CN111368737A - A system and method for automatically analyzing employee work behavior - Google Patents
A system and method for automatically analyzing employee work behaviorDownload PDFInfo
- Publication number
- CN111368737A CN111368737ACN202010144845.3ACN202010144845ACN111368737ACN 111368737 ACN111368737 ACN 111368737ACN 202010144845 ACN202010144845 ACN 202010144845ACN 111368737 ACN111368737 ACN 111368737A
- Authority
- CN
- China
- Prior art keywords
- module
- employee
- file
- server
- image
- 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 OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Multimedia (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Collating Specific Patterns (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本发明涉及一种管理系统领域，尤其涉及一种自动分析员工工作行为的系统及方法。The invention relates to the field of management systems, in particular to a system and method for automatically analyzing the work behavior of employees.
背景技术Background technique
现在的公司评判员工工作行为和状态大多采用的是上级的主观判断，部分优秀的公司采用的是OKR等考核指标，但这些指标本身也存在主观依据，很难从两个都优秀的员工，或两个都差的员工中进行选择，优中选优，差中选差，这些一直是公司人力资源的难题，困扰着很多的管理人员。Today’s companies mostly use the subjective judgment of their superiors to judge employees’ work behavior and status. Some excellent companies use OKR and other assessment indicators, but these indicators themselves also have subjective basis, and it is difficult to judge from two excellent employees, or The choice between two poor employees, the best among the best, and the poor among the poor, has always been a difficult problem for the company's human resources, which has plagued many managers.
发明内容SUMMARY OF THE INVENTION
本发明提供一种自动分析员工工作行为的系统及方法，解决上述难题。具体方案如下。The present invention provides a system and method for automatically analyzing the work behavior of employees to solve the above problems. The specific plan is as follows.
一种自动分析员工工作行为的系统，其特征在于：A system for automatically analyzing employee work behavior, characterized by:
监控模块，与一服务器连接，用于拍摄员工的工作视频文件并上传到服务器；The monitoring module, connected with a server, is used to shoot the working video files of employees and upload them to the server;
视频处理模块，与服务器连接，用于定期处理工作视频文件得到图像文件；The video processing module is connected with the server, and is used for regularly processing working video files to obtain image files;
人脸检测模块，与服务器连接，用于根据图像文件识别员工身份信息；A face detection module, connected to the server, is used to identify employee identity information based on image files;
图像分类模块，分别与服务器和和人脸检测模块连接，用于将图像文件和员工身份信息进行匹配得到匹配结果；The image classification module is connected to the server and the face detection module respectively, and is used to match the image file with the employee identity information to obtain the matching result;
分析计算模块，与图像分类模块连接，用于根据匹配结果计算员工的工作状态得分；The analysis and calculation module is connected with the image classification module, and is used to calculate the employee's work status score according to the matching result;
显示模块，与分析计算模块连接，用于显示员工的每天工作状态得分。The display module is connected with the analysis and calculation module to display the daily work status score of the employee.
其特征在于，该系统还包括：It is characterized in that the system also includes:
注册模块，对员工人脸进行注册，将注册的人脸特征信息上传到云端；The registration module registers the employee's face and uploads the registered face feature information to the cloud;
考核模块，制定考核指标并上传到云端；Assessment module, formulate assessment indicators and upload them to the cloud;
视频处理模块用于定期从服务器中提取工作视频文件，对工作视频文件进行图像按帧处理分割成图像文件，将图像文件按时间存储在服务器中；The video processing module is used for regularly extracting working video files from the server, performing image processing on the working video files and dividing them into image files by frame, and storing the image files in the server according to time;
人脸检测模块用于从服务器中提取图像文件，检测图像文件中的人脸特征信息并与云端存储的人脸特征信息比较，识别员工身份信息，进而将确定的员工身份发送给图像分类模块；The face detection module is used to extract the image file from the server, detect the face feature information in the image file and compare it with the face feature information stored in the cloud, identify the employee identity information, and then send the determined employee identity to the image classification module;
图像分类模块用于从服务器中提取图像文件，识别人脸附近的物体类型并与确定的员工身份匹配，将匹配结果发送至分析计算模块；The image classification module is used to extract image files from the server, identify the types of objects near the face and match them with the determined employee identity, and send the matching results to the analysis and calculation module;
分析计算模块用于综合分析匹配结果，得到员工的工作状态，根据从云端提取的考核指标计算得出员工的每天工作状态得分。The analysis and calculation module is used to comprehensively analyze the matching results, obtain the working status of the employees, and calculate the daily working status scores of the employees according to the assessment indicators extracted from the cloud.
