System and method for setting job hunting intention by using AI (artificial intelligence) technology

Abstract

The invention relates to the technical field of job hunting and recruitment, and discloses a job hunting intention setting system and method using an AI technology, and the system comprises an initial setting module, a setting updating module, a virtual position output module and a setting output module. The system corresponds to the method. According to the application, the initial setting module provides a follow-up basis through preset questionnaire collection information, the virtual position output module recombines the position vector based on the initial information to generate the virtual position, the limitation of relying on the actual position is broken through, and the setting updating module continuously optimizes the job hunting intention according to the feedback of the job hunter to the virtual position. According to the method, the defect that the job-hunting intention is set by only depending on personal information is avoided, the risk of personal information leakage is reduced, the problem that the actual position is difficult to accord with the job-hunting intention is solved, the setting quality of the job-hunting intention is improved, position recommendation which is more accordant with the expectation is provided for job seekers, and the job-hunting intention setting efficiency is improved. And the recruitment efficiency of enterprises is also improved.

Description

Technical Field

[0001] The present application relates to the technical field of job seeking and recruitment, and specifically to a job seeking intention setting system and method using AI technology. Background Art

[0002] In the current job seeking and recruitment field, accurate job seeking intention setting is crucial for improving the efficiency and quality of job seeking. However, the inventor found in the analysis of the existing job seeking process that most job seeking and recruitment focus on job recommendations, and job seeking intention setting mainly relies on stacking personal information, which not only easily leads to the leakage of personal information, but may also cause incorrect setting due to inaccurate information. At the same time, the actual positions and the job seeker's intentions often cannot fully match. Existing technologies often limit the deviation between the actual position and the job seeking intention in the form of setting thresholds and control this deviation in an attempt to improve the quality of job recommendations. However, this approach inevitably leads to the selection and rejection of job seeking intentions, which is not conducive to the job seeking experience of job seekers and the employment experience of enterprises. Therefore, the existing job recommendations cannot effectively solve this problem, resulting in job seekers having difficulty finding ideal jobs and enterprises having difficulty recruiting suitable talents.

[0003] Chinese Patent No. CN116401464B discloses a method, device, equipment and storage medium for constructing a professional user portrait, which to a certain extent improves the recruitment efficiency based on the constructed professional user portrait, but there are still obvious deficiencies. Specifically, it does not pay attention to the problem of low matching degree between the actual position and the job seeking intention, and does not consider the actual matching situation between the position and the job seeking intention when generating associated positions. Moreover, for the problem of personal information security, this invention does not take effective measures to protect it. In addition, this invention does not involve optimizing job seeking intention setting and cannot meet the actual needs of job seekers and enterprises in the job seeking and recruitment process.

[0004] In summary, there is an urgent need for a new technical solution for job seeking intention setting using AI technology to solve the above technical problems. Summary of the Invention

[0005] The purpose of the present application is to provide a job seeking intention setting system and method using AI technology to solve the technical problems raised in the above background art.

[0006] To achieve the above purpose, the present application discloses the following technical solutions:

[0007] In the first aspect, the present application discloses a job seeking intention setting system using AI technology, which includes an initial setting module for collecting initial job seeking intentions and corresponding initial job seeking information, a setting update module for updating job seeking intentions, a virtual position output module for outputting virtual positions, and a setting output module for outputting final job seeking intentions;

[0008] The initial setting module collects the initial job hunting intention and the corresponding initial job hunting information based on a preset job hunting questionnaire and transmits them to the virtual job output module; the virtual job output module extracts job vectors for actual jobs in a preset job pool using AI technology, recombines the job vectors based on the initial job hunting intention and the corresponding initial job hunting information to generate virtual jobs and transmits them to the setting and updating module. Multiple actual jobs are stored in the job pool, and the job vectors are used to represent the actual job information of the actual jobs. The virtual jobs are virtual job information for updating the job hunting intention formed based on the job vectors; the setting and updating module updates the job hunting intention based on the feedback from the job seeker on the virtual jobs and generates a corresponding job hunting information completion instruction, generates a new job hunting intention and the corresponding job hunting information based on the completed job hunting information. The job hunting information completion instruction is used to prompt the job seeker to complete the job hunting information; repeatedly run the virtual job output module and the setting and updating module using AI technology for n rounds of setting and updating, where n is a positive integer. This setting and updating is based on the nth round of job hunting intention and the corresponding nth round of job hunting information obtained from the nth round of setting and updating, outputs the nth round of virtual jobs, updates to obtain the (n + 1)th round of job hunting intention and the corresponding (n + 1)th round of job hunting information based on the feedback from the job seeker on the nth round of virtual jobs. When the (n + 1)th round of job hunting intention meets the preset job hunting intention satisfaction threshold, transmit the (n + 1)th round of job hunting intention and the corresponding (n + 1)th round of job hunting information to the setting output module. The job hunting intention satisfaction threshold is generated based on n rounds of setting and updating; the setting output module outputs the (n + 1)th round of job hunting intention and the corresponding (n + 1)th round of job hunting information to a preset job recommendation module, and the job recommendation module is used to recommend the actual jobs based on the job pool.

