CN114819304A - NLP-based interviewing process double-group association evaluation method - Google Patents
NLP-based interviewing process double-group association evaluation method Download PDFInfo
- Publication number
- CN114819304A CN114819304A CN202210382260.4A CN202210382260A CN114819304A CN 114819304 A CN114819304 A CN 114819304A CN 202210382260 A CN202210382260 A CN 202210382260A CN 114819304 A CN114819304 A CN 114819304A
- Authority
- CN
- China
- Prior art keywords
- interviewer
- interview
- questions
- interviewee
- prediction model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06398—Performance of employee with respect to a job function
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
- G06Q10/1053—Employment or hiring
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an interview process double-group association evaluation method based on NLP, which comprises the steps of firstly carrying out multi-dimensional dynamic acquisition and multi-dimensional tracking marking on sample data in each stage in an interviewer occupational life cycle and in an interview process by an NLP technology; then carrying out multidimensional training on sample data and marked data of the double-population to obtain a plurality of models such as a staff stability prediction model, a staff capability level prediction model, an interviewer suitability field and an interview skill prediction model; and finally, predicting the situation (stability), the work performance situation and the like of the follow-up interviewer by using the model, and predicting the effectiveness of interview questioning of the interviewer, the group and the field direction suitable for interview and the like at regular intervals. The invention can improve the 'retention rate' of recruiting screening interviewees to a certain extent, optimize the configuration and direction of an interviewer team, reduce the cost waste caused by frequent employee departure of employees and ensure the sustainable health development of enterprises.
Description
Technical Field
The invention belongs to the field of interview evaluation, and particularly relates to a double-population association evaluation method based on NLP in an interview process.
Background
Employees are the basic building blocks of an enterprise, and the enterprise can continue to develop without a high-loyalty team of employees. Currently, enterprises generally improve loyalty of employees during their jobs through various measures or reply to employee departure situations through data statistics, but need to manually collect a large number of employee attribute fields from tables from different sources, and although collecting such information is very simple, the workload is huge in the face of continuously increasing materials.
Although the current AI technology is applied to resume screening work, the rigid condition applied by interviewers can only be simply matched with the recruitment requirement of an enterprise, the granularity of judgment is large, the validity of the result cannot meet the further requirement of the enterprise, and the behavior prediction in the staff occupation life cycle cannot be realized. In addition, whether the interview questions of the interviewer are effective and whether the technical fields are matched or not, and whether the competence reaches the standard or not, corresponding analysis data and evaluation means are lacked.
Disclosure of Invention
In view of the above problems, the invention provides an NLP-based interview process double-population association evaluation method for an interviewer and an interviewer, so as to improve the accuracy of interviewer skill judgment in an enterprise recruitment process, reduce the risk of leaving the job of the interviewer after entering the job, and simultaneously evaluate the interview ability and the field preference of the interviewer.
In order to achieve the purpose, the invention adopts the following technical scheme:
a double-population correlation evaluation method based on NLP in an interviewing process comprises the following steps:
s1, formulating a semi-structured interview question with an association relation according to the employment post of an interviewer;
s2, primarily screening the delivery resume based on the NLP technology, and selecting interviewees meeting the recruitment requirement to participate in interviewing;
s3, collecting samples of answers of semi-structured interview questions given by interviewers, interview questions provided by interviewers and answers of the interviewers to the interview questions;
s4, eliminating samples of which the interview post of the interviewer is inconsistent with the actual post of enrollment;
s5, carrying out multi-dimensional marking on the collected samples according to the performance of the interviewer and the interviewee in the interviewing process and the performance of the interviewee after entering the job;
s6, constructing a plurality of prediction models by using the collected samples and the corresponding marks thereof according to the associated evaluation targets;
and S7, predicting the interviewing ability of the interviewer and the working stability and the working ability of the subsequent interviewer by using the prediction model.
Further, the semi-structured interview questions in S1 include human resource general interview questions and ability interview questions corresponding to the recruitment position, where the ability interview questions are used to examine the professional ability of the interviewer, and to examine the interview skill level of the interviewer according to the question order and the logical reasonableness of the questions of the interviewer.
Further, in S5, the sample related to the interviewer is labeled, including but not limited to: marking the effectiveness of the problem proposed by the interviewer in the interviewing process, and marking the post type of the interviewer suitable for interviewing; the sample associated with the interviewer is labeled, including but not limited to: whether the interviewee is in the job or not or whether the interviewee is out of the job after the interview is marked, and the work performance of the interviewee after the interview is marked.
