CN109961213A - A kind of behavior evaluation method and system of shop maintenance personnel - Google Patents
A kind of behavior evaluation method and system of shop maintenance personnel Download PDFInfo
- Publication number
- CN109961213A CN109961213A CN201910091070.5A CN201910091070A CN109961213A CN 109961213 A CN109961213 A CN 109961213A CN 201910091070 A CN201910091070 A CN 201910091070A CN 109961213 A CN109961213 A CN 109961213A
- Authority
- CN
- China
- Prior art keywords
- maintenance
- maintenance personal
- behavior
- evaluation
- personal
- 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
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
- G06Q10/06—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
- G06Q10/063114—Status monitoring or status determination for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06398—Performance of employee with respect to a job function
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- General Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Primary Health Care (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides the behavior evaluation method and system of shop maintenance personnel a kind of, this method comprises: when maintenance personal repairs board, obtain the human body image of maintenance personal and the equipment image of board, and the face feature and behavior posture feature of maintenance personal, and the equipment posture feature according to the equipment image extractor platform are extracted according to the human body image.The face feature is compared with preset shop maintenance demographic data library, to obtain the corresponding identity ID of maintenance personal.Machine self-learning is carried out to the behavior posture feature of the maintenance personal and the equipment posture feature by deep learning algorithm, to determine the maintenance progress of the maintenance personal.The maintenance progress is stored in the mantenance data for forming the maintenance personal in the MES system of workshop, and generates the maintenance evaluation index of the maintenance personal according to the mantenance data.The present invention can improve workshop intelligent management level, improve the safety of plant personnel.
Description
Technical field
The present invention relates to workshop intelligent management technical field more particularly to a kind of behavior evaluation methods of shop maintenance personnel
And system.
Background technique
Currently, there is no relatively science, objectively for unit maintenance personal behavior state between the cigarette hired car of tobacco factory
Appraisement system, only rely on the experience of manager and examine and want to carry out assessment marking to unit maintenance personal behavior.It is existing
The mode for by virtue of experience judging unit maintenance personal's behavior state there are following two points defects: (1) lack objectively it is theoretical according to
According to, lack real data support.(2) rely on artificial micro-judgment merely, often will appear and the biggish deviation of actual state.Separately
It outside, can not real-time perfoming correction and prompting when non-standard operation occurs in maintenance personal's operation board.
Summary of the invention
The present invention provides the behavior evaluation method and system of shop maintenance personnel a kind of, solves existing shop maintenance personnel's
Behavior state evaluation can only easily have evaluation inaccuracy, lack visitor by carrying out subjective assessment after monitor video or artificial observation
The problem of data are supported is seen, workshop intelligent management level can be improved, improve the safety of plant personnel.
In order to achieve the above object, the present invention the following technical schemes are provided:
A kind of behavior evaluation method of shop maintenance personnel, comprising:
When maintenance personal repairs board, the human body image of maintenance personal and the equipment image of board are obtained, and
The face feature and behavior posture feature of maintenance personal are extracted according to the human body image, and according to the equipment image extractor
The equipment posture feature of platform;
The face feature is compared with preset shop maintenance demographic data library, it is corresponding to obtain maintenance personal
Identity ID;
The behavior posture feature of the maintenance personal and the equipment posture feature are carried out by deep learning algorithm
Machine self-learning, to determine the maintenance progress of the maintenance personal;
The maintenance progress is stored in the mantenance data that the maintenance personal is formed in the MES system of workshop, and according to the dimension
The maintenance evaluation index that data generate the maintenance personal is repaired, the evaluation index includes: maintenance response time, maintenance duration, dimension
Repair evaluation, maintenance rework rate and maintenance responsibility unit operation efficiency.
Preferably, further includes:
Judge whether the operation of the maintenance personal meets preset maintenance instruction according to the maintenance progress of the maintenance personal, such as
Fruit does not meet, then generates maintenance fault record;
The negative index of maintenance for determining the maintenance personal is recorded according to the maintenance fault, the negative index includes: to lose
The accidentally frequency, delay duration and shutdown duration.
Preferably, further includes:
The weight of each evaluation index and the negative index is set, and each institute is obtained according to the weight calculation
State the weighted value of evaluation index and the negative index;
The behavior evaluation score of the maintenance personal is calculated according to the weighted value, and will be described according to the identity ID
Behavior evaluation score is stored into shop maintenance demographic data library.