[0009] Preferably, the extraction of the job vector includes:

[0010] Extract multiple job characteristics of each actual job in the job pool to form a feature vector; wherein, the job characteristics are calculated from the corresponding initial weights and original values.

[0011] Preferably, the generation of the virtual job includes:

[0012] Obtain each of the job characteristics in the feature vector to get the corresponding initial weight and the original value, generate a corresponding dynamic factor for each job characteristic in combination with the initial job hunting intention and the corresponding initial job hunting information, calculate the virtual job characteristic corresponding to the job characteristic based on the initial weight, the dynamic factor and the original value, and obtain a corresponding virtual feature vector based on the virtual job characteristic. The virtual feature vector is used to represent the virtual job.

[0013] Preferably, the generation of the virtual position further includes:

[0014] Based on the correlation degree of the position features, obtain the virtual correlation degree between the virtual position features. When the virtual correlation degree is greater than or equal to the preset virtual correlation degree threshold, the calculation of the virtual position features is updated to be calculated based on the initial weight, the dynamic factor, the original value, the virtual position features corresponding to the virtual correlation degree, and the virtual correlation degree; wherein, the correlation degree is obtained based on the preset correlation relationship of the position features.

[0015] Preferably, when performing the (n + 1)-th round of setting update, when the virtual position output module generates the (n + 1)-th round of virtual positions, adjust the dynamic factor based on the feedback of the previous n rounds. The adjustment is as follows: Collect the feedback satisfaction of the n-th round of job seekers for each virtual position feature, obtain the preset feedback adjustment coefficient, and calculate the adjusted dynamic factor based on the feedback satisfaction and the feedback adjustment coefficient.

[0016] Preferably, when performing the (n + 1)-th round of setting update, when the virtual position output module generates the (n + 1)-th round of virtual positions, determine whether there is a preset necessary original value based on the feedback of the previous n rounds. If so, update the calculation of the virtual position features; otherwise, do not update the calculation of the virtual position features; wherein, the necessary original value is used to retain the necessary original position features when generating the (n + 1)-th round of virtual positions. The update of the calculation of the virtual position features is as follows: Obtain the preset feature retention degree parameter, and calculate the new virtual position features based on the feature retention degree parameter, the necessary original value, the dynamic factor, and the original value.

[0017] Preferably, the output of the (n + 1)-th round of job search intention includes:

[0018] Collect the virtual positions of the n-th round as the job search intention I n , and collect the feedback features r n,k of the job seekers for the virtual positions of the n-th round, the learning and growth factors g n,k of the job seekers, and the market dynamic factors m n,k ; wherein, the learning and growth factors are obtained based on the changes in the work experience of the job seekers during the job search period, and the market dynamic factors are obtained based on the changes in the market position requirements and the corresponding position quantities of the job seekers during the job search period;

[0019] Then the calculation formula of the (n + 1)-th round of job search intention I n+1 is:

[0020]

[0021] Among them, γ1, γ2, and γ3 are the intention adjustment coefficients corresponding to the preset feedback features, learning and growth factors, and market dynamics factors respectively.

[0022] Preferably, the intention adjustment coefficient is adjusted based on the stability and influence corresponding to the feedback feature, the learning and growth factor, and the market dynamics factor in the nth round of setting update.

[0023] Preferably, the generation of the job intention satisfaction threshold includes:

[0024] Calculating the average feedback satisfaction of the feedback satisfaction collected during the nth round of setting update and the market position matching difficulty coefficient D n ; among them, the market position matching difficulty coefficient is obtained based on the value of n and the number of virtual positions in the matching channel;

[0025] The calculation formula for calculating the job intention satisfaction threshold in the (n + 1)th round is:

[0026]

[0027] where T0 is the preset initial job intention satisfaction threshold, T n is the job intention satisfaction threshold in the nth round, and δ1 and δ2 are the threshold adjustment coefficients of the preset average feedback satisfaction and the market position matching difficulty respectively.

[0028] In a second aspect, the present application discloses a job intention setting method using AI technology. This method is applicable to the job intention setting system using AI technology as described above. This method includes:

[0029] Collecting the initial job intention and the corresponding initial job information based on a preset job questionnaire;

[0030] Using AI technology to extract the position vectors of actual positions in a preset position pool, and reorganizing the position vectors based on the initial job intention and the corresponding initial job information to generate virtual positions; wherein, multiple actual positions are stored in the position pool, the position vector is used to represent the actual position information of the actual position, and the virtual position is the virtual position information based on the position vector and used to update the job intention.

[0031] Based on the feedback of the job seeker on the virtual position, updating the job intention and generating a corresponding job information completion instruction, and generating a new job intention and the corresponding job information based on the completed job information; wherein, the job information completion instruction is used to prompt the job seeker to complete the job information.