Further, in S6, the first step,
adopting a prediction class deep learning model framework including but not limited to a classifier, taking questions about human resources and answered keywords of an interviewee in an interviewing process as input items, taking trial examination results of the interviewee collected regularly after enrollment as labeled items, and training to generate an employee stability prediction model;
adopting a prediction class deep learning model framework including but not limited to a classifier, taking the relevant technical questions and the answered keywords of an interviewee in the interviewing process as input items, taking interview skill application scores of the interviewee, periodically collected assessment results of the interviewee after entering the job and instructor coaching scores as marking items, and training to generate an employee competence level prediction model;
the method comprises the steps of training and generating a prediction model for predicting the effectiveness of questions posed by an interviewee by using a deep learning model framework including but not limited to a time series based, taking questions posed by the interviewee in an interviewing process and keywords extracted by the interviewee based on NLP as input items, and taking the effectiveness of the questions posed by an expert group as a marking item.
Further, in S7, based on the employee stability prediction model and the employee competence level prediction model, the job stability and job ability of the subsequent interviewer after employment are predicted; and (3) periodically predicting the question effectiveness of the interviewer participating in the interviewing process based on a prediction model for the question effectiveness proposed by the interviewer, and if the number of invalid questions is greater than a set threshold, properly reducing the interviewing field number of the interviewer.
A two-group correlation evaluation system based on the evaluation method in the interviewing process comprises a data acquisition module, a sample marking module, a prediction model construction module and a prediction model application module; the data acquisition module is used for acquiring answers of semi-structured interview questions, interview questions and answers of interviewers to the interview questions, wherein the answers are given by the interviewers in the interview process; the sample marking module is used for carrying out multi-dimensional marking on the data sample acquired by the data acquisition module according to the working performance of the interviewer after employment and the effectiveness judgment of the problem posed in the interviewing process of the interviewer; the prediction model construction module is used for training and generating a plurality of prediction models for associated evaluation according to the multi-dimensional marked sample data; the prediction model application module is used for predicting the interviewing capability of the interviewer and the working stability and the working capability of the subsequent interviewer according to a plurality of prediction models generated by training.
The invention has the beneficial effects that:
the invention provides a double-group correlation evaluation method based on NLP (non-line-of-sight) interviewing process, which comprises the steps of firstly carrying out multi-dimensional dynamic acquisition and multi-dimensional tracking marking on sample data of interviewers at each stage in the full-time business life cycle and in the interviewing process of interviewers by NLP technology; then carrying out multidimensional training on sample data and marked data of the double-population to obtain a plurality of models such as a staff stability prediction model, a staff capability level prediction model, an interviewer suitability field and an interview skill prediction model; finally, the model is used for predicting the behavior of the follow-up interviewer on-off situation (stability), work performance situation and the like, and the effectiveness of interview questioning of interviewers, groups suitable for interviews, field directions and the like can be predicted regularly. The method is simple to operate, low in cost and easy to popularize, breaks through the conventional summarized interview data statistical analysis, and realizes the two-group association prediction of interviewers and interviewees; the method can improve the 'retention rate' of recruiting screening interviewees to a certain extent, optimize the configuration and direction of an interviewer team, reduce the cost waste caused by frequent employee departure of employees, and ensure the sustainable and healthy development of enterprises.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The present invention will now be described in further detail with reference to the accompanying drawings.
Aiming at a 'double-group' of an interviewee and an interviewer, the invention designs a semi-structured interview subject with an incidence relation, firstly, matching the resume of the interviewer with the recruitment requirement by an NLP (Natural Language Processing) technology to form a first round of screening of the interviewee and determine the technical field of the interviewee; secondly, in the interviewing process, questions of interviewees and answers of interviewees are collected and analyzed, and unstructured data in the questions and answers are converted into structured data by the NLP technology; after a sample that the interview post (or the technical direction) is inconsistent with the post (or the technical direction) after actual job entry is removed, the interview behavior of an interviewer is marked for the 'double-group' object according to the business requirement, and in addition, multi-dimensional tracking marking is carried out according to a certain time interval in the whole job life cycle of the interviewer; then carrying out multi-dimensional model training based on the samples and the labels to generate a plurality of models such as a staff stability prediction model, a staff competence level prediction model, an interviewer suitability field and an interview skill prediction model; and finally, performing multi-dimensional prediction including but not limited to job intentions, job leaving risks, technical abilities and the like on subsequent interviewers based on different models, and periodically analyzing and recommending the question effectiveness and interview field suitability of interviewers.