Preferably, further includes:
Judge whether the maintenance personal is in safe work state according to the face feature and the behavior posture feature,
If it is not, then reporting unsafe condition information according to the identity ID, and generate unsafe condition record;
The dangerous evaluation index for generating the maintenance personal is recorded according to the unsafe condition, the dangerous evaluation refers to
Mark includes: the dangerous frequency and dangerous duration;
The safety in production score of the maintenance personal is determined according to the dangerous evaluation index, and according to the behavior evaluation
Score and the safety in production score carry out behavior evaluation to the maintenance personal.
Preferably, described that the maintenance progress is stored in the mantenance data that the maintenance personal is formed in the MES system of workshop, packet
It includes:
Obtain operation duration and service record information that maintenance personal repairs board;
Equipment after obtaining board maintenance reprocesses duration and equipment operation duration;
The operation duration, the service record information, the equipment are reprocessed into duration and the equipment operation duration is deposited
Enter in the MES system of workshop.
The present invention also provides the behavior evaluation systems of shop maintenance personnel a kind of, comprising:
Feature extraction unit, for when maintenance personal repairs board, obtain maintenance personal human body image and
The equipment image of board, and according to the face feature and behavior posture feature of human body image extraction maintenance personal, and according to
The equipment posture feature of the equipment image extractor platform;
Identity comparing unit, for the face feature to be compared with preset shop maintenance demographic data library, with
Obtain the corresponding identity ID of maintenance personal;
Maintenance progress determination unit, for by deep learning algorithm to the behavior posture feature of the maintenance personal and
The equipment posture feature carries out Machine self-learning, to determine the maintenance progress of the maintenance personal;
First evaluation unit, for the maintenance progress to be stored in the maintenance for forming the maintenance personal in the MES system of workshop
Data, and the maintenance evaluation index of the maintenance personal is generated according to the mantenance data, the evaluation index includes: maintenance response
Duration, maintenance duration, maintenance evaluation, maintenance rework rate and maintenance responsibility unit operation efficiency.
Preferably, further includes:
Fault determination unit, judges whether the operation of the maintenance personal meets for the maintenance progress according to the maintenance personal
Preset maintenance instruction generates maintenance fault record if do not met;
Second evaluation unit, for recording the negative index of maintenance for determining the maintenance personal, institute according to the maintenance fault
Negative index is stated to include: the fault frequency, delay duration and shut down duration.
Preferably, further includes:
Weight setting unit, for the weight of each evaluation index and the negative index to be arranged, and according to described
Weight calculation obtains the weighted value of each evaluation index and the negative index;
Behavior evaluation unit, for the behavior evaluation score of the maintenance personal, and root to be calculated according to the weighted value
The behavior evaluation score is stored into shop maintenance demographic data library according to the identity ID.
Preferably, further includes:
Unsafe condition determination unit, for judging maintenance people according to the face feature and the behavior posture feature
Whether member is in safe work state, if it is not, then reporting unsafe condition information according to the identity ID, and generates dangerous
State recording;
Third evaluation unit, the dangerous evaluation for generating the maintenance personal according to unsafe condition record refer to
Mark, the dangerous evaluation index includes: the dangerous frequency and dangerous duration;
The behavior evaluation unit is also used to determine the safety in production of the maintenance personal according to the dangerous evaluation index
Score, and behavior evaluation is carried out to the maintenance personal according to the behavior evaluation score and the safety in production score.
The present invention provides the behavior evaluation method and system of shop maintenance personnel a kind of, special by the face to maintenance personal
The equipment posture of behavior posture feature and board of seeking peace identified, and by deep learning algorithm to behavior posture feature and
Equipment posture is learnt the maintenance progress to determine maintenance personal, and then obtains maintenance evaluation index according to maintenance progress.Solution
The behavior state evaluation of certainly existing shop maintenance personnel can only be by carrying out subjective assessment, Yi Cun after monitor video or artificial observation
In evaluation inaccuracy, lack the problem of objective data is supported, workshop intelligent management level can be improved, improve the peace of plant personnel
Quan Xing.
Detailed description of the invention
In order to illustrate more clearly of specific embodiments of the present invention, attached drawing needed in the embodiment will be made below
Simply introduce.
Fig. 1: being the behavior evaluation method schematic diagram of shop maintenance personnel provided by the invention a kind of;
Fig. 2: being behavior evaluation method flow diagram provided in an embodiment of the present invention.