[0032] Repeatedly utilize AI technology to perform n rounds of setting updates. The setting update is based on the nth round of job seeking intention and the corresponding nth round of job seeking information obtained from the nth round of setting updates, output the nth round of virtual positions, update the (n + 1)th round of job seeking intention and the corresponding (n + 1)th round of job seeking information based on the feedback of the job seeker on the nth round of virtual positions, and when the (n + 1)th round of job seeking intention meets the preset job seeking intention satisfaction threshold, output the (n + 1)th round of job seeking intention and the corresponding (n + 1)th round of job seeking information; wherein, the job seeking intention satisfaction threshold is generated based on n rounds of setting updates.

[0033] Output the (n + 1)th round of job seeking intention and the corresponding (n + 1)th round of job seeking information, and use them for recommending the actual positions from the position pool based on the preset position recommendation.

[0034] Beneficial effects: The job seeking intention setting system and method using AI technology in this application achieve more accurate job seeking intention setting. The initial setting module collects information through a preset questionnaire, providing a basis for subsequent processes. The virtual position output module generates virtual positions by recombining position vectors based on the initial information, breaking the limitation of relying only on actual positions. The setting update module continuously optimizes the job seeking intention according to the feedback of the job seeker on the virtual positions, iterating multiple times until the satisfaction threshold is met. Based on the cooperation of multiple modules, dynamic update, and utilization of virtual positions, it avoids the drawbacks of setting job seeking intentions solely relying on personal information, reduces the risk of personal information leakage, and also solves the problem that it is difficult for actual positions to match job seeking intentions, improving the quality of job seeking intention setting, providing more job recommendations that meet the expectations of job seekers, and also improving the enterprise recruitment efficiency. Description of the Drawings

[0035] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0036] Figure 1 It is the structural block diagram of the job seeking intention setting system using AI technology provided by the embodiment of the present application.

[0037] Figure 2 It is the flow block diagram of the job seeking intention setting method using AI technology provided by the embodiment of the present application. Detailed Embodiments

[0038] The technical solutions in the embodiments of the present application will be described clearly and completely below. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0039] In this article, the term "including" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, the elements defined by the statement "including..." do not exclude the existence of additional identical elements in the process, method, article or device including the said elements.

[0040] The first aspect of this embodiment discloses a job intention setting system using AI technology as shown in Figure 1 The system includes an initial setting module for collecting initial job intentions and corresponding initial job information, a setting update module for updating job intentions, a virtual job output module for outputting virtual positions, and a setting output module for outputting final job intentions.

[0041] The initial setting module collects the initial job hunting intention and the corresponding initial job hunting information based on a preset job hunting questionnaire and transmits them to the virtual job output module; the virtual job output module extracts job vectors for actual jobs in a preset job pool using AI technology, reorganizes the job vectors based on the initial job hunting intention and the corresponding initial job hunting information to generate virtual jobs and transmits them to the setting update module. There are multiple actual jobs stored in the job pool, and the job vectors are used to represent the actual job information of the actual jobs. The virtual jobs are virtual job information based on the job vectors and are used to update the job hunting intention; the setting update module updates the job hunting intention based on the feedback of the job seeker on the virtual job and generates a corresponding job hunting information completion instruction, generates a new job hunting intention and the corresponding job hunting information based on the completed job hunting information. The job hunting information completion instruction is used to prompt the job seeker to complete the job hunting information; the virtual job output module and the setting update module are repeatedly run using AI technology for n rounds of setting updates, where n is a positive integer. This setting update is based on the nth round of job hunting intention and the corresponding nth round of job hunting information obtained from the nth round of setting updates, outputs the nth round of virtual jobs, and updates the (n + 1)th round of job hunting intention and the corresponding (n + 1)th round of job hunting information based on the feedback of the job seeker on the nth round of virtual jobs. When the (n + 1)th round of job hunting intention meets the preset job hunting intention satisfaction threshold, the (n + 1)th round of job hunting intention and the corresponding (n + 1)th round of job hunting information are transmitted to the setting output module. The job hunting intention satisfaction threshold is generated based on n rounds of setting updates; the setting output module outputs the (n + 1)th round of job hunting intention and the corresponding (n + 1)th round of job hunting information to a preset job recommendation module, and the job recommendation module is used to recommend actual jobs based on the job pool.

[0042] It should be noted that this embodiment uses existing AI technologies, such as natural language processing technology, to implement the setting of job hunting intentions. Moreover, the job recommendation module in this embodiment can be any existing job recommendation method, as long as it can process the (n + 1)th round of job hunting intention and the corresponding (n + 1)th round of job hunting information output by the setting output module. This text does not limit it here. This embodiment accurately sets the job hunting intention based on the iteration of virtual jobs, providing accurate data reference for any subsequent job recommendation method.

