CN117291559A - Intelligent talent management system for enterprises - Google Patents
Intelligent talent management system for enterprises Download PDFInfo
- Publication number
- CN117291559A CN117291559A CN202311484249.XA CN202311484249A CN117291559A CN 117291559 A CN117291559 A CN 117291559A CN 202311484249 A CN202311484249 A CN 202311484249A CN 117291559 A CN117291559 A CN 117291559A
- Authority
- CN
- China
- Prior art keywords
- talent
- enterprise
- information
- evaluation
- talents
- 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
- 238000011156 evaluation Methods 0.000 claims abstract description 170
- 238000004458 analytical method Methods 0.000 claims abstract description 129
- 230000008520 organization Effects 0.000 claims abstract description 52
- 239000013598 vector Substances 0.000 claims description 61
- 230000006870 function Effects 0.000 claims description 12
- 230000004927 fusion Effects 0.000 claims description 12
- 230000007115 recruitment Effects 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 13
- 238000012545 processing Methods 0.000 description 8
- 230000002093 peripheral effect Effects 0.000 description 7
- 238000012795 verification Methods 0.000 description 6
- 238000012797 qualification Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000012216 screening Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 241000209504 Poaceae Species 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063112—Skill-based matching of a person or a group to a task
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
- G06Q50/2057—Career enhancement or continuing education service
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Educational Technology (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an intelligent talent management system for enterprises, which comprises a talent library management module, an enterprise architecture management module and an evaluation analysis module; the talent library management module is used for establishing an enterprise talent resource library and storing and managing talent files of enterprise talents according to the enterprise talent resource library; the enterprise architecture management module is used for building an enterprise organization architecture according to actual conditions, wherein the enterprise organization architecture comprises position information and position corresponding incumbent personnel information, and the position information comprises position description and position required conditions; the evaluation analysis module is used for performing evaluation analysis according to the position information and the corresponding incumbent personnel information in the enterprise organization architecture to obtain an incumbent personnel evaluation analysis result; and/or according to the position information in the enterprise organization architecture and the talents files of the enterprise talents in the enterprise talents resource library, performing evaluation analysis to obtain talent recommendation evaluation analysis results. The invention improves the intelligent level of talent management of enterprises.
Description
Technical Field
The invention relates to the technical field of enterprise talent management, in particular to an intelligent enterprise talent management system.
Background
Enterprise talent management has a great positive influence on enterprise development, and currently, large enterprises perform centralized management on enterprise talents (including incumbent talents, backup talents and the like) through an established talent management library to assist the enterprises in solving the personnel configuration problem of key posts.
However, in the talent management system used by the current enterprise, only the talent database building function is generally included, and when the human resource requirement is generated, the talent resource manager is required to traverse and mine the required talent resources from the talent database, so that the talent management system is very inconvenient to use.
Disclosure of Invention
Aiming at the problems, the invention aims to provide an intelligent enterprise talent management system.
The aim of the invention is realized by adopting the following technical scheme:
the invention discloses an intelligent enterprise talent management system, which comprises a talent library management module, an enterprise architecture management module and an evaluation analysis module; wherein,
the talent library management module is used for establishing an enterprise talent resource library and storing and managing talent files of enterprise talents according to the enterprise talent resource library, wherein the enterprise talents comprise staff in the enterprise and external reserve staff, and the talent files of the enterprise talents comprise staff in-staff information, identity information, resume information and evaluation information;
The enterprise architecture management module is used for building an enterprise organization architecture according to actual conditions, wherein the enterprise organization architecture comprises position information and position corresponding incumbent personnel information, and the position information comprises position description and position required conditions;
the evaluation analysis module is used for performing evaluation analysis according to the position information and the corresponding incumbent personnel information in the enterprise organization architecture to obtain an incumbent personnel evaluation analysis result; and/or according to the position information in the enterprise organization architecture and the talents files of the enterprise talents in the enterprise talents resource library, performing evaluation analysis to obtain talent recommendation evaluation analysis results.
Preferably, the talent library management module comprises a talent archive establishment unit and a talent resource library management unit;
the talent file establishing unit establishes a talent file for personnel of an incumbent enterprise or personnel outside the enterprise, and stores the talent file into a talent resource library;
the talent resource library management unit is used for performing management operations such as consulting, updating, deleting and the like on talent files in the talent resource library.
Preferably, the enterprise architecture management module comprises an organization architecture setting unit and a personnel setting unit;
the organization architecture setting unit is used for setting up an enterprise organization architecture according to the actual situation of an enterprise, wherein the enterprise organization architecture comprises position information of each position and upper and lower relation information among the positions; the position information comprises position names, the number of staff members, required skill requirements and the like;
The personnel setting unit is used for setting corresponding incumbent personnel information for each position in the enterprise organization structure according to the actual condition of the enterprise, including adding, modifying and deleting the corresponding incumbent personnel information for the position.
Preferably, the evaluation analysis module comprises an incumbent personnel evaluation unit and a staff talent recommendation unit;
the incumbent staff assessment unit is used for carrying out assessment analysis according to the position information of one position in the organization architecture and the corresponding talent files of the incumbent staff to obtain an incumbent staff assessment analysis result;
the staff recommending unit is used for configuring the staff of the not-fully-filled staff in the organization structure, and performing evaluation analysis according to the staff information of the staff and the staff files of the enterprise staff in the enterprise staff resource library to obtain staff recommending evaluation analysis results.