Specific embodiment
The scheme of embodiment in order to enable those skilled in the art to better understand the present invention with reference to the accompanying drawing and is implemented
Mode is described in further detail the embodiment of the present invention.
Evaluation for current inter-vehicular maintenance personal relies primarily on artificial observation or monitor video, and existing cannot be objective and quasi-
Really the problem of evaluation.The present invention provides the behavior evaluation method and system of shop maintenance personnel a kind of, by maintenance personal's
The equipment posture of face feature and behavior posture feature and board is identified, and passes through deep learning algorithm to behavior posture
Feature and equipment posture are learnt the maintenance progress to determine maintenance personal, and then are obtained maintenance evaluation according to maintenance progress and referred to
Mark.The behavior state evaluation for solving existing shop maintenance personnel can only be commented by carrying out subjectivity after monitor video or artificial observation
Easily there is evaluation inaccuracy, lack objective data support, workshop intelligent management level can be improved, improve workshop in valence
The safety of personnel.
As shown in Figure 1, a kind of behavior evaluation method of shop maintenance personnel, comprising:
S1: when maintenance personal repairs board, obtaining the human body image of maintenance personal and the equipment image of board,
And the face feature and behavior posture feature of maintenance personal is extracted according to the human body image, and according to the equipment image zooming-out
The equipment posture feature of board.
S2: the face feature is compared with preset shop maintenance demographic data library, to obtain maintenance personal couple
The identity ID answered.
S3: by deep learning algorithm to the behavior posture feature of the maintenance personal and the equipment posture feature into
Row Machine self-learning, to determine the maintenance progress of the maintenance personal.
S4: the maintenance progress is stored in the mantenance data that the maintenance personal is formed in the MES system of workshop, and according to described
Mantenance data generates the maintenance evaluation index of the maintenance personal, the evaluation index include: maintenance response time, maintenance duration,
Maintenance evaluation, maintenance rework rate and maintenance responsibility unit operation efficiency.
Specifically, unit maintenance personal is got respectively by technological means such as deep learning, recognition of face, gesture recognitions
Maintenance progress, and by workshop MES system formed maintenance evaluation index.Workshop management person can be by evaluation index to maintenance people
The working condition of member is inquired and is investigated, and the behavior of workshop unit maintenance personal can be objectively evaluated according to real data, is realized
Save the cost improves the efficiency of management.It should be noted that artificial neural network algorithm progress can be used in Machine self-learning.
This method further include:
S5: judge whether the operation of the maintenance personal meets preset maintenance and advise according to the maintenance progress of the maintenance personal
Model generates maintenance fault record if do not met.
S6: recording the negative index of maintenance for determining the maintenance personal according to the maintenance fault, and the negative index includes:
The fault frequency, delay duration and shutdown duration.
In practical applications, negative index can react the job specification of maintenance personal, can judge the skilled journey of maintenance personal
Degree.If the negative index of maintenance personal is high, illustrate that maintenance personal fault frequency is higher, it is seen then that negative index can characterize this
The fault situation of the operational motion of maintenance personal.
This method further include:
S7: the weight of the setting each evaluation index and the negative index, and obtained respectively according to the weight calculation
The weighted value of a evaluation index and the negative index.
S8: the behavior evaluation score of the maintenance personal is calculated according to the weighted value, and will according to the identity ID
The behavior evaluation score storage is into shop maintenance demographic data library.
In practical applications, as shown in Fig. 2, by modes such as deep learning algorithm, recognition of face, human body attitude detections,
It is obtained respectively from maintenance response time, maintenance duration, maintenance evaluation, maintenance rework rate and maintenance responsibility unit operation efficiency etc.
Objective data is got, and each single item is assigned to different weights, the behavior evaluation for finally calculating workshop unit maintenance personal obtains
Point.By the extraction and analysis to data, assigns weight and finally provide unit maintenance personal's behavior evaluation score, as shown in table 1.
Table 1
Its algorithm and decision logic implementation steps are as follows:
Step 1: unessential assignment 1, somewhat important assignment 2, important assignment 3, very important assignment 4, pole
For important assignment 5, if important and above data is only selected to enter statistics, the weight of these three options is respectively as follows: 3/ (3+4+
5)=0.25;4/ (3+4+5)=0.33;5/ (3+4+5)=0.42.