其特征在于，该系统还包括：It is characterized in that the system also includes:
视频处理模块用于将工作视频文件转换为音频文件，将音频文件按时间存储在服务器中；The video processing module is used to convert the working video files into audio files, and store the audio files in the server according to time;
一音频检测模块，音频检测模块分别与服务器和分析计算模块连接，用于从服务器中提取音频文件，提取与工作相关的关键字和时间点发送至分析计算模块；an audio detection module, the audio detection module is respectively connected with the server and the analysis calculation module, and is used for extracting audio files from the server, extracting keywords and time points related to the work and sending them to the analysis calculation module;
分析计算模块用于综合分析匹配结果以及与工作相关的关键字和时间点得到员工的工作状态，根据从云端提取的考核指标计算得出员工的每天工作状态得分。The analysis and calculation module is used to comprehensively analyze the matching results and the keywords and time points related to the work to obtain the employee's work status, and calculate the employee's daily work status score according to the assessment indicators extracted from the cloud.
其特征在于：注册模块还用于对员工声音进行注册，将注册的声音特征信息上传至云端；It is characterized in that: the registration module is also used to register the employee's voice, and upload the registered voice feature information to the cloud;
音频检测模块还用于检测音频文件中的声音特征信息，并与与云端存储的声音特征信息比较，进而识别员工身份信息；The audio detection module is also used to detect the sound feature information in the audio file, and compare it with the sound feature information stored in the cloud, so as to identify the employee identity information;
该系统包含一确定模块，该确定模块分别与人脸检测模块、音频检测模块以及分析计算模块连接，用于根据人脸检测模块识别的员工身份信息和音频检测模块识别的员工身份信息进一步确定员工身份，将确定的员工身份发送给图像分类模块。The system includes a determination module, which is respectively connected with the face detection module, the audio detection module and the analysis and calculation module, and is used to further determine the employee according to the employee identity information identified by the face detection module and the employee identity information identified by the audio detection module. identity, and send the determined employee identity to the image classification module.
其特征在于：该系统包括一数据提取模块，数据提取模块分别与分别与服务器、图像分类模块、音频检测模块和人脸检测模块连接；It is characterized in that: the system includes a data extraction module, and the data extraction module is respectively connected with the server, the image classification module, the audio detection module and the face detection module;
数据提取模块用于从服务器中提取图像文件和音频文件，将图像文件分别转发给人脸检测模块和图像分类模块，将音频文件转发给音频检测模块；The data extraction module is used to extract image files and audio files from the server, forward the image files to the face detection module and the image classification module respectively, and forward the audio files to the audio detection module;
人脸检测模块用于从数据提取模块中接收图像文件；The face detection module is used to receive image files from the data extraction module;
音频检测模块用于从数据提取模块中接收音频文件；The audio detection module is used to receive audio files from the data extraction module;
图像分类模块用于从数据提取模块中接收图像文件。The image classification module is used to receive image files from the data extraction module.
一种自动分析员工工作行为的方法，其特征在于：使用如上的一种自动分析员工工作行为的系统，具有如下步骤：A method for automatically analyzing employee work behavior, characterized in that: using the above system for automatically analyzing employee work behavior, the method has the following steps:
步骤S1，监控模块拍摄员工的工作视频文件并上传到服务器；Step S1, the monitoring module captures the working video file of the employee and uploads it to the server;
步骤S2，视频处理模块用于定期处理工作视频文件得到图像文件；Step S2, the video processing module is used for regularly processing working video files to obtain image files;
步骤S3，人脸检测模块用于根据图像文件识别员工身份信息；Step S3, the face detection module is used to identify employee identity information according to the image file;
步骤S4，图像分类模块用于将图像文件和员工身份信息进行匹配得到匹配结果；Step S4, the image classification module is used for matching the image file and the employee identity information to obtain a matching result;
步骤S5，分析计算模块用于根据匹配结果计算员工的工作状态得分；Step S5, the analysis and calculation module is used to calculate the work status score of the employee according to the matching result;
步骤S6：显示模块显示员工的工作状态得分。Step S6: The display module displays the employee's work status score.
其特征在于：It is characterized by:
在步骤S1之前还执行步骤S01：一注册模块对员工人脸进行注册，将注册的人脸特征信息上传到云端，考核模块制定考核指标并上传到云端；Step S01 is also performed before step S1: a registration module registers the employee's face, uploads the registered face feature information to the cloud, and the assessment module formulates assessment indicators and uploads them to the cloud;
在步骤S2中执行如下步骤S21:视频处理模块定期从服务器中提取工作视频文件,对工作视频文件进行图像按帧处理分割成图像文件,将图像文件按时间存储在服务器中；In step S2, perform the following steps S21: the video processing module regularly extracts the working video file from the server, performs the image processing on the working video file and divides it into image files by frame, and stores the image files in the server by time;
在步骤S3中执行如下步骤S31:人脸检测模块从服务器中提取图像文件；检测图像文件中的人脸特征信息并与云端存储的人脸特征信息比较，识别员工身份信息将确定的员工身份发送给图像分类模块；In step S3, execute the following steps S31: the face detection module extracts the image file from the server; detects the face feature information in the image file and compares it with the face feature information stored in the cloud, identifying the employee identity information and sending the determined employee identity Classify the image module;
在步骤S4中执行如下步骤S41:图像分类模块从服务器中提取图像文件，识别人脸附近的物体类型并与确定的员工身份匹配，将匹配结果发送至分析计算模块；In step S4, execute the following steps S41: the image classification module extracts the image file from the server, identifies the object type near the face and matches with the determined employee identity, and sends the matching result to the analysis calculation module;
在步骤S5中执行如下步骤S51:分析计算模块综合分析匹配结果，得到员工的工作状态；根据从云端提取的考核指标计算得出员工的每天工作状态得分。In step S5, the following step S51 is performed: the analysis and calculation module comprehensively analyzes the matching result to obtain the working status of the employee; and calculates the daily working status score of the employee according to the assessment index extracted from the cloud.