Preferably, the incumbent person assessment unit includes:
aiming at position information of one position in an organization structure, acquiring skill requirements and position characteristics of the position, and constructing a position feature vector;
acquiring a talent file of the job title, acquiring resume information and evaluation information of the job title according to the talent file of the job title, extracting professional skill information of the job title from the resume information, acquiring evaluation characteristics of the job title from the evaluation information, and constructing talent characteristic vectors of the job title according to the acquired professional skill information and the evaluation characteristics;
Inputting the acquired position feature vector and talent feature vector into a trained evaluation analysis model to obtain position matching degree output by the evaluation analysis model as an evaluation analysis result of on-job personnel;
and when the job matching degree is lower than a preset standard, marking that the evaluation analysis result of the job personnel is abnormal.
Preferably, the evaluation analysis model is built based on a neural network of deep learning, wherein the evaluation analysis model comprises an input layer, a skill evaluation layer, a characteristic evaluation layer and a fusion analysis layer;
the input layer is used for acquiring a position feature vector and a talent feature vector, extracting skill requirements from the position feature vector and extracting professional skill information from the talent feature vector, and inputting the skill requirements and the talent feature vector to the skill assessment layer; extracting position characteristics from the position characteristic vectors and extracting evaluation characteristics from talent characteristic vectors respectively, and inputting the evaluation characteristics to a characteristic evaluation layer;
the skill evaluation layer is used for matching corresponding items from the practice skill information based on the obtained skill requirements, when the skill requirements can be matched with the corresponding practice skill information, the skill requirements are marked to finish matching, otherwise, the skill requirements are marked to fail to finish matching, and skill requirement evaluation results are obtained according to the skill requirements and corresponding matching marks and are output to the fusion analysis layer;
The characteristic evaluation layer extracts position characteristic text representation and evaluation characteristic text representation according to the acquired position characteristics and evaluation characteristics respectively by using a BiLSTM model, calculates similarity between the position characteristic text representation and the evaluation characteristic text representation by adopting a similarity analysis model in combination with a preset text characteristic weight factor, and inputs a position characteristic evaluation analysis result into the fusion analysis layer; the activation function adopted by the similarity analysis model is a sigmoid function;
the fusion analysis layer is used for carrying out normalization operation according to the acquired skill requirement evaluation result and the acquired position characteristic evaluation analysis result, so as to obtain and output the position matching degree between the designated position and the personnel.
Preferably, the job title recommending unit includes:
aiming at personnel configuration in an organization structure, acquiring the skill requirement and the position characteristic of the position, and constructing a position feature vector;
acquiring resume information and evaluation information of enterprise talents according to talents files of the enterprise talents in an enterprise talent resource library, extracting professional skill information of the enterprise talents from the resume information, acquiring evaluation characteristics of the enterprise talents from the evaluation information, and constructing talent feature vectors of the enterprise talents according to the acquired professional skill information and the evaluation characteristics;
According to the acquired position feature vector and talent feature vector, inputting the acquired position feature vector and talent feature vector into a trained evaluation analysis model, and obtaining position matching degree output by the evaluation analysis model as matching degree of enterprise talents and target positions;
and arranging the talents of each enterprise according to the matching degree of the talents and the target positions from high to low, and obtaining a list as a talent recommendation evaluation analysis result.
Preferably, the system further comprises a recruitment interview module;
the recruitment interview module is used for recommending, evaluating and analyzing results according to talents obtained by the position talent recommending unit, calling corresponding talent files according to the talent recommending, interviewing corresponding positions according to talent file information and corresponding recommended talents, and recording corresponding interview results.
Preferably, the recruitment interview module includes an archive retrieving unit and an online interview unit;
the file retrieving unit is used for retrieving corresponding talent files according to talent recommendation evaluation analysis results obtained by the position talent recommendation unit and according to the talent recommendation evaluation analysis results;
the online interview unit is used for sending interview requests of corresponding positions to the talents of the enterprise according to the talent file information and inviting the talents of the enterprise to finish online interview so as to obtain corresponding online interview results; wherein the online interview includes an online video interview.
The beneficial effects of the invention are as follows: according to the intelligent talent management system for enterprises, on the basis of establishment of the talent resource library of the enterprises, enterprise architecture information is further established, intelligent evaluation analysis is conducted on the matching degree of positions and incumbent staff in an enterprise organization architecture according to the enterprise architecture information, when position vacancies occur, evaluation analysis is conducted on the enterprise talents in the talent resource library of the enterprises according to the position information of the vacancies, talent recommendation information for the vacancies is obtained in an assisted mode, intelligent evaluation analysis is conducted on the enterprise organization architecture by assisting enterprise human resource managers on the basis of the established talent resource library of the enterprises, application environments of the talent resource library of the enterprises are enriched, and the intelligent level of talent management of the enterprises is improved.
Drawings
The invention will be further described with reference to the accompanying drawings, in which embodiments do not constitute any limitation of the invention, and other drawings can be obtained by one of ordinary skill in the art without inventive effort from the following drawings.
Fig. 1 is a block diagram of an intelligent talent management system for enterprises according to an exemplary embodiment of the present invention.
Detailed Description
The invention is further described in connection with the following application scenario.
Referring to fig. 1, an intelligent talent management system for enterprises, which is shown in an exemplary embodiment, includes a talent library management module, an enterprise architecture management module, and an evaluation analysis module; wherein,
the talent library management module is used for establishing an enterprise talent resource library and storing and managing talent files of enterprise talents according to the enterprise talent resource library, wherein the enterprise talents comprise staff in the enterprise and external reserve staff, and the talent files of the enterprise talents comprise staff in-staff information, identity information, resume information and evaluation information;
the enterprise architecture management module is used for building an enterprise organization architecture according to actual conditions, wherein the enterprise organization architecture comprises position information and position corresponding incumbent personnel information, and the position information comprises position description and position required conditions;
the evaluation analysis module is used for performing evaluation analysis according to the position information and the corresponding incumbent personnel information in the enterprise organization architecture to obtain an incumbent personnel evaluation analysis result; and/or according to the position information in the enterprise organization architecture and the talents files of the enterprise talents in the enterprise talents resource library, performing evaluation analysis to obtain talent recommendation evaluation analysis results.
