Automatic intelligent recruitment method, system, equipment and medium

Abstract

The invention discloses an automatic intelligent recruitment method, system and device and a medium. The automatic intelligent recruitment method comprises the steps of autonomously performing interactive guidance with an enterprise when the enterprise has a recruitment demand so as to actively guide the enterprise to perfect recruitment information and obtain real enterprise terminal information of the enterprise; when an applicant has an application demand, interactive guidance with the applicant is autonomously carried out, so that the applicant is actively guided to perfect a resume and the application demand, and real comprehensive information of the applicant is obtained; and according to the accurate recruitment information of the enterprise, the enterprise terminal information, the accurate resume of the applicant, the job application demand and the comprehensive information, the enterprise and the applicant are matched, and an accurate matching result is obtained. By adopting the method and the device, personnel work such as resume searching, screening and matching before offline interview can be automatically completed, accurate two-way matching of an enterprise and an applicant is realized, respective screening work of the enterprise and the applicant is saved, and then the recruitment efficiency, the recruitment quality and the recruitment satisfaction degree are improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent recruitment technology, and in particular to an automated intelligent recruitment method, system, device and medium. Background Art

[0002] The role of the Internet recruitment platform is mainly to collect job information from the enterprise side (B side) and resume information from the candidate side (C side). On this basis, the enterprise human resources or candidates initiate manual inquiries and screening of the information. The basic workflow is as follows: Figure 9 As shown. The role of the platform is still to collect job positions and resume information, and the matching work still relies mainly on manpower. In addition, whether it is the B-end or the C-end, there may be exaggeration or beautification when publishing information; in addition, when the B-end forms a JD for a position, there may be ambiguity or inaccuracy in the understanding of job responsibilities, requirements, etc., resulting in insufficient accuracy of the original information. Therefore, even though many platforms are now introducing AI intelligent automatic matching, the effect is difficult to achieve the ideal level. In addition, the entire recruitment process still relies mainly on the interaction between the company's human resources and candidates, and has not achieved full process automated management.

[0003] Traditional Internet recruitment platforms have the following technical problems. The accuracy and authenticity of the data cannot be well guaranteed: inaccurate data or untrue information not only makes it difficult to improve the accuracy of automatic matching, but also causes a huge waste of time even for manual screening. Problems with process automation: Current corporate recruitment and candidate job hunting involve a large number of processes that require manual participation, which is time-consuming and labor-intensive. Efficiency issues (simultaneous parallel processing, countless human resources / headhunters): Even if a company is equipped with multiple human resources, difficulty in recruiting is still a problem faced by many companies. The problem of closed loop, feedback data, and tracking process: Traditional recruitment does not introduce feedback and evaluation data, making it impossible to form a closed loop. Therefore, when necessary, manual background checks have to be used to track the candidate's previous records. Summary of the Invention

[0004] Based on this, it is necessary to provide an automated intelligent recruitment method, system, equipment and medium to address the above technical problems, which can automatically complete the personnel work before offline interviews, accurately achieve two-way matching between enterprises and applicants, save the screening work of both enterprises and applicants, and thus improve recruitment efficiency, recruitment quality and recruitment satisfaction.

[0005] In a first aspect, the present application provides an automated intelligent recruitment method, comprising:

[0006] When an enterprise has recruitment needs, it will autonomously interact with the enterprise to guide the enterprise to improve its recruitment information and obtain the enterprise's real enterprise-side information;

[0007] When an applicant has a job application need, the system will autonomously interact with the applicant to guide the applicant to complete their resume and job application needs, and obtain the applicant's true comprehensive information;

[0008] Based on the company's accurate recruitment information, the company's corporate-side information, and the applicant's accurate resume, job search needs, and comprehensive information of the applicant, the company and the applicant are matched to obtain an accurate matching result between the company and the applicant.

[0009] In some examples, autonomously interacting and guiding an enterprise when it has recruitment needs, so as to proactively guide the enterprise to improve its recruitment information and obtain the enterprise's real enterprise-side information, includes:

[0010] After receiving the initial job description information submitted by the enterprise, it autonomously establishes interactive guidance with the enterprise to proactively guide the enterprise to improve the accurate description of the position based on the industry job knowledge graph, thereby forming a level of accurate recruitment information;

[0011] Obtaining enterprise big data, and forming another level of comprehensive health status evaluation of the enterprise based on the enterprise big data;

[0012] Obtain previous recruitment feedback and evaluation data, and form a comprehensive and relevant evaluation of the recruitment position at another level based on the previous recruitment feedback and evaluation data.

[0013] In some examples, when an applicant has a job application requirement, the system autonomously interacts with the applicant to proactively guide the applicant to complete their resume and job application requirements, and obtains the applicant's true comprehensive information, including:

[0014] After receiving the initial resume information submitted by the applicant, autonomously establish interactive guidance with the recruiter to actively guide the recruiter to improve the initial resume information to form a true resume;

[0015] Based on the industry position knowledge graph and the applicant's resume, guide the applicant to form accurate job search needs, wherein the job search need is at least one;

[0016] Obtaining a personality profile of the applicant through communication with the applicant, and forming a personality assessment of the applicant based on the personality profile, wherein the personality profile includes at least one of a personality profile, a blood type profile, and a constellation profile;

[0017] Obtain the applicant's big data and job application feedback evaluation data, and form a comprehensive quality evaluation of the recruiter based on the applicant's big data and previous job application feedback evaluation data.