其特征在于：It is characterized by:
在步骤S2中还执行步骤S22：视频处理模块将工作视频文件转换为音频文件，将音频文件按时间存储在服务器中，其中步骤S22和步骤S21不分先后进行；In step S2, also perform step S22: the video processing module converts the working video file into an audio file, and stores the audio file in the server by time, wherein step S22 and step S21 are carried out in no particular order;
在步骤S3中还执行步骤S32：音频检测模块从服务器中提取音频文件，提取与工作相关的关键字和时间点发送至分析计算模块；其中步骤S31和步骤S32不分先后进行；In step S3, also perform step S32: the audio detection module extracts the audio file from the server, extracts the keywords and time points related to the work and sends them to the analysis and calculation module; wherein step S31 and step S32 are carried out in no particular order;
步骤S5执行如下步骤S52：分析计算模块综合分析匹配结果以及与工作相关的关键字和时间点得到员工的工作状态，根据从云端提取的考核指标计算得出员工的每天工作状态得分。Step S5 executes the following step S52: the analysis and calculation module comprehensively analyzes the matching result and the keywords and time points related to the work to obtain the working status of the employee, and calculates the daily work status score of the employee according to the assessment index extracted from the cloud.
其特征在于：It is characterized by:
在步骤S1之前还执行步骤S02：注册模块还对员工声音进行注册，将注册的声音特征信息上传至云端；其中步骤S01和步骤S02不分先后进行；Before step S1, step S02 is also performed: the registration module also registers the employee's voice, and uploads the registered voice feature information to the cloud; wherein step S01 and step S02 are performed in no particular order;
步骤S3执行如下步骤：Step S3 performs the following steps:
一步骤S33,音频检测模块还检测音频文件中的声音特征信息，并与云端存储的声音特征信息比较，进而识别员工身份信息；In step S33, the audio detection module also detects the sound feature information in the audio file, and compares it with the sound feature information stored in the cloud, thereby identifying the employee identity information;
一步骤S34：一确定模块根据人脸检测模块识别的员工身份信息和音频检测模块识别的员工身份信息进一步确定员工身份，将确定的员工身份发送给图像分类模块。Step S34: a determination module further determines the employee identity according to the employee identity information identified by the face detection module and the employee identity information identified by the audio detection module, and sends the determined employee identity to the image classification module.
其特征在于：It is characterized by:
在步骤S2和步骤S3之间还包括一步骤S203：一数据提取模块从服务器中提取图像文件和音频文件，将图像文件分别转发给人脸检测模块和图像分类模块，将音频文件转发给音频检测模块；A step S203 is also included between the step S2 and the step S3: a data extraction module extracts the image file and the audio file from the server, forwards the image file to the face detection module and the image classification module respectively, and forwards the audio file to the audio detection module. module;
在步骤S31中人脸检测模块从数据提取模块中接收图像文件；In step S31, the face detection module receives the image file from the data extraction module;
在步骤S32中音频检测模块从数据提取模块中接收音频文件；In step S32, audio detection module receives audio file from data extraction module;
在步骤S33中图像分类模块从数据提取模块中接收图像文In step S33, the image classification module receives the image file from the data extraction module.
本发明的有益技术效果是：全程自动化处理完成，提高员工工作行为，考核标准，为企业实现员工优中选优，晋升等提供数据依据。The beneficial technical effects of the invention are: the whole process of automatic processing is completed, the work behavior and assessment standards of employees are improved, and data basis is provided for enterprises to realize the selection of the best among the best and the promotion of employees.
附图说明Description of drawings
附图用来提供对本发明的进一步理解，并且构成说明书的一部分，与本发明的实施例一起用于解释本发明，并不构成对本发明的限制。在附图中：The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the specification, and are used to explain the present invention together with the embodiments of the present invention, and do not constitute a limitation to the present invention. In the attached image:
图1-5为本发明实施例提供的系统结构示意图；1-5 are schematic diagrams of a system structure provided by an embodiment of the present invention;
图6-10为本发明实施例的方法流程示意图。6-10 are schematic flowcharts of methods according to embodiments of the present invention.
