Position publishing platform based on artificial intelligence and electronic equipment

Abstract

The invention discloses a position publishing platform based on artificial intelligence and electronic equipment, and the position publishing platform executes the following processing after being started: carrying out the reasoning analysis of enterprise business data and market data of a target enterprise through an AI position mining large model, and determining a list of positions needing to be recruited by the target enterprise; in response to a target position selected by the target enterprise from the recommended positions, calling an AI position generation large model to perfect multiple contents of the target position according to basic information of the target position and recruitment requirements of a knowledge base in the reference enterprise and / or historical position description information of the target position, and generating target position description information; and performing reasoning analysis on the position features in the target position description information and the target recruitment crowd through an AI position publishing and tracking large model, and selecting a target recruitment publishing channel to publish a target position. According to the invention, automation of the position release process is realized, and the recruitment efficiency and quality of enterprises are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of recruitment, and in particular to a position publishing platform based on artificial intelligence and an electronic device. BACKGROUND

[0002] In today's competitive business environment, talent recruitment of an enterprise is crucial for the development of the enterprise. However, traditional position publishing methods have many drawbacks.

[0003] On the one hand, when determining the positions to be recruited by the enterprise, it is often dependent on the human resources department to determine according to the recruitment needs submitted by each department, which is difficult to fully and accurately grasp the actual needs of the enterprise, and is likely to lead to a mismatch between the recruitment positions and the business development of the enterprise, which may result in insufficient recruitment or over-recruitment, affecting the normal operation and rational allocation of resources of the enterprise.

[0004] On the other hand, in the position description information generation link, it is usually written by the recruitment personnel based on experience, which may lead to inaccurate and imperfect position description, and the key information of the position cannot be clearly conveyed, resulting in deviation in the understanding of the position by job seekers, and reducing the effectiveness of recruitment.

[0005] In addition, when selecting a recruitment publishing channel, the traditional method mostly relies on subjective judgment or past experience, which may lead to the publication of positions in mismatched channels, failing to accurately reach the target talents, resulting in waste of recruitment resources, prolonging the recruitment cycle, and increasing the recruitment cost of the enterprise.

[0006] In summary, the existing position publishing method cannot meet the needs of efficient and accurate recruitment of enterprises. Therefore, an innovative position publishing scheme is needed to realize the automation of the whole process of position publishing, solve the problems existing in the current position publishing process, and improve the recruitment efficiency and quality of enterprises. SUMMARY

[0007] Therefore, the embodiments of the present application provide a position publishing platform based on artificial intelligence and an electronic device to solve at least one of the above technical problems existing in the traditional position publishing method.

[0008] In a first aspect, the embodiments of the present application provide a position publishing platform based on artificial intelligence, which is equipped with a plurality of pre-trained AI large models. After the position publishing platform is started, the following processing is performed:

[0009] Enter the enterprise business data of the target enterprise and the market data related to the target enterprise into the AI position mining large model;

[0010] The AI position mining large model analyzes enterprise business data and market data, determines and recommends a position list that the target enterprise needs to recruit to the target enterprise, wherein the position list includes at least one position name, a department to which the position belongs, and a preliminary job responsibility description;

[0011] In response to a target position selected by the target enterprise from the recommended position, and according to the position name, the department to which the position belongs, and the preliminary job responsibility description of the target position, and referring to the recruitment requirements of the enterprise internal knowledge base and / or the historical position description information of the target position of at least one enterprise in the same industry, the AI position generation large model is called to perfect the multiple contents of the target position, and the target position description information of the target position is generated;

[0012] The AI position publishing and tracking large model analyzes the position characteristics and the target recruitment population in the target position description information, and according to the analysis result, selects a target recruitment publishing channel matched with the position characteristics and / or the target recruitment population from multiple recruitment publishing channels; and publishes the target position description information of the target position through the target recruitment publishing channel.

[0013] According to some embodiments of the present application, optionally, the position publishing platform further performs the following processing after being started: collecting feedback data of the target recruitment publishing channel through the AI position publishing and tracking large model, wherein the feedback data includes at least one of the following: the browsing volume of the target position within a preset period, the resume delivery volume, the basic information of the job seekers, and the interview data; and according to the feedback data, calculating a publishing effect parameter of the target position; in the case that the publishing effect parameter does not meet the requirements, analyzing the reasons for the publishing effect parameter not meeting the requirements, and generating a modification suggestion for the target position description information and / or the target recruitment publishing channel.

[0014] According to some embodiments of the present application, optionally, the basic information of the job seekers includes the education background, skill level and work experience of the job seekers, and the interview data includes the interview invitation volume, the interview pass rate and the interview evaluation;

[0015] The publishing effect parameter includes at least one of the following: the browsing volume, the resume delivery volume, the interview invitation volume, the interview pass rate, the resume conversion rate and the talent matching degree, wherein the resume conversion rate is the ratio of the resume delivery volume to the interview invitation volume, and the talent matching degree is the matching degree of the basic information of the job seekers and the target position description information.

[0016] According to some embodiments of the present application, optionally, the enterprise business data includes enterprise strategic planning, department business demand and existing employee skill matrix, and the market data includes at least one of the following: industry development trend, industry talent supply and demand situation, competitor recruitment dynamics and policy regulations;

[0017] The AI position exploration large model analyzes the target enterprise's business data and market data to determine and recommend a list of positions that the target enterprise needs to recruit, including at least one of the following:

[0018] The AI position exploration large model analyzes the target enterprise's business data and market data to determine and recommend a list of positions that the target enterprise needs to recruit, including at least one of the following:

[0019] The AI position exploration large model analyzes the target enterprise's business data and market data to determine and recommend a list of positions that the target enterprise needs to recruit, including at least one of the following:

[0020] The AI position exploration large model analyzes the target enterprise's business data and market data to determine and recommend a list of positions that the target enterprise needs to recruit, including at least one of the following:

[0021] The AI position exploration large model analyzes the target enterprise's business data and market data to determine and recommend a list of positions that the target enterprise needs to recruit, including at least one of the following:

[0022] The AI position exploration large model analyzes the target enterprise's business data and market data to determine and recommend a list of positions that the target enterprise needs to recruit, including at least one of the following:

[0023] According to some embodiments of the present application, optionally, according to the position name, department and preliminary job description of the target position, and referring to the recruitment requirements of the enterprise internal knowledge base and / or the historical position description information of the target position of at least one enterprise in the same industry, the AI position generation large model is called to perfect the multiple contents of the target position, and the target position description information of the target position is generated, including:

[0024] The AI position generation large model extracts the work location requirements, education requirements, skill requirements, work experience requirements, salary standards and / or welfare standards from the reference enterprise internal knowledge base, and refers to the education requirements, skill requirements, work experience requirements, salary standards and / or welfare standards in the historical position description information to supplement the work location, education requirements, skill requirements, work experience requirements, salary and / or welfare of the target position;

[0025] The natural language processing function of the AI position generation large model is used to perfect the preliminary job responsibility description and optimize the expression of the text content thereof, with reference to the job responsibility description in the historical position description information.

