A data processing method, apparatus, electronic device, and storage medium

Abstract

The present application discloses a data processing method, device, electronic device, and storage medium. Through the present application, in the scenario of recommending positions to job seekers, not only the matching between the job seeker and the position is taken into account, but also the matching between the job seeker and the job recruiter with respect to the position is taken into account. In this way, the possibility of the job seeker being interested in the recommended position and the possibility of the job recruiter being satisfied with the job seeker's conditions for the position can be increased as much as possible. For example, the probability of the job seeker viewing the position information when the position is recommended to the job seeker can be increased, the probability of the job seeker submitting his / her resume to the position when the job seeker views the position information can be increased, and the probability of the job recruiter returning positive feedback information to the job seeker regarding the position when the job seeker submits his / her resume to the position can be increased.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a data processing method, device, electronic device, and storage medium. Background Art

[0002] With the continuous growth of the number of enterprises in various industries and the gradual upgrading of various industries, the focus of competition among major enterprises has shifted to the competition for talent. Therefore, the recruitment of talent has become a top priority for major enterprises. Secondly, with the rapid development of the Internet, online recruitment has become an efficient and convenient recruitment method.

[0003] However, the current recruitment method has a low matching degree between job seekers and companies, resulting in low job search efficiency for job seekers on recruitment websites. Over time, this will cause recruitment websites to lose job seekers. Summary of the Invention

[0004] The present application provides a data processing method, device, electronic device, and storage medium.

[0005] In a first aspect, the present application provides a data processing method, the method comprising:

[0006] Obtaining job application information of job seekers; and obtaining job information of each of multiple positions in the recruitment status;

[0007] Based on the job application information of the job seeker and the position information of each position, respectively predicting a first probability of each position, a second probability of each position, and a third probability of each position, wherein the first probability includes the probability that the job seeker views the position information of the position if the position is recommended to the job seeker, the second probability includes the probability that the job seeker submits the resume of the position if the job seeker views the position information, and the third probability includes the probability that the job seeker returns positive feedback information to the job seeker regarding the position if the job seeker submits the resume of the position;

[0008] Obtaining a recommendation score for each position for the job seeker based on the first probability of each position, the second probability of each position, and the third probability of each position;

[0009] At least one of the plurality of positions is recommended to the job seeker based on the recommendation scores of the respective positions for the job seeker.

[0010] In an optional implementation, obtaining the recommendation score for each position for the job seeker based on the first probability of each position, the second probability of each position, and the third probability of each position includes:

[0011] Obtaining the probability that the job seeker is interested in each position based on the first probability of each position and the second probability of each position;

[0012] According to the probability that the job seeker is interested in each position and the third probability of each position, a recommendation score for each position for the job seeker is obtained.

[0013] In an optional implementation, obtaining the probability that the job seeker is interested in each position based on the first probability of each position and the second probability of each position includes:

[0014] For any one of the multiple positions, a product of the first probability of the position and the second probability of the position is calculated, and a probability that the job seeker is interested in the position is obtained according to the product.

[0015] In an optional implementation, obtaining a recommendation score for each position for the job seeker based on the probability that the job seeker is interested in each position and the third probability of each position includes:

[0016] For any one of the plurality of positions, determining a first sequence number for the probability of the job seeker being interested in the position in a descending order of the probability of the job seeker being interested in each position; and determining a second sequence number for the third probability of each position in a descending order of the third probability of each position;

[0017] A recommendation score of the position for the job seeker is obtained according to the probability that the job seeker is interested in the position, the first sequence number, and the second sequence number.

[0018] In an optional implementation, obtaining a recommendation score of the position for the job seeker based on the probability of the job seeker being interested in the position, the first sequence number, and the second sequence number includes:

[0019] Obtain the number of positions that need to be recommended for the job seeker;

[0020] Calculating the difference between the first sequence number and the second sequence number;

[0021] A recommendation score of the position for the job seeker is obtained based on the quantity, the difference, and the probability that the job seeker is interested in the position.

[0022] In an optional implementation, obtaining a recommendation score for the job seeker based on the number, the difference, and the probability that the job seeker is interested in the job seeker includes:

[0023] When the difference is greater than or equal to the number, obtaining a recommendation score for the job seeker based on the probability that the job seeker is interested in the job and the number;

[0024] or,

[0025] When the difference is smaller than the number, the absolute value of the difference is obtained, and the recommendation score of the position for the job seeker is obtained based on the probability that the job seeker is interested in the position and the absolute value of the difference.

[0026] In an optional implementation, the process of predicting the third probability of each position based on the job application information of the job seeker and the position information of each position includes:

[0027] For any one of the multiple positions, the position information of the position and the job-seeking information of the job seeker are input into a trained feedback rate model, so that the feedback rate model processes the position information of the position and the job-seeking information of the job seeker to obtain a third probability of the position.

[0028] In an optional implementation, the method further includes:

[0029] Acquire at least one sample data set, the sample data set including sample job application information of a sample job seeker, sample job position information of a sample position, and sample feedback information returned by a sample recruiter of the sample position to the sample job seeker for the sample position when the sample job seeker submits a resume for the sample position;

[0030] Training the model according to at least one sample data set until the parameters in the model converge, thereby obtaining the feedback rate model;

[0031] The time interval between the time when the sample recruiter of the sample position in the sample data set returns sample feedback information to the sample job seeker for the sample position and the current time is less than the preset time interval.

[0032] In a second aspect, the present application provides a data processing device, comprising:

[0033] The first acquisition module is used to acquire job application information of job seekers; and acquire job information of each position in a plurality of positions in the recruitment state;

[0034] a prediction module for predicting, based on the job application information of the job applicant and the position information of each position, a first probability of each position, a second probability of each position, and a third probability of each position, respectively, wherein the first probability includes the probability that the job applicant views the position information of the position if the position is recommended to the job applicant, the second probability includes the probability that the job applicant submits the resume of the position if the job applicant views the position information, and the third probability includes the probability that the job applicant returns positive feedback information to the job applicant regarding the position if the job applicant submits the resume of the position;

[0035] A second acquisition module is configured to acquire a recommendation score for each position for the job seeker based on the first probability of each position, the second probability of each position, and the third probability of each position;

[0036] The recommendation module is configured to recommend at least one of the plurality of positions to the job seeker based on the recommendation scores of the respective positions for the job seeker.