其中：1、监控模块；2、服务器；3、视频处理模块；5、人脸检测模块，4、图像分类模块；6、音频检测模块；7、分析计算模块；8、显示模块；9、确定模块；10、数据提取模块；注册模块11；考核模块12。Among them: 1. Monitoring module; 2. Server; 3. Video processing module; 5. Face detection module; 4. Image classification module; 6. Audio detection module; 7. Analysis and calculation module; 8. Display module; 9. Confirmation module; 10, data extraction module; registration module 11; assessment module 12.
具体实施方式Detailed ways
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动的前提下所获得的所有其他实施例，都属于本发明保护的范围。The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present invention.
需要说明的是，在不冲突的情况下，本发明中的实施例及实施例中的特征可以相互组合。It should be noted that the embodiments of the present invention and the features of the embodiments may be combined with each other under the condition of no conflict.
下面结合附图和具体实施例对本发明作进一步说明，但不作为本发明的限定。The present invention will be further described below with reference to the accompanying drawings and specific embodiments, but it is not intended to limit the present invention.
请参阅图1-4，本发明提供一种自动分析员工工作行为的方法，包括注册模块(未在图中示出)、考核模块(未在图中示出)、监控模块1、视频处理模块3、音频检测模块6、人脸检测模块5、图像分类模块4、计算分析模块7以及显示模块8。1-4, the present invention provides a method for automatically analyzing the work behavior of employees, including a registration module (not shown in the figure), an assessment module (not shown in the figure), a monitoring module 1, and a video processing module 3. Audio detection module 6 , face detection module 5 , image classification module 4 , calculation analysis module 7 and display module 8 .
服务器2分别与监控模块1、视频处理模块3、音频检测模块6、人脸检测模块5、图像分类模块4连接。The server 2 is respectively connected with the monitoring module 1 , the video processing module 3 , the audio detection module 6 , the face detection module 5 , and the image classification module 4 .
其中，计算分析模块7分别与图像分类模块4和音频检测模块6、及显示模块8连接。The calculation and analysis module 7 is respectively connected with the image classification module 4, the audio detection module 6, and the display module 8.
在本系统中，对于注册模块，收集员工信息，将员工信息上传到云端。具体的，注册模块存储员工的人脸特征信息，将各员工的人脸特征信息上传到云端。具体的，注册模块包括人脸注册设备，人脸注册设备包括人脸注册硬件装置和人脸注册软件，通过人脸注册设备将各员工的人脸特征上传到云端。人脸注册软件可以是SDK或者APP。In this system, for the registration module, employee information is collected and uploaded to the cloud. Specifically, the registration module stores the facial feature information of employees, and uploads the facial feature information of each employee to the cloud. Specifically, the registration module includes a face registration device, the face registration device includes a face registration hardware device and a face registration software, and the face features of each employee are uploaded to the cloud through the face registration device. The face registration software can be SDK or APP.
进一步的，注册模块还用于收集和存储员工的声音特征信息，将各员工的声音特征信息上传到云端。具体的，注册模块还包括声音注册设备，声音注册设备包括声音注册硬件装置和声音注册软件，例如SDK或者APP。通过声音注册设备将各个员工的声音特征信息上传到云端。Further, the registration module is also used to collect and store the voice feature information of the employees, and upload the voice feature information of each employee to the cloud. Specifically, the registration module further includes a sound registration device, and the sound registration device includes a sound registration hardware device and a sound registration software, such as SDK or APP. Upload the voice feature information of each employee to the cloud through the voice registration device.
作为本发明的优选实施方式，注册模块存储各个员工的人脸特征信息和声音特征信息，将人脸特征信息和声音特征信息上传到云端。As a preferred embodiment of the present invention, the registration module stores face feature information and voice feature information of each employee, and uploads the face feature information and voice feature information to the cloud.
在本系统中，考核模块用于存储管理员工的考核指标。具体的，考核模块2可以进行账号管理，设置一个或者多个考核量化标准，不同职位的人员设置不同的考核项目，不同的考核对应不同的人员，每个考核项目均有分值量化评判标准，总分100分。具体的，考核模块将考核指标上传到云端。In this system, the assessment module is used to store the assessment indicators of the management staff. Specifically, the assessment module 2 can perform account management, set one or more quantitative assessment standards, and set different assessment items for personnel in different positions, and different assessments correspond to different personnel. The total score is 100 points. Specifically, the assessment module uploads the assessment indicators to the cloud.
在本系统中，监控模块1监控员工的工作状态并存储到服务器中。监控模块1可以是视频摄像机。具体的，监控模块1能够360度无死角拍摄视频，能够从各个方向对员工进行拍摄。监控模块1可以实时收集视频文件，并按日期存储到服务器中。In this system, the monitoring module 1 monitors the working status of employees and stores them in the server. The monitoring module 1 may be a video camera. Specifically, the monitoring module 1 can shoot video in 360 degrees without dead angle, and can shoot employees from all directions. The monitoring module 1 can collect video files in real time and store them in the server by date.