The intelligent enterprise talent management system provided by the above-mentioned exemplary embodiment further builds enterprise architecture information on the basis of building the enterprise talent resource library, and carries out intelligent evaluation analysis on the matching degree of the position in the enterprise organization architecture and the incumbent personnel according to the enterprise architecture information, and carries out evaluation analysis on the enterprise talents in the enterprise talent resource library according to the position information of the available position when the position is available, so as to assist in acquiring talent recommendation information for the available position, and help assist enterprise human resource managers in carrying out intelligent evaluation analysis on the enterprise organization architecture based on the built enterprise talent resource library, enrich the application environment of the enterprise talent resource library, and improve the intelligent level of enterprise talent management.
Preferably, the talent library management module comprises a talent archive establishment unit and a talent resource library management unit;
the talent file establishing unit establishes a talent file for personnel of an incumbent enterprise or personnel outside the enterprise, and stores the talent file into a talent resource library;
the talent resource library management unit is used for performing management operations such as consulting, updating, deleting and the like on talent files in the talent resource library.
The talent archives are built for the incumbent staff information and the external reserve staff information of the enterprise to enrich the talent resource library of the enterprise, and serve as the basis of talent reserve and talent management of the enterprise. The human resource manager completes the management of the talent resource library of the enterprise through the operation of the talent library management module.
In a scene, when a manual resource manager of an enterprise performs resume screening or preliminary interview, the manual resource manager can select external reserve talents of the enterprise according to the resume of the cardiology, and a talent file of corresponding enterprise talents is established.
Preferably, the enterprise architecture management module comprises an organization architecture setting unit and a personnel setting unit;
the organization architecture setting unit is used for setting up an enterprise organization architecture according to the actual situation of an enterprise, wherein the enterprise organization architecture comprises position information of each position and upper and lower relation information among the positions; the position information comprises position names, the number of staff members, required skill requirements and the like;
the personnel setting unit is used for setting corresponding incumbent personnel information for each position in the enterprise organization structure according to the actual condition of the enterprise, including adding, modifying and deleting the corresponding incumbent personnel information for the position.
Building a corresponding enterprise organization architecture through an organization architecture setting unit according to the actual organization architecture condition of an enterprise, wherein the enterprise organization architecture comprises a plurality of job position information, and relationship information such as upper and lower levels (such as a special person, a manager, a general supervision and the like) and the like are arranged between different job positions; corresponding position information is set for each position according to recruitment requirements of human resources, and requirements of subsequent position management and personnel management are met.
Preferably, the evaluation analysis module comprises an incumbent personnel evaluation unit and a staff talent recommendation unit;
the incumbent staff assessment unit is used for carrying out assessment analysis according to the position information of one position in the organization architecture and the corresponding talent files of the incumbent staff to obtain an incumbent staff assessment analysis result;
the staff recommending unit is used for configuring the staff of the not-fully-filled staff in the organization structure, and performing evaluation analysis according to the staff information of the staff and the staff files of the enterprise staff in the enterprise staff resource library to obtain staff recommending evaluation analysis results.
The evaluation analysis module carries out intelligent evaluation analysis on positions in the enterprise organization structure, wherein the two conditions are included, and when the positions contain corresponding incumbent staff, evaluation analysis is carried out based on position information and the corresponding incumbent staff to complete the matching degree evaluation of the incumbent staff and the corresponding positions. Aiming at the positions with personnel available, intelligent evaluation analysis is carried out based on position information and personnel files in an enterprise personnel resource library to obtain personnel recommendation results matched with the positions; the human resource manager is facilitated to adjust the personnel configuration of the position or further recruit/pick up personnel according to the evaluation result; helps to improve the level of intelligence of personnel management for job positions.
Preferably, the incumbent person assessment unit includes:
aiming at position information of one position in an organization structure, acquiring skill requirements and position characteristics of the position, and constructing a position feature vector;
acquiring a talent file of the job title, acquiring resume information and evaluation information of the job title according to the talent file of the job title, extracting professional skill information of the job title from the resume information, acquiring evaluation characteristics of the job title from the evaluation information, and constructing talent characteristic vectors of the job title according to the acquired professional skill information and the evaluation characteristics;
inputting the acquired position feature vector and talent feature vector into a trained evaluation analysis model to obtain position matching degree output by the evaluation analysis model as an evaluation analysis result of on-job personnel;
and when the job matching degree is lower than a preset standard, marking that the evaluation analysis result of the job personnel is abnormal.
Wherein the skill requirements include working years requirements, qualification certificates requirements, academic school requirements, professional skill rating requirements, and the like; professional skill information includes working years information, qualification certificate information, academic degree information, professional skill rating information, and the like; the job characteristics include job content description, responsibility description and the like; the evaluation characteristics comprise personnel self-evaluation, interview evaluation, superior evaluation, historical work record and the like;
In one scenario, based on the job description of the target job, the skill requirement (such as possession of professional qualification, foreign language level, etc.) that the job needs to be rigidly specified and the job characteristic (such as responsibility information) that the job needs to be met are extracted, and a job feature vector (such as { accounting special personnel, financial accounting, finance, economy, management, etc. related professional university and college, 3-year working experience, responsibility for checking ERP system expense reimbursement documents and various flows … … are carefully, honest, straight, work responsibility center is … … }) corresponding to the job is constructed; acquiring resume information and evaluation information of the incumbent person according to the talent record of the incumbent person in the position to construct talent feature vectors of the incumbent person (such as { Gramineae, accountant profession, 5-year working experience, accountant qualification, medium-grade economic qualification, familiarity with financial tax management system use … … … … }); inputting the acquired job feature vector and talent feature vector into a trained evaluation analysis model, performing matching degree evaluation analysis by the evaluation analysis model according to the acquired two feature vectors, and acquiring evaluation analysis results of the job personnel according to the matching degree between the job personnel and the job site.