[0037] In an optional implementation, the second acquisition module includes:

[0038] A first acquisition submodule is configured to acquire the probability that the job seeker is interested in each position based on the first probability of each position and the second probability of each position;

[0039] The second acquisition submodule is configured to acquire a recommendation score for each position for the job seeker based on the probability that the job seeker is interested in each position and the third probability of each position.

[0040] In an optional implementation, the first acquisition submodule is specifically configured to: for any one of the multiple positions, calculate the product between the first probability of the position and the second probability of the position, and obtain the probability that the job seeker is interested in the position based on the product.

[0041] In an optional implementation, the second acquisition submodule includes:

[0042] a determining unit configured to determine, for any one of the plurality of positions, a first sequence number of the probability of the job seeker being interested in the position in a descending order of the probabilities of the job seeker being interested in the respective positions; and to determine a second sequence number of the third probability of the position in a descending order of the third probabilities of the respective positions;

[0043] An acquiring unit is configured to acquire a recommendation score of the position for the job seeker based on the probability that the job seeker is interested in the position, the first sequence number, and the second sequence number.

[0044] In an optional implementation, the acquiring unit includes:

[0045] A first obtaining subunit is used to obtain the number of positions that need to be recommended to the job seeker;

[0046] a calculation subunit, configured to calculate a difference between the first sequence number and the second sequence number;

[0047] The second obtaining subunit is configured to obtain a recommendation score of the position for the job seeker based on the quantity, the difference, and the probability that the job seeker is interested in the position.

[0048] In an optional implementation, the second acquiring subunit is specifically configured to:

[0049] When the difference is greater than or equal to the number, obtaining a recommendation score for the job seeker based on the probability that the job seeker is interested in the job and the number;

[0050] or,

[0051] When the difference is smaller than the number, the absolute value of the difference is obtained, and the recommendation score of the position for the job seeker is obtained based on the probability that the job seeker is interested in the position and the absolute value of the difference.

[0052] In an optional implementation, the prediction module includes:

[0053] The input submodule is used to input the job information of any one of the multiple positions and the job application information of the job seeker into the trained feedback rate model, so that the feedback rate model processes the job information of the position and the job application information of the job seeker to obtain a third probability of the position.

[0054] In an optional implementation, the prediction module further includes:

[0055] a third acquisition submodule, configured to acquire at least one sample data set, the sample data set including sample job application information of a sample job seeker, sample job position information of a sample position, and sample feedback information returned by a sample recruiter of the sample position to the sample job seeker for the sample position when the sample job seeker submits a resume for the sample position;

[0056] A training submodule, configured to train the model according to at least one sample data set until the parameters in the model converge, thereby obtaining the feedback rate model;

[0057] The time interval between the time when the sample recruiter of the sample position in the sample data set returns sample feedback information to the sample job seeker for the sample position and the current time is less than the preset time interval.

[0058] In a third aspect, the present application shows an electronic device, which includes: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the data processing method as described in any aspect.

[0059] In a fourth aspect, the present application illustrates a non-temporary computer-readable storage medium, which, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute the data processing method as described in any one of the aspects.

[0060] In a fifth aspect, the present application illustrates a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device is enabled to perform the data processing method as described in any one of the aspects.

[0061] The technical solution provided by this application may have the following beneficial effects:

[0062] In the present application, job application information of a job seeker is obtained. Also, job information of each position in a plurality of positions in a recruitment state is obtained. Based on the job application information of the job seeker and the job information of each position, a first probability of each position, a second probability of each position, and a third probability of each position are predicted respectively. The first probability includes the probability that the job seeker views the job information of the position when the position is recommended to the job seeker. The second probability includes: the probability that the job seeker submits the job information of the position when the job seeker views the job information of the position. The third probability includes: the probability that the job seeker's recruiter returns positive feedback information to the job seeker regarding the position when the job seeker submits the job seeker's resume to the position. Based on the first probability of each position, the second probability of each position, and the third probability of each position, a recommendation score for each position for the job seeker is obtained. Based on the recommendation score for each position for the job seeker, at least one position from the plurality of positions is recommended to the job seeker.

[0063] Through this application, in the scenario of recommending positions to job seekers, not only the matching between job seekers and positions is taken into account, but also the matching between job seekers and job recruiters regarding positions is taken into account. In this way, the possibility of job seekers being interested in the recommended positions and the possibility of job recruiters being satisfied with the job seekers' conditions for the positions can be increased as much as possible. For example, the probability of job seekers viewing the job information of the position when a position is recommended to job seekers can be increased, the probability of job seekers submitting their resumes to the position when a job seeker views the job information of the position can be increased, and the probability of job recruiters returning positive feedback information to job seekers regarding the position when a job seeker submits their resumes to the position can be increased.

[0064] In this way, the operation of recommending jobs to job seekers can meet the needs of both job seekers and job recruiters as much as possible. This makes the operation of recommending jobs to job seekers generate real value, improve job seekers' job search efficiency, enhance their job search experience, and prevent job seekers from leaving the recruitment website. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a flowchart of the steps of a data processing method of the present application.

[0066] Figure 2 This is a structural block diagram of a data processing device of the present application.

[0067] Figure 3 It is a block diagram of an electronic device shown in this application.

[0068] Figure 4 It is a block diagram of an electronic device shown in this application. DETAILED DESCRIPTION

[0069] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0070] Major companies can publish the positions they need to recruit on recruitment websites. Job seekers can search for positions on the website and submit their resumes to the positions. After receiving the resumes submitted by job seekers for the positions they have published, the company can evaluate the resumes of the job seekers. If the resumes of the job seekers meet the requirements, the company can contact the job seekers for written tests and interviews, etc.

[0071] However, the inventors discovered that the following problems exist in online recruitment:

[0072] Since there are a large number of companies that need to recruit and each company has a large number of positions that need to be recruited, the number of positions that need to be recruited posted on recruitment websites is often huge. As a result, it is very difficult for job seekers to search for positions that they are interested in among the massive number of positions posted on recruitment websites. This will reduce the job search efficiency of job seekers on recruitment websites, thereby reducing the job search experience of job seekers on recruitment websites, which may cause job seekers to stop using recruitment websites, resulting in the loss of job seekers from recruitment websites.

[0073] To this end, the need to prevent recruitment websites from losing job seekers has been raised.

[0074] In order to achieve the goal of avoiding the loss of job seekers on recruitment websites, the job search experience of job seekers on recruitment websites can be improved.

[0075] In order to achieve the purpose of improving the job-seeking experience of job seekers on recruitment websites, the job-seeking efficiency of job seekers on recruitment websites can be improved.