[0043] It can be understood that existing job recommendations collect a large amount of personal information of users in the early stage, which leads to problems in personal information security. The job hunting information completion instruction designed in this embodiment aims to collect as little personal information of users as possible to avoid problems in personal information security. It should be noted that the method of generating the job hunting information completion instruction in this embodiment can, but is not limited to, using the generation technology in existing AI technologies to generate the information completion content based on the updated job hunting intention. The content to be completed can, but is not limited to, professional qualification certificates, social security records, etc.

[0044] Through the above, this embodiment realizes a more precise job intention setting. The initial setting module collects information through a preset questionnaire, providing a basis for subsequent processes. The virtual job output module generates virtual jobs by reorganizing job vectors based on the initial information, breaking the limitation of relying only on actual jobs. The setting update module continuously optimizes the job intention according to the job seeker's feedback on the virtual jobs, iterating multiple times until the satisfaction threshold is met. By means of the cooperation of multiple modules, dynamic update, and the use of virtual jobs, it avoids the drawbacks of setting job intentions solely relying on personal information, reduces the risk of personal information leakage, and also solves the problem that it is difficult for actual jobs to match job intentions, improving the quality of job intention setting, providing more job recommendations that meet the expectations of job seekers, and also improving the enterprise recruitment efficiency.

[0045] Specifically, the extraction of job vectors includes:

[0046] Extract multiple job features of each actual job in the job pool to form a feature vector; among them, the job features are calculated from the corresponding initial weights and original values.

[0047] Through the above, this embodiment realizes the effective quantification and characteristic expression of actual job information by extracting multiple job features of actual jobs in the job pool to form a feature vector and calculating job features through initial weights and original values, thereby providing more accurate and representative basic data for subsequent virtual job generation, and realizing a more detailed reflection of the characteristics of actual jobs. The initial weights set based on the common knowledge of those skilled in the art can highlight key job features, making the generated virtual jobs better fit the core information of actual jobs, so as to better match the needs of job seekers and job requirements in the process of virtual job generation and job intention setting, and improve the accuracy and reliability of the entire job intention setting system.

[0048] Specifically, the generation of virtual jobs includes:

[0049] Obtain each job feature in the feature vector to get the corresponding initial weight and original value, generate a corresponding dynamic factor for each job feature in combination with the initial job intention and the corresponding initial job information, calculate the virtual job feature corresponding to the job feature based on the initial weight, dynamic factor, and original value, and obtain the corresponding virtual feature vector based on the virtual job feature. The virtual feature vector is used to represent the virtual job.

[0050] As a preferred implementation manner of this embodiment, the dynamic factor is generated using the dynamic factor calculation formula, and the dynamic factor calculation formula is:

[0051]

[0052] Wherein, is the initial weight of the job feature, θj is the dynamic factor adjustment weight obtained by combining the initial job search intention and the corresponding initial job search information. This dynamic factor adjustment weight can be obtained based on the existing semantic analysis and machine learning models to evaluate the relevance between the initial job search intention and the job characteristics, as well as the importance of the job characteristics in the job vector, ω j is the calculated dynamic factor.

[0053] It should be noted that in this embodiment, the method for calculating the virtual job characteristics can be, but is not limited to, weighted summing the original values using the dynamic factor.

[0054] By the above, this embodiment uses the method of generating dynamic factors for job characteristics by combining the initial job search intention and the initial job search information, and calculating the virtual job characteristics based on the initial weight, dynamic factor, and original value, to achieve the personalization and intelligence of virtual job generation, and to adjust the job characteristics according to the situation of the job seeker to generate a virtual job that better meets their expectations. In a simple example, if a job seeker has special requirements for a certain type of skill, the dynamic factor will strengthen the manifestation of relevant job characteristics in the virtual job, making the virtual job more targeted, better guiding the job seeker to clarify their job search intention, providing more targeted feedback to the job seeker during the setting update process, thereby improving the accuracy of job search intention setting and meeting the job seeker's pursuit of an ideal job.

[0055] Specifically, the generation of the virtual job further includes:

[0056] Obtaining the virtual correlation degree between virtual job characteristics based on the correlation degree of job characteristics. When the virtual correlation degree is greater than or equal to the preset virtual correlation degree threshold, the calculation of the virtual job characteristics is updated to be calculated based on the initial weight, dynamic factor, original value, virtual job characteristics corresponding to the virtual correlation degree, and the virtual correlation degree; wherein, the correlation degree is obtained based on the preset correlation relationship of job characteristics.

[0057] It should be noted that the correlation degree of the job characteristics in this embodiment can be an empirical value set based on the common knowledge known to those skilled in the art. Exemplarily, within a reasonable range, the correlation degree between job salary and job experience requirements is higher than the correlation degree between job salary and working hours.