The intelligent evaluation analysis between the incumbent personnel information and the corresponding position information is beneficial to assisting a human resource manager in adjusting and managing the position/post arrangement of the incumbent personnel, completing the allocation of human resources and improving the intelligent level of talent management of the enterprise position.
The evaluation analysis model can adopt an evaluation analysis model trained in the prior art to acquire the matching degree between the talent information and the position information according to the talent information and the position information; or training the evaluation analysis model based on the built model and the built training set to obtain a trained evaluation analysis model, and acquiring the matching degree between talent information and position information through the evaluation analysis model.
The training set can be used for completing construction by manually marking the matching degree of talent information and position information by a human resource manager, and further training and verifying the evaluation analysis model by the training set to complete construction of the evaluation analysis model.
Preferably, the evaluation analysis model is built based on a neural network of deep learning, wherein the evaluation analysis model comprises an input layer, a skill evaluation layer, a characteristic evaluation layer and a fusion analysis layer;
The input layer is used for acquiring a position feature vector and a talent feature vector, extracting skill requirements from the position feature vector and extracting professional skill information from the talent feature vector, and inputting the skill requirements and the talent feature vector to the skill assessment layer; extracting position characteristics from the position characteristic vectors and extracting evaluation characteristics from talent characteristic vectors respectively, and inputting the evaluation characteristics to a characteristic evaluation layer;
the skill evaluation layer is used for matching corresponding items from the practice skill information based on the obtained skill requirements, when the skill requirements can be matched with the corresponding practice skill information, the skill requirements are marked to finish matching, otherwise, the skill requirements are marked to fail to finish matching, and skill requirement evaluation results are obtained according to the skill requirements and corresponding matching marks and are output to the fusion analysis layer;
the characteristic evaluation layer extracts position characteristic text representation and evaluation characteristic text representation according to the acquired position characteristics and evaluation characteristics respectively by using a BiLSTM model, calculates similarity between the position characteristic text representation and the evaluation characteristic text representation by adopting a similarity analysis model in combination with a preset text characteristic weight factor, and inputs a position characteristic evaluation analysis result into the fusion analysis layer; the activation function adopted by the similarity analysis model is a sigmoid function;
The fusion analysis layer is used for carrying out normalization operation according to the acquired skill requirement evaluation result and the acquired position characteristic evaluation analysis result, so as to obtain and output the position matching degree between the designated position and the personnel.
Based on the built evaluation analysis model, comprehensive evaluation analysis can be performed on the hard index on the skill level and the soft index on the talent characteristic level, and the matching degree between the target talents and the positions is analyzed from 2 dimensions and is used as the basis for evaluation analysis results of staff in charge and recommendation evaluation analysis results of talents.
Preferably, the job title recommending unit includes:
aiming at personnel configuration in an organization structure, acquiring the skill requirement and the position characteristic of the position, and constructing a position feature vector;
acquiring resume information and evaluation information of enterprise talents according to talents files of the enterprise talents in an enterprise talent resource library, extracting professional skill information of the enterprise talents from the resume information, acquiring evaluation characteristics of the enterprise talents from the evaluation information, and constructing talent feature vectors of the enterprise talents according to the acquired professional skill information and the evaluation characteristics;
according to the acquired position feature vector and talent feature vector, inputting the acquired position feature vector and talent feature vector into a trained evaluation analysis model, and obtaining position matching degree output by the evaluation analysis model as matching degree of enterprise talents and target positions;
And arranging the talents of each enterprise according to the matching degree of the talents and the target positions from high to low, and obtaining a list as a talent recommendation evaluation analysis result.
Aiming at the positions with personnel available, the talent recommending unit constructs corresponding feature vectors according to position information and talent files in the talent resource library of the enterprise, obtains the matching degree between different talents and the available positions based on the evaluation analysis model, ranks and outputs talent recommending, evaluating and analyzing results corresponding to the available positions according to the matching degree, and provides personnel for a human resource manager to supplement the available positions according to the talent recommending, evaluating and analyzing results as references.
When the matching degree analysis of the available positions is performed based on the talent files in the talent resource library, a simple screening mechanism can be added to primarily screen the talent files meeting the hardness index or requirement, and further matching degree evaluation analysis is performed, so that the performance of the position talent recommending unit is improved.
The limited evaluation analysis model can be adopted in the position talent recommending unit to acquire the matching degree between the target position of the unfilled person and the talents of the enterprise; and arranging the talents of each enterprise according to the matching degree of the talents and the target positions from high to low to obtain a list as talent recommendation evaluation analysis results.
Preferably, the system further comprises a recruitment interview module;
the recruitment interview module is used for recommending, evaluating and analyzing results according to talents obtained by the position talent recommending unit, calling corresponding talent files according to the talent recommending, interviewing corresponding positions according to talent file information and corresponding recommended talents, and recording corresponding interview results.
Aiming at personnel supplement of the available position, a human resource manager can acquire talent archive information of corresponding enterprise talents according to talent recommendation evaluation analysis results (lists) obtained by a talent recommendation unit, and send a interview request of the available position to the enterprise talents according to the talent archive information, so that the enterprise talents (particularly personnel outside enterprises) can initiate interviews with the available position according to the interview request. The interview mode can be performed in an online interview mode, so that the adaptability and the intelligent level of the talent management system are further improved.