[0076] In order to achieve the purpose of improving the job-hunting efficiency of job seekers on recruitment websites, the difficulty of job seekers in obtaining positions that they are interested in on the recruitment websites can be reduced.

[0077] In order to reduce the difficulty for job seekers to find positions of interest on recruitment websites, in one method, the recruitment website can obtain the job seeker's job information, such as the job seeker's age, gender, region, education level or major, etc., and then automatically screen the positions of interest to the job seeker from a large number of positions published on the recruitment website based on the job seeker's job information, and recommend the screened positions of interest to the job seeker.

[0078] In this way, job seekers can obtain positions recommended by the recruitment website without having to manually search for positions on the recruitment website, thereby reducing the difficulty for job seekers to obtain positions they are interested in on the recruitment website.

[0079] However, after statistical analysis of the above methods, the inventors found that: for the job-seeking scenario, at least job seekers and recruiters (enterprises) are involved, that is, at least applicants and recruiters are involved.

[0080] Although the above method can recommend the positions that the job seekers are interested in to the job seekers, it reduces the difficulty for the job seekers to find the positions that they are interested in on the recruitment website.

[0081] However, the inventors discovered that in a recruitment scenario, an important goal is to facilitate a two-way match between job seekers and recruiters. For example, not only does it need to be that the positions recommended to job seekers are positions that the job seekers are interested in, but it also needs to be that the recruiters of the positions are satisfied with the qualifications of the job seekers to whom the positions are recommended. In this way, recommending positions to job seekers can meet both the needs of the job seekers and the needs of the recruiters of the positions.

[0082] However, in a recruitment scenario, when recommending a position to a job seeker, if one only refers to the job seeker's relevant information without referring to the employer's relevant information, it is often impossible to achieve the goal of "meeting both the job seeker's needs and the employer's needs."

[0083] For example, while a job seeker may be interested in a certain position, the recruiter may not be satisfied with the job seeker's qualifications. Therefore, even if the position is recommended to the job seeker and the job seeker submits a resume, the recruiter may not contact the job seeker for an interview or written test. This can lead to the job seeker receiving no positive feedback from the recruiter regarding the position after submitting their resume. This can cause the job seeker to feel like their resume has fallen on deaf ears, thus failing to achieve their job search goals. The recommended position has no real value. This can reduce the job seeker's job search efficiency on recruitment websites, thereby diminishing their job search experience. This can lead to job seekers abandoning the recruitment website, leading to job seeker loss.

[0084] In view of this, in the scenario of recommending positions to job seekers, there is a need to increase the possibility that job seekers will be satisfied with the recommended positions, and a need for job recruiters to be satisfied with the qualifications of job seekers who are recommended for the positions.

[0085] In order to achieve the goal of "increasing the possibility of job seekers being satisfied with the recommended positions and the need for job recruiters to be satisfied with the qualifications of job seekers who are recommended to the positions in the scenario of recommending positions to job seekers", in the scenario of recommending positions to job seekers, it is necessary to refer not only to the relevant circumstances of the job seekers but also to the relevant circumstances of the recruiters.

[0086] Specifically, see Figure 1 , shows a flow chart of a data processing method of the present application, which is applied to electronic devices, and the electronic devices may include a server of a job search website, etc.

[0087] The method includes:

[0088] In step S101, job-seeking information of a job seeker is obtained, and job information of each of a plurality of positions in the recruitment state is obtained.

[0089] The job-seeking information of a job-seeker includes at least one of the following: basic job-seeking information of the job-seeker, statistical job-seeking information of the job-seeker, and preferred job-seeking information of the job-seeker.

[0090] The basic job application information of a job seeker includes at least one of the following: the job seeker's gender, age, work experience, education background, university where the job seeker graduated, and major, etc.

[0091] The statistical job search information of job seekers includes at least one of the following: the job seeker's recent or long-term job click-through rate (for example, the ratio between the total number of positions for which the job seeker has viewed job information in the recommended positions and the total number of positions recommended to the job seeker, etc.), the job seeker's recent or long-term resume submission rate (the ratio between the total number of positions for which the job seeker has submitted resumes in the recommended positions and the total number of positions for which the job seeker has viewed job information in the recommended positions), and the job seeker's instant messaging initiation rate (the ratio between the number of target positions and the total number of positions for which the job seeker has viewed job information in the recommended positions, etc., the target positions include the positions in the recommended positions for which the job seeker communicates with the corresponding recruiter through instant messaging tools, etc.).

[0092] The job seeker's preferred job information includes at least one of the following: the job seeker's desired job position, desired position type, desired salary, desired company size, and desired promotion prospects, etc.

[0093] The job seeker's desired job location is the location where the job seeker wants to find a job. Job locations include "province-city-district / county-road-building" and so on.

[0094] Desired job types include "sales", "medical care", "security" and "cleaning", etc., and this application does not limit them.

[0095] Among them, all data in this application are obtained under the premise of authorization.

[0096] Job seekers include those who are browsing job openings or watching live recruitment broadcasts, etc.

[0097] The position information of a position includes at least one of the following: basic position information of the position, statistical position information of the position, and preferred position information of the position.

[0098] The basic position information of a position includes at least one of the following: the corporate attributes of the position recruiter (nature of the company and industry, etc.), the job title of the position, the job location of the position, the salary and benefits of the position, the name of the position recruiter, the name of the department of the position recruiter, the position type of the position, the welfare benefits of the position, the number of people in the position recruiter, the comment information of the position and the promotion prospects of the position, etc.

[0099] The statistical position information of a position includes at least one of the following: the reading rate of resumes by recruiters for recent or long-term positions (the ratio between the total number of resumes viewed by the recruiter of the position among the resumes received for the position and the total number of resumes received by the recruiter for the position), the total number of resumes received by the recruiter for the position, and the response rate of resumes by recruiters for recent or long-term positions (the ratio between the total number of resumes of corresponding job seekers to which the recruiter of the position replies among the resumes received for the position and the total number of resumes received by the recruiter for the position).

[0100] The preferred job information of a job position includes at least one of the following: preferred job requirements of the job position, preferred gender, preferred work experience, preferred education level, preferred major, and preferred age, etc.

[0101] The job application information of the job seeker and the position information of the position can be used to determine the cross-information and cross-statistical information between the job seeker and the position, which is convenient for subsequent screening of positions that need to be recommended to the job seeker, so as to improve the accuracy of the recommendation (which can meet both the job seeker's requirements for the position and the recruiter's requirements for the job seeker's conditions, etc.).