[0026] According to some embodiments of the present application, optionally, the position characteristics include a position type and / or a position level, and the target recruitment release channel includes one or more recruitment release channels.

[0027] The AI position release and tracking large model is used to analyze the position characteristics and the target recruitment crowd in the target position description information, and according to the analysis result, a target recruitment release channel that matches the position characteristics and / or the target recruitment crowd is selected from the plurality of recruitment release channels, including:

[0028] The AI position release and tracking large model is used to analyze the position type and the position level, and a target recruitment release channel that matches the position type and / or the position level is selected from the plurality of recruitment release channels.

[0029] And / or, the AI position release and tracking large model is used to analyze the education requirement, the skill requirement, the work experience requirement and / or the work location in the target position description information, determine the target recruitment crowd, and select a target recruitment release channel that matches the education, the skill, the work experience and / or the work location of the target recruitment crowd from the plurality of recruitment release channels.

[0030] According to some embodiments of the present application, optionally, the position release platform further performs the following processing after being started: the AI position release and tracking large model is used to analyze the position characteristics and the target recruitment crowd in the target position description information, and determine the release parameters of the target recruitment release channel; wherein the release parameters include whether to open value-added services, a release time and a release frequency.

[0031] According to some embodiments of the present application, optionally, the AI position exploration large model is trained or fine-tuned by using the enterprise business data and market data of a preset number of sample enterprises with different industries, scales and natures as input, and using the position list actually needed to be recruited by the sample enterprises as expected output; the AI position generation large model is trained or fine-tuned by using the position name, the belonging department and the preliminary job responsibility description of a preset number of sample positions, the recruitment requirement of the enterprise internal knowledge base of the sample position belonging enterprise and / or the historical position description information of the same industry as input, and using the sample position description information as expected output.

[0032] According to some embodiments of the present application, optionally, the AI job posting and tracking large model is obtained by multi-task learning of the AI large model, wherein one task is to train the AI large model to learn the ability of selecting a recruitment release channel by taking sample job description information as input and taking the historical recruitment release channel of the sample job as expected output; and another task is to train the AI large model to learn the ability of generating modification suggestions for job description information and / or a historical recruitment release channel by taking feedback data of the historical recruitment release channel of the sample job as input and taking the modification suggestions for the sample job description information and / or the historical recruitment release channel as expected output.

[0033] In a second aspect, the embodiments of the present application provide an electronic device, which is deployed with the AI-based job posting platform according to any of the above embodiments, and implements the processing steps after the AI-based job posting platform is started by calling the plurality of pre-trained AI large models.

[0034] The AI-based job posting platform and the electronic device provided by the embodiments of the present application realize the automation of the whole job posting process by using the plurality of pre-trained AI large models, can deeply analyze enterprise business data and market data, accurately determine recruitment positions, perfect job description information, and reasonably select recruitment release channels. Each link is closely connected and does not require excessive manual intervention. This whole-process automation mode helps to improve the recruitment efficiency and quality of enterprises and reduce the time and energy cost of manual operation. For example, in the traditional recruitment process, position exploration may require repeated communication and research between the human resources department and each department, consuming a lot of time; while the AI position exploration large model of the present application can quickly and accurately identify potential position vacancies by analyzing enterprise business data and market data, shortening the preparation time. At the same time, the job description generation and release channel selection are also completed by the pre-trained AI large model, avoiding subjective errors and low efficiency problems that may occur when manually writing descriptions and selecting channels, and significantly improving the efficiency of the recruitment process as a whole, so that enterprises can quickly fill the position vacancies and meet the business development needs. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings in the embodiments of the present application.

[0036] Figure 1 A structural block diagram of the AI-based job posting platform provided by the embodiments of the present application.

[0037] Figure 2 A flowchart of the AI-based job posting platform provided by the embodiments of the present application.

[0038] Figure 3A flowchart of S202 in the position publishing platform based on artificial intelligence provided by an embodiment of the present application is shown.

[0039] Figure 4 Another flowchart of the position publishing platform based on artificial intelligence provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0040] The features and exemplary embodiments of various aspects of the present application will be described in detail below with reference to the drawings. To make the purposes, technical solutions, and advantages of the present application more clear, the present application will be further described in detail below with reference to the drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, but not to limit the present application. The present application can be implemented without some of the specific details by those skilled in the art. The following description of the embodiments is only intended to provide a better understanding of the present application by showing examples of the present application.

[0041] It should be noted that, in this document, the terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between the entities or operations. Moreover, the terms “include”, “contain” or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the elements defined by the statement “include” do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0042] It should be understood that the term “and / or” used herein is only used to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, the character “ / ” herein generally represents an “or” relationship between the front and rear associated objects.

[0043] Various modifications and changes can be made to the present application without departing from the spirit or scope of the present application, which will be apparent to those skilled in the art. Therefore, the present application is intended to cover the modifications and changes of the present application falling within the scope of the corresponding claims (claimed technical solutions) and their equivalents. It should be noted that the embodiments provided by the embodiments of the present application can be combined with each other without contradiction.

[0044] Before describing the technical solutions provided in the embodiments of this application, in order to facilitate understanding of the embodiments of this application, this application first specifically explains the problems existing in the related technologies:

[0045] In today's highly competitive business environment, talent recruitment is crucial for a company's development. However, traditional job posting methods have many drawbacks.