Preferably, the recruitment interview module includes an archive retrieving unit and an online interview unit;
the file retrieving unit is used for retrieving corresponding talent files according to talent recommendation evaluation analysis results obtained by the position talent recommendation unit and according to the talent recommendation evaluation analysis results;
The online interview unit is used for sending interview requests of corresponding positions to the talents of the enterprise according to the talent file information and inviting the talents of the enterprise to finish online interview so as to obtain corresponding online interview results; wherein the online interview includes an online video interview;
preferably, the online test unit includes a video call unit;
the video call unit is used for establishing video call connection with the talents of the enterprise after the talents of the enterprise receive the interview request;
preferably, the online test unit further comprises an identity recognition unit;
the identity recognition unit is used for acquiring face image information of the interviewee according to the acquired video call picture and carrying out identity recognition according to the acquired face image information in the process that the video call unit is used for carrying out video interview on enterprise personnel, so as to acquire the identity information of the interviewee; and comparing and matching the obtained identity information of the interviewee with the identity information in the talent file, and obtaining the identity verification result of the interviewee to be consistent when the identity information obtained by matching is consistent.
Aiming at the situation that identities such as false identities, replacement interviews and the like possibly appear in the video interview process (for example, external reserve personnel established for resume screening, resume information of the external reserve personnel is different from real personnel conditions and the like), the identity information of the interview person is particularly identified according to video images when the video interview is carried out, and intelligent verification is carried out according to the identified identity information and the corresponding identity information in talent files, so that the identity of the interview personnel is ensured to be consistent with the talent files reserved by enterprises, and the reliability of the video interview is improved.
Preferably, the identification unit comprises:
in the interviewee video interview process, performing face recognition according to the acquired video image to obtain an interviewee face image;
extracting features according to the face images of the interviewees to obtain face feature data of the interviewees;
and carrying out matching comparison analysis on the face feature data of the interviewee and the face feature data corresponding to the interviewee identity (according to the identity information recorded in the talent file) in the real-name information database or the face feature data corresponding to the photo reserved in the talent file according to the acquired face feature data of the interviewee, and outputting an identity verification result to be consistent when the matching comparison similarity is higher than a preset threshold value.
Preferably, extracting a face image of a interviewee by adopting a face recognition model based on YoloV5 according to the acquired video image; extracting features of the face image of the interviewer according to the face image of the interviewer, wherein a CNN-based neural network model is adopted to extract the features of the face image of the interviewer, so as to obtain feature vectors corresponding to the face image; matching and matching the obtained feature vector with a feature vector prestored in a real-name information database by an interviewer (or a feature vector obtained according to a face image reserved in a talent archive of the interviewer), and obtaining an identity verification result.
The face image of the interviewee is extracted in the video interview process, and the identity recognition is further completed, so that the authenticity of the identity of the video interviewee can be ensured, the possible abnormal situation of an enterprise can be timely reminded, unnecessary manpower and material resources (the identity of the interviewee is found to be counterfeited after the interview is completed, and the like) are avoided, and the intelligent level of the enterprise for the match and interview of the staff in the available positions is further improved.
Preferably, the video call unit includes a video enhancement unit;
the video enhancement unit is used for enhancing the video image picture of the interviewee in the process of performing video interview with the interviewee and improving the definition of the video image picture.
Aiming at the video interview process, an interviewer usually performs video interview in an indoor environment, the indoor environment is easily influenced by the state of illumination light, and the face of the interviewer reflects light or is dark in a video image picture, so that the face detail information in the video image picture is captured or is not clearly expressed, and the accuracy of identifying the identity information of the interviewer is influenced. The video enhancement unit is particularly arranged in the video call unit to enhance the video image picture, so that the definition of the video image picture is improved, and the adaptability and the reliability of video interview are improved.
Preferably, the video enhancement unit includes:
aiming at the acquired video image picture, adopting a face recognition model based on a YoloV5 deep learning network to process the video image picture, extracting and marking face area images in the video image picture, wherein the extracted face area images are rectangular areas;
performing image wavelet decomposition according to the obtained face region image to obtain a low-frequency component subgraph FraL and three high-frequency component subgraphs FraH of the face region image 1 、FraH 2 And FraH 3 ；
Calculating the detail characteristics of each pixel point according to the acquired high-frequency component subgraph, wherein the adopted detail characteristic calculation function is as follows:
where minu (x, y) represents the minutiae feature values at the pixel point (x, y),representing the energy characteristics of a pixel point (x, y) in the r-th high-frequency component subgraph, wherein when r satisfies +.>And->When in use, then->Otherwise, go (L)>Wherein the method comprises the steps ofRepresents a first peripheral region at a pixel point (x, y), and (a, b) is a variable representing +.>Pixel within range VaH s (a, b) representing pixel values of pixel points (x, y) in the s-th high-frequency component sub-graph, and EThr representing a preset energy threshold, wherein EThr > 0; s represents a variable; vaH r (x, y) represents the pixel value of the pixel point (x, y) in the r-th high-frequency component sub-graph;
Forming a detail high-frequency component subgraph FraM according to detail characteristic values of all pixel points, marking the pixel points with the detail characteristic values larger than 0 in the peripheral pixel points in a second peripheral area taking the pixel point as a center as detail pixel points, and taking an area covered by the detail pixel points of the general machine as a detail area;
reconstructing according to the detail high-frequency component subgraph FraM and the low-frequency component subgraph FraL to obtain a transition image Fratds;
returning the obtained transition image Fratds to the video image picture, converting the video image picture from RGB color space to Lab color space, and extracting the brightness component Luc of the video image picture;
and carrying out regional brightness adjustment processing according to the obtained brightness component Luc:
and carrying out brightness adjustment on the detail area, wherein the adopted detail area brightness adjustment function is as follows:
where vL' (x, y) represents the luminance component value of the pixel (x, y) after luminance adjustment in the detail region, where (x, y) is the pixel belonging to the detail region, vL (x, y) represents the luminance component value of the pixel (x, y),representing the average luminance component value of all pixel points belonging to the detail region in the second peripheral range centered on the pixel point (x, y), vLthr representing a preset detail luminance standard value, ω a And omega b Respectively represent weight factors, wherein omega a +ω b ＝1；vLdd u And vLdd d Respectively represent preset brightness boundaries, vLdd t Representing a preset brightness change factor;
and carrying out brightness adjustment on other areas except the detail area, wherein the brightness adjustment function of the adopted other areas is as follows:
wherein vL' (x, y) represents the brightness component value of the pixel point (x, y) after brightness adjustment in other areas, wherein (x, y) is the pixel point belonging to other areas except the detail area, vLθ (x, y) represents the average brightness component value of all the pixel points in the second peripheral range with the pixel point (x, y) as the center, and vLthr represents the preset detail brightness standardThe value of the quasi-constant is set,representing the nearest pixel distance of the pixel point (x, y) from the detail area, disthr representing a preset distance standard value, alpha u And alpha d Representing a predetermined variation factor omega c And omega d Respectively represent weight factors, wherein omega c +ω d ＝1；
And carrying out Lab-to-RGB color space inverse transformation according to the brightness component Luc' after the regional brightness adjustment processing to obtain an enhanced video image picture.