[0102] The cross-information may include whether the job applicant's desired job location matches the actual job location of the position.

[0103] The cross-statistical information may include whether the job applicant's work experience matches the work experience required for the position and whether the job applicant's academic qualifications match the academic qualifications required for the position.

[0104] The job information of the position can be provided directly to the electronic device by the job recruiter. The recruiter can freely configure the job information of the position, which can increase the recruiter's freedom in recruitment and the recruiter's participation.

[0105] In this way, for any one of the multiple positions, the position information provided in advance by the recruiter of the position can be obtained. The above operation is performed similarly for each of the other positions in the multiple positions.

[0106] In step S102, based on the job application information of the job applicant and the job information of each position, a first probability, a second probability, and a third probability are predicted for each position. The first probability includes the probability that the job applicant will view the job information if the position is recommended to the job applicant. The second probability includes the probability that the job applicant will submit their resume to the position if the job applicant views the job information. The third probability includes the probability that the job applicant will receive positive feedback from the job recruiter regarding the position if the job applicant submits their resume to the position.

[0107] In one embodiment of the present application, a viewing rate model may be trained in advance, which is used to obtain the probability that a job seeker views the job information of a job when a job seeker receives a recommended job.

[0108] The training process may include: obtaining at least one sample data set.

[0109] The sample data set includes sample job application information of sample job seekers, sample job information of sample positions, and the results of whether the sample job seekers viewed the job information of the sample positions when they received the recommended sample positions, wherein the results include whether the job information of the sample positions was viewed or whether the sample job seekers did not view the job information of the sample positions within a preset time after receiving the recommended sample positions.

[0110] The preset duration can be determined according to actual conditions, for example, it can include 1 minute, 2 minutes or 5 minutes, etc. This application does not limit this.

[0111] The model is then trained based on at least one sample data set until parameters in the model converge, thereby obtaining a viewing rate model.

[0112] The model may include: LR (Logistic Regression, logistic regression model) and the like.

[0113] When optimizing the view rate model later, you can refer to indicators such as AUC (Area Under Curve, the area under the ROC curve and the coordinate axis).

[0114] In this way, when predicting the first probability of each position based on the job applicant's job information and the job information of each position, for any one of the multiple positions, the job information of the position and the job applicant's job information can be input into the trained viewing rate model, so that the viewing rate model processes the job information of the position and the job applicant's job information to obtain the first probability of the position.

[0115] The same is true for each of the other positions in the multiple positions.

[0116] In another embodiment of the present application, a delivery rate model may be trained in advance, which is used to obtain the probability that a job seeker will deliver his / her resume to a position after viewing the position information of the position.

[0117] The training process may include: obtaining at least one sample data set.

[0118] The sample data set includes sample job application information of a sample job seeker, sample job information of a sample position, and the result of whether the sample job seeker submits the resume of the sample job seeker to the sample position after viewing the position information of the sample position, wherein the result includes submitting the resume of the sample job seeker to the sample position or not submitting the resume of the sample job seeker to the sample position within a preset time after the sample job seeker views the position information of the sample position, etc.

[0119] The preset duration can be determined according to actual conditions, for example, it can include 1 minute, 2 minutes or 5 minutes, etc. This application does not limit this.

[0120] The model is then trained based on at least one sample data set until the parameters in the model converge, thereby obtaining a delivery rate model.

[0121] Among them, the model may include: LR, etc.

[0122] When optimizing the delivery rate model later, you can refer to the AUC indicator, etc.

[0123] In this way, when predicting the second probability of each position based on the job applicant's job information and the job information of each position, for any one of the multiple positions, the job information of the position and the job applicant's job information can be input into the trained delivery rate model, so that the delivery rate model processes the job information of the position and the job applicant's job information to obtain the second probability of the position.

[0124] The same is true for each of the other positions in the multiple positions.

[0125] In another embodiment of the present application, a feedback rate model can be trained in advance to obtain the probability that the job recruiter returns positive feedback information to the job seeker (for example, the job recruiter proactively contacts the job seeker, etc.) after the job seeker submits a resume for the position.

[0126] The training process may include: obtaining at least one sample data set.

[0127] The sample data set includes sample job application information of sample job seekers, sample job information of sample positions, and sample feedback information returned by the sample recruiting organization of the sample position to the sample job seekers when the sample job seekers submit resumes to the sample positions.

[0128] Sample job seekers include those who have actually submitted resumes to actual recruitment positions in the historical process.

[0129] Sample positions include: positions that have actually been recruited in the historical process.

[0130] The sample feedback information includes: in the historical process, when the job seeker actually submitted a resume to the actual recruitment position, the job recruiter actually returned the feedback information to the job seeker for the actual recruitment position, etc.

[0131] Sample feedback information may include: positive feedback information and negative feedback information.

[0132] Positive feedback information includes: within the effective period after the sample job seeker submits the sample job seeker's resume to the sample position (the effective period can be determined according to actual circumstances, for example, it can be 1 minute, 2 minutes or 5 minutes, etc., and this application does not limit this), the sample recruiter of the sample position checks the contact information of the sample job seeker for the sample position, calls the sample job seeker, invites the sample job seeker for an interview, invites the sample job seeker to take a written test, communicates with the sample job seeker online point-to-point through instant messaging tools, saves the sample job seeker's resume, and marks the sample job seeker's resume as suitable, etc.

[0133] Negative feedback information includes: within the effective period (the effective period can be determined according to actual circumstances, for example, it can be 1 minute, 2 minutes or 5 minutes, etc., and this application does not limit this) after the sample job seeker submits the sample job seeker's resume to the sample position, the sample recruiter of the sample position did not check the sample job seeker's contact information for the sample position, did not call the sample job seeker, did not invite the sample job seeker for an interview, did not invite the sample job seeker to take a written test, did not communicate with the non-sample job seeker online point-to-point through instant messaging tools, marked the sample job seeker's resume as inappropriate, and deleted the sample job seeker's resume, etc.

[0134] Afterwards, the model is trained according to at least one sample data set until the parameters in the model converge, thereby obtaining a feedback rate model.

[0135] Among them, the model may include: LR, etc.

[0136] When optimizing the feedback rate model later, you can refer to the AUC indicator, etc.

[0137] In one embodiment of the present application, with respect to "the sample feedback information returned by the sample recruiter of the sample position to the sample job seeker regarding the sample position when the sample job seeker submits a resume to the sample position", the submission time of the sample job seeker submitting the resume to the sample position and the return time of the sample recruiter of the sample position returning the sample feedback information to the sample job seeker regarding the sample position are often different.