[0018] In some examples, the enterprise and the applicant are matched based on the enterprise's accurate recruitment information, the enterprise's enterprise-side information, and the applicant's accurate resume, job search requirements, and comprehensive information of the applicant to obtain an accurate matching result between the enterprise and the applicant, including:

[0019] Based on the recruitment information of the enterprise, the enterprise's enterprise-side information, as well as the applicant's resume, job search requirements, and the applicant's comprehensive information, the enterprise and the applicant are matched with multi-level real and accurate comprehensive information to obtain a matching score between the enterprise and the applicant;

[0020] According to the matching score, an accurate matching result between the enterprise and the applicant is obtained.

[0021] In some examples, when a candidate applies to a company, it also includes:

[0022] Obtain the recruitment feedback evaluation data of the enterprise to the applicant, and the job search feedback evaluation data of the applicant to the enterprise.

[0023] In some examples, the method further includes: continuously updating the matching accuracy between the enterprise and the applicant based on the previous recruitment feedback evaluation data and the previous job search feedback evaluation data.

[0024] Secondly, an automated intelligent recruitment system is provided, comprising:

[0025] An enterprise-side interactive intelligent module is used to autonomously interact with enterprises when they have recruitment needs, proactively guiding them to improve their recruitment information and obtain their real enterprise-side information;

[0026] The candidate-side interactive intelligent module is used to autonomously interact with the candidate when the candidate has a job application need, actively guide the candidate to improve his resume and job application needs, and obtain the candidate's real comprehensive information;

[0027] The intelligent matching module is used to match enterprises and applicants based on the accurate recruitment information of the enterprise, the enterprise-side information of the enterprise, the accurate resume, job search requirements and comprehensive information of the applicant, and obtain accurate matching results between the enterprise and the applicant.

[0028] In some examples, where:

[0029] The enterprise-side interactive intelligent module includes a position demand model, an enterprise status description model, and a position-related evaluation model, wherein:

[0030] The position demand model is used to autonomously establish interactive guidance with the enterprise after receiving the initial position description information submitted by the enterprise, so as to proactively guide the enterprise to improve the accurate description of the position based on the industry position knowledge graph, thereby forming a level of accurate recruitment information;

[0031] The enterprise status description model is used to obtain enterprise big data and form another level of comprehensive health status evaluation of the enterprise based on the enterprise big data;

[0032] The position-related evaluation model is used to obtain previous recruitment feedback evaluation data, and form a comprehensive evaluation of the recruitment position at another level based on the previous recruitment feedback evaluation data;

[0033] The candidate-side interactive intelligent module includes a resume preparation and improvement model, a job search planning model, a personal character evaluation model, and a personal workplace evaluation model, among which:

[0034] The resume preparation and improvement model is used to autonomously establish interactive guidance with the recruiter after receiving the initial resume information submitted by the applicant, so as to actively guide the recruiter to improve the initial resume information and form a real resume;

[0035] The job search planning model is used to guide the applicant to form accurate job search needs based on the industry position knowledge map and the applicant's resume, wherein the job search need is at least one;

[0036] The personal character evaluation model is used to obtain a personality positioning-related map of the applicant through communication with the applicant, and to form a personality positioning evaluation of the applicant based on the personality positioning-related map, wherein the personality positioning-related map includes at least one of a personality map, a blood type map, and a constellation map;

[0037] The personal workplace evaluation model is used to obtain the applicant's big data and job application feedback evaluation data, and to form a comprehensive quality evaluation of the recruiter based on the applicant's big data and previous job application feedback evaluation data.

[0038] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the automated intelligent recruitment method of the first aspect and any possible implementation of the first aspect are implemented.

[0039] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the program implements the steps of the automated intelligent recruitment method of the above-mentioned first aspect and any possible implementation method of the first aspect.

[0040] By adopting the embodiments of the present application, when an enterprise has a recruitment demand, it is possible to autonomously interact with the enterprise to guide the enterprise to improve the recruitment information and obtain the enterprise's real information on the enterprise side, such as the relevant evaluation of the enterprise and the recruitment position. When the applicant has a job application demand, it is possible to autonomously interact with the applicant to guide the applicant to improve the resume and job search needs, and obtain the applicant's real comprehensive information such as personality and skill quality evaluation, etc. Finally, according to the enterprise's recruitment information, the relevant evaluation of the enterprise and the recruitment position, and the applicant's resume, job search needs, and the applicant's personality and skill quality evaluation, the enterprise and the applicant are matched to obtain an accurate matching result between the enterprise and the applicant. In this way, the personnel work before the offline interview can be automatically completed, and the two-way matching of the enterprise and the applicant can be accurately achieved, which saves the screening work of both the enterprise and the applicant, and thus improves the recruitment efficiency, recruitment quality and recruitment satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Other features, objects and advantages of the present application will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0042] Figure 1 This is a flow chart of the automated intelligent recruitment method provided in an embodiment of the present application;