在本系统中，视频处理模块3对存放在服务器中的视频进行图像按帧处理。具体的，视频处理模块3将视频文件通过软件分割成帧格式的图像文件并存储于服务器中。具体的，视频处理模块3还将视频文件转换为音频文件并存储于服务器中。具体的，视频处理模块3将图像文件按时间存储的服务器中。具体的，视频处理模块3可以定时清理视频和图片，对视频文件进行统一处理，例如，每天的0点进行处理。In this system, the video processing module 3 performs frame-by-frame image processing on the video stored in the server. Specifically, the video processing module 3 divides the video files into frame format image files by software and stores them in the server. Specifically, the video processing module 3 also converts the video file into an audio file and stores it in the server. Specifically, the video processing module 3 stores the image files in the server by time. Specifically, the video processing module 3 can periodically clean up the videos and pictures, and perform unified processing on the video files, for example, processing at 0:00 every day.
在本系统中，人脸检测模块5，用于将图像文件进行人脸检测，识别出各位员工的身份。即，通过人脸检测分辨出是哪一位员工。具体地，人脸检测模块5检测出各个图像文件中的人脸，通过检测获取的人脸特征和云端的人脸特征比对识别出员工身份。具体的，主要用AI尝试学习技术将Yuface，mobilefacenet，mtcnn等模型进行算法训练，并通过底层的框架如tengine或ncnn进行封装，最终识别出各个不同的人脸，并将识别的人脸和注册的人脸特征比对，识别出各个员工。In this system, the face detection module 5 is used to perform face detection on the image file to identify the identity of each employee. That is, which employee is identified through face detection. Specifically, the face detection module 5 detects the faces in each image file, and identifies the employee identity by comparing the face features obtained by the detection and the face features in the cloud. Specifically, it mainly uses AI learning technology to train Yuface, mobilefacenet, mtcnn and other models for algorithm training, and encapsulates them through the underlying framework such as tengine or ncnn, and finally recognizes different faces, and registers the recognized faces and registrations. The facial features are compared to identify each employee.
作为本发明的一个实施方式，人脸检测模块5可以从服务器中获取图像文件。As an embodiment of the present invention, the face detection module 5 may acquire image files from a server.
作为本发明的另一种实施方式，人脸检测模块5可以从一数据提取模块10处接收获取图像文件。As another embodiment of the present invention, the face detection module 5 may receive and acquire image files from a data extraction module 10 .
在本系统中，音频检测模块6用于对音频文件进行检测识别，识别出和工作相关的信息。例如，列出每位员工的工作关键字的时间点、内容等。具体的，音频检测模块6包括训练声音模型，设置多个关键字，上传音频文件，加载声音模型分析上传的音频文件，列出每位员工的工作关键字的时间点。通过AI尝试学习技术将用户的声音特征和工作关键字进行算法训练生成声音模型，并通过AI框架进行封装，最终识别出各个不同的声音，并将识别的声音和注册的声音特征比对，识别出各个员工的工作关键字出现的时间点和内容。In this system, the audio detection module 6 is used to detect and identify audio files, and identify information related to work. For example, list the time point, content, etc. of each employee's job keywords. Specifically, the audio detection module 6 includes training a sound model, setting multiple keywords, uploading an audio file, loading the sound model to analyze the uploaded audio file, and listing the time points of each employee's work keywords. Through AI trial learning technology, the user's voice characteristics and work keywords are algorithmically trained to generate a voice model, and then encapsulated by the AI framework, and finally each different voice is identified, and the identified voice is compared with the registered voice characteristics. The time point and content of each employee's job keywords appear.
进一步的，音频检测模块6可以从服务器中获取音频文件。进一步的，音频检测模块6可以从一数据提取模块10处接收获取音频文件。Further, the audio detection module 6 can acquire audio files from the server. Further, the audio detection module 6 may receive and acquire audio files from a data extraction module 10 .
作为本发明的一个具体实施例，音频检测模块6还用于检测音频文件中的声音特征信息，并与云端存储的声音特征信息比较，进而识别员工身份信息。As a specific embodiment of the present invention, the audio detection module 6 is further configured to detect the sound feature information in the audio file, and compare it with the sound feature information stored in the cloud, thereby identifying the employee identity information.
该系统包含一确定模块9，该确定模块9根据人脸检测模块识别的员工身份信息和音频检测模块识别的员工身份信息进一步确定员工身份，将确定的员工身份发送给图像分类模块。The system includes a determination module 9, the determination module 9 further determines the employee identity according to the employee identity information identified by the face detection module and the employee identity information identified by the audio detection module, and sends the determined employee identity to the image classification module.
人脸检测模块5很可能识别出多个员工身份信息，此时，通过音频检测模块6根据声音特征信息识别员工身份，二者结合进一步确定真正的员工身份信息。The face detection module 5 is likely to identify multiple employee identity information. At this time, the audio detection module 6 identifies the employee identity according to the sound feature information, and the combination of the two further determines the real employee identity information.