[0138] Moreover, the time when the sample recruiters of the sample positions return sample feedback information to the sample job seekers for the sample positions is often later than the time when the sample job seekers submit their resumes for the sample positions.

[0139] In this way, there is often a delay between the event of "the sample job seeker submitting a resume to the sample position" and the event of "the sample recruiter of the sample position returning sample feedback information to the sample job seeker regarding the sample position."

[0140] In one method, the sample data set can be filtered based on the "submission time of the sample job seeker to the sample position". For example, when the time interval between the "submission time of the sample job seeker to the sample position" and the current time is less than the preset time interval, a sample data set is generated based on the sample job application information of the sample job seeker, the sample position information of the sample position, and the sample feedback information returned by the sample recruiter of the sample position to the sample job seeker when the sample job seeker submits his resume to the sample position.

[0141] However, the feedback rate model is mainly used to obtain the probability that the job recruiter returns positive feedback information to the job seeker after the job seeker submits a resume for the position (for example, the job recruiter actively contacts the job seeker, etc.). Therefore, the moment when the job recruiter returns feedback information to the job seeker in the feedback rate model is more important.

[0142] In this way, even if the time interval between "the moment when the sample job seeker submits his resume to the sample position" and the current moment is less than the preset time interval, if the time interval between the moment when the sample recruiter of the sample position returns the sample feedback information to the sample job seeker for the sample position and the current moment is large, the real-time performance is low, and the timeliness of the feedback rate model trained using such a sample data set is low, which leads to the inaccurate probability predicted by the trained feedback rate model of "after the job seeker submits his resume to the position, the recruiter of the position returns positive feedback information to the job seeker (for example, the recruiter of the position actively contacts the job seeker, etc.)

[0143] In this way, in order to improve the accuracy of the trained feedback rate model's prediction of "the probability that the job recruiter returns positive feedback information to the job seeker after the job seeker submits a resume for the position (for example, the job recruiter actively contacts the job seeker, etc.), the timeliness of the trained feedback rate model can be improved.

[0144] In order to improve the timeliness of the trained feedback rate model, it is necessary to shorten the time interval between the time when the sample recruitment agency of the sample position returns sample feedback information to the sample job seeker for the sample position and the current time.

[0145] In this way, the sample data set can be filtered based on the "return time of the sample recruiter of the sample position returning the sample feedback information to the sample job seeker for the sample position". For example, the time interval between the return time of the sample feedback information in the sample data set (the return time of the sample recruiter of the sample position returning the sample feedback information to the sample job seeker for the sample position) and the current time is less than the preset time interval.

[0146] Among them, the preset time interval may include 2 days, 5 days or 7 days, etc., which can be determined according to actual conditions and is not limited in this application.

[0147] In this way, when predicting the third probability of each position based on the job applicant's job information and the job information of each position, for any one of the multiple positions, the position information of the position and the job applicant's job information can be input into the trained feedback rate model, so that the feedback rate model processes the position information of the position and the job applicant's job information to obtain the third probability of the position.

[0148] The same is true for each of the other positions in the multiple positions.

[0149] In step S103 , the recommendation score of each position for the job seeker is obtained based on the first probability of each position, the second probability of each position, and the third probability of each position.

[0150] In one embodiment of the present application, this step can be implemented through the following process, including:

[0151] 1031. Obtain the probability that the job seeker is interested in each position based on the first probability of each position and the second probability of each position.

[0152] In one embodiment of the present application, for any one of a plurality of positions, the product of the first probability of the position and the second probability of the position can be calculated, and then the probability of the job seeker's interest in the position can be obtained based on the product. For example, the product can be directly used as the probability of the job seeker's interest in the position, or the product can be multiplied by a preset coefficient to obtain a numerical value, which can be used as the probability of the job seeker's interest in the position.

[0153] The same is true for each of the other positions in the multiple positions.

[0154] Among them, the preset coefficient can be determined according to actual conditions and will not be described in detail here. For example, the preset system may include 1.01, 1.02 or 1.03, etc., and this application does not limit this.

[0155] 1032. Obtain a recommendation score for each position for the job seeker based on the probability that the job seeker is interested in each position and the third probability of each position.

[0156] In this step, for any of the multiple positions, the recommended score for the job seeker can be obtained through the following process.

[0157] Among them, the greater the recommendation score of the position for the job seeker, the more likely it is that the job seeker is interested in the position and the more likely the recruiter of the position is satisfied with the job seeker's qualifications.

[0158] That is, the greater the recommendation score of the position for the job seeker, the greater the probability that the job seeker will view the job information of the position after the position is recommended to the job seeker, the greater the probability that the job seeker will submit his / her resume to the position after viewing the job information of the position, and the greater the probability that the recruitment policy of the position will return positive feedback information to the job seeker after the job seeker submits his / her resume to the position.

[0159] The smaller the recommendation score of the position for the job seeker, the less likely the job seeker is to be interested in the position and the less likely the recruiter is to be satisfied with the job seeker's qualifications.

[0160] That is, the smaller the recommendation score of the position for the job seeker, the smaller the probability that the job seeker will view the job information of the position after the position is recommended to the job seeker, the smaller the probability that the job seeker will submit his / her resume to the position after viewing the job information of the position, and the smaller the probability that the recruitment policy of the position will return positive feedback information to the job seeker after the job seeker submits his / her resume to the position.

[0161] The same is true for each of the other positions in the multiple positions.

[0162] The process specifically includes:

[0163] 11) In the descending order of the probability of the job seeker being interested in each position, determine the first sequence number of the probability of the job seeker being interested in the position.

[0164] For example, in one approach, the probability of a job seeker being interested in each position can be sorted from high to low. Thus, in the sorted probabilities of a job seeker being interested in each position, each probability has its own sequence number, and the probabilities of a job seeker being interested in different positions have different sequence numbers. The probability of a job seeker being interested in the position can be determined to be the first sequence number in the sorted probabilities of a job seeker being interested in each position.

[0165] Among the ranked probabilities of the job seeker being interested in each position, if there are M probabilities of interest before the probability of the job seeker being interested in the position, the first sequence number may be M+1, where M is greater than or equal to 0.

[0166] 12) Determine the second sequence number of the third probability of each position in the descending order of the third probability of the position.

[0167] For example, in one approach, the third probabilities of various positions can be sorted from high to low. Thus, in the sorted third probabilities of various positions, each position has its own sequence number, and different positions have different sequence numbers. The third probability of the position can be determined to be the second sequence number among the sorted third probabilities of various positions.