[0046] On the one hand, when determining the positions that companies need to recruit, they often rely on the human resources department to determine the recruitment needs submitted by each department. This makes it difficult to fully and accurately grasp the actual needs of the company, which can easily lead to a mismatch between the recruitment positions and the company's business development. This may result in insufficient or excessive recruitment, affecting the company's normal operation and the rational allocation of resources.

[0047] On the other hand, in the job description information generation stage, it is usually written by recruiters based on their experience, which may result in the job description being inaccurate and incomplete, failing to clearly convey the key information of the job, causing job seekers to have a distorted understanding of the job, and reducing the effectiveness of recruitment.

[0048] In addition, when choosing recruitment channels, traditional methods mostly rely on subjective judgment or past experience, which may result in job postings being placed on mismatched channels, failing to accurately reach target talents, wasting recruitment resources, prolonging the recruitment cycle, and increasing the company's recruitment costs.

[0049] To this end, this application provides an artificial intelligence-based job posting platform and electronic device. The job posting platform uses multiple large AI models to work collaboratively to automate and intelligently handle aspects of the recruitment process, such as job discovery, job description generation, and recruitment channel selection. This reduces human intervention, improves recruitment efficiency and accuracy, helps companies quickly find suitable talent, and enhances their competitiveness in the recruitment market.

[0050] The following section first introduces the AI-based job posting platform provided in the embodiments of this application.

[0051] Figure 1 This is a structural block diagram of an AI-based job posting platform provided in an embodiment of this application. Figure 1 As shown, the AI-based job posting platform 10 is equipped with multiple pre-trained AI models, including an AI job discovery model 101, an AI job generation model 102, and an AI job posting and tracking model 103. The AI ​​job discovery model 101 can be used for job discovery, the AI ​​job generation model 102 can be used for job description generation, and the AI ​​job posting and tracking model 103 can be used for recruitment channel selection. In some embodiments, the AI ​​job posting and tracking model 103 can also be used for tracking job posting effectiveness.

[0052] Figure 2 A flowchart of a position publishing platform based on artificial intelligence provided by an embodiment of the present application is shown. As shown, the position publishing platform based on artificial intelligence 10 can perform the following processes after being started, such as performing steps S201 to S204. Figure 2

[0053] S201: input the enterprise business data of the target enterprise and the market data related to the target enterprise into the AI position mining large model.

[0054] The target enterprise can be any enterprise that has a position publishing demand, and the present application does not limit this. Exemplarily, the enterprise business data of the target enterprise can be imported to the position publishing platform 10 through an enterprise internal system, or can also be manually input to the position publishing platform 10 by the target enterprise, and the present application does not limit this. The market data related to the target enterprise can be obtained from a database storing these market data, or can also be obtained through network search or web crawler, and the present application does not limit this.

[0055] In some embodiments, the enterprise business data can include enterprise strategic planning, departmental business needs and existing employee skill matrix, and the market data can include at least one of industry development trend, industry talent supply and demand situation, competitor recruitment dynamics and policy regulations.

[0056] In S201, the enterprise business data uploaded by the target enterprise and the market data related to the target enterprise obtained can be input to the AI position mining large model 101.

[0057] S202: reasoning analysis of the enterprise business data and the market data by the AI position mining large model, determining and recommending a position list that the target enterprise needs to recruit to the target enterprise, wherein the position list includes at least one position name, department and preliminary job responsibility description.

[0058] The AI position mining large model 101 can be trained or fine-tuned by taking the enterprise business data and market data of sample enterprises of different industries, sizes and natures in a preset number as input, and taking the actual position list that the sample enterprises need to recruit as expected output.

[0059] ​Specifically, the business data of a preset number of sample enterprises of different industries, scales and natures can be collected, such as the enterprise strategic planning of the sample enterprises, the business requirements of each department and the existing employee skill matrix. At the same time, market data related to the sample enterprises can be collected, such as industry development trends, industry talent supply and demand, competitor recruitment dynamics and / or policies and regulations. In addition, the historical recruitment records of the sample enterprises can be collected to determine the list of positions that the sample enterprises actually need to recruit in the historical period.

[0060] The business data and market data of each sample enterprise are taken as input, and the list of positions that each sample enterprise actually needs to recruit is taken as output label. The AI large model is trained or fine-tuned so that the AI large model can accurately predict the positions that the enterprise needs to recruit according to the business data and market data, thereby obtaining the AI position exploration large model.

[0061] In S202, the business data and market data of the target enterprise are analyzed by the AI position exploration large model to determine the list of positions that the target enterprise needs to recruit, and the target enterprise is recommended the list of positions that the target enterprise needs to recruit. The position list can include at least one position name, department and preliminary responsibility description.

[0062] S203: In response to the target position selected by the target enterprise from the recommended positions, and according to the position name, department and preliminary responsibility description of the target position, and referring to the recruitment requirements of the enterprise internal knowledge base and / or the historical position description information of the target position of at least one enterprise in the same industry, the AI position generation large model is called to perfect the multiple contents of the target position, and the target position description information of the target position is generated.

[0063] After the position list is recommended to the target enterprise, the target enterprise can select one or more positions from the recommended positions as target positions.

[0064] Traditional position descriptions may have problems of ambiguity and lack of targeting, which makes it difficult for job seekers to understand the position requirements and reduces the recruitment efficiency. Therefore, in the present application, in response to the target position selected by the target enterprise from the recommended positions, and according to the position name, department and preliminary responsibility description of the target position, and referring to the recruitment requirements of the enterprise internal knowledge base and / or the historical position description information of the target position of at least one enterprise in the same industry, the AI position generation large model is called to perfect the multiple contents of the target position, and the target position description information of the target position is generated.

[0065] For example, the natural language processing function of the AI job generation large model can refine the preliminary job description and optimize the expression of the text content to ensure clear and accurate language and avoid ambiguous words to facilitate the understanding of job seekers. At the same time, the AI job generation large model can refer to the recruitment requirements in the enterprise internal knowledge base and / or the recruitment requirements of other enterprises in the same industry for the target position to supplement the content of the target position, such as work location, educational requirements, skill requirements, work experience requirements, salary and / or welfare benefits, etc.