在本系统中，图像分类模块4用于将图像文件进行物体分类检测，识别出每位员工附近的物体。其目的是结合员工身份信息和员工附近的物体识别员工在做什么事情。该物体可以是会议室、电脑、桌子等。图像分类模块4接收人脸检测模块5或确定模块9处确定的员工身份信息以及接收图像文件。In this system, the image classification module 4 is used to classify and detect objects in the image files, and identify objects near each employee. Its purpose is to identify what the employee is doing by combining the employee's identity information with objects in the employee's vicinity. The object can be a conference room, computer, table, etc. The image classification module 4 receives the employee identity information determined at the face detection module 5 or the determination module 9 and receives an image file.
作为本发明的一个实施方式，图像分类模块4可以从服务器中获取图像文件。As an embodiment of the present invention, the image classification module 4 may acquire image files from a server.
作为本发明的另一种实施方式，图像分类模块4也可以从数据提取模块10处接收获取图像文件。As another embodiment of the present invention, the image classification module 4 may also receive and acquire image files from the data extraction module 10 .
具体的，图像分类模块4主要采用AI的分类模型如SSD，mobilenetSSD等进行算法训练，并通过底层的框架如tengine或ncnn进行封装，识别出各个物体是什么，再结合各个员工的人脸分类和物体相结合，得出当前各个员工在做的事情。Specifically, the image classification module 4 mainly uses AI classification models such as SSD, mobilenetSSD, etc. for algorithm training, and encapsulates it through the underlying framework such as tengine or ncnn to identify what each object is, and then combines the face classification and classification of each employee. The objects are combined to get what each employee is currently doing.
在本系统中，分析计算模块7用于将识别的结果按照考核的指标进行计算，计算出每位员工的每天工作状态得分。具体的，分析计算模块7接收来自音频检测模块6和图像分类模块4的处理信息，集合图像分类的结果，通过不同的时间，计算出每位员工每天在各个不同工作状态下的时间，如电脑前，如开会，如闲聊等，再集合考核指标的量化计算标准，计算出每位员工每天的工作得分。具体的，分析计算模块7根据来自音频检测模块6和图像分类模块4的处理结果以及从云端拉取的考核信息来计算工作得分。In this system, the analysis and calculation module 7 is used to calculate the identification result according to the assessment index, and calculate the daily work status score of each employee. Specifically, the analysis and calculation module 7 receives the processing information from the audio detection module 6 and the image classification module 4, collects the results of the image classification, and calculates the time of each employee in different working states every day through different times, such as computer Before the meeting, such as chatting, etc., the quantitative calculation standards of the assessment indicators are collected to calculate the daily work score of each employee. Specifically, the analysis and calculation module 7 calculates the work score according to the processing results from the audio detection module 6 and the image classification module 4 and the assessment information pulled from the cloud.
在本系统中，显示模块8将显示出每位员工的每天工作状态得分。显示模块8可以通过排序显示各个员工每天的得分，可以按日生成图形。In this system, the display module 8 will display the daily work status score of each employee. The display module 8 can display the daily scores of each employee by sorting, and can generate graphs by day.
使用如上述的一种自动分析员工工作行为的系统，具有如下步骤：Using the above-mentioned system for automatically analyzing employee work behavior, the steps are as follows:
步骤S1，监控模块1拍摄员工的工作视频文件并上传到服务器。In step S1, the monitoring module 1 shoots a working video file of the employee and uploads it to the server.
步骤S2，视频处理模块3用于定期处理工作视频文件得到图像文件。In step S2, the video processing module 3 is used for regularly processing the working video files to obtain image files.
步骤S3，人脸检测模块5用于根据图像文件识别员工身份信息。Step S3, the face detection module 5 is used to identify the employee identity information according to the image file.
步骤S4，图像分类模块4用于将图像文件和员工身份信息进行匹配得到匹配结果。Step S4, the image classification module 4 is used for matching the image file and the employee identity information to obtain a matching result.
步骤S5，分析计算模块7用于根据匹配结果计算员工的工作状态得分。Step S5, the analysis and calculation module 7 is used to calculate the employee's work status score according to the matching result.
步骤S6：显示模块8显示员工的工作状态得分。Step S6: The display module 8 displays the employee's work status score.
其在步骤S1之前还执行步骤S01：一注册模块11对员工人脸进行注册，将注册的人脸特征信息上传到云端，一考核模块12，制定考核指标并上传到云端。Before step S1, it also executes step S01: a registration module 11 registers the employee's face, and uploads the registered face feature information to the cloud; an assessment module 12 formulates assessment indicators and uploads them to the cloud.
在步骤S2中执行如下步骤S21：：视频处理模块3定期从服务器2中提取工作视频文件，对工作视频文件进行图像按帧处理分割成图像文件，将图像文件按时间存储在服务器2中。In step S2, the following step S21 is performed: the video processing module 3 periodically extracts the working video file from the server 2, performs image processing on the working video file and divides it into image files, and stores the image files in the server 2 according to time.