[0168] Among the sorted third probabilities of each position, if there are Q third probabilities before the third probability of the position, the second sequence number may be Q+1, where Q is greater than or equal to 0.

[0169] Among them, step 11) and step 12) can be executed in parallel or one after the other. This application does not limit the execution order of step 11) and step 12).

[0170] 13) Obtain a recommendation score for the job seeker based on the probability that the job seeker is interested in the position, the first sequence number, and the second sequence number.

[0171] In one embodiment of the present application, the number of positions that need to be recommended to the job seeker can be obtained (that is, the maximum number of positions that can be recommended to the job seeker at the same time each time a position is recommended to the job seeker, etc.).

[0172] The number of positions to be recommended to the job seeker can be a uniform number pre-set in the electronic device. That is, the number of positions recommended each time for all job seekers can be uniform. In this way, the electronic device can obtain the pre-set number and use it as the number of positions to be recommended to the job seeker. The number can include 1, 3, or 5, etc., depending on the actual situation and is not limited by this application.

[0173] Then, the difference between the first sequential number and the second sequential number may be calculated.

[0174] Afterwards, a recommendation score for the job seeker for the position may be obtained based on the number, the difference, and the probability that the job seeker is interested in the position.

[0175] For example, the magnitude relationship between the difference and the quantity may be compared.

[0176] In a possible implementation, when the difference is greater than or equal to the number, a recommendation score for the job seeker for the position can be obtained based on the probability that the job seeker is interested in the position and the number.

[0177] For example, based on the probability and number of job seekers interested in the position, the recommendation score for the position for the job seeker can be obtained according to the following formula:

[0178] S=C*e -X*P .

[0179] In the above formula, S is the recommendation score of the position for the job seeker, C is the probability that the job seeker is interested in the position, P is the number, and X is the preset parameter.

[0180] The preset parameter X can be determined according to actual conditions, and this application will not elaborate on this.

[0181] e is a natural constant, including 2.71828, etc.

[0182] Alternatively, in another possible implementation, when the difference is less than the number, the absolute value of the difference can be obtained, and the recommendation score for the job seeker is obtained based on the absolute value of the difference and the probability that the job seeker is interested in the position.

[0183] For example, based on the probability and number of job seekers interested in the position, the recommendation score for the position for the job seeker can be obtained according to the following formula:

[0184] S=C*e -X*W .

[0185] In the above formula, S is the recommendation score of the position for the job seeker, C is the probability that the job seeker is interested in the position, W is the absolute value of the difference, and X is a preset parameter.

[0186] The preset parameter X can be determined according to actual conditions, and this application will not elaborate on this.

[0187] e is a natural constant, including 2.71828, etc.

[0188] In step S104, at least one of the plurality of positions is recommended to the job seeker based on the recommendation scores of the respective positions for the job seeker.

[0189] In one embodiment, the top N positions with the highest recommendation scores may be recommended to the job seeker, where N may be greater than or equal to 1. For example, multiple positions may be sorted in descending order according to their respective recommendation scores for the job seeker, and then at least one position may be selected in that order, and the selected at least one position may be recommended to the job seeker.

[0190] In one embodiment, at least one position may be recommended to the job seeker in the form of a position card. One position corresponds to one position card, and the position card may display position information of the position.

[0191] In the present application, job application information of a job seeker is obtained. Also, job information of each position in a plurality of positions in a recruitment state is obtained. Based on the job application information of the job seeker and the job information of each position, a first probability of each position, a second probability of each position, and a third probability of each position are predicted respectively. The first probability includes the probability that the job seeker views the job information of the position when the position is recommended to the job seeker. The second probability includes: the probability that the job seeker submits the job information of the position when the job seeker views the job information of the position. The third probability includes: the probability that the job seeker's recruiter returns positive feedback information to the job seeker regarding the position when the job seeker submits the job seeker's resume to the position. Based on the first probability of each position, the second probability of each position, and the third probability of each position, a recommendation score for each position for the job seeker is obtained. Based on the recommendation score for each position for the job seeker, at least one position from the plurality of positions is recommended to the job seeker.

[0192] Through this application, in the scenario of recommending positions to job seekers, not only the matching between job seekers and positions is taken into account, but also the matching between job seekers and job recruiters regarding positions is taken into account. In this way, the possibility of job seekers being interested in the recommended positions and the possibility of job recruiters being satisfied with the job seekers' conditions for the positions can be increased as much as possible. For example, the probability of job seekers viewing the job information of the position when a position is recommended to job seekers can be increased, the probability of job seekers submitting their resumes to the position when a job seeker views the job information of the position can be increased, and the probability of job recruiters returning positive feedback information to job seekers regarding the position when a job seeker submits their resumes to the position can be increased.

[0193] In this way, the operation of recommending jobs to job seekers can meet the needs of both job seekers and job recruiters as much as possible. This makes the operation of recommending jobs to job seekers generate real value, improve job seekers' job search efficiency, enhance their job search experience, and prevent job seekers from leaving the recruitment website.

[0194] It should be noted that for the method embodiments, for simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions involved are not necessarily required by this application.

[0195] Reference Figure 2 , shows a structural block diagram of a data processing device of the present application, which may specifically include the following modules:

[0196] The first acquisition module 11 is used to acquire job application information of job seekers; and acquire job information of each position in a plurality of positions in the recruitment state;

[0197] Prediction module 12 is configured to predict, based on the job application information of the job applicant and the position information of each position, a first probability of each position, a second probability of each position, and a third probability of each position, respectively, wherein the first probability includes the probability that the job applicant views the position information of the position if the position is recommended to the job applicant, the second probability includes the probability that the job applicant submits the resume of the position if the job applicant views the position information, and the third probability includes the probability that the job applicant returns positive feedback information to the job applicant regarding the position if the job applicant submits the resume of the position;

[0198] A second obtaining module 13 is configured to obtain a recommendation score for each position for the job seeker based on the first probability of each position, the second probability of each position, and the third probability of each position;

[0199] The recommendation module 14 is configured to recommend at least one of the plurality of positions to the job seeker based on the recommendation scores of the respective positions for the job seeker.

[0200] In an optional implementation, the second acquisition module includes:

[0201] A first acquisition submodule is configured to acquire the probability that the job seeker is interested in each position based on the first probability of each position and the second probability of each position;

[0202] The second acquisition submodule is configured to acquire a recommendation score for each position for the job seeker based on the probability that the job seeker is interested in each position and the third probability of each position.