[0066] In some embodiments, the AI job generation large model can be trained or fine-tuned by taking the job title, department, and preliminary job description of a preset number of sample positions, the recruitment requirements of the enterprise internal knowledge base of the enterprise to which the sample positions belong, and / or the historical position description information of the same industry as input, and the sample position description information as expected output.

[0067] S204: The AI job posting and tracking large model analyzes the position characteristics and target recruitment population in the target position description information, and selects a target recruitment posting channel that matches the position characteristics and / or target recruitment population from multiple recruitment posting channels according to the analysis result; and posts the target position description information of the target position through the target recruitment posting channel.

[0068] Traditional job posting channel selection often relies on manual judgment and lacks scientific basis, resulting in poor posting results. Therefore, the AI job posting and tracking large model analyzes the position characteristics and target recruitment population in the target position description information, and selects a target recruitment posting channel suitable for the target position according to the analysis result. Then, the target position description information of the target position is posted through the target recruitment posting channel.

[0069] For example, the AI job posting and tracking large model can analyze at least one of the position type, position level, educational requirements, skill requirements, work experience requirements, and / or work location of the target position, and select one or more recruitment posting channels that match it as the target recruitment posting channel. For example, if the target position is for a graduate, the target recruitment posting channel can be a campus recruitment channel, an internship recruitment platform, and / or some job websites for graduates. For example, if the target position is for a professional with certain work experience, the target recruitment posting channel can be a social recruitment channel, an industry association website, and / or a professional forum, etc.

[0070] The embodiments of the present application provide an AI-based position publishing platform. The AI-based position publishing platform realizes the automation of the whole process of position publishing by using multiple pre-trained AI large models, can deeply analyze enterprise business data and market data, accurately determine recruitment positions, perfect position description information, and reasonably select recruitment publishing channels. Each link is closely connected and does not require excessive manual intervention. This whole-process automation mode helps to improve the recruitment efficiency and quality of enterprises and reduce the time and energy cost of manual operation. For example, in the traditional recruitment process, position exploration may require repeated communication and research between the human resources department and each department, which consumes a lot of time. The AI position exploration model of the present application can quickly and accurately identify potential position vacancies by analyzing enterprise business data and market data, thereby shortening the preparation time. At the same time, the position description generation and the selection of the publishing channel are also completed by the pre-trained AI large model, which avoids subjective errors and low efficiency problems that may occur when manually writing descriptions and selecting channels, and significantly improves the efficiency of the recruitment process as a whole, so that enterprises can quickly fill the position vacancies and meet the business development needs.

[0071] For ease of understanding, the above steps are illustrated below with some specific embodiments.

[0072] In some embodiments, the enterprise business data can include enterprise strategic planning, department business needs, and existing employee skill matrix, and the market data can include at least one of industry development trend, industry talent supply and demand situation, competitor recruitment dynamics, and policy regulations.

[0073] Figure 3 A flowchart of S202 in the AI-based position publishing platform provided by the embodiments of the present application is shown in FIG. 2. Figure 3 As shown in FIG. 2, correspondingly, S202: reasoning and analyzing the enterprise business data and market data by the AI position exploration model, determining and recommending a position list that the target enterprise needs to recruit to the target enterprise, can include at least one of the following steps S301 to S305.

[0074] S301: analyzing the target achieved by the enterprise strategic planning and the skill set required to achieve the target by the AI position exploration model, and comparing with the existing employee skill matrix to obtain the missing skills; determining the positions that need to be recruited according to the missing skills.

[0075] The AI position exploration large model analyzes the strategic planning of the target enterprise and determines the goals to be achieved. For example, if the target enterprise plans to enter a new market field, such as expanding from the domestic market to the international market, the AI position exploration large model can help analyze the professional knowledge and skills required in international business operations, such as international market marketing, cross-cultural communication, international business law, etc. For example, if the target enterprise plans to increase investment in artificial intelligence, the AI position exploration large model can help analyze the professional knowledge and skills required in artificial intelligence, such as artificial intelligence algorithms, data labeling, etc. Then, through the AI position exploration large model, the skill set required to achieve the goal is compared with the existing employee skill matrix (i.e., the existing skills of the existing employees), and the skills that the target enterprise lacks are obtained. According to the skills that the target enterprise lacks, the positions that need to be recruited are determined.

[0076] S302: Through the AI position exploration large model, the business processes of each department are analyzed, and the bottlenecks or low-efficiency links in the business processes are found out, and according to the determined links, the positions that need to be recruited are determined.

[0077] Through the AI position exploration large model, the business processes of each department of the target enterprise are comprehensively analyzed, and a detailed business process diagram is drawn. Through the analysis of the business process, the links that exist bottlenecks, low efficiency or need to be improved are found out. For example, through the AI position exploration large model, it is found that due to the lack of manpower in the quality detection link in the production process, the product backlog is caused, which affects the overall production efficiency. At this time, the AI position exploration large model gives the suggestion that quality detection personnel need to be recruited.

[0078] S303: Through the AI position exploration large model, the skill set required by the projects currently being carried out or planned to be carried out by each department is analyzed, and compared with the existing employee skill matrix, the missing skills are obtained; according to the missing skills, the positions that need to be recruited are determined.

[0079] Through the AI position exploration large model, the skill set required by the projects currently being carried out or planned to be carried out by each department of the target enterprise is analyzed, and the skill set is compared with the existing employee skill matrix, and the skills that the target enterprise lacks are obtained. According to the skills that the target enterprise lacks, the positions that need to be recruited are determined.

[0080] S304: Through the AI position exploration large model, the industry development trend, industry talent supply and demand situation and / or policy and regulation are analyzed, the target business that the target enterprise is expected to carry out in the future and the skill set required to carry out the target business are predicted, and compared with the existing employee skill matrix, the missing skills are obtained; according to the missing skills, the positions that need to be recruited are determined.