[0043] Figure 2 A schematic diagram of an implementation step of the automated intelligent recruitment method provided in an embodiment of the present application;

[0044] Figure 3 This is another schematic diagram of the implementation steps of the automated intelligent recruitment method provided in the embodiments of the present application;

[0045] Figure 4 This is a schematic diagram of another implementation step of the automated intelligent recruitment method provided in the embodiments of the present application;

[0046] Figure 5 This is a schematic diagram of the fourth implementation step of the automated intelligent recruitment method provided in the embodiments of the present application;

[0047] Figure 6 This is a structural block diagram of the automated intelligent recruitment system provided in an embodiment of the present application;

[0048] Figure 7 This is an architectural diagram of the automated intelligent recruitment system provided in the embodiments of this application;

[0049] Figure 8 A structural block diagram of a computer device provided in an embodiment of the present application;

[0050] Figure 9The present invention is a schematic diagram of a recruitment process of a recruitment platform in related technologies. DETAILED DESCRIPTION

[0051] The present application will be further described in detail below with reference to the embodiments and accompanying drawings. It should be understood that the specific embodiments described herein are intended only to illustrate the relevant application and are not intended to limit the application. It should also be noted that, for ease of description, only the portions relevant to the application are shown in the accompanying drawings.

[0052] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0053] The following describes in detail the automated intelligent recruitment method, system, device and medium according to the embodiments of the present application in conjunction with the accompanying drawings.

[0054] In the following description, the enterprise is also referred to as the enterprise side or the B-side, and the applicant is also referred to as the candidate side or the C-side.

[0055] Figure 1 This is a flow chart of an automated intelligent recruitment method according to one embodiment of the present application. Figure 1 As shown, the automated intelligent recruitment method according to an embodiment of the present application includes the following steps:

[0056] S101: When an enterprise has recruitment needs, autonomously interact and guide the enterprise to actively guide the enterprise to improve recruitment information and obtain the enterprise's real enterprise-side information, wherein the enterprise-side short information of the enterprise includes, for example, relevant evaluations of the enterprise and the recruitment position.

[0057] In one embodiment of the present application, when an enterprise has a recruitment need, interactive guidance is autonomously conducted with the enterprise to actively guide the enterprise to improve the recruitment information and obtain the enterprise-side information of the enterprise, including: after receiving the initial position description information submitted by the enterprise, autonomously establishing interactive guidance with the enterprise to actively guide the enterprise to improve the position description based on the industry position knowledge graph to form one level of the recruitment information; obtaining enterprise big data, and forming another level of the health status evaluation of the enterprise based on the enterprise big data; obtaining recruitment feedback evaluation data, and forming another level of relevant evaluation of the recruitment position based on the recruitment feedback evaluation data.

[0058] S102: When the applicant has a job application need, autonomously interact and guide the applicant to actively guide the applicant to complete the resume and job application needs, and obtain the applicant's real comprehensive information, wherein the applicant's comprehensive information includes but is not limited to the applicant's personality and skill quality evaluation.

[0059] In one embodiment of the present application, when an applicant has a job application need, interactive guidance is autonomously conducted with the applicant to actively guide the applicant to complete his / her resume and job-seeking needs, and obtain comprehensive information about the applicant, including: after receiving the initial resume information submitted by the applicant, autonomously establishing interactive guidance with the recruiter to actively guide the recruiter to complete the initial resume information to form the resume; guiding the applicant to form job-seeking needs based on the industry position knowledge map, wherein the job-seeking need is at least one; obtaining a personality positioning related map, and forming a personality positioning score of the recruiter based on the personality positioning related map, wherein the personality positioning related map includes at least one of a personality map, a blood type map, and a constellation map; obtaining the applicant's big data and job-seeking feedback evaluation data, and forming the recruiter's skill and quality evaluation based on the applicant's big data and job-seeking feedback evaluation data.

[0060] S103: Matching the enterprise and the applicant based on the recruitment information of the enterprise, the enterprise-side information of the enterprise, the resume of the applicant, the job search requirements, and the comprehensive information of the applicant to obtain a matching result between the enterprise and the applicant.

[0061] In one embodiment of the present application, the enterprise and the applicant are matched based on the enterprise's recruitment information, the enterprise's enterprise-side information, and the applicant's resume, job-seeking needs, and the applicant's comprehensive information to obtain a matching result between the enterprise and the applicant, including: matching the enterprise and the applicant based on the enterprise's recruitment information, the enterprise's enterprise-side information such as the relevant evaluation of the enterprise and the recruitment position, and the applicant's resume, job-seeking needs, and the applicant's comprehensive information such as the applicant's personality and skill quality evaluation to obtain a matching score between the enterprise and the applicant; obtaining a matching result between the enterprise and the applicant based on the matching score.

[0062] In practical applications, this method can be configured to include an intelligent agent that interacts with the enterprise side, an intelligent agent that interacts with the candidate side, and an intelligent agent that matches positions with candidates.