Step 2: calculating the weight of each index.
The weight of index 1=(30*0.25+20*0.33+40*0.42)/(30*0.25+20*0.33+40*0.42)+
(10*0.25+30*0.33+40*0.42)+(40*0.25+30*0.33+10*0.42)+(30*0.25+40*0.33+20*0.42)
+ (30*0.25+40*0.33+10*0.42) }=30.9/ (30.9+29.2+24.1+29.1+24.9)=30.9/138.2=
0.223。
It similarly can be obtained, weight=29.2/138.2=0.211 of index 2, weight=24.1/138.2=of index 3
0.174, weight=29.1/138.2=0.210 of index 4, weight=24.9/138.2=0.180 of index 5.Specific such as table 2
In all indexs weighted value shown in.
Table 2
This method further include:
S9: judge whether the maintenance personal is in trouble free service shape according to the face feature and the behavior posture feature
State if it is not, then reporting unsafe condition information according to the identity ID, and generates unsafe condition record.
S10: recording the dangerous evaluation index for generating the maintenance personal according to the unsafe condition, described dangerous to comment
Valence index includes: the dangerous frequency and dangerous duration.
S11: the safety in production score of the maintenance personal is determined according to the dangerous evaluation index, and according to the behavior
It evaluates score and the safety in production score and behavior evaluation is carried out to the maintenance personal.
In practical applications, maintenance personal may meet emergency situation, at this point, maintenance personal may shout or wave
Seek help, judge that maintenance personal may meet unsafe incidents by face feature and behavior posture feature at this time, need and
When by unsafe condition information reporting, and generate unsafe condition record, in case inquiry and evaluation analysis, Workshop Production can be improved
Safety and intelligence.
Further, described that the maintenance progress is stored in the mantenance data that the maintenance personal is formed in the MES system of workshop, packet
It includes:
S41: operation duration and service record information that maintenance personal repairs board are obtained.
S42: the equipment after obtaining board maintenance reprocesses duration and equipment operation duration.
S43: when the operation duration, the service record information, the equipment are reprocessed duration and equipment operation
In long deposit workshop MES system.
Further, described that the face feature is compared with preset shop maintenance demographic data library, to obtain
The corresponding identity ID of maintenance personal, comprising: carried out according to face feature pre- in recognition of face, with shop maintenance demographic data library
If face database be compared, successfully determine identity ID in the face database and maintenance people if compared
Member is corresponding, otherwise determines that the maintenance personal is illegal maintenance personal.
As it can be seen that the present invention provides the behavior evaluation method of shop maintenance personnel a kind of, it is special by the face to maintenance personal
The equipment posture of behavior posture feature and board of seeking peace identified, and by deep learning algorithm to behavior posture feature and
Equipment posture is learnt the maintenance progress to determine maintenance personal, and then obtains maintenance evaluation index according to maintenance progress.Solution
The behavior state evaluation of certainly existing shop maintenance personnel can only be by carrying out subjective assessment, Yi Cun after monitor video or artificial observation
In evaluation inaccuracy, lack the problem of objective data is supported, workshop intelligent management level can be improved, improve the peace of plant personnel
Quan Xing.
The present invention also provides the behavior evaluation systems of shop maintenance personnel a kind of, comprising: feature extraction unit, for tieing up
When repairing personnel and repairing to board, the human body image of maintenance personal and the equipment image of board are obtained, and according to the human body
The face feature and behavior posture feature of image zooming-out maintenance personal, and the equipment posture according to the equipment image extractor platform
Feature.Identity comparing unit, for the face feature to be compared with preset shop maintenance demographic data library, to obtain
The corresponding identity ID of maintenance personal.Maintenance progress determination unit, for passing through deep learning algorithm to described in the maintenance personal
Behavior posture feature and the equipment posture feature carry out Machine self-learning, to determine the maintenance progress of the maintenance personal.First
Evaluation unit, for the maintenance progress to be stored in the mantenance data for forming the maintenance personal in the MES system of workshop, and according to institute
The maintenance evaluation index that mantenance data generates the maintenance personal is stated, when the evaluation index includes: maintenance response time, maintenance
Long, maintenance evaluation, maintenance rework rate and maintenance responsibility unit operation efficiency.
