personal data to obtain a classification result; Using a preset feature extraction algorithm to extract feature information of the target object from the personal data; Determining the feature weight of the feature information based on a preset weight allocation strategy; Based on the classification result, the feature information and the feature weight, construct a portrait framework of the target object; Based on the personal data, the portrait framework is filled to obtain a preset reference portrait.

3. The method according to claim 2, characterized in that The step of determining a candidate object from the initial candidate objects based on the recruitment demand information, the target data of the initial candidate objects, and a preset reference portrait specifically includes: Determining screening conditions based on the recruitment demand information and the target data of the initial candidate objects; Screening out target initial candidate objects that meet the screening conditions from the initial candidate objects; Extracting a feature vector of the target data of the target initial candidate object, and constructing a detailed portrait of the target initial candidate object based on the feature vector; Performing similarity matching on the detailed portrait and the reference portrait to obtain a similarity matching result; Based on the similarity matching result, the target initial candidate objects are screened to obtain screened candidate objects.

4. The method according to claim 1, characterized in that The step of generating target interview questions for the candidate based on the target data of the candidate using a preset question-answering model specifically includes: Obtaining job description information of the target job applied for by the candidate; extracting educational background information and work experience information from the target data of the candidate; Integrate the educational background information, the work experience information and the job description information according to a preset data format to obtain model input data; Using a preset question-answering model, analyzing and processing the model input data to generate interview questions; The interview questions are screened using a preset question quality assessment algorithm to obtain target interview questions.

5. The method according to claim 1, characterized in that The step of using a preset scoring model to score the response data to obtain the scoring result of the candidate object specifically includes: extracting a response feature of the response data; Inputting the response features into a preset scoring model to obtain a preliminary score for the candidate; Obtaining a preset scoring standard, and correcting the preliminary score according to the scoring standard to obtain a corrected target score; The target score is output as the score result of the candidate object.

6. The method according to claim 5, characterized in that The step of selecting a candidate to be recruited from the candidate objects based on the scoring result specifically includes: Obtaining a reference score of the candidate; Obtaining a reference weight of the reference score, and obtaining a target weight of the target score; Performing a weighted operation on the reference score, the reference weight, the target score, and the target weight to obtain a weighted average score of the candidate object; Based on the weighted average score, a candidate for recruitment is selected from the candidate objects.

7. The method according to claim 1, characterized in that After the step of selecting a candidate to be recruited from the candidate objects based on the scoring result, the method further comprises: Obtaining historical staff data of the target organization; Using a preset association rule mining algorithm, mining association rules between the attribute characteristics of the target employee and the career development path from the historical employee data; Extracting attribute feature vectors of target data of the object to be recruited; Determining a target career development path from the career development paths based on the association rules and the attribute feature vector; Based on the target career development path, a career development reference for the person to be recruited is generated.

8. A device for increasing staff, characterized in that: include: An acquisition module is used to obtain the target organization's recruitment demand information and target data of initial candidates; A determination module, configured to determine a candidate object from the initial candidate objects based on the recruitment demand information, the target data of the initial candidate objects, and a preset reference portrait; A question generation module, configured to generate target interview questions for the candidate based on the target data of the candidate and using a preset question-answering model, so as to obtain answer data of the candidate to the target interview questions; A scoring module, used to score the response data using a preset scoring model to obtain a scoring result for the candidate object; A selection module is used to select a candidate to be recruited from the candidate objects based on the scoring result.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the method for increasing staffing as claimed in any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the method for increasing the number of employees in an organization as claimed in any one of claims 1 to 7 are implemented.

Images