[0063] The intelligent agent that interacts with the enterprise side implements the function in step S101, the intelligent agent that interacts with the candidate side implements the function in step S102, and the intelligent agent that matches positions with candidates implements the function in step S103.

[0064] Specifically, the intelligent agent that interacts with the enterprise side helps the enterprise side form accurate job descriptions (JD) and form more accurate data for the enterprise side.

[0065] The intelligent agent that interacts with the enterprise side uses the AI ​​large model algorithm for automatic interaction with the B-side to conduct fully automated AI intelligent voice or text interactive communication with the enterprise side at the early stage of job posting. On the one hand, it actively guides the enterprise to improve the accurate description of job requirements. On the other hand, it also forms further evaluation of the enterprise, position, team, culture, etc. through enterprise big data, evaluation feedback data, etc., providing more valuable reference for candidates and intelligent matching systems.

[0066] On traditional Internet recruitment platforms, candidates can only see the JD information of the positions to be recruited by the companies, which basically describes the responsibilities of the positions, the requirements for candidates, etc. These rough information are not enough for candidates to refer to. Figure 2 As shown, the intelligent agent that interacts with the enterprise side is more based on industry expertise. Based on the complete definition of the job level, content, reporter, etc. of the industry map formed by itself, it helps enterprises to form accurate JD description information for recruitment positions.

[0067] The intelligent agent that interacts with the enterprise side can include three sub-intelligent agent models on the basis of language and text interaction provided by the traditional large language model: a large model of job demand, a large model of enterprise status evaluation, and a large model of job evaluation. By interacting with enterprise-side users and with the data support of industry job maps, enterprise big data, and feedback evaluation information data, it can complete the following three tasks: actively guiding the formation of more accurate positioning and information of positions to be recruited, forming an evaluation of the health status of the enterprise, and forming job-related evaluations.

[0068] For example, a company is hiring a CTO. A traditional JD typically includes a job description (e.g., responsible for IT architecture design, team management, performance management, and supporting pre-sales and after-sales departments) and candidate requirements (e.g., a master's degree or higher and at least five years of project and team management experience). However, this JD description doesn't necessarily fully capture the company's needs, as candidates' requirements are often vague.

[0069] like Figure 2 As shown in the figure, the intelligent agent interacting with the enterprise side will form the description of the three parts on the right side of the figure through interactive communication with the enterprise side, so that the candidate can have a full understanding of the requirements of the required person, the status of the enterprise itself, and the status of the position and team.

[0070] At the JD level, for example, for a CTO position, more complete JD information will be generated through communication with the intelligent agent interacting with the enterprise side, including the position's positioning (level, reporting party, number of subordinate management team members, salary level, and other ancillary information such as whether there are equity options, whether they are on the board of directors, etc.), job responsibilities (similar to traditional descriptions, but mainly formed through questions and answers to form a complete description, eliminating some ambiguity), and candidate requirements (similar to the iceberg model, including knowledge and skills requirements such as academic qualifications and work experience, including general qualities such as the ability to learn actively, strong logical thinking and communication and collaboration skills, and personality values ​​such as extroversion, optimism, and honesty). In addition to JD descriptions, big data and feedback evaluation information are also used to form descriptive information at the enterprise and position levels as much as possible, such as enterprise-related (headcount and revenue scale, financing situation, senior management situation, patent situation, staff increase and decrease rate, annual number of hires or dismissals, corporate culture, etc.) and position-related (recruitment and dismissal information for superior positions, recruitment and dismissal information for subordinate teams, etc.) information.

[0071] It's important to note that the three sub-agent models operate synchronously and in parallel, and the results they generate serve as supplementary data, feeding back into the various sub-agent models for further computation. The model algorithm ultimately produces results at three levels, which serve as preliminary management reports for this position and are published for reference by candidates and automated matching. This resulting data itself is even more valuable, providing relevant category data to the relevant agent models during subsequent computations. This continuously refined data allows for more comprehensive evaluations and more accurate matching of positions and candidates.

[0072] The intelligent agent that interacts with the candidate side actively guides the candidate to improve his resume and job search requirements, and forms an accurate evaluation of the candidate.

[0073] Candidate resumes are often embellished, and forming accurate information has a fundamental impact on the accuracy of the recruitment agent. This application uses an automated algorithm of the agent that interacts with the candidate to conduct a "pre-interview" with the candidate through language or text. The algorithm diagram is shown below. Figure 3 shown.

[0074] On traditional online recruitment platforms, corporate recruiters can only view the resumes submitted by candidates themselves. The completeness and authenticity of the resumes themselves cannot be guaranteed, and resumes only provide a small portion of the assessment of a person's work ability. As a result, recruiters may struggle to find the right candidates even after multiple rounds of interviews, while also preventing potentially qualified candidates from getting interviews. Therefore, the intelligent agent interacting with candidates features an automated pre-interview algorithm. This proactively guides candidates to create more complete resumes, assesses their authenticity, and evaluates their innate personality, acquired skills, qualities, and values. This information provides a more comprehensive assessment of the candidate.