The system further include: fault determination unit, for judging the maintenance personal according to the maintenance progress of the maintenance personal
Operation whether meet preset maintenance instruction, if do not met, generate maintenance fault record.Second evaluation unit, is used for
The negative index of maintenance for determining the maintenance personal is recorded according to the maintenance fault, the negative index includes: the fault frequency, indulges in
It puts duration and shuts down duration.
The system further include: weight setting unit, for the power of each evaluation index and the negative index to be arranged
Weight, and the weighted value of each evaluation index and the negative index is obtained according to the weight calculation.Behavior evaluation unit,
For being calculated the behavior evaluation score of the maintenance personal according to the weighted value, and according to the identity ID by the behavior
Score storage is evaluated into shop maintenance demographic data library.
The system further include: unsafe condition determination unit, for special according to the face feature and the behavior posture
Sign judges whether the maintenance personal is in safe work state, if it is not, then reporting unsafe condition to believe according to the identity ID
Breath, and generate unsafe condition record.Third evaluation unit generates the maintenance personal for recording according to the unsafe condition
Dangerous evaluation index, the dangerous evaluation index includes: the dangerous frequency and dangerous duration.The behavior evaluation list
Member is also used to determine the safety in production score of the maintenance personal according to the dangerous evaluation index, and according to the behavior evaluation
Score and the safety in production score carry out behavior evaluation to the maintenance personal.
Further, the first evaluation unit includes: first acquisition unit, is repaired to board for obtaining maintenance personal
Operate duration and service record information;Second acquisition unit reprocesses duration and equipment fortune for obtaining the equipment after board repairs
Row duration;Data entry element, for the operation duration, the service record information, the equipment to be reprocessed duration and institute
It states in equipment operation duration deposit workshop MES system.
Further, the identity comparing unit includes: face identification unit, for carrying out face knowledge according to face feature
Not, it is compared with the preset face database in shop maintenance demographic data library, if compared successfully, determines the people
Identity ID in face database is corresponding with the maintenance personal, otherwise determines that the maintenance personal is illegal maintenance personal.
As it can be seen that the present invention provides the behavior evaluation method and system of shop maintenance personnel a kind of, by maintenance personal's
The equipment posture of face feature and behavior posture feature and board is identified, and passes through deep learning algorithm to behavior posture
Feature and equipment posture are learnt the maintenance progress to determine maintenance personal, and then are obtained maintenance evaluation according to maintenance progress and referred to
Mark.The behavior state evaluation for solving existing shop maintenance personnel can only be commented by carrying out subjectivity after monitor video or artificial observation
Easily there is evaluation inaccuracy, lack objective data support, workshop intelligent management level can be improved, improve workshop in valence
The safety of personnel.
Structure, feature and effect of the invention, the above institute is described in detail according to diagrammatically shown embodiment above
Only presently preferred embodiments of the present invention is stated, but the present invention does not limit the scope of implementation as shown in the drawings, it is all according to structure of the invention
Think made change or equivalent example modified to equivalent change, when not going beyond the spirit of the description and the drawings,
It should all be within the scope of the present invention.
Claims (10)
1. a kind of behavior evaluation method of shop maintenance personnel characterized by comprising
When maintenance personal repairs board, the human body image of maintenance personal and the equipment image of board are obtained, and according to
The human body image extracts the face feature and behavior posture feature of maintenance personal, and according to the equipment image extractor platform
Equipment posture feature;
The face feature is compared with preset shop maintenance demographic data library, to obtain the corresponding identity of maintenance personal
ID;
Machine is carried out to the behavior posture feature of the maintenance personal and the equipment posture feature by deep learning algorithm
Self study, to determine the maintenance progress of the maintenance personal;
The maintenance progress is stored in the mantenance data that the maintenance personal is formed in the MES system of workshop, and according to the maintenance number
According to the maintenance evaluation index for generating the maintenance personal, the evaluation index includes: maintenance response time, maintenance duration, repairs and comment
Valence, maintenance rework rate and maintenance responsibility unit operation efficiency.
2. the behavior evaluation method of shop maintenance personnel according to claim 1, which is characterized in that further include:
Judge whether the operation of the maintenance personal meets preset maintenance instruction according to the maintenance progress of the maintenance personal, if not
Meet, then generates maintenance fault record;
The negative index of maintenance for determining the maintenance personal is recorded according to the maintenance fault, the negative index includes: fault frequency
Secondary, delay duration and shutdown duration.