[0058] Through the above, this embodiment utilizes the virtual correlation degree between virtual job characteristics obtained based on the job characteristic correlation degree, and updates the calculation method of virtual job characteristics when the virtual correlation degree meets the conditions, achieving the optimization of virtual job characteristics, thereby making full use of the correlation relationship between characteristics and making the generated virtual jobs more logical and reasonable. In a simple example, when two job characteristics are closely correlated, a change in one characteristic will affect the presentation of the other characteristic in the virtual job, thus avoiding the isolated calculation of virtual job characteristics and ensuring that the virtual job can more truly reflect the comprehensive characteristics of the actual job. During the job intention setting process, it provides a more comprehensive and accurate reference for job seekers, improving the effectiveness of virtual job updates for job intention updates, and further enhancing the quality of job intention setting.

[0059] Specifically, when performing the (n + 1)-th round of setting update, when the virtual job output module generates the (n + 1)-th round of virtual jobs, it adjusts the dynamic factor based on the feedback of the previous n rounds. The adjustment is as follows: collect the feedback satisfaction of the job seekers in the n-th round for each virtual job characteristic, obtain the preset feedback adjustment coefficient, and calculate the adjusted dynamic factor based on the feedback satisfaction and the feedback adjustment coefficient.

[0060] In this embodiment, this embodiment utilizes the existing feedback collection technology to implement the feedback of job seekers on virtual jobs, such as semantic analysis technology, and realizes the corresponding quantification.

[0061] Through the above, this embodiment realizes the dynamic optimization of virtual job generation by adjusting the dynamic factor based on the feedback of the previous round during the setting update. By collecting the feedback satisfaction of job seekers on virtual job characteristics and combining the preset feedback adjustment coefficient to calculate the adjusted dynamic factor, the virtual job can continuously adapt to the feedback of job seekers, and thus continuously optimize the generation of virtual jobs according to the actual responses of job seekers. In a simple example, if a job seeker gives poor feedback on a certain virtual job characteristic, the dynamic factor adjustment in the next round will weaken the weight of this characteristic in the virtual job, making the virtual job more in line with the expectations of job seekers, providing more accurate guidance in subsequent job intention updates, and improving the accuracy of job intention setting and the satisfaction of job seekers.

[0062] Specifically, when performing the (n + 1)-th round of setting update, when the virtual job output module generates the (n + 1)-th round of virtual jobs, it determines whether there is a preset necessary original value based on the feedback of the previous n rounds. If so, it updates the calculation of the virtual job characteristics; otherwise, it does not update the calculation of the virtual job characteristics. Among them, the necessary original value is used to retain the necessary original job characteristics when generating the (n + 1)-th round of virtual jobs. The update of the calculation of the virtual job characteristics is as follows: obtain the preset feature retention degree parameter, and calculate the new virtual job characteristics based on the feature retention degree parameter, the necessary original value, the dynamic factor, and the original value.

[0063] With the above, in this embodiment, by determining whether there is a preset necessary original value during setting update and updating the calculation method of virtual position features accordingly, the reasonable retention and utilization of original position features are realized. It can be understood that when generating a virtual position, the preset feature retention degree parameter can ensure that key original position features are retained, avoiding the loss of important information due to over-optimization, so that the generated virtual position can not only reflect the personalized needs of job seekers but also maintain the connection with the actual position. In a simple example, for some core skills or key responsibilities, even after multiple rounds of adjustment, they can still be reflected in the virtual position, which helps job seekers better grasp the balance between the actual position and their own expectations during the job intention setting process, and improve the scientificity and practicality of job intention setting.

[0064] Specifically, the output of the (n + 1)-th round of job intention includes:

[0065] Collect the virtual position of the n-th round as the job intention I of the n-th round n , and collect the feedback feature r of the job seeker on the virtual position of the n-th round n,k , the learning and growth factor g of the job seeker n,k and the market dynamic factor m n,k ; where the learning and growth factor is obtained based on the change in the work experience of the job seeker during the job search period, and the market dynamic factor is obtained based on the change in the market position requirements and the corresponding number of positions of the job seeker during the job search period;

[0066] Then the calculation formula of the (n + 1)-th round of job intention I n+1 is:

[0067]

[0068] where γ1, γ2, and γ3 are the intention adjustment coefficients corresponding to the preset feedback feature, learning and growth factor, and market dynamic factor respectively.

[0069] With the above, in this embodiment, by collecting the virtual position of the n-th round, the job seeker feedback feature, the learning and growth factor, and the market dynamic factor of the job seeker, and calculating the job intention of the n-th round through the preset intention adjustment coefficient, the comprehensive consideration of the job intention is realized, achieving the technical effect of fully considering various factors affecting the job intention. Among them, the learning and growth factor reflects the change in the job seeker's own ability, and the market dynamic factor reflects the influence of the external environment. Combining these factors with the virtual position and the feedback feature can more comprehensively reflect the job intention of the job seeker at different stages. Exemplarily, when a certain industry in the market develops rapidly, the market dynamic factor will prompt the job intention to tilt towards this industry, so that the job intention setting is more in line with the actual situation, improving the comprehensiveness and accuracy of the job intention setting.