As shown in fig. 1, the method of the present invention may specifically include the following steps:
step 1: in order to predict the abilities of an interviewer and an interviewer at the same time, semi-structured interview questions with an association relationship are prepared according to the employment position, the technical direction and the like of the interviewer, wherein the semi-structured interview questions comprise general interview questions of human resources, ability interview questions (classification combined with position characteristics, technical direction and the like) and the like. The ability type interview questions have certain logic correlation, on one hand, the real ability of an interviewer is investigated, and on the other hand, the interview skill level of the interviewer is checked according to the order of questions asked by the interviewer and the logic reasonableness of the questions before and after.
Step 2: and (3) performing first-round screening on resumes delivered by interviewers based on an NLP technology, segmenting unstructured data such as education backgrounds, work experiences and the like in the resumes, extracting keywords, and screening the interviewers meeting the recruitment requirements.
Step 3-1: the answers to the semi-structured questions in the interviewing process of the interviewer are collected in a plurality of modes;
step 3-2: the interview questions presented by the interviewer on site are collected in a variety of ways.
And 4, step 4: the samples of the interview post (or the technical direction) of the interviewer inconsistent with the post (or the technical direction) after the actual job are artificially eliminated, and behavior prediction under the condition of post matching is guaranteed.
And 5: on one hand, the interview behavior of an interviewer in the interview process is marked; on the other hand, in the full-time business life cycle of the interviewer, multi-dimensional tracking marking is carried out on the samples according to business requirements according to a certain time period. Labeled samples include, but are not limited to: marking invalid questions proposed by an interviewer in an interviewing process; the method comprises the steps of extracting keywords from answers of interviewees in an interviewing process by means of an NLP technology, and marking the entry/exit conditions, trial entrance examination and review evaluation, monthly performance evaluation, monthly evaluation of professional instructors, application scoring of interview skills (key investigation skills in interviewing) and the like.
Aiming at an interviewee, keywords in answers of each question answered by the interviewee are automatically combed through NLP word segmentation, the keywords are used as input samples for judging the effectiveness of interview questions, and invalid questions proposed by the interviewee are artificially marked;
marking interview answer keywords of an interviewer at the current period; in the long term, the system marks the departure behavior on one hand and marks the evaluation judgment of the daily performance result (including but not limited to evaluation results of different periods, project experience, skill certification and the like) on the other hand.
And 6: and carrying out multi-dimensional model training by using the sample data and the label data to obtain a plurality of prediction models, including a staff stability prediction model, a staff capability level prediction model, an interviewer suitability field, an interview skill prediction model and the like. The method specifically comprises the following steps:
the method comprises the steps of training and generating an employee stability prediction model by adopting a related prediction class deep learning model framework including but not limited to a classifier, taking questions about human resources and answered keywords of an interviewer in an interviewing process as input items, and taking periodically collected trial period examination results and the like of employees as marking items.
And a related prediction class deep learning model framework including but not limited to a classifier is also adopted, keywords of related technical questions and answers of an interviewee in the interviewing process are used as input items, and staff assessment results (trial period assessment, monthly performance, quarterly assessment and the like), instructor coaching scores, interview skills (skills which are mainly studied in interviewing) application scores, project experiences and the like which are collected periodically are used as marking items, so that the staff competency level prediction model is trained and generated.
By adopting a deep learning model framework which comprises but is not limited to and is based on time series, the order of questions asked by an interviewer in the interviewing process is taken as an input item of the model, keywords which are extracted based on NLP and answered by the interviewer are taken as label items, and invalid questions marked by an expert group are taken as label items, so that a prediction model for predicting the invalid questions in the subsequent questioning process is trained and generated.
Step 7-1: based on a prediction model, taking the semi-structured interview question answers of subsequent interviewers as input, and predicting whether the interviewers are stable and can have corresponding capabilities;
step 7-2: the questioning effectiveness of the interviewers participating in the interview is predicted regularly, so that the people-recognizing ability and the technical expertise of the interviewers are indirectly inferred. The method mainly carries out statistics to judge the problem invalidity of the interviewer in the interviewing process, when the invalid problem threshold value exceeds the set upper limit value, on one hand, the interviewing times of the current interviewing position (or the technical aspect) of the interviewer are properly reduced to match the interviewing chance suitable for the interviewing position, on the other hand, the interviewing functional ability improvement is strengthened, the corresponding enabling training is increased, the interviewer configuration is further rationalized, and the interviewing ability and skill of the interviewer are improved.