3. the behavior evaluation method of shop maintenance personnel according to claim 2, which is characterized in that further include:
The weight of each evaluation index and the negative index is set, and each institute's commentary is obtained according to the weight calculation
The weighted value of valence index and the negative index;
It is calculated the behavior evaluation score of the maintenance personal according to the weighted value, and according to the identity ID by the behavior
Score storage is evaluated into shop maintenance demographic data library.
4. the behavior evaluation method of shop maintenance personnel according to claim 3, which is characterized in that further include:
Judge whether the maintenance personal is in safe work state according to the face feature and the behavior posture feature, if
It is no, then unsafe condition information is reported according to the identity ID, and generate unsafe condition record;
The dangerous evaluation index for generating the maintenance personal, the dangerous evaluation index packet are recorded according to the unsafe condition
It includes: the dangerous frequency and dangerous duration;
The safety in production score of the maintenance personal is determined according to the dangerous evaluation index, and according to the behavior evaluation score
Behavior evaluation is carried out to the maintenance personal with the safety in production score.
5. the behavior evaluation method of shop maintenance personnel according to claim 4, which is characterized in that described by the face
Feature is compared with preset shop maintenance demographic data library, to obtain the corresponding identity ID of maintenance personal, comprising:
The preset face database in recognition of face, with shop maintenance demographic data library is carried out according to face feature to compare
It is right, successfully determine that the maintenance personal is corresponding with the identity ID in the face database if compared, otherwise determines the dimension
Repairing personnel is illegal maintenance personal.
6. the behavior evaluation method of shop maintenance personnel according to claim 5, which is characterized in that described by the maintenance
The mantenance data of the maintenance personal is formed in progress deposit workshop MES system, comprising:
Obtain operation duration and service record information that maintenance personal repairs board;
Equipment after obtaining board maintenance reprocesses duration and equipment operation duration;
The operation duration, the service record information, the equipment are reprocessed into duration and equipment operation duration deposit vehicle
Between in MES system.
7. a kind of behavior evaluation system of shop maintenance personnel characterized by comprising
Feature extraction unit, for when maintenance personal repairs board, obtaining the human body image and board of maintenance personal
Equipment image, and the face feature and behavior posture feature of maintenance personal is extracted according to the human body image, and according to described
The equipment posture feature of equipment image extractor platform;
Identity comparing unit, for the face feature to be compared with preset shop maintenance demographic data library, to obtain
The corresponding identity ID of maintenance personal;
Maintenance progress determination unit, for by deep learning algorithm to the behavior posture feature of the maintenance personal and described
Equipment posture feature carries out Machine self-learning, to determine the maintenance progress of the maintenance personal;
First evaluation unit, for the maintenance progress to be stored in the mantenance data for forming the maintenance personal in the MES system of workshop,
And the maintenance evaluation index of the maintenance personal is generated according to the mantenance data, the evaluation index include: maintenance response time,
Repair duration, maintenance evaluation, maintenance rework rate and maintenance responsibility unit operation efficiency.
8. the behavior evaluation system of shop maintenance personnel according to claim 7, which is characterized in that further include:
Make mistakes determination unit, for the maintenance progress according to the maintenance personal judge the maintenance personal operation whether meet it is default
Maintenance instruction, if do not met, generate maintenance fault record;
Second evaluation unit, it is described negative for recording the negative index of maintenance for determining the maintenance personal according to the maintenance fault
Face index includes: the fault frequency, delay duration and shuts down duration.
9. the behavior evaluation system of shop maintenance personnel according to claim 8, which is characterized in that further include:
Weight setting unit, for the weight of each evaluation index and the negative index to be arranged, and according to the weight
The weighted value of each evaluation index and the negative index is calculated;
Behavior evaluation unit, for the behavior evaluation score of the maintenance personal to be calculated according to the weighted value, and according to institute
Identity ID is stated to store the behavior evaluation score into shop maintenance demographic data library.