Preferably, the first peripheral region at the pixel point (x, y) includes a rectangular region of 3×3,5×5,7×7, etc. centered on the pixel point (x, y), or a circular range region centered on the pixel point (x, y), r=1, 2,3 … being a radius.
Preferably, the second peripheral region at the pixel point (x, y) includes a 3×3,5×5 rectangular region centered on the pixel point (x, y), or a circular range region centered on the pixel point (x, y), r=1, 2,3 being a radius.
Optionally, vLdd for luminance boundary u The value of (2) is in the range of 80-85, preferably 85; vLdd for luminance boundary d The value of (2) is in the range of 10-15, preferably 10; the luminance change factor vLddt has a value ranging from 4 to 5, preferably 5.
Optionally, the value of the detail brightness standard value vLthr is in the range of 60-65, preferably 65.
Alternatively, the variation factor alpha u The value of (2) is in the range of 0.7-0.8, preferably 0.8; factor of change alpha d The value of (2) is in the range of 0.2 to 0.3, preferably 0.3.
Optionally, the range of the distance standard value disthr isD represents the image size, preferably +.>
Further, the identity recognition unit performs further face extraction and identity recognition processing according to the enhanced video image picture, and performs intelligent verification on the identity information of the face tester.
The method aims at solving the problems that the video image picture in the video interview process is easily influenced by environmental factors, so that the detailed characteristic representation of the face part is unclear, and the accuracy and the video definition of the subsequent face-based identity recognition are influenced. The above embodiment provides a technical scheme for enhancing the video image of the interviewee specially aiming at the video interview process so as to improve the image definition and the characterization level of the face features. Specifically, firstly, processing a video image picture based on a face recognition model, extracting a face region in the picture, further decomposing a wavelet of a local image according to the obtained face region, analyzing a detail characteristic region according to an obtained high-frequency component subgraph, and accurately extracting the detail characteristic part of the image through pixel points in the high-frequency component subgraph. Considering that in the traditional detailed part extraction process, the judgment of a single pixel point is generally carried out based on a high-frequency component subgraph, so that the situation that noise pixel points are misjudged as characteristic pixel points exists, the detailed feature calculation function is particularly provided for representing and extracting detailed parts in the whole image based on the regional energy of the pixel points based on the characteristics of face images acquired in the video interview process, meanwhile, noise interference in the image is effectively provided, the detailed high-frequency component subgraph is formed through the extracted detailed feature values, the image is further reconstructed, and the detailed features of face regions in the image can be highlighted. Meanwhile, in subsequent processing, according to the obtained characteristic part, brightness components extracted based on Lab color space are further subjected to regional brightness adjustment on the video image picture, wherein in the process of adjusting a detail region, self-adaptive correction is focused on the condition of influencing characteristic representation such as reflection, darkness and the like, and meanwhile, the overall brightness level and definition of the detail part are improved. After the brightness of the detail area is adjusted, the other areas are further subjected to adaptive brightness adjustment, wherein in the adjustment process, the adaptive setting adjustment can be performed based on other areas (including the background and other areas which do not belong to the detail part in the face area), and the characteristic representation level of the face area is further improved while the image distortion easily occurring in the traditional background adjustment technology is avoided under the condition that the brightness level of the face area is adaptively improved in a gradual change adjustment mode, and the definition of a video image picture is effectively improved. By adopting the method, the self-adaptive enhancement processing is carried out on the video image pictures acquired by both sides in the video interview process, so that the definition of the video pictures can be improved, the experience of the video interview is improved, and the reliability and the robustness of the identity verification are further carried out according to the video image pictures.
It should be noted that, in each embodiment of the present invention, each functional unit/module may be integrated in one processing unit/module, or each unit/module may exist alone physically, or two or more units/modules may be integrated in one unit/module. The integrated units/modules described above may be implemented either in hardware or in software functional units/modules.