[0075] The algorithm, based on the language and text interaction provided by traditional large language models, includes four sub-agent models: a resume preparation model, a job search planning model, a personal character assessment model, and a personal workplace competency assessment model. These models, supported by industry job profiles, personality and blood type profiles, personal big data, and job search feedback and evaluation big data, accomplish the following tasks: helping candidates refine their resumes and form authenticity evaluations, guiding them in defining their job search needs, evaluating their innate character, and assessing their acquired skills, qualities, and values. A comprehensive report from these dimensions creates a more complete profile of the candidate.

[0076] For example, for candidates applying for the above CTO positions, traditional resume information basically includes personal situation, educational background, work background, project background, and other supplementary information. Figure 3 The Agent interacts with the candidate during the pre-interview, forming the following Figure 3The four sections on the right side of the center provide a more complete, multi-dimensional description of the candidate. At the resume level, for example, if the original resume has discontinuous timelines, the agent will communicate to create a complete timeline and verify and improve the authenticity of the relevant information. Regarding job requirements, based on the candidate's information and requirements, and comparing them with successful candidates, the agent can recommend which types of job requirements the candidate is most likely to meet. This is equivalent to guiding candidates to avoid missing out on the best options through the perspective of models and algorithms. Personal character and workplace-related assessments are the most lacking aspects of current online recruitment models, corresponding to the iceberg model of enterprise positions. The personal character level focuses on describing the candidate's innate personality, using personality assessments similar to the MBTI, and also assessing general personal qualities such as a love of challenges, active learning, and logical thinking. The workplace-related level emphasizes acquired qualities, such as knowledge and skills (mastery of Java, C++, and Python skills, in-depth understanding of AI algorithms, and 10 years of project management and team management experience) and values ​​(emphasis on teamwork and dedication, and a preference for a simple and efficient team culture), providing as detailed a description as possible.

[0077] It should be noted that the four sub-agent Agent models mentioned above are run synchronously during the pre-interview communication with the candidate. The intermediate data produced by each model can also be fed back to the Agent model for further reasoning until the pre-interview phase is completed and a pre-interview report on the candidate is formed.

[0078] Therefore, the pre-interview phase is a preliminary screening of candidates, not a macro-evaluation of a specific position. This evaluation can also provide targeted guidance on the candidate's job search needs. Because this pre-interview phase is fully automated, multiple agents can simultaneously conduct preliminary screening interviews with candidates, replacing traditional HR specialists, eliminating the most time-consuming and labor-intensive part of the traditional recruitment model.

[0079] The intelligent agent that matches positions with candidates can use the automated AI intelligent matching algorithm to make more accurate position / candidate matching. Figure 4As shown, two categories of data are covered, raw data and high-value data, respectively, on the enterprise and candidate sides. Enterprise-side raw data primarily consists of the company's initial JD requirements, while candidate-side raw data includes the candidate's original resume and job application requirements. In addition to this raw data, all inferred data is considered high-value data. Enterprise-side data primarily includes refined JD information, company / position evaluations, and feedback. Candidate-side data primarily includes resume completion and authenticity evaluations, post-guidance job application requirements, and assessments of the candidate's innate personality and acquired professional abilities, as well as feedback. Using a customized large language model, the enterprise and candidate data are vectorized and then evaluated for match accuracy within the model, yielding matching scores for each dimension and an overall match score. Initially trained on a labeled training set, the large model can surpass existing matching accuracy based on raw data. With continued accumulation and operation, the increasing volume of data will rapidly improve matching accuracy.

[0080] When an applicant applies for a job at a company, the method also includes: obtaining the company's recruitment feedback evaluation data on the applicant, and the applicant's job search feedback evaluation data on the company. Furthermore, the matching accuracy between the company and the applicant can be continuously updated based on the recruitment feedback evaluation data and the job search feedback evaluation data.

[0081] The automated intelligent recruitment method of the embodiment of the present application automatically interacts with the company for preliminary communication after the company posts a position; automatically conducts a preliminary interview with the candidate after the candidate posts his resume and job application information, replacing the traditional initial screening process; automatically matches positions with candidates, and the company and candidate determine online or offline interviews based on the appropriate information; tracks interview results and obtains feedback and evaluation information, completing the entire recruitment process. Figure 5 As shown in the figure, it provides automated management of the entire recruitment process. In each link of the process, both the company and the candidate can evaluate the performance of the other two. The feedback evaluation information formed is first-hand word-of-mouth data. Therefore, the data used is divided into three levels from the source dimension: self-provided, agent interaction evaluation and automatic collection, and feedback evaluation. The data at the latter two levels are more critical descriptive information and have more important value for more accurate matching of positions and candidates. They are intertwined with the description objects divided into the company side and the candidate side to form the following Figure 5 The system data matrix shown is used for large model inference.