10. the behavior evaluation system of shop maintenance personnel according to claim 9, which is characterized in that further include:
Unsafe condition determination unit, for judging that the maintenance personal is according to the face feature and the behavior posture feature
It is no to be in safe work state, if it is not, then reporting unsafe condition information according to the identity ID, and generate unsafe condition
Record;
Third evaluation unit, for recording the dangerous evaluation index for generating the maintenance personal, institute according to the unsafe condition
Stating dangerous evaluation index includes: the dangerous frequency and dangerous duration;
The behavior evaluation unit is also used to determine the safety in production score of the maintenance personal according to the dangerous evaluation index,
And behavior evaluation is carried out to the maintenance personal according to the behavior evaluation score and the safety in production score.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910091070.5A CN109961213A (en) | 2019-01-30 | 2019-01-30 | A kind of behavior evaluation method and system of shop maintenance personnel |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910091070.5A CN109961213A (en) | 2019-01-30 | 2019-01-30 | A kind of behavior evaluation method and system of shop maintenance personnel |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109961213A true CN109961213A (en) | 2019-07-02 |
Family
ID=67023561
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910091070.5A Pending CN109961213A (en) | 2019-01-30 | 2019-01-30 | A kind of behavior evaluation method and system of shop maintenance personnel |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109961213A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107590452A (en) * | 2017-09-04 | 2018-01-16 | 武汉神目信息技术有限公司 | A kind of personal identification method and device based on gait and face fusion |
CN108268832A (en) * | 2017-12-20 | 2018-07-10 | 广州供电局有限公司 | Electric operating monitoring method, device, storage medium and computer equipment |
CN109034509A (en) * | 2017-06-08 | 2018-12-18 | 株式会社日立制作所 | Operating personnel's evaluation system, operating personnel's evaluating apparatus and evaluation method |
CN109086895A (en) * | 2018-07-06 | 2018-12-25 | 山东中瑞新能源科技有限公司 | A kind of operation management system and method for heating ventilation air-conditioning system |
-
2019
- 2019-01-30 CN CN201910091070.5A patent/CN109961213A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109034509A (en) * | 2017-06-08 | 2018-12-18 | 株式会社日立制作所 | Operating personnel's evaluation system, operating personnel's evaluating apparatus and evaluation method |
CN107590452A (en) * | 2017-09-04 | 2018-01-16 | 武汉神目信息技术有限公司 | A kind of personal identification method and device based on gait and face fusion |
CN108268832A (en) * | 2017-12-20 | 2018-07-10 | 广州供电局有限公司 | Electric operating monitoring method, device, storage medium and computer equipment |
CN109086895A (en) * | 2018-07-06 | 2018-12-25 | 山东中瑞新能源科技有限公司 | A kind of operation management system and method for heating ventilation air-conditioning system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110059631B (en) | Contact net non-contact type monitoring defect identification method | |
CN111445106B (en) | Safety control method and system for fault processing operation site of electricity acquisition equipment | |
CN109905885A (en) | A kind of method and inspection device of determining inspection station list | |
CN107862395A (en) | Alarm method is checked and accepted and maked an inspection tour to intelligent substation | |
CN112383052A (en) | Power grid fault repairing method and device based on power internet of things | |
JP2016136380A (en) | Retention risk determiner | |
CN111126217A (en) | Intelligent operation and maintenance management system for power transmission line based on intelligent identification | |
CN112200263B (en) | Self-organizing federal clustering method applied to power distribution internet of things | |
CN108776452B (en) | Special equipment field maintenance monitoring method and system | |
CN111126820A (en) | Electricity stealing prevention method and system | |
CN110378273A (en) | A kind of method and apparatus of monitoring results process | |
CN101770602A (en) | Flight safety margin risk evaluating method, specialist system and establishing method thereof | |
Bernard | Safety culture as a way of responsive regulation: proposal for a nuclear safety culture oversight model | |
CN111626372A (en) | Online teaching supervision management method and system | |
CN111881822A (en) | Access control method, device, equipment and storage medium based on face recognition | |
Shubinsky et al. | Application of machine learning methods for predicting hazardous failures of railway track assets | |
CN115550609A (en) | Building Internet of things monitoring system capable of realizing automatic adaptation | |
CN111369140B (en) | Teaching evaluation system and method | |
CN109948890A (en) | A kind of behavior evaluation method and system of workshop machine operations personnel | |
CN109961213A (en) | A kind of behavior evaluation method and system of shop maintenance personnel | |
CN116777227A (en) | Hierarchical supervision method and system for enterprise safety production risk | |
CN113506247A (en) | Transmission line inspection defect detection method based on variational Bayesian inference | |
CN116664001A (en) | Student skill assessment method and system based on artificial intelligence | |
CN115601010A (en) | Artificial intelligence fire control wisdom information management platform | |
Chandrahasa et al. | Machine Learning Algorithms based Student Performance Prediction based on Previous Records |
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 |