在步骤S3中执行如下步骤S31：人脸检测模块5从服务器2中提取图像文件，检测图像文件中的人脸特征信息并与云端存储的人脸特征信息比较，识别员工身份信息，进而将确定的员工身份发送给图像分类模块4。In step S3, the following step S31 is performed: the face detection module 5 extracts the image file from the server 2, detects the face feature information in the image file and compares it with the face feature information stored in the cloud, identifies the employee identity information, and then determines the The employee identities are sent to the image classification module 4.
在步骤S4中执行如下步骤S41：：图像分类模块4从服务器2中提取图像文件，识别人脸附近的物体类型并与确定的员工身份匹配，将匹配结果发送至分析计算模块7。In step S4, the following step S41 is performed: the image classification module 4 extracts the image file from the server 2, identifies the object type near the face and matches with the determined employee identity, and sends the matching result to the analysis and calculation module 7.
在步骤S5中执行如下步骤S51：分析计算模块7综合匹配结果，得到员工的工作状态，根据从云端提取的考核指标计算得出员工的每天工作状态得分。In step S5, the following step S51 is performed: the analysis and calculation module 7 synthesizes the matching results to obtain the working status of the employee, and calculates the daily working status score of the employee according to the assessment index extracted from the cloud.
在步骤S2中还执行步骤S22：视频处理模块3将工作视频文件转换为音频文件，将音频文件按时间存储在服务器2中，其中步骤S22和步骤S21不分先后进行。In step S2, step S22 is also executed: the video processing module 3 converts the working video file into an audio file, and stores the audio file in the server 2 according to time, wherein step S22 and step S21 are performed in no particular order.
步骤S3中还执行步骤S32：具有一音频检测模块6，音频检测模块6分别与服务器2和分析计算模块7连接，从服务器中提取音频文件，提取与工作相关的关键字和时间点发送至分析计算模块7；其中步骤S31和步骤S32不分先后进行。Step S32 is also executed in step S3: there is an audio detection module 6, the audio detection module 6 is connected with the server 2 and the analysis calculation module 7 respectively, extracts the audio file from the server, extracts the keywords and time points relevant to the work and sends them to the analysis. Calculation module 7; wherein step S31 and step S32 are performed in no particular order.
步骤S5执行如下步骤S52：分析计算模块7综合分析匹配结果以及与工作相关的关键字和时间点得到员工的工作状态，根据从云端提取的考核指标计算得出员工的工作状态得分。Step S5 executes the following step S52: the analysis and calculation module 7 comprehensively analyzes the matching results and the keywords and time points related to the work to obtain the employee's work status, and calculates the employee's work status score according to the assessment indicators extracted from the cloud.
在步骤S1之前还执行步骤S02：注册模块11还对员工声音进行注册，将注册的声音特征信息上传至云端。Before step S1, step S02 is also performed: the registration module 11 also registers the employee's voice, and uploads the registered voice feature information to the cloud.
步骤S3执行如下步骤：Step S3 performs the following steps:
一步骤S33,音频检测模块6还用于检测音频文件中的声音特征信息，并与与云端存储的声音特征信息比较，进而识别员工身份信息；In a step S33, the audio detection module 6 is also used to detect the sound feature information in the audio file, and compare it with the sound feature information stored in the cloud, and then identify the employee identity information;
一步骤S34：一确定模块9，确定模块9分别于与人脸检测模块5、音频检测模块6以及分析计算模块7连接，根据人脸检测模块5识别的员工身份信息和音频检测模块6识别的员工身份信息进一步确定员工身份，将确定的员工身份发送给图像分类模块。A step S34: a determination module 9, the determination module 9 is respectively connected with the face detection module 5, the audio detection module 6 and the analysis calculation module 7, according to the employee identity information identified by the face detection module 5 and the audio detection module 6 The employee identity information further determines the employee identity, and sends the determined employee identity to the image classification module.
在步骤S2和步骤S3之间还包括一步骤S203：包括一数据提取模块10，数据提取模块10与服务器2、图像分类模块4、音频检测模块6和人脸检测模块5连接；A step S203 is also included between the step S2 and the step S3: a data extraction module 10 is included, and the data extraction module 10 is connected with the server 2, the image classification module 4, the audio detection module 6 and the face detection module 5;
数据提取模块10用于从服务器中提取图像文件和音频文件，将图像文件分别转发给人脸检测模块5和图像分类模块4，将音频文件转发给音频检测模块6。The data extraction module 10 is used for extracting image files and audio files from the server, forwarding the image files to the face detection module 5 and the image classification module 4 respectively, and forwarding the audio files to the audio detection module 6 .