The invention breaks through the simple matching process that the AI technology is only applied to resume screening, reduces the manual statistics complexity of the review analysis of the staff who have left the job, can not only look back at the historical data, but also realize the double-group correlation prediction of interviewees and interviewees, and achieves two purposes at one stroke. And through carrying out multi-dimensional acquisition on sample data generated in the interview process, marking according to multi-dimensional attributes and obtaining a multi-dimensional prediction model based on continuous training, interviewees with potential slot jumping risks can be excluded in advance, behaviors of employees (interviewees) in the full-time business life cycle can be further predicted, appropriate employee development plans and construction measures are matched, employee loyalty is strengthened in each link, and a stable talent base support is provided for sustainable high-quality development of enterprises.
The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above-mentioned embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may be made by those skilled in the art without departing from the principle of the invention.
Claims (6)
1. A double-population correlation evaluation method based on NLP interview process is characterized by comprising the following steps:
s1, formulating a semi-structured interview question with an association relation according to the employment post of an interviewer;
s2, primarily screening the delivery resume based on the NLP technology, and selecting interviewees meeting the recruitment requirement to participate in interviewing;
s3, collecting samples of answers of semi-structured interview questions given by interviewers, interview questions provided by interviewers and answers of the interviewers to the interview questions;
s4, eliminating samples of which the interview post of the interviewer is inconsistent with the actual post of enrollment;
s5, carrying out multi-dimensional marking on the collected samples according to the performance of the interviewer and the interviewee in the interviewing process and the performance of the interviewee after entering the job;
s6, constructing a plurality of prediction models by using the collected samples and the corresponding marks thereof according to the associated evaluation targets;
and S7, predicting the interviewing ability of the interviewer and the working stability and the working ability of the subsequent interviewer by using the prediction model.
2. The NLP-based interview process double-population associated evaluation method according to claim 1, wherein the semi-structured interview questions in S1 comprise human resource general interview questions and competence interview questions corresponding to recruitment positions, and the competence interview questions are used for investigating the professional competencies of the interviewer and investigating the interview skill level of the interviewer according to the question order and the logical reasonableness of questions of the interviewer.
3. The NLP-based interview process double-population association evaluation method according to claim 1, wherein in S5, samples related to the interviewer are labeled, including but not limited to: marking the effectiveness of the problem proposed by the interviewer in the interviewing process, and marking the post type of the interviewer suitable for interviewing; the sample associated with the interviewer is labeled, including but not limited to: whether the interviewee is in the job or not or whether the interviewee is out of the job after the interview is marked, and the work performance of the interviewee after the interview is marked.
4. The NLP-based interview process double-population association evaluation method according to claim 1, wherein in S6,
adopting a prediction class deep learning model framework including but not limited to a classifier, taking questions about human resources and answered keywords of an interviewee in an interviewing process as input items, taking trial examination results of the interviewee collected regularly after enrollment as labeled items, and training to generate an employee stability prediction model;
adopting a prediction class deep learning model framework including but not limited to a classifier, taking the relevant technical questions and the answered keywords of an interviewee in the interviewing process as input items, taking interview skill application scores of the interviewee, periodically collected assessment results of the interviewee after entering the job and instructor coaching scores as marking items, and training to generate an employee competence level prediction model;
the method comprises the steps of training and generating a prediction model for predicting the effectiveness of questions posed by an interviewee by using a deep learning model framework including but not limited to a time series based, taking questions posed by the interviewee in an interviewing process and keywords extracted by the interviewee based on NLP as input items, and taking the effectiveness of the questions posed by an expert group as a marking item.
5. The NLP-based interview process double-population association evaluation method according to claim 4, wherein in S7, based on the employee stability prediction model and the employee competence level prediction model, the work stability and the work ability of a subsequent interviewee after employment are predicted; and (3) periodically predicting the question effectiveness of the interviewer participating in the interviewing process based on a prediction model for the question effectiveness proposed by the interviewer, and if the number of invalid questions is greater than a set threshold, properly reducing the interviewing field number of the interviewer.