[0081] The AI position exploration large model analyzes the industry development trend, industry talent supply and demand situation and / or policy and regulation of the target enterprise, and predicts the target business that the target enterprise will prefer to carry out in the future and the skill set required to carry out the target business. For example, taking a retail enterprise as an example, the AI position exploration large model analyzes the industry development trend and finds that: at present, online shopping is developing rapidly, and consumers' shopping habits are gradually shifting to online, and emerging sales models such as live streaming have become industry hotspots. And / or, the AI position exploration large model analyzes the industry talent supply and demand situation and finds that: at present, the market has a large demand for talents with e-commerce operation, data analysis, live streaming technology and other related skills, but the supply is relatively insufficient. And / or, the AI position exploration large model analyzes the policy and regulation and finds that: at present, the policy encourages traditional enterprises to carry out digital transformation, and a series of supporting policies have been introduced. Therefore, it is predicted that the target business that the target enterprise will prefer to carry out in the future is to expand online sales channels, build a live streaming platform, and the skill set required to carry out the target business includes e-commerce operation skills, data analysis skills, live streaming technology skills and content creation skills, etc.

[0082] Then, the AI position exploration large model compares the skill set required to carry out the target business with the existing employee skill matrix (i.e. the existing skills of the existing employees), and finds that at present, the existing employees of the target enterprise mostly have traditional offline retail skills such as store sales, inventory management, etc., but lack skills in e-commerce operation, data analysis, live streaming technology and content creation. Therefore, according to the missing skills, the positions that need to be recruited include e-commerce operation specialists, data analysts, live streaming technology engineers and content creation specialists, etc.

[0083] S305: The AI position exploration large model analyzes the recruitment position layout of the competitors, and compares it with the existing positions and the positions being recruited of the target enterprise, to find out the positions that the target enterprise has not recruited or the number of which is insufficient.

[0084] The AI position exploration large model analyzes the recruitment position layout of the competitors, and compares it with the existing positions and the positions being recruited of the target enterprise, to find out the positions that the target enterprise has not recruited or the number of which is insufficient. For example, the AI position exploration large model analyzes and finds that the competitors have recruited a large number of positions in a certain field, while the target enterprise's recruitment in this field is relatively lagging behind, so the positions that the target enterprise has not recruited or the number of which is insufficient in this field can be determined as the positions that need to be recruited.

[0085] In order to facilitate understanding, an application embodiment of the AI position exploration large model for position exploration is given below.

[0086] Taking a retail enterprise as an example, the AI position exploration large model finds that, when analyzing the enterprise internal data, with the rapid growth of online business, the average response time of online customer service is gradually extended, and the customer complaint rate has also increased. Through detailed analysis of the business process, it is found that the existing online customer service team is insufficient in personnel and lacks professional training when handling a large number of inquiries and complaints, resulting in a decline in service efficiency and quality. At the same time, in terms of market data monitoring, the AI position exploration large model pays attention to the fact that competitors in the industry have successively launched personalized recommendation services and achieved good sales performance. However, the retail enterprise is relatively lagging behind in this regard, lacking relevant technical and data analysis talents to support the development and operation of personalized recommendation systems. Based on these analyses, the AI position exploration large model discovers three potential position vacancies: online customer service supervisor, data analyst, and algorithm engineer. The online customer service supervisor is responsible for managing and training the customer service team to improve service quality. The data analyst is responsible for collecting and analyzing user data to provide data support for personalized recommendations. The algorithm engineer is responsible for developing and optimizing personalized recommendation algorithms to improve user shopping experience, thereby helping the enterprise better cope with market competition and business development needs.

[0087] In this way, by inputting enterprise business data and related market data into the AI position exploration large model, its powerful reasoning and analysis capabilities can comprehensively and deeply analyze enterprise business needs and market dynamics. Compared with traditional manual analysis to determine recruitment positions, the present application can improve the accuracy of position exploration, so that the position list recommended to the target enterprise is highly consistent with the actual needs of the enterprise, effectively avoiding under-recruitment or over-recruitment, and enabling the enterprise's human resources to be reasonably allocated.

[0088] According to some embodiments of the present application, optionally, S203: according to the position name, department and preliminary job responsibility description of the target position, and referring to the recruitment requirements of the enterprise internal knowledge base and / or the historical position description information of the target position of at least one enterprise in the same industry, calling an AI position generation large model to perfect the multiple contents of the target position, and generating the target position description information of the target position, which can include the following steps one and two.

[0089] Step one: extracting the work location requirement, education requirement, skill requirement, work experience requirement, salary standard and / or welfare standard from the reference enterprise internal knowledge base through the AI position generation large model, and referring to the education requirement, skill requirement, work experience requirement, salary standard and / or welfare standard in the historical position description information, to supplement the work location, education requirement, skill requirement, work experience requirement, salary and / or welfare of the target position.

[0090] Specifically, the AI job generation large model can refer to the enterprise internal knowledge base of the target enterprise and accurately extract key information such as work location requirements, education requirements, skill requirements, work experience requirements, salary standards, and / or welfare treatment standards. At the same time, the AI job generation large model can also refer to similar requirements in the historical position description information of at least one enterprise in the same industry, such as education requirements, skill requirements, work experience requirements, salary standards, and / or welfare treatment standards. On this basis, based on these information, the work location, education requirements, skill requirements, work experience requirements, salary, and welfare treatment of the target position which are originally relatively brief or incomplete are fully supplemented.

[0091] In this way, by learning from the experience of enterprises in the same industry, the characteristics of the talents required for the target position can be more accurately defined, making the recruitment information more targeted, helping to attract candidates who truly meet the job requirements, and avoiding the setting of the requirements of the target position (such as education, skills, experience, etc.) to be too high or too low, ensuring that talents with matching capabilities are recruited for the target position.

[0092] Step two: through the natural language processing function of the AI job generation large model, and referring to the job responsibility description in the historical position description information, the preliminary job responsibility description is perfected, and the expression of the text content is optimized; based on the supplemented and optimized content of the target position, the target position description information of the target position is obtained.

[0093] Specifically, the powerful natural language processing function of the AI job generation large model can be used to finely perfect the preliminary job responsibility description of the target position. In this process, the AI job generation large model can refer to the job responsibility description part in the historical position description information to extract reasonable and effective expression methods and content points, and enrich the content of the job responsibility description. In addition, the AI job generation large model can also check the accuracy, fluency, and logic of the language, and avoid using ambiguous or ambiguous words. For example, through synonym replacement, sentence transformation, etc., the position description is made more fluent and accurate.