[0203] In an optional implementation, the first acquisition submodule is specifically configured to: for any one of the multiple positions, calculate the product between the first probability of the position and the second probability of the position, and obtain the probability that the job seeker is interested in the position based on the product.

[0204] In an optional implementation, the second acquisition submodule includes:

[0205] a determining unit configured to determine, for any one of the plurality of positions, a first sequence number of the probability of the job seeker being interested in the position in a descending order of the probabilities of the job seeker being interested in the respective positions; and to determine a second sequence number of the third probability of the position in a descending order of the third probabilities of the respective positions;

[0206] An acquiring unit is configured to acquire a recommendation score of the position for the job seeker based on the probability that the job seeker is interested in the position, the first sequence number, and the second sequence number.

[0207] In an optional implementation, the acquiring unit includes:

[0208] A first obtaining subunit is used to obtain the number of positions that need to be recommended to the job seeker;

[0209] a calculation subunit, configured to calculate a difference between the first sequence number and the second sequence number;

[0210] The second obtaining subunit is configured to obtain a recommendation score of the position for the job seeker based on the quantity, the difference, and the probability that the job seeker is interested in the position.

[0211] In an optional implementation, the second acquiring subunit is specifically configured to:

[0212] When the difference is greater than or equal to the number, obtaining a recommendation score for the job seeker based on the probability that the job seeker is interested in the job and the number;

[0213] or,

[0214] When the difference is smaller than the number, the absolute value of the difference is obtained, and the recommendation score of the position for the job seeker is obtained based on the probability that the job seeker is interested in the position and the absolute value of the difference.

[0215] In an optional implementation, the prediction module includes:

[0216] The input submodule is used to input the job information of any one of the multiple positions and the job application information of the job seeker into the trained feedback rate model, so that the feedback rate model processes the job information of the position and the job application information of the job seeker to obtain a third probability of the position.

[0217] In an optional implementation, the prediction module further includes:

[0218] a third acquisition submodule, configured to acquire at least one sample data set, the sample data set including sample job application information of a sample job seeker, sample job position information of a sample position, and sample feedback information returned by a sample recruiter of the sample position to the sample job seeker for the sample position when the sample job seeker submits a resume for the sample position;

[0219] a training submodule, configured to train the model according to at least one sample data set until the parameters in the model converge, thereby obtaining the feedback rate model;

[0220] The time interval between the time when the sample recruiter of the sample position in the sample data set returns sample feedback information to the sample job seeker for the sample position and the current time is less than the preset time interval.

[0221] In the present application, job application information of a job seeker is obtained. Also, job information of each position in a plurality of positions in a recruitment state is obtained. Based on the job application information of the job seeker and the job information of each position, a first probability of each position, a second probability of each position, and a third probability of each position are predicted respectively. The first probability includes the probability that the job seeker views the job information of the position when the position is recommended to the job seeker. The second probability includes: the probability that the job seeker submits the job information of the position when the job seeker views the job information of the position. The third probability includes: the probability that the job seeker's recruiter returns positive feedback information to the job seeker regarding the position when the job seeker submits the job seeker's resume to the position. Based on the first probability of each position, the second probability of each position, and the third probability of each position, a recommendation score for each position for the job seeker is obtained. Based on the recommendation score for each position for the job seeker, at least one position from the plurality of positions is recommended to the job seeker.

[0222] Through this application, in the scenario of recommending positions to job seekers, not only the matching between job seekers and positions is taken into account, but also the matching between job seekers and job recruiters regarding positions is taken into account. In this way, the possibility of job seekers being interested in the recommended positions and the possibility of job recruiters being satisfied with the job seekers' conditions for the positions can be increased as much as possible. For example, the probability of job seekers viewing the job information of the position when a position is recommended to job seekers can be increased, the probability of job seekers submitting their resumes to the position when a job seeker views the job information of the position can be increased, and the probability of job recruiters returning positive feedback information to job seekers regarding the position when a job seeker submits their resumes to the position can be increased.

[0223] In this way, the operation of recommending jobs to job seekers can meet the needs of both job seekers and job recruiters as much as possible. This makes the operation of recommending jobs to job seekers generate real value, improve job seekers' job search efficiency, enhance their job search experience, and prevent job seekers from leaving the recruitment website.

[0224] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0225] Figure 3 8 is a block diagram of an electronic device 800 shown in the present application. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0226] Reference Figure 3 , the electronic device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0227] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 802 may include one or more modules to facilitate interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

[0228] The memory 804 is configured to store various types of data to support operations on the device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, images, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0229] The power supply component 806 provides power to the various components of the electronic device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 800.

[0230] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have a focal length and optical zoom capability.

[0231] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), which is configured to receive external audio signals when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0232] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include but are not limited to: a home button, volume buttons, a start button, and a lock button.

[0233] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the electronic device 800. For example, the sensor assembly 814 can detect the open / closed state of the device 800, the relative positioning of components, such as the display and keypad of the electronic device 800. The sensor assembly 814 can also detect changes in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and temperature changes of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0234] The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a communication standard, such as WiFi, an operator network (such as 2G, 3G, 4G or 5G), or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast operation information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0235] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0236] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the instructions can be executed by the processor 820 of the electronic device 800 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0237] Figure 41 is a block diagram of an electronic device 1900 shown in the present application. For example, the electronic device 1900 can be provided as a server.

[0238] Reference Figure 4 The electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute the instructions to perform the above-described method.

[0239] The electronic device 1900 may further include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output (I / O) interface 1958. The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or the like.

[0240] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0241] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, devices, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0242] The present application is described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0243] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0244] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0245] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0246] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0247] The above is a detailed introduction to a data processing method, device, electronic device and storage medium provided by the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the ideas of the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present application.