以上仅为本发明较佳的实施例，并非因此限制本发明的实施方式及保护范围，对于本领域技术人员而言，应当能够意识到凡运用本发明说明书及图示内容所作出的等同替换和显而易见的变化所得到的方案，均应当包含在本发明的保护范围内。The above are only preferred embodiments of the present invention, and are not intended to limit the embodiments and protection scope of the present invention. For those skilled in the art, they should be aware of the equivalent replacement and Solutions obtained by obvious changes shall all be included in the protection scope of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010144845.3ACN111368737A (en) | 2020-03-04 | 2020-03-04 | A system and method for automatically analyzing employee work behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010144845.3ACN111368737A (en) | 2020-03-04 | 2020-03-04 | A system and method for automatically analyzing employee work behavior |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111368737Atrue CN111368737A (en) | 2020-07-03 |
Family
ID=71206705
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010144845.3APendingCN111368737A (en) | 2020-03-04 | 2020-03-04 | A system and method for automatically analyzing employee work behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111368737A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113240396A (en)* | 2021-05-20 | 2021-08-10 | 北京明略昭辉科技有限公司 | Method, device and equipment for analyzing working state of employee and storage medium |
| CN116303296A (en)* | 2023-05-22 | 2023-06-23 | 天宇正清科技有限公司 | Data storage method, device, electronic equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018113526A1 (en)* | 2016-12-20 | 2018-06-28 | 四川长虹电器股份有限公司 | Face recognition and voiceprint recognition-based interactive authentication system and method |
| CN109686447A (en)* | 2019-01-28 | 2019-04-26 | 远光软件股份有限公司 | A kind of employee status's monitoring system based on artificial intelligence |
| CN109766773A (en)* | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Match monitoring method, device, computer equipment and storage medium |
| CN110533288A (en)* | 2019-07-23 | 2019-12-03 | 平安科技（深圳）有限公司 | Business handling process detection method, device, computer equipment and storage medium |
- 2020
- 2020-03-04CNCN202010144845.3Apatent/CN111368737A/enactivePending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018113526A1 (en)* | 2016-12-20 | 2018-06-28 | 四川长虹电器股份有限公司 | Face recognition and voiceprint recognition-based interactive authentication system and method |
| CN109766773A (en)* | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Match monitoring method, device, computer equipment and storage medium |
| CN109686447A (en)* | 2019-01-28 | 2019-04-26 | 远光软件股份有限公司 | A kind of employee status's monitoring system based on artificial intelligence |
| CN110533288A (en)* | 2019-07-23 | 2019-12-03 | 平安科技（深圳）有限公司 | Business handling process detection method, device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 李澎林;张慧珂;李伟;: "基于移动办公的员工定性指标定量化考核方法研究", no. 04* |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113240396A (en)* | 2021-05-20 | 2021-08-10 | 北京明略昭辉科技有限公司 | Method, device and equipment for analyzing working state of employee and storage medium |
| CN116303296A (en)* | 2023-05-22 | 2023-06-23 | 天宇正清科技有限公司 | Data storage method, device, electronic equipment and medium |
| CN116303296B (en)* | 2023-05-22 | 2023-08-25 | 天宇正清科技有限公司 | Data storage method, device, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110826538B (en) | An Abnormal Leaving Recognition System for Electric Power Business Hall | |
| CN105160318B (en) | Lie detecting method based on facial expression and system | |
| CN111726586A (en) | A production system operation specification monitoring and reminder system | |
| CN109165685B (en) | Expression and action-based method and system for monitoring potential risks of prisoners | |
| CN107679504A (en) | Face identification method, device, equipment and storage medium based on camera scene | |
| CN107679475B (en) | Store monitoring and evaluating method and device and storage medium | |
| CN110096945B (en) | Indoor monitoring video key frame real-time extraction method based on machine learning | |
| CN112487928A (en) | Classroom learning condition real-time monitoring method and system based on feature model | |
| CN109638959B (en) | Power equipment remote signaling function debugging method and system based on AR and deep learning | |
| CN111539313A (en) | Examination cheating behavior detection method and system | |
| CN104917803A (en) | Autonomous inspection system based on user behavior control | |
| CN111368737A (en) | A system and method for automatically analyzing employee work behavior | |
| CN109873979A (en) | Camera-based static image difference comparison method and device | |
| CN106022313A (en) | Scene-automatically adaptable face recognition method | |
| CN113850183A (en) | Method for judging behaviors in video based on artificial intelligence technology | |
| CN109117771A (en) | Incident of violence detection system and method in a kind of image based on anchor node | |
| CN116403158A (en) | Method, device, equipment and storage medium for summarizing damaged short packages of express packages | |
| CN118470612B (en) | Behavior recognition method and system for safe production workers based on multimodal information fusion | |
| CN114155612A (en) | Restaurant personnel non-standard behavior model training method, detection method and processing equipment | |
| CN106971150B (en) | Logistic regression-based method and device for queuing anomaly detection | |
| CN116343343B (en) | Intelligent evaluation method for crane lifting command action based on cloud end architecture | |
| CN112070185A (en) | Re-ID-based non-contact fever person tracking system and tracking method thereof | |
| CN107330419A (en) | It is a kind of to carry out the method and device that recognition of face impersonates examinee using real-time monitoring | |
| CN117809066A (en) | System, method, equipment and medium for checking consistency of delivery destination of cigarettes | |
| CN117636335A (en) | Endoscope image detection method based on improved YOLOv8 and VGG19 models |
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 | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20200703 | |
| RJ01 | Rejection of invention patent application after publication |