From the description of the embodiments above, it will be apparent to those skilled in the art that the embodiments described herein may be implemented in hardware, software, firmware, middleware, code, or any suitable combination thereof. For a hardware implementation, the processor may be implemented in one or more of the following units: an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a processor, a controller, a microcontroller, a microprocessor, other electronic units designed to perform the functions described herein, or a combination thereof. For a software implementation, some or all of the flow of an embodiment may be accomplished by a computer program to instruct the associated hardware. When implemented, the above-described programs may be stored in or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a computer. The computer readable media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the scope of the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (9)
1. An intelligent talent management system for enterprises is characterized by comprising a talent library management module, an enterprise architecture management module and an evaluation analysis module; wherein,
the talent library management module is used for establishing an enterprise talent resource library and storing and managing talent files of enterprise talents according to the enterprise talent resource library, wherein the enterprise talents comprise staff in the enterprise and external reserve staff, and the talent files of the enterprise talents comprise staff in-staff information, identity information, resume information and evaluation information;
the enterprise architecture management module is used for building an enterprise organization architecture according to actual conditions, wherein the enterprise organization architecture comprises position information and position corresponding incumbent personnel information, and the position information comprises position description and position required conditions;
The evaluation analysis module is used for performing evaluation analysis according to the position information and the corresponding incumbent personnel information in the enterprise organization architecture to obtain an incumbent personnel evaluation analysis result; and/or according to the position information in the enterprise organization architecture and the talents files of the enterprise talents in the enterprise talents resource library, performing evaluation analysis to obtain talent recommendation evaluation analysis results.
2. The intelligent enterprise talent management system according to claim 1, wherein the talent library management module comprises a talent archive creation unit and a talent resource library management unit;
the talent file establishing unit establishes a talent file for personnel of an incumbent enterprise or personnel outside the enterprise, and stores the talent file into a talent resource library;
the talent resource library management unit is used for performing the management operations of consulting, updating and deleting the talent files in the talent resource library.
3. The intelligent talent management system of claim 1, wherein the enterprise architecture management module comprises an organization architecture setting unit and a personnel setting unit;
the organization architecture setting unit is used for setting up an enterprise organization architecture according to the actual situation of an enterprise, wherein the enterprise organization architecture comprises position information of each position and upper and lower relation information among the positions; the position information comprises position names, the number of staff members and required skill requirements;
The personnel setting unit is used for setting corresponding incumbent personnel information for each position in the enterprise organization structure according to the actual condition of the enterprise, including adding, modifying and deleting the corresponding incumbent personnel information for the position.
4. The intelligent enterprise talent management system of claim 1, wherein the assessment and analysis module comprises an incumbent personnel assessment unit and a job talent recommendation unit;
the incumbent staff assessment unit is used for carrying out assessment analysis according to the position information of one position in the organization architecture and the corresponding talent files of the incumbent staff to obtain an incumbent staff assessment analysis result;
the staff recommending unit is used for configuring the staff of the not-fully-filled staff in the organization structure, and performing evaluation analysis according to the staff information of the staff and the staff files of the enterprise staff in the enterprise staff resource library to obtain staff recommending evaluation analysis results.
5. The intelligent talent management system of claim 4, wherein the incumbent person assessment unit comprises:
aiming at position information of one position in an organization structure, acquiring skill requirements and position characteristics of the position, and constructing a position feature vector;
Acquiring a talent file of the job title, acquiring resume information and evaluation information of the job title according to the talent file of the job title, extracting professional skill information of the job title from the resume information, acquiring evaluation characteristics of the job title from the evaluation information, and constructing talent characteristic vectors of the job title according to the acquired professional skill information and the evaluation characteristics;
inputting the acquired position feature vector and talent feature vector into a trained evaluation analysis model to obtain position matching degree output by the evaluation analysis model as an evaluation analysis result of on-job personnel;
and when the job matching degree is lower than a preset standard, marking that the evaluation analysis result of the job personnel is abnormal.
6. The intelligent enterprise talent management system of claim 5, wherein the assessment analysis model is built based on a deep learning neural network, wherein the assessment analysis model comprises an input layer, a skill assessment layer, a characteristic assessment layer and a fusion analysis layer;
the input layer is used for acquiring a position feature vector and a talent feature vector, extracting skill requirements from the position feature vector and extracting professional skill information from the talent feature vector, and inputting the skill requirements and the talent feature vector to the skill assessment layer; extracting position characteristics from the position characteristic vectors and extracting evaluation characteristics from talent characteristic vectors respectively, and inputting the evaluation characteristics to a characteristic evaluation layer;
The skill evaluation layer is used for matching corresponding items from the practice skill information based on the obtained skill requirements, when the skill requirements can be matched with the corresponding practice skill information, the skill requirements are marked to finish matching, otherwise, the skill requirements are marked to fail to finish matching, and skill requirement evaluation results are obtained according to the skill requirements and corresponding matching marks and are output to the fusion analysis layer;
the characteristic evaluation layer extracts position characteristic text representation and evaluation characteristic text representation according to the acquired position characteristics and evaluation characteristics respectively by using a BiLSTM model, calculates similarity between the position characteristic text representation and the evaluation characteristic text representation by adopting a similarity analysis model in combination with a preset text characteristic weight factor, and inputs a position characteristic evaluation analysis result into the fusion analysis layer; the activation function adopted by the similarity analysis model is a sigmoid function;
the fusion analysis layer is used for carrying out normalization operation according to the acquired skill requirement evaluation result and the acquired position characteristic evaluation analysis result, so as to obtain and output the position matching degree between the designated position and the personnel.
