CN110348754A - A kind of campus despot's Ling Hangwei early warning system and method based on artificial intelligence technology - Google Patents
A kind of campus despot's Ling Hangwei early warning system and method based on artificial intelligence technology Download PDFInfo
- Publication number
- CN110348754A CN110348754A CN201910641993.3A CN201910641993A CN110348754A CN 110348754 A CN110348754 A CN 110348754A CN 201910641993 A CN201910641993 A CN 201910641993A CN 110348754 A CN110348754 A CN 110348754A
- Authority
- CN
- China
- Prior art keywords
- student
- value
- alarm
- processor
- despot
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 24
- 238000005516 engineering process Methods 0.000 title claims abstract description 23
- 238000004458 analytical method Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 5
- 230000005540 biological transmission Effects 0.000 claims abstract description 3
- 230000014509 gene expression Effects 0.000 claims description 34
- 238000012790 confirmation Methods 0.000 claims description 21
- 238000012795 verification Methods 0.000 claims description 10
- 238000012546 transfer Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 4
- 238000012986 modification Methods 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 208000019901 Anxiety disease Diseases 0.000 claims description 3
- 230000036506 anxiety Effects 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims description 3
- 230000002459 sustained effect Effects 0.000 claims description 3
- 206010016275 Fear Diseases 0.000 claims 2
- 230000010365 information processing Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000006399 behavior Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 210000001747 pupil Anatomy 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000010195 expression analysis Methods 0.000 description 2
- 230000008921 facial expression Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 241001626506 Philypnodon Species 0.000 description 1
- 241000543375 Sideroxylon Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000003756 stirring Methods 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Educational Technology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
A kind of campus despot's Ling Hangwei early warning system and method based on artificial intelligence technology, including three processor, student terminal and teacher's terminal parts, wherein processor is for executing calculating and artificial intelligence analysis, the student terminal carries out despot for student and insults alarm use, teacher's terminal receives the information of processor transmission for teacher and carries out subsequent processing according to transmitted information, the processor includes memory, master database is stored in memory, master database includes the information of all students.Accurate despot, which is carried out, using the system insults early warning.
Description
Technical field
The present invention relates to a kind of campus despot's Ling Hangwei early warning system and method based on artificial intelligence technology, belong to campus intelligence
It can security fields.
Background technique
By artificial intelligence technology application arrive school it is middle realize Campus Security monitoring or in order to realize campus information management
Intelligent automaticization be known, such as CN101674461A discloses a kind of intelligence of School safety
Network monitoring system realizes the alarm of campus abnormal conditions using network connection monitoring device.CN104349127 is also public
Similar device is opened, it follows that artificial intelligence technology is already belonged to people institute public affairs applied to Campus Security or informationization
The technology known, on this basis, people propose some new applications for campus intellectual technology, and this application is often reality
What demand was guided.In school, other than Campus Security is the subject under discussion of people's general concern, the school that more highlights in recent years
Garden despot Ling Hangwei increasingly attracts people's attention and pays close attention to, and seizes by force Ling Hangwei for campus, there has been proposed be much based on campus
The identification of intellectual technology and method for early warning, CN104468981 disclose a kind of campus despot's icepro detection based on intelligent mobile phone platform
Method mainly identifies that despot's atom is made by three axis accelerometer built in mobile phone and three-axis gyroscope, voice and the state of mind,
With this come differentiate whether campus despot Ling Hangwei.It requires everyone in campus to wear a smart phone.This mode exists
Following disadvantage: students in middle and primary schools usually do not allow carrying mobile phone to enter campus, because students in middle and primary schools are poor for mobile phone resistance,
Ability of differentiating between right and wrong is poor, it is easy to it is addicted and neglect one's studies to play mobile phone, so current campus is typically all that student is forbidden to carry hand
Machine enters, second is that this mode is at high cost, everyone is needed to be equipped with a smart phone, third is that information processing capacity is huge, this side
Method needs will analyze each movement of each student and language, and algorithm current first is inaccurate, even if after
Accurate algorithm can be developed, then information processing capacity is necessarily huge, fourth is that often there is the situation judged by accident, only according to
Language and the movement state of mind are analyzed, real middle school student, especially pupil, are normally played to quarrel and fight noisily between classmate and are also passed through
It often will appear the situation of uncivil language and indignation, this judgment mode lacks quantizating index, differentiates and is easy error.
CN106973142 discloses the method and intelligent mobile phone terminal of a kind of icepro of opposing local despots, realizes despot Ling Hangwei's using mobile phone terminal
Notice and evidence obtaining record, the disadvantages of this method are still to need everyone to carry a smart phone, and existing despot icepro is past
It is in addition exactly that playful frolicking behavior between pupil is non-toward being to be seized by force the student of icepro when being insulted by despot to be alarmed by threatening
It is often universal, and despot is insulted child and non-despot Ling Hangwei cannot accomplish correctly to distinguish, as long as this will lead to child's sense
Feel eaten lose will trigger alarm, parents of student sees that alarm and notification signal are thought that oneself child is seized by force and insulted, often with
School or other parents generate sour experience and unpleasantness.Still another shortcoming is that pupil is especially active, it is easy to
This mobile phone terminal regard a game, it is busy have nothing to do or consciously or unconsciously go pressing alarm button, eventually lead to parent and
Teacher can not judge which is real despot Ling Hangwei at all.CN109214961 discloses a kind of digit learning wisdom permit identification,
Alarm button is set on certificate, it is similar, there are the problem of it is similar with CN106973142.CN108630230 discloses one kind
Campus despot based on movement voice data joint identification insults detection method, and there is similar with CN104468981 to ask for this method
Topic, the problem that detection is inaccurate and information processing