[0070] Specifically, the intention adjustment coefficient is adjusted based on the stability and influence corresponding to the feedback features, learning and growth factors, and market dynamic factors in the nth round of setting updates.

[0071] In a simple example, the stability and influence of the learning and growth factors are obtained based on the changes in the job seeker's professional qualification certificates, and the stability and influence of the market dynamic factors are obtained based on the industry prospects.

[0072] As a preferred implementation manner of this embodiment, this embodiment uses the general formula of the intention adjustment coefficient to calculate the intention adjustment coefficient of the (n + 1)th round. The general formula of this intention adjustment coefficient is:

[0073]

[0074] where γ x,n represents the intention adjustment coefficient of the nth round (i.e., γ 1,n , γ 2,n and γ 3,n ), St x,n is the value of the stability corresponding to γ x,n , Im x,n is the value of the influence corresponding to γ x,n , represents the sum of the products of the stability values and influence values corresponding to all the intention adjustment coefficients of the nth round, and γ x,n+1 is the calculated intention adjustment coefficient of the (n + 1)th round (i.e., γ 1,n+1 , γ 2,n+1 and γ 3,n+1 ).

[0075] Through the above, this embodiment realizes the adaptive optimization of intention adjustment, and realizes the flexible adjustment of the weights of various factors when calculating the job search intention according to the changes of different factors. For example, in a certain stage, the job seeker grows rapidly in learning, and the growth factor has high stability and great influence. Then, when calculating the job search intention, the intention adjustment coefficient corresponding to the learning and growth factor will increase, making it play a greater role in the update of the job search intention. Based on this adaptive adjustment mechanism, it can ensure that the calculation of the job search intention more accurately reflects the actual situation, improve the scientificity and adaptability of the job search intention setting, and provide a job search intention that is more in line with the current situation of the job seeker.

[0076] Specifically, the generation of the job search intention satisfaction threshold includes:

[0077] Calculating the average feedback satisfaction of the feedback satisfaction collected during the n rounds of setting updates and the market position matching difficulty coefficient D n ; among them, the market position matching difficulty coefficient is obtained based on the value of n and the number of virtual positions in the matching channel;

[0078] The calculation formula for the satisfaction threshold of job search intention in the (n + 1)-th round is as follows:

[0079]

[0080] where T0 is the preset initial satisfaction threshold of job search intention, T n is the satisfaction threshold of job search intention in the n-th round, and δ1 and δ2 are respectively the preset threshold adjustment coefficients of average feedback satisfaction and market job matching difficulty.

[0081] Through the above, in this embodiment, by calculating the average feedback satisfaction and market job matching difficulty coefficient in the setting update process of n rounds, and generating the satisfaction threshold of job search intention accordingly, a reasonable setting of the termination condition for job search intention setting is realized, so as to adjust the threshold according to the actual situation. Specifically, when the average feedback satisfaction is high and the market job matching difficulty is low, the threshold is appropriately increased to prompt the system to optimize the job search intention more accurately; conversely, the threshold is decreased to ensure that the job search intention can be set even in complex situations. Based on the dynamic generation of the threshold, the job search intention setting process is made more flexible, avoiding the problems of inaccurate or inefficient job search intention setting caused by a fixed threshold, and improving the practicality and reliability of the job search intention setting system.

[0082] In the second aspect of this embodiment, there is disclosed a job search intention setting method using AI technology as shown in Figure 2 . This method is applicable to the job search intention setting system using AI technology as described above. The method includes:

[0083] Collecting initial job search intention and corresponding initial job information based on a preset job search questionnaire;

[0084] Using AI technology to extract job vectors for actual jobs in a preset job pool, and recombining the job vectors based on the initial job search intention and corresponding initial job information to generate virtual jobs; where multiple actual jobs are stored in the job pool, and the job vector is used to represent the actual job information of the actual job, and the virtual job is virtual job information for updating the job search intention constituted based on the job vector;

[0085] Based on the feedback of the job seeker on the virtual job, updating the job search intention and generating a corresponding job information completion instruction, and generating a new job search intention and corresponding job information based on the completed job information; where the job information completion instruction is used to prompt the job seeker to complete the job information;

[0086] Repeatedly use AI technology to perform n rounds of setting updates. The setting update is based on the nth round of job seeking intention and the corresponding nth round of job seeking information obtained from the nth round of setting updates, output the nth round of virtual positions, and update the (n + 1)th round of job seeking intention and the corresponding (n + 1)th round of job seeking information based on the feedback of the job seeker on the nth round of virtual positions. When the (n + 1)th round of job seeking intention meets the preset job seeking intention satisfaction threshold, output the (n + 1)th round of job seeking intention and the corresponding (n + 1)th round of job seeking information; among them, the job seeking intention satisfaction threshold is generated based on n rounds of setting updates.