[0082] According to the automated intelligent recruitment method of the embodiment of the present application, when the enterprise has recruitment needs, it can autonomously interact and guide the enterprise to actively guide the enterprise to improve the recruitment information and obtain the enterprise-side information of the enterprise, such as the relevant evaluation of the enterprise and the recruitment position. When the applicant has an application need, it can autonomously interact and guide the applicant to actively guide the applicant to improve his resume and job search needs, and obtain the applicant's comprehensive information such as personality and skill quality evaluation, etc. Finally, according to the enterprise's recruitment information, the relevant evaluation of the enterprise and the recruitment position, and the applicant's resume, job search needs, and the applicant's personality and skill quality evaluation, the enterprise and the applicant are matched to obtain the matching result of the enterprise and the applicant. In this way, the personnel work before the offline interview can be automatically completed, and the two-way matching of the enterprise and the applicant can be accurately achieved, which saves the screening work of both the enterprise and the applicant, and thus improves the recruitment efficiency, recruitment quality and recruitment satisfaction.

[0083] Compared with related recruitment methods, this system uses content generation to help companies generate job information or help candidates create or improve resumes; AI-based automatic matching algorithms based on existing information; interview question generation or virtual interviews. Through fully automated recruitment systems and automated interactions, more high-value data can be obtained and more accurate matching can be achieved, with the following advantages:

[0084] It replaces existing real human resources or headhunters and fully utilizes AI to automate the entire recruitment process. In particular, through "pre-communication" with companies and "pre-interviews" with candidates, it not only replaces the most time-consuming and labor-intensive initial screening process in the traditional recruitment model, but also obtains more dimensional and higher-value accurate data.

[0085] Through full-process management, online and offline are integrated, and motivation is provided for obtaining feedback and evaluation.

[0086] By integrating big data from the internet and using automated AI interactions, the system accurately evaluates companies, positions, and candidates. It also collects feedback from both companies and candidates throughout the recruitment process, generating word-of-mouth data. This high-value data creates more accurate descriptions across multiple dimensions. Furthermore, as the system continues to operate, the collection of more and more data will allow for increasingly precise descriptions of companies and candidates, ultimately improving the match between companies and candidates.

[0087] Figure 6 This is a structural diagram of an automated intelligent recruitment system according to an embodiment of the present application. Figure 6 As shown, the automated intelligent recruitment system according to an embodiment of the present application includes: an enterprise-side interactive intelligent module 610, an applicant-side interactive intelligent module 620, and a matching intelligent module 630, wherein:

[0088] The enterprise-side interactive intelligent module 610 is used to autonomously interact with the enterprise when the enterprise has recruitment needs, so as to proactively guide the enterprise to improve recruitment information and obtain the enterprise-side information of the enterprise;

[0089] The candidate-side interactive intelligent module 620 is used to autonomously interact with the candidate when the candidate has a job application need, proactively guiding the candidate to complete their resume and job application needs, and obtain comprehensive information about the candidate, such as the candidate's personality and skill quality evaluation;

[0090] The intelligent matching module 630 is used to match the enterprise and the applicant based on the recruitment information of the enterprise, the enterprise-side information of the enterprise such as the relevant evaluation of the enterprise and the recruitment position, as well as the applicant's resume, job search requirements, and the comprehensive information of the applicant such as the applicant's personality and skill quality evaluation, to obtain the matching results of the enterprise and the applicant.

[0091] like Figure 7 As shown, the automated intelligent recruitment system utilizes AI agents, acting as virtual headhunters, to completely replace the work of traditional HR and headhunting agencies, as well as traditional online recruitment platforms. The system is no longer simply an online information collection and matching platform; it is a fully automated management system for the entire recruitment process. After a company posts a position, the system automatically interacts with the company for preliminary communication. After a candidate posts their resume and job application information, the system automatically conducts a preliminary interview with the candidate, replacing the traditional initial screening process. Positions are automatically matched with candidates, and if suitable information is found, the company and candidate will determine whether to conduct an online or offline interview. The system tracks interview results and obtains feedback and evaluation information, completing the entire recruitment process.

[0092] The system itself is an automated agent with AI capabilities, composed of multiple agents, including one that interacts with the enterprise, one that interacts with candidates, and one that matches positions with candidates. For specific recruitment tasks, the system agent connects the required sub-agents through specific process connections, automating the entire process.

[0093] Combine Figure 2 and Figure 3As shown, the enterprise-side interactive intelligent module includes a job demand model, an enterprise status description model and a job-related evaluation model, wherein the job demand model is used to autonomously establish interactive guidance with the enterprise after receiving the initial job description information submitted by the enterprise, so as to actively guide the enterprise to improve the job description according to the industry job knowledge map to form one level of recruitment information, the enterprise status description model is used to obtain enterprise big data, and form another level of health status evaluation of the enterprise according to the enterprise big data, the job-related evaluation model is used to obtain recruitment feedback evaluation data, and form another level of relevant evaluation of the recruitment position according to the recruitment feedback evaluation data; the applicant-side interactive intelligent module includes a resume preparation and improvement model, a job search planning model, a personal character evaluation model and a personal workplace evaluation model type, wherein the resume preparation and improvement model is used to autonomously establish interactive guidance with the recruiter after receiving the initial resume information submitted by the applicant, so as to actively guide the recruiter to improve the initial resume information to form the resume, and the job search planning model is used to guide the applicant to form job search needs based on the industry position knowledge map, wherein the job search need is at least one, and the personal character evaluation model is used to obtain a character positioning related map, and form the character positioning score of the recruiter based on the character positioning related map, wherein the character positioning related map includes at least one of a character map, a blood type map and a constellation map, and the personal workplace evaluation model is used to obtain the applicant's big data and job search feedback evaluation data, and form the recruitment based on the applicant's big data and job search feedback evaluation data.