[0094] Finally, the content of the target position supplemented and optimized by the AI job generation large model is integrated to obtain the complete target position description information of the target position. Exemplarily, the target position description information includes but is not limited to position name, department to which it belongs, work location, education requirements, skill requirements, work experience requirements, salary, welfare treatment, and perfected job responsibility description, etc.

[0095] In this way, the AI job generation large model can improve the target job description information according to the basic information of the target job, and refer to the recruitment requirements of the enterprise internal knowledge base and the historical job description information of the same industry, so that the generated target job description information is more accurate, comprehensive and targeted, which can clearly convey the key information of the job to the job seekers, reduce the deviation of the job seekers in understanding the job, and help to improve the recruitment efficiency and success rate.

[0096] According to some embodiments of the present application, optionally, the job features can include job type and / or job level, and the target recruitment channel can include one or more recruitment channels.

[0097] Correspondingly, S204: reasoning and analyzing the job features and the target recruitment crowd in the target job description information by the AI job posting and tracking large model, and selecting the target recruitment channel matching the job features and / or the target recruitment crowd from the multiple recruitment channels according to the reasoning and analysis results, can include the following steps three and / or step four.

[0098] Step three: analyzing the job type and the job level by the AI job posting and tracking large model, and selecting the target recruitment channel matching the job type and / or the job level from the multiple recruitment channels.

[0099] Specifically, the AI job posting and tracking large model can analyze the job title and / or the responsibility description of the target job to determine the job type of the target job. For example, the job type includes but is not limited to technical, management or marketing, etc. Then, the target recruitment channel matching the job type is selected from the multiple recruitment channels. For example, taking the target job as "algorithm engineer" as an example, the responsibility description involves professional technical fields such as machine learning and deep learning, as well as the research, development, optimization and application of algorithms. Based on this, the job type of the target job is determined as technical. Then, a recruitment website focusing on the recruitment of talents in the technical field can be selected as the target recruitment channel.

[0100] In addition, the job level can also be an important factor for selecting the recruitment channel. For senior management positions, the AI job posting and tracking large model can recommend using headhunting companies and high-end talent recruitment channels as the target recruitment channel. For middle-level positions, the AI job posting and tracking large model can recommend using comprehensive recruitment websites, enterprise websites, etc. as the target recruitment channel. For entry-level positions, the AI job posting and tracking large model can recommend using local recruitment websites, comprehensive recruitment websites, social media groups, etc. as the target recruitment channel.

[0101] Step four: determining the target recruitment crowd by analyzing the education requirement, skill requirement, work experience requirement and / or work location in the target job description information through the AI job posting and tracking large model, and selecting the target recruitment channel from multiple recruitment channels that matches the education, skill, work experience and / or work location of the target recruitment crowd.

[0102] Specifically, the AI job posting and tracking large model can analyze the education requirement, skill requirement, work experience requirement and / or work location in the target job description information to determine what education, skill and / or work experience the target recruitment crowd of the target job needs to have, and where the specific work location is. Then, the target recruitment channel is selected from multiple recruitment channels that matches the education, skill, work experience and / or work location of the target recruitment crowd.

[0103] For example, if the target recruitment crowd of the target job is a graduate, the target recruitment channel can be a campus recruitment channel, an internship recruitment platform and / or some job-seeking websites for graduates. For example, if the target recruitment crowd of the target job is a professional with certain work experience, the target recruitment channel can be a social recruitment channel, an industry association website and / or a professional forum, etc. For example, if the target job requires the work location to be A, the local recruitment website, community forum, etc. can be used as the target recruitment channel.

[0104] In this way, the AI job posting and tracking large model can accurately select the target recruitment channel that matches the job characteristics and the target recruitment crowd from multiple recruitment channels by in-depth reasoning and analysis of the job characteristics and the target recruitment crowd in the target job description information. In this way, the blindness of selecting recruitment channels based on subjective experience in the traditional way can be avoided, the dissemination efficiency of recruitment information can be improved, the recruitment cycle can be shortened, and the recruitment cost of enterprises can be reduced.

[0105] Figure 4 Another flowchart of the job posting platform based on artificial intelligence provided by the embodiments of the present application is shown in FIG. 6. Figure 4 As shown in FIG. 6, according to some embodiments of the present application, after the job posting platform is started, the following processing is optionally performed:

[0106] S205: collecting feedback data of the target recruitment channel through the AI job posting and tracking large model, wherein the feedback data includes at least one of the browsing volume, the resume delivery volume, the basic information of the job seeker and the interview data of the target job in a preset period; calculating the publication effect parameter of the target job according to the feedback data; in the case that the publication effect parameter does not meet the requirements, reasoning and analyzing the reasons for the publication effect parameter not meeting the requirements, and generating modification suggestions for the target job description information and / or the target recruitment channel.

[0107] Specifically, the feedback data of the target recruitment publishing channel can be collected by the AI job publishing and tracking large model. The feedback data includes, but is not limited to, at least one of the following: the number of views of the target position within a preset period, the number of resume submissions, the basic information of job seekers, and interview data. For example, the basic information of the job seeker can include the education, skill level, and work experience of the job seeker. The interview data can include the number of interview invitations, the interview pass rate, and the interview evaluation, etc.

[0108] According to the feedback data, the AI job publishing and tracking large model can determine or calculate the publishing effect parameter of the target position. The publishing effect parameter can be used to evaluate the publishing effect or recruitment effect of the target position, which can be flexibly set according to actual conditions, and the present application does not limit it. For example, in some embodiments, the publishing effect parameter can include at least one of the following: the number of views, the number of resume submissions, the number of interview invitations, the interview pass rate, the resume conversion rate, and the talent matching degree. The resume conversion rate is the ratio of the number of resume submissions to the number of interview invitations, that is, the proportion from resume submission to interview invitation. The talent matching degree is the matching degree of the basic information of the job seeker and the description information of the target position.

[0109] In the case where the publishing effect parameter does not meet the requirements, such as low number of views, number of resume submissions, number of interview invitations, interview pass rate, resume conversion rate, and / or talent matching degree, the AI job publishing and tracking large model can infer and analyze the reasons for the publishing effect parameter not meeting the requirements, and generate modification suggestions for the target position description information and / or the target recruitment publishing channel based on the reasons.