[0087] Output the (n + 1)th round of job seeking intention and the corresponding (n + 1)th round of job seeking information, and use them for the recommendation of actual positions from the position pool based on the preset position recommendation.

[0088] It should be noted that the job seeking intention setting method using AI technology in this embodiment corresponds to the aforementioned job seeking intention setting system using AI technology. Therefore, the content not specifically described in the job seeking intention setting method using AI technology in this embodiment, which may but is not limited to function definitions, working principles, technical effects, etc., can refer to the records in the aforementioned job seeking intention setting system using AI technology, and will not be elaborated in this text.

[0089] In summary, the job seeking intention setting system and method using AI technology in this embodiment achieve more accurate job seeking intention setting. The initial setting module collects information through a preset questionnaire, providing a basis for subsequent processes. The virtual position output module generates virtual positions by recombining position vectors based on the initial information, breaking the limitation of relying only on actual positions. The setting update module continuously optimizes the job seeking intention according to the feedback of the job seeker on the virtual positions, and iterates multiple times until the satisfaction threshold is met. By means of the cooperation of multiple modules, dynamic update, and the use of virtual positions, it avoids the drawbacks of setting job seeking intentions solely relying on personal information, reduces the risk of personal information leakage, and also solves the problem that it is difficult for actual positions to match job seeking intentions, improving the quality of job seeking intention setting, providing more job recommendations that meet the expectations of job seekers, and also improving the enterprise recruitment efficiency.

[0090] In the embodiments provided in the present application, it should be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code, or any appropriate combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processor, controller, microcontroller, microprocessor, or other electronic units designed to implement the functions described herein, or a combination thereof. For software implementation, part or all of the processes of the embodiments can be completed by instructing the relevant hardware through a computer program. When implemented, the above program can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. The computer-readable storage medium includes computer storage media and communication media, where the communication media includes any medium that facilitates the transmission of a computer program from one place to another. The storage media can be any available medium that can be accessed by a computer. The computer-readable storage medium can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM, or other optical disk storage, magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer.

[0091] Finally, it should be noted that the above are only the preferred embodiments of the present application and are not intended to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A job intention setting system using AI technology, characterized in that, The system includes an initial setting module for collecting initial job search intentions and corresponding initial job search information, a setting update module for updating job search intentions, a virtual job output module for outputting virtual jobs, and a setting output module for outputting final job search intentions; The initial setting module collects the initial job search intention and the corresponding initial job search information based on a preset job search questionnaire and transmits them to the virtual job output module; the virtual job output module extracts job vectors for actual jobs using AI technology in a preset job pool, reorganizes the job vectors based on the initial job search intention and the corresponding initial job search information to generate virtual jobs and transmits them to the setting update module. A plurality of actual jobs are stored in the job pool, and the job vector is used to represent the actual job information of the actual job. The virtual job is virtual job information based on the job vector and used to update the job search intention; The setting update module updates the job search intention based on the feedback of the job seeker on the virtual job and generates a corresponding job search information completion instruction. Based on the completed job search information, a new job search intention and corresponding job search information are generated. The job search information completion instruction is used to prompt the job seeker to complete the job search information; the virtual job output module and the setting update module are repeatedly run using AI technology for n rounds of setting updates, where n is a positive integer. This setting update is based on the nth round of job search intention and the corresponding nth round of job search information obtained from the nth round of setting updates to output the nth round of virtual jobs. Based on the feedback of the job seeker on the nth round of virtual jobs, the (n + 1)th round of job search intention and the corresponding (n + 1)th round of job search information are obtained. When the (n + 1)th round of job search intention meets the preset job search intention satisfaction threshold, the (n + 1)th round of job search intention and the corresponding (n + 1)th round of job search information are transmitted to the setting output module. The job search intention satisfaction threshold is generated based on n rounds of setting updates; The setting output module outputs the (n + 1)th round of job search intention and the corresponding (n + 1)th round of job search information to a preset job recommendation module, and the job recommendation module is used to recommend the actual jobs based on the job pool.

2. The job intention setting system using AI technology according to claim 1, characterized in that The extraction of the job vector includes: Extracting multiple job characteristics of each actual job in the job pool to form a feature vector; among them, the job characteristic is calculated from the corresponding initial weight and the original value.

3. The job intention setting system using AI technology according to claim 2, characterized in that, The generation of the virtual job includes: Obtaining each job characteristic in the feature vector to obtain the corresponding initial weight and the original value, combining the initial job search intention and the corresponding initial job search information to generate a corresponding dynamic factor for each job characteristic, calculating the virtual job characteristic corresponding to the job characteristic based on the initial weight, the dynamic factor, and the original value, and obtaining a corresponding virtual feature vector based on the virtual job characteristic. The virtual feature vector is used to represent the virtual job.