7. The intelligent talent management system of claim 4, wherein the job title recommending unit comprises:
Aiming at personnel configuration in an organization structure, acquiring the skill requirement and the position characteristic of the position, and constructing a position feature vector;
acquiring resume information and evaluation information of enterprise talents according to talents files of the enterprise talents in an enterprise talent resource library, extracting professional skill information of the enterprise talents from the resume information, acquiring evaluation characteristics of the enterprise talents from the evaluation information, and constructing talent feature vectors of the enterprise talents according to the acquired professional skill information and the evaluation characteristics;
according to the acquired position feature vector and talent feature vector, inputting the acquired position feature vector and talent feature vector into a trained evaluation analysis model, and obtaining position matching degree output by the evaluation analysis model as matching degree of enterprise talents and target positions;
and arranging the talents of each enterprise according to the matching degree of the talents and the target positions from high to low, and obtaining a list as a talent recommendation evaluation analysis result.
8. The intelligent talent management system of claim 1, further comprising a recruitment interview module;
the recruitment interview module is used for recommending, evaluating and analyzing results according to talents obtained by the position talent recommending unit, calling corresponding talent files according to the talent recommending, interviewing corresponding positions according to talent file information and corresponding recommended talents, and recording corresponding interview results.
9. The intelligent talent management system of claim 8, wherein the recruitment interview module comprises an archive retrieval unit and an online interview unit;
the file retrieving unit is used for retrieving corresponding talent files according to talent recommendation evaluation analysis results obtained by the position talent recommendation unit and according to the talent recommendation evaluation analysis results;
the online interview unit is used for sending interview requests of corresponding positions to the talents of the enterprise according to the talent file information and inviting the talents of the enterprise to finish online interview so as to obtain corresponding online interview results; wherein the online interview includes an online video interview.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311484249.XA CN117291559A (en) | 2023-11-08 | 2023-11-08 | Intelligent talent management system for enterprises |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311484249.XA CN117291559A (en) | 2023-11-08 | 2023-11-08 | Intelligent talent management system for enterprises |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117291559A true CN117291559A (en) | 2023-12-26 |
Family
ID=89251946
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311484249.XA Pending CN117291559A (en) | 2023-11-08 | 2023-11-08 | Intelligent talent management system for enterprises |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117291559A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110363498A (en) * | 2019-07-12 | 2019-10-22 | 北京亮马手信息咨询有限公司 | A kind of team's recruitment methods and system |
| CN110378544A (en) * | 2018-04-12 | 2019-10-25 | 百度在线网络技术（北京）有限公司 | A kind of personnel and post matching analysis method, device, equipment and medium |
| CN115018468A (en) * | 2022-07-01 | 2022-09-06 | 佛山市蜂王人力资源有限公司 | Network recruitment management system and method based on big data analysis |
| US20230196296A1 (en) * | 2021-12-16 | 2023-06-22 | Tata Consultancy Services Limited | Method and system for prediction of proficiency of person in skills from resume |
-
2023
- 2023-11-08 CN CN202311484249.XA patent/CN117291559A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110378544A (en) * | 2018-04-12 | 2019-10-25 | 百度在线网络技术（北京）有限公司 | A kind of personnel and post matching analysis method, device, equipment and medium |
| CN110363498A (en) * | 2019-07-12 | 2019-10-22 | 北京亮马手信息咨询有限公司 | A kind of team's recruitment methods and system |
| US20230196296A1 (en) * | 2021-12-16 | 2023-06-22 | Tata Consultancy Services Limited | Method and system for prediction of proficiency of person in skills from resume |
| CN115018468A (en) * | 2022-07-01 | 2022-09-06 | 佛山市蜂王人力资源有限公司 | Network recruitment management system and method based on big data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9652745B2 (en) | Model-driven evaluator bias detection | |
| US11769014B2 (en) | Classifying digital documents in multi-document transactions based on signatory role analysis | |
| CN110069609B (en) | Referee document analysis method, referee document analysis device, computer equipment and storage medium | |
| US11790499B2 (en) | Certificate image extraction method and terminal device | |
| CN110446063A (en) | Generation method, device and the electronic equipment of video cover | |
| CN106557995A (en) | Based on intelligent terminal and the Teaching Management Method of cloud platform | |
| CN110139067A (en) | A kind of wild animal monitoring data management information system | |
| CN113287133A (en) | Interview image automatic evaluation model management method, interview image automatic evaluation model management system and computer readable medium | |
| CN112651333B (en) | Silence living body detection method, silence living body detection device, terminal equipment and storage medium | |
| CN111815169A (en) | Business approval parameter configuration method and device | |
| CN110502694A (en) | Lawyer's recommended method and relevant device based on big data analysis | |
| CN105957172A (en) | Photograph attendance application system of intelligent photograph electrical screen | |
| KR102519033B1 (en) | Artificial intelligence learning-based monitoring method for artificial intelligence learning-based laws and regulations and a program for this | |
| CN117114514A (en) | Talent information analysis management method, system and device based on big data | |
| CN111784665A (en) | OCT image quality assessment method, system and device based on Fourier transform | |
| CN116205726B (en) | Loan risk prediction method and device, electronic equipment and storage medium | |
| CN109710628A (en) | Information processing method and device, system, computer and readable storage medium storing program for executing | |
| CN116701706A (en) | Data processing method, device, equipment and medium based on artificial intelligence | |
| CN117291559A (en) | Intelligent talent management system for enterprises | |
| CN111898548A (en) | Visitor identity authentication method and device based on machine learning and computer equipment | |
| CN116052251A (en) | Face image optimization method, device, equipment and storage medium | |
| CN113128452A (en) | Greening satisfaction acquisition method and system based on image recognition | |
| CN114529244A (en) | HRD-based interview data processing method and interview evaluation method and device | |
| CN110955727A (en) | Automatic student homework recording system | |
| CN110751110A (en) | Identity image information verification method, device, equipment and storage medium |
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 |