[0110] For example, assuming that the target enterprise is recruiting a data analyst position, at the initial stage of recruitment, the target enterprise selects a comprehensive recruitment website, a professional data forum, and an enterprise website as target recruitment publishing channels according to the recommendation of the AI job publishing and tracking large model. In one case, the publishing effect parameters of the multiple recruitment publishing channels do not meet the requirements, such as low resume delivery volume and low talent matching degree. After inference and analysis by the AI job publishing and tracking large model, it is found that in the target job description information of the position, the salary setting is too low, and the specific job responsibilities of the data analyst are not clearly described in the job description, which makes it difficult for job seekers to judge whether they are suitable for the position. Therefore, the AI job publishing and tracking large model can generate modification suggestions for the salary and job responsibility description, such as increasing the salary and further clarifying the specific job responsibilities of the data analyst. For another example, in another case, although the comprehensive recruitment website has a large number of resume delivery volumes, the talent matching degree is low, and many deliverers lack relevant data analysis project experience. However, the resume delivery volume of the professional data forum is small, but the talent matching degree is high. Based on this, the AI job publishing and tracking large model can generate modification suggestions for the target recruitment publishing channels, such as reducing the advertising budget on the comprehensive recruitment website and optimizing the job display page on the professional data forum.

[0111] In this way, by timely analyzing feedback data and making adjustments through the AI job publishing and tracking large model, the target job description information and / or the target recruitment publishing channels can be optimized, and excessive time and resources wasted on ineffective recruitment strategies by the target enterprise can be reduced. For example, instead of continuously publishing job information in unsuitable channels or repeatedly launching ineffective job descriptions, resources can be concentrated on more effective ways, thereby shortening the recruitment cycle and reducing recruitment costs.

[0112] According to some embodiments of the present application, the job publishing platform can also perform the following processing after being started:

[0113] The AI job publishing and tracking large model infers and analyzes the job features in the target job description information and the target recruitment population to determine the publishing parameters of the target recruitment publishing channels; wherein the publishing parameters include whether to open value-added services, publishing time, and publishing frequency.

[0114] For example, still taking the target position of data analyst as an example, the AI job posting and tracking large model finds through analysis that the competition for data analysts is relatively fierce, and therefore suggests opening value-added services to improve the competitiveness and exposure of the position, such as purchasing a top service, priority recommendation service, etc. on a recruitment website. Analyzing the online habits of the target recruitment group, it is found that the late evening and weekends are the peak times for the target recruitment group to browse recruitment information. Therefore, it is suggested that the publication time be set to the late evening or weekends. The AI job posting and tracking large model finds through analysis that the data analyst talent market is relatively active, and therefore suggests that the publication frequency should not be too low, such as publishing 2-3 recruitment information per week, so as to ensure that the position appears in the field of view of potential candidates.

[0115] According to some embodiments of the present application, optionally, the modification suggestion of the target recruitment publication channel can include a modification suggestion of the publication parameters of the target recruitment publication channel, such as adjusting whether to open value-added services, publication time and / or publication frequency.

[0116] According to some embodiments of the present application, optionally, the AI job posting and tracking large model can generate a job posting effect report based on the feedback data, the publication effect parameters and the modification suggestion. The job posting effect report can include the feedback data, the publication effect parameters, and the modification suggestion of the target position description information and / or the target recruitment publication channel.

[0117] According to some embodiments of the present application, optionally, the job posting platform can also perform the following processing after starting: recording the detailed information of the target position published each time through the AI job posting and tracking large model. The detailed information of the target position can include publication time, recruitment publication channel, position description version, etc., thereby facilitating the target enterprise to review and summarize.

[0118] According to some embodiments of the present application, optionally, the AI job posting and tracking large model is an AI large model obtained through multi-task learning, wherein one task is to take the sample position description information as input and the historical recruitment publication channel of the sample position as expected output, to train the AI large model to learn the ability to select recruitment publication channels; another task is to take the feedback data of the historical recruitment publication channel of the sample position as input, and to take the sample position description information and / or the modification suggestion of the historical recruitment publication channel as expected output, to train the AI large model to learn the ability to generate the modification suggestion of the position description information and / or the recruitment publication channel.

[0119] Based on the AI-based position publishing platform 10 provided in the above embodiments, the application further provides an electronic device. The electronic device is deployed with the AI-based position publishing platform 10 provided in any of the above embodiments, and the electronic device realizes the processing steps after the position publishing platform is started by calling a plurality of pre-trained AI large models. The electronic device in the embodiments of the application can be a user terminal device, can be a server, can be other computing devices, and can also be a cloud server, and the application does not limit this.

[0120] The functional blocks shown in the structural block diagram of the embodiments of the application can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, etc.; when implemented in software, it is a program or a code segment used to perform the required tasks. The program or code segment can be stored in a memory or transmitted on a transmission medium or a communication link through a data signal carried in a carrier wave. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0121] It should be noted that the application is not limited to the specific configurations and processes described above or shown in the drawings. The above description is merely a specific embodiment of the application, and those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described system, device, module or unit can refer to the corresponding process in the method embodiments, which need not be described again. It should be understood that the protection scope of the application is not limited to this, and any person skilled in the art can think of various equivalent modifications or replacements within the technical range disclosed in the application, and these modifications or replacements should be covered within the protection scope of the application.

Claims

1. A job posting platform based on artificial intelligence, characterized in that, The job posting platform is equipped with multiple pre-trained AI models. After the job posting platform is started, it performs the following processes: Input the target company's business data and related market data into the AI ​​job discovery model; By using an AI job discovery model to reason and analyze enterprise business data and market data, the system identifies and recommends a list of job openings that the target enterprise needs to recruit. The job list includes at least one job title, department, and preliminary job description. In response to the target company's selection of a target position from the recommended positions, and based on the target position's job title, department, and preliminary job description, as well as referencing the company's internal knowledge base for recruitment requirements and / or historical job description information of the target position from at least one company in the same industry, the AI ​​job generation model is invoked to refine multiple aspects of the target position and generate the target job description information. The AI ​​job posting and tracking big data model is used to infer and analyze the job characteristics and target recruitment audience in the target job description information. Based on the inference and analysis results, the target job posting channel that matches the job characteristics and / or target recruitment audience is selected from multiple job posting channels. The target job description information of the target job is then posted through the target job posting channel.