Claims

1. A data processing method, characterized in that: The method comprises: Obtaining job application information of job seekers; and obtaining job information of each of multiple positions in the recruitment status; Based on the job application information of the job seeker and the position information of each position, respectively predicting a first probability of each position, a second probability of each position, and a third probability of each position, wherein the first probability includes the probability that the job seeker views the position information of the position if the position is recommended to the job seeker, the second probability includes the probability that the job seeker submits the resume of the position if the job seeker views the position information, and the third probability includes the probability that the job seeker returns positive feedback information to the job seeker regarding the position if the job seeker submits the resume of the position; Obtaining a recommendation score for each position for the job seeker based on the first probability of each position, the second probability of each position, and the third probability of each position, including: obtaining the probability of the job seeker being interested in each position based on the first probability of each position and the second probability of each position; obtaining a recommendation score for each position for the job seeker based on the probability of the job seeker being interested in each position and the third probability of each position, including: for any one of the multiple positions, determining a first sequence number of the probability of the job seeker being interested in the position in a descending order of the probabilities of the job seeker being interested in the position; and determining a second sequence number of the third probability of the position in a descending order of the third probabilities of the position; obtaining the recommendation score for the position for the job seeker based on the probability of the job seeker being interested in the position, the first sequence number, and the second sequence number; At least one of the plurality of positions is recommended to the job seeker based on the recommendation scores of the respective positions for the job seeker.

2. The method according to claim 1, characterized in that The obtaining of the probability that the job seeker is interested in each position according to the first probability of each position and the second probability of each position includes: For any one of the multiple positions, a product of the first probability of the position and the second probability of the position is calculated, and a probability that the job seeker is interested in the position is obtained according to the product.

3. The method according to claim 1, characterized in that The step of obtaining a recommendation score of the position for the job seeker based on the probability that the job seeker is interested in the position, the first sequence number, and the second sequence number includes: Obtain the number of positions that need to be recommended for the job seeker; Calculating the difference between the first sequence number and the second sequence number; A recommendation score of the position for the job seeker is obtained based on the quantity, the difference, and the probability that the job seeker is interested in the position.

4. The method according to claim 3, characterized in that The obtaining, based on the quantity, the difference, and the probability that the job seeker is interested in the position, a recommendation score for the position for the job seeker includes: When the difference is greater than or equal to the number, obtaining a recommendation score for the job seeker based on the probability that the job seeker is interested in the job and the number; or, When the difference is smaller than the number, the absolute value of the difference is obtained, and the recommendation score of the position for the job seeker is obtained based on the probability that the job seeker is interested in the position and the absolute value of the difference.

5. The method according to claim 1, wherein The process of predicting the third probability of each position based on the job application information of the job seeker and the position information of each position includes: For any one of the multiple positions, the position information of the position and the job-seeking information of the job seeker are input into a trained feedback rate model, so that the feedback rate model processes the position information of the position and the job-seeking information of the job seeker to obtain a third probability of the position.

6. The method according to claim 5, characterized in that The method further comprises: Acquire at least one sample data set, the sample data set including sample job application information of a sample job seeker, sample job position information of a sample position, and sample feedback information returned by a sample recruiter of the sample position to the sample job seeker for the sample position when the sample job seeker submits a resume for the sample position; Training the model according to at least one sample data set until the parameters in the model converge, thereby obtaining the feedback rate model; The time interval between the time when the sample recruiter of the sample position in the sample data set returns sample feedback information to the sample job seeker for the sample position and the current time is less than the preset time interval.

7. A data processing device, characterized in that: The device comprises: The first acquisition module is used to acquire job application information of job seekers; and acquire job information of each position in a plurality of positions in the recruitment state; a prediction module for predicting, based on the job application information of the job applicant and the position information of each position, a first probability of each position, a second probability of each position, and a third probability of each position, respectively, wherein the first probability includes the probability that the job applicant views the position information of the position if the position is recommended to the job applicant, the second probability includes the probability that the job applicant submits the resume of the position if the job applicant views the position information, and the third probability includes the probability that the job applicant returns positive feedback information to the job applicant regarding the position if the job applicant submits the resume of the position; The second acquisition module is configured to acquire the recommendation score of each position for the job seeker based on the first probability of each position, the second probability of each position, and the third probability of each position, including: a first acquisition submodule configured to acquire the probability of the job seeker being interested in each position based on the first probability of each position and the second probability of each position; a second acquisition submodule configured to acquire the recommendation score of each position for the job seeker based on the probability of the job seeker being interested in each position and the third probability of each position, including: a determination unit configured to determine, for any one of the multiple positions, a first sequence number of the probability of the job seeker being interested in the position in a descending order of the probabilities of the job seeker being interested in the position; and, in a descending order of the third probabilities of the positions, determine a second sequence number of the third probability of the position; an acquisition unit configured to acquire the recommendation score of the position for the job seeker based on the probability of the job seeker being interested in the position, the first sequence number, and the second sequence number; The recommendation module is configured to recommend at least one of the plurality of positions to the job seeker based on the recommendation scores of the respective positions for the job seeker.

8. The device according to claim 7, characterized in that The first acquisition submodule is specifically configured to: for any one of the multiple positions, calculate the product between the first probability of the position and the second probability of the position, and obtain the probability that the job seeker is interested in the position based on the product.

9. The device according to claim 7, characterized in that The acquisition unit includes: A first obtaining subunit is used to obtain the number of positions that need to be recommended to the job seeker; a calculation subunit, configured to calculate a difference between the first sequence number and the second sequence number; The second obtaining subunit is configured to obtain a recommendation score of the position for the job seeker based on the quantity, the difference, and the probability that the job seeker is interested in the position.

10. The device according to claim 9, characterized in that The second acquiring subunit is specifically configured to: When the difference is greater than or equal to the number, obtaining a recommendation score for the job seeker based on the probability that the job seeker is interested in the job and the number; or, When the difference is smaller than the number, the absolute value of the difference is obtained, and the recommendation score of the position for the job seeker is obtained based on the probability that the job seeker is interested in the position and the absolute value of the difference.

11. The device according to claim 7, characterized in that The prediction module includes: The input submodule is used to input the job information of any one of the multiple positions and the job application information of the job seeker into the trained feedback rate model, so that the feedback rate model processes the job information of the position and the job application information of the job seeker to obtain a third probability of the position.

12. The device according to claim 11, characterized in that The prediction module also includes: a third acquisition submodule, configured to acquire at least one sample data set, the sample data set including sample job application information of a sample job seeker, sample job position information of a sample position, and sample feedback information returned by a sample recruiter of the sample position to the sample job seeker for the sample position when the sample job seeker submits a resume for the sample position; A training submodule, configured to train the model according to at least one sample data set until the parameters in the model converge, thereby obtaining the feedback rate model; The time interval between the time when the sample recruiter of the sample position in the sample data set returns sample feedback information to the sample job seeker for the sample position and the current time is less than the preset time interval.

13. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing processor-executable instructions; The processor is configured to execute the method according to any one of claims 1 to 6.

14. A non-transitory computer-readable storage medium, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform the method according to any one of claims 1 to 6.

Images