[0094] According to the automated intelligent recruitment system of the embodiment of the present application, when an enterprise has recruitment needs, it can autonomously interact and guide the enterprise to actively guide the enterprise to improve the recruitment information and obtain the enterprise-side information of the enterprise, such as the relevant evaluation of the enterprise and the recruitment position. When the applicant has an application need, it can autonomously interact and guide the applicant to actively guide the applicant to improve his resume and job search needs, and obtain the applicant's comprehensive information such as personality and skill quality evaluation, etc. Finally, according to the enterprise's recruitment information, the relevant evaluation of the enterprise and the recruitment position, and the applicant's resume, job search needs, and the applicant's personality and skill quality evaluation, the enterprise and the applicant are matched to obtain the matching result of the enterprise and the applicant. In this way, the personnel work before the offline interview can be automatically completed, and the two-way matching of the enterprise and the applicant can be accurately achieved, which saves the screening work of both the enterprise and the applicant, and thus improves the recruitment efficiency, recruitment quality and recruitment satisfaction.

[0095] The specific definition of the automated intelligent recruitment system can be found in the definition of the automated intelligent recruitment method described above and will not be repeated here. The various modules of the automated intelligent recruitment system described above can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0096] In one embodiment, a computer device is provided. Figure 8 This is a block diagram of the computer device provided in the embodiment of the present application, refer to Figure 8 The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the aforementioned automated intelligent recruitment method embodiment is implemented. For example, executing:

[0097] When an enterprise has recruitment needs, it will autonomously interact with the enterprise to guide the enterprise to improve its recruitment information and obtain the enterprise-side information of the enterprise;

[0098] When an applicant has a job application need, the system will autonomously interact with the applicant to guide the applicant to complete their resume and job application needs, and obtain comprehensive information about the applicant;

[0099] According to the recruitment information of the enterprise, the enterprise-side information of the enterprise, the resume of the applicant, the job search requirements, and the comprehensive information of the applicant, the enterprise and the applicant are matched to obtain the matching result of the enterprise and the applicant.

[0100] The present application also provides a computer-readable storage medium storing a computer program. When the processor executes the computer program, the aforementioned automated intelligent recruitment method embodiment is implemented. For example, executing:

[0101] When an enterprise has recruitment needs, it will autonomously interact with the enterprise to guide the enterprise to improve its recruitment information and obtain the enterprise-side information of the enterprise;

[0102] When an applicant has a job application need, the system will autonomously interact with the applicant to guide the applicant to complete their resume and job application needs, and obtain comprehensive information about the applicant;

[0103] According to the recruitment information of the enterprise, the enterprise-side information of the enterprise, the resume of the applicant, the job search requirements, and the comprehensive information of the applicant, the enterprise and the applicant are matched to obtain the matching result of the enterprise and the applicant.

[0104] The present application embodiment provides a computer program product, which includes instructions. When the instructions are executed, the method described in the embodiment of the present application is executed. For example, you can execute Figure 1 The various steps of the automated intelligent recruitment method are shown, for example, to perform:

[0105] When an enterprise has recruitment needs, it will autonomously interact with the enterprise to guide the enterprise to improve its recruitment information and obtain the enterprise-side information of the enterprise;

[0106] When an applicant has a job application need, the system will autonomously interact with the applicant to guide the applicant to complete their resume and job application needs, and obtain comprehensive information about the applicant;

[0107] According to the recruitment information of the enterprise, the enterprise-side information of the enterprise, the resume of the applicant, the job search requirements, and the comprehensive information of the applicant, the enterprise and the applicant are matched to obtain the matching result of the enterprise and the applicant.

[0108] Those skilled in the art will appreciate that all or part of the processes in the methods for implementing the above embodiments can be accomplished by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include processes of the embodiments of the above methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0109] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0110] The above embodiments merely illustrate several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. An automated intelligent recruitment method, characterized in that: include: When an enterprise has recruitment needs, it will autonomously interact with the enterprise to guide the enterprise to improve its recruitment information and obtain the enterprise's real enterprise-side information; When an applicant has a job application need, the system will autonomously interact with the applicant to guide the applicant to complete their resume and job application needs, and obtain the applicant's true comprehensive information; Based on the company's accurate recruitment information, the company's corporate-side information, and the applicant's accurate resume, job search needs, and comprehensive information of the applicant, the company and the applicant are matched to obtain an accurate matching result between the company and the applicant.