4. The job intention setting system using AI technology according to claim 3, characterized in that, The generation of the virtual job further includes: Based on the correlation degree of the job characteristics, obtain the virtual correlation degree between the virtual job characteristics. When the virtual correlation degree is greater than or equal to the preset virtual correlation degree threshold, the calculation of the virtual job characteristics is updated to be calculated based on the initial weight, the dynamic factor, the original value, the virtual job characteristics corresponding to the virtual correlation degree, and the virtual correlation degree; wherein, the correlation degree is obtained based on the preset correlation relationship of the job characteristics.

5. The job intention setting system using AI technology according to claim 3, characterized in that, When performing the (n + 1)-th round of setting update, when generating the (n + 1)-th round of virtual jobs, the virtual job output module adjusts the dynamic factor based on the feedback of the previous n rounds. The adjustment is as follows: Collect the feedback satisfaction of the n-th round of job seekers for each of the virtual job characteristics, and obtain the preset feedback adjustment coefficient, and calculate the adjusted dynamic factor based on the feedback satisfaction and the feedback adjustment coefficient.

6. The job intention setting system using AI technology according to claim 3, characterized in that, When performing the (n + 1)-th round of setting update, when generating the (n + 1)-th round of virtual jobs, the virtual job output module determines whether there is a preset necessary original value based on the feedback of the previous n rounds. If so, update the calculation of the virtual job characteristics; otherwise, do not update the calculation of the virtual job characteristics; wherein, the necessary original value is used to retain the necessary original job characteristics when generating the (n + 1)-th round of virtual jobs, and the update of the calculation of the virtual job characteristics is as follows: Obtain the preset feature retention degree parameter, and calculate the new virtual job characteristics based on the feature retention degree parameter, the necessary original value, the dynamic factor, and the original value.

7. The job intention setting system using AI technology according to claim 1, characterized in that The output of the (n + 1)-th round of job intention includes: Collect the virtual positions in the nth round as the job search intention I in the nth round n , and collect the feedback characteristics r of the job seeker on the virtual positions in the nth round n,k , the learning and growth factors g of the job seeker n,k and the market dynamics factors m n,k ; wherein, the learning and growth factors are obtained based on the changes in the work experience of the job seeker during the job search, and the market dynamics factors are obtained based on the changes in the market position requirements and the corresponding number of positions of the job seeker during the job search; Then the job hunting intention I in the (n + 1)-th round n+1 is calculated as follows: Among them, γ1, γ2, and γ3 are the intention adjustment coefficients corresponding to the preset feedback characteristics, learning and growth factors, and market dynamic factors respectively.

8. The job intention setting system using AI technology according to claim 7, characterized in that, The intention adjustment coefficient is adjusted based on the stability and influence corresponding to the feedback characteristics, the learning and growth factors, and the market dynamic factors in the (n)-th round of setting update.

9. The job intention setting system using AI technology according to claim 1, characterized in that The generation of the job intention satisfaction threshold includes: Calculate the average feedback satisfaction of the feedback satisfaction during the setting update process for n rounds of collection and the market position matching difficulty coefficient D n ; wherein, the market position matching difficulty coefficient is obtained based on the value of n and the number of virtual positions in the matching channel; The calculation formula for calculating the job intention satisfaction threshold of the (n + 1)-th round is: Among them, T0 is the preset initial satisfaction threshold of job hunting intention, and T n is the satisfaction threshold of job hunting intention in the nth round, and δ1 and δ2 are the threshold adjustment coefficients of the preset average feedback satisfaction and the market job matching difficulty respectively.

10. A job intention setting method using AI technology, which is applicable to the job intention setting system using AI technology as described in any one of claims 1-9, characterized in that, This method includes: Collect the initial job intention and the corresponding initial job information based on the preset job survey questionnaire; Use AI technology to extract job vectors for actual jobs in the preset job pool, and reorganize the job vectors based on the initial job intention and the corresponding initial job information to generate virtual jobs; wherein, multiple actual jobs are stored in the job pool, the job vector is used to represent the actual job information of the actual job, and the virtual job is the virtual job information based on the job vector and used to update the job intention. Based on the feedback of the job seekers on the virtual jobs, update the job intention and generate the corresponding job information completion instruction, and generate a new job intention and the corresponding job information based on the completed job information; wherein, the job information completion instruction is used to prompt the job seekers to complete the job information. Repeatedly use AI technology to perform n rounds of setting updates. The setting updates are based on the nth round of job search intentions and the corresponding nth round of job search information obtained from the nth round of setting updates, and the nth round of virtual positions are output. Based on the feedback of the job seeker on the nth round of virtual positions, the (n + 1)th round of job search intentions and the corresponding (n + 1)th round of job search information are updated. When the (n + 1)th round of job search intentions meet the preset job search intention satisfaction threshold, the (n + 1)th round of job search intentions and the corresponding (n + 1)th round of job search information are output; wherein, the job search intention satisfaction threshold is generated based on n rounds of setting updates; Output the (n + 1)th round of job search intentions and the corresponding (n + 1)th round of job search information, and use them to recommend the actual positions from the position pool based on the preset position recommendations.

Images