2. The job posting platform according to claim 1, characterized in that, After the job posting platform is started, it also performs the following processes: The AI ​​job posting and tracking model collects feedback data from target job posting channels. This feedback data includes at least one of the following: number of views, number of resumes submitted, basic information of job seekers, and interview data within a preset period. Based on the feedback data, the model calculates the posting performance parameters for the target job. If the posting performance parameters do not meet the requirements, the model infers and analyzes the reasons for the non-compliance, and generates modification suggestions for the target job description and / or target job posting channels.

3. The job posting platform according to claim 2, characterized in that, The job seeker’s basic information includes their education, skill level and work experience, and the interview data includes the number of interview invitations, the interview pass rate and the interview evaluation. The posting performance parameters include at least one of the following: page views, number of resumes submitted, number of interview invitations, interview pass rate, resume conversion rate, and talent matching degree. Among them, the resume conversion rate is the ratio of the number of resumes submitted to the number of interview invitations, and the talent matching degree is the degree of matching between the job seeker's basic information and the target job description information.

4. The job posting platform according to claim 1, characterized in that, Enterprise business data includes enterprise strategic planning, business needs of various departments and existing employee skills matrix; market data includes industry development trends, industry talent supply and demand, competitor recruitment dynamics and at least one of the following: By using AI job discovery models to analyze and reason about enterprise business and market data, the system identifies and recommends a list of job openings that the target company needs to fill, including at least one of the following: By using AI job discovery models to analyze the goals of corporate strategic planning and the skill set required to achieve those goals, and comparing them with the existing employee skill matrix, missing skills can be identified. Based on the skills lacking, identify the positions that need to be filled; By using AI job discovery models to analyze the business processes of various departments, bottlenecks or inefficient links in the business processes are identified, and positions that need to be recruited are determined based on the identified links. By using an AI job discovery model, we analyze the skill sets required for projects currently underway or planned by each department, and compare them with the existing employee skill matrix to identify missing skills. Based on the skills lacking, identify the positions that need to be filled; By using AI job discovery models to analyze industry development trends, industry talent supply and demand, and / or policies and regulations, we can predict the target businesses that target companies will prioritize in the future and the skill set required to carry out those target businesses. We can then compare these skills with the existing employee skill matrix to identify the skills that are missing. Based on the skills lacking, identify the positions that need to be filled; By using AI job discovery models to analyze competitors' job postings and compare them with the target company's existing and currently recruiting positions, the system can identify positions that the target company has not yet recruited for or has not recruited enough for.

5. The job posting platform according to claim 1, characterized in that, Based on the job title, department, and initial job description of the target position, and referring to the recruitment requirements in the company's internal knowledge base and / or historical job descriptions of the target position from at least one company in the same industry, the AI ​​job generation model is used to refine multiple aspects of the target position, generating the target job description information, including: The AI ​​job generation model extracts work location requirements, education requirements, skill requirements, work experience requirements, salary standards and / or benefits standards from the internal knowledge base of reference companies, and supplements the work location, education requirements, skill requirements, work experience requirements, salary standards and / or benefits standards of the target position by referring to the education requirements, skill requirements, work experience requirements, salary standards and / or benefits standards in the historical job description information. By leveraging the natural language processing capabilities of the AI ​​job generation model and referencing job descriptions from historical job postings, the initial job description is refined and its textual content is optimized. Based on the supplemented and optimized content of the target job, the target job description information is obtained.

6. The job posting platform according to claim 1, characterized in that, Job characteristics include job type and / or job level, and target job posting channels include one or more job posting channels; The AI-powered job posting and tracking model analyzes and infers the job characteristics and target audience in the job descriptions. Based on the analysis results, it selects target job posting channels that match the job characteristics and / or target audience from multiple channels, including: By analyzing job types and job levels through an AI job posting and tracking big data model, target job posting channels that match the job type and / or job level can be selected from multiple job posting channels. And / or, by analyzing the educational requirements, skill requirements, work experience requirements and / or work location in the target job description information through an AI job posting and tracking big data model, identify the target recruitment audience, and select the target recruitment posting channel from multiple recruitment posting channels that matches the educational requirements, skill requirements, work experience and / or work location of the target recruitment audience.

7. The job posting platform according to claim 1, characterized in that, After the job posting platform is started, it also performs the following processes: By using an AI job posting and tracking model, the characteristics of the job in the target job description and the target recruitment audience are inferred and analyzed to determine the posting parameters of the target recruitment posting channels. Among these parameters are whether value-added services are enabled, posting time, and posting frequency.

8. The job posting platform according to claim 1, characterized in that, The AI ​​job discovery model is obtained by training or fine-tuning the AI ​​model using business data and market data from a preset number of sample companies of different industries, sizes and natures as input, and the expected output being a list of job openings that the sample companies actually need to recruit. The AI ​​job generation model is obtained by training or fine-tuning a large AI model with the job titles, departments, and preliminary job descriptions of a preset number of sample jobs, the recruitment requirements of the companies to which the sample jobs belong, and / or historical job descriptions from the same industry, and the sample job descriptions as the expected output.

9. The job posting platform according to claim 1, characterized in that, The AI ​​job posting and tracking big data model is obtained through multi-task learning. One task is to train the AI ​​big data model to learn the ability to select recruitment posting channels, taking sample job description information as input and the historical recruitment posting channels of sample jobs as the expected output. Another task is to train the AI ​​big data model to learn the ability to generate job description information and / or recruitment posting channel modification suggestions, taking feedback data from the historical recruitment posting channels of sample jobs as input and the modification suggestions from the sample job description information and / or historical recruitment posting channels as the expected output.

10. An electronic device, characterized in that, The electronic device is equipped with an AI-based job posting platform as described in any one of claims 1-9, and the electronic device implements the processing steps after the job posting platform is started by calling multiple pre-trained AI models.

Images