2. The automated intelligent recruitment method according to claim 1, characterized in that: The autonomous interactive guidance with the enterprise when the enterprise has recruitment needs, so as to proactively guide the enterprise to improve recruitment information and obtain the real enterprise-side information of the enterprise, includes: After receiving the initial job description information submitted by the enterprise, it autonomously establishes interactive guidance with the enterprise to proactively guide the enterprise to improve the accurate description of the position based on the industry job knowledge graph, thereby forming a level of accurate recruitment information; Obtaining enterprise big data, and forming another level of comprehensive health status evaluation of the enterprise based on the enterprise big data; Obtain previous recruitment feedback and evaluation data, and form a comprehensive and relevant evaluation of the recruitment position at another level based on the previous recruitment feedback and evaluation data.

3. The automated intelligent recruitment method according to claim 1, characterized in that: When an applicant has a job application need, we will autonomously interact with the applicant to guide the applicant to complete their resume and job application needs, and obtain the applicant's true comprehensive information, including: After receiving the initial resume information submitted by the applicant, autonomously establish interactive guidance with the recruiter to actively guide the recruiter to improve the initial resume information to form a true resume; Based on the industry position knowledge graph and the applicant's resume, guide the applicant to form accurate job search needs, wherein the job search need is at least one; Obtaining a personality profile of the applicant through communication with the applicant, and forming a personality assessment of the applicant based on the personality profile, wherein the personality profile includes at least one of a personality profile, a blood type profile, and a constellation profile; Obtain the applicant's big data and job application feedback evaluation data, and form a comprehensive quality evaluation of the recruiter based on the applicant's big data and previous job application feedback evaluation data.

4. The automated intelligent recruitment method according to any one of claims 1 to 3, characterized in that: According to the accurate recruitment information of the enterprise, the enterprise's enterprise-side information, and the accurate resume, job search requirements, and comprehensive information of the applicant, the enterprise and the applicant are matched to obtain an accurate matching result between the enterprise and the applicant, including: Based on the recruitment information of the enterprise, the enterprise's enterprise-side information, as well as the applicant's resume, job search requirements, and the applicant's comprehensive information, the enterprise and the applicant are matched with multi-level real and accurate comprehensive information to obtain a matching score between the enterprise and the applicant; According to the matching score, an accurate matching result between the enterprise and the applicant is obtained.

5. The automated intelligent recruitment method according to claim 4, characterized in that: When a candidate applies to a company, it also includes: Obtain the recruitment feedback evaluation data of the enterprise to the applicant, and the job search feedback evaluation data of the applicant to the enterprise.

6. The automated intelligent recruitment method according to claim 5, characterized in that: Also includes: The matching accuracy between the enterprise and the applicant is continuously updated based on the previous recruitment feedback evaluation data and the previous job search feedback evaluation data.

7. An automated intelligent recruitment system, characterized in that: include: An enterprise-side interactive intelligent module is used to autonomously interact with enterprises when they have recruitment needs, proactively guiding them to improve their recruitment information and obtain their real enterprise-side information; The candidate-side interactive intelligent module is used to autonomously interact with the candidate when the candidate has a job application need, actively guide the candidate to improve his resume and job application needs, and obtain the candidate's real comprehensive information; The intelligent matching module is used to match enterprises and applicants based on the accurate recruitment information of the enterprise, the enterprise-side information of the enterprise, the accurate resume, job search requirements and comprehensive information of the applicant, and obtain accurate matching results between the enterprise and the applicant.

8. The automated intelligent recruitment system according to claim 7, characterized in that: in: The enterprise-side interactive intelligent module includes a position demand model, an enterprise status description model, and a position-related evaluation model, wherein: The position demand model is used to autonomously establish interactive guidance with the enterprise after receiving the initial position description information submitted by the enterprise, so as to proactively guide the enterprise to improve the accurate description of the position based on the industry position knowledge graph, thereby forming a level of accurate recruitment information; The enterprise status description model is used to obtain enterprise big data and form another level of comprehensive health status evaluation of the enterprise based on the enterprise big data; The position-related evaluation model is used to obtain previous recruitment feedback evaluation data, and form a comprehensive evaluation of the recruitment position at another level based on the previous recruitment feedback evaluation data; The candidate-side interactive intelligent module includes a resume preparation and improvement model, a job search planning model, a personal character evaluation model, and a personal workplace evaluation model, among which: The resume preparation and improvement model is used to autonomously establish interactive guidance with the recruiter after receiving the initial resume information submitted by the applicant, so as to actively guide the recruiter to improve the initial resume information and form a real resume; The job search planning model is used to guide the applicant to form accurate job search needs based on the industry position knowledge map and the applicant's resume, wherein the job search need is at least one; The personal character evaluation model is used to obtain a personality positioning-related map of the applicant through communication with the applicant, and to form a personality positioning evaluation of the applicant based on the personality positioning-related map, wherein the personality positioning-related map includes at least one of a personality map, a blood type map, and a constellation map; The personal workplace evaluation model is used to obtain the applicant's big data and job application feedback evaluation data, and to form a comprehensive quality evaluation of the recruiter based on the applicant's big data and previous job application feedback evaluation data.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, it implements the automated intelligent recruitment method according to any one of claims 1 to 6.

10. A computer-readable storage medium comprising a memory and a computer program stored in the memory and executable on a processor, characterized in that: When the program is executed by a processor, the automated intelligent recruitment method according to any one of claims 1 to 6 is implemented.

Images