6. An interview process 'double-population' associated evaluation system based on the evaluation method of any one of the preceding claims, which is characterized by comprising a data acquisition module, a sample marking module, a prediction model construction module and a prediction model application module; the data acquisition module is used for acquiring answers of semi-structured interview questions, interview questions and answers of interviewers to the interview questions, wherein the answers are given by the interviewers in the interview process; the sample marking module is used for carrying out multi-dimensional marking on the data sample acquired by the data acquisition module according to the working performance of the interviewer after employment and the effectiveness judgment of the problem posed in the interviewing process of the interviewer; the prediction model construction module is used for training and generating a plurality of prediction models for associated evaluation according to the multi-dimensional marked sample data; the prediction model application module is used for predicting the interviewing capability of the interviewer and the working stability and the working capability of the subsequent interviewer according to a plurality of prediction models generated by training.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210382260.4A CN114819304A (en) | 2022-04-13 | 2022-04-13 | NLP-based interviewing process double-group association evaluation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210382260.4A CN114819304A (en) | 2022-04-13 | 2022-04-13 | NLP-based interviewing process double-group association evaluation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114819304A true CN114819304A (en) | 2022-07-29 |
Family
ID=82534025
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210382260.4A Pending CN114819304A (en) | 2022-04-13 | 2022-04-13 | NLP-based interviewing process double-group association evaluation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114819304A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115758178A (en) * | 2022-11-23 | 2023-03-07 | 北京百度网讯科技有限公司 | Data processing method, data processing model training method, device and equipment |
-
2022
- 2022-04-13 CN CN202210382260.4A patent/CN114819304A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115758178A (en) * | 2022-11-23 | 2023-03-07 | 北京百度网讯科技有限公司 | Data processing method, data processing model training method, device and equipment |
| CN115758178B (en) * | 2022-11-23 | 2024-02-06 | 北京百度网讯科技有限公司 | Data processing method, data processing model training method, device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jia et al. | A conceptual artificial intelligence application framework in human resource management | |
| CN112069970B (en) | Classroom teaching event analysis method and device | |
| Chanpoom et al. | The influence of strategic leadership and organizational climate on organizational commitment of savings cooperative employees, Thailand | |
| Alvani et al. | Presenting a succession management model based on organizational capabilities in knowledgebased organizations (Case study: Science and Technology Park of Tehran University and Science and Technology Park of Tarbiat Modares University) | |
| CN114819304A (en) | NLP-based interviewing process double-group association evaluation method | |
| Stefanova et al. | Educational data mining perspectives within university big data environment | |
| Jayanti et al. | Application of Predictive Analytics To Improve The Hiring Process In A Telecommunications Company | |
| Engetou | Impact of insufficient personnel on organizational performance | |
| Gromov et al. | Human resources intelligent selection algorithm with improvement of data validity | |
| CN113408930B (en) | Employee behavior analysis method, system and storage medium based on employee service system | |
| Swamy et al. | Recruitment and selection process in the IT firms | |
| Gupta et al. | Effect of performance appraisal on employee productivity in an automation solution company | |
| Behrens et al. | Competences in Health Network Management (Com. HeNet) | |
| Gayatri et al. | Artificial intelligence deployment and the potency of HRM functions | |
| Arulan et al. | The Effect Of Compensation, Work Discipline And Motivation On Employee Productivity In The Service Pekanbaru City Msme Cooperative | |
| CN114626654A (en) | Personnel training early warning analysis method based on professional skill training personnel management system | |
| Rudnak | The study of employee motivation in a Chinese private enterprise | |
| Movia et al. | Identification of competences in regional health network management | |
| Perello-Marin et al. | Are we ready to implement artificial intelligence in HR performance management | |
| Uzondu | Evaluation of human resource management practices on the productivity and performance of transport organizations in Nigeria | |
| CN108961112A (en) | A kind of talent's big data distributed management system | |
| Indriastuti et al. | Development of an Adaptive Higher Education Management Model with Artificial Intelligence | |
| Thongkaew et al. | Data Analytics for Admission Process: Bachelor of Engineering Program | |
| TABARCIA et al. | KNOWLEDGE MANAGEMENT AND ASSESSMENT OF THE ONLINE LEARNING SYSTEM OF ROMANIAN EMERGENCY CALL CENTER EMPLOYEES. | |
| Larasati et al. | The Effect of Recruitment and Achievement Motivation on Discipline of Teacher Work at Private Kristen Kindergarten (TK) in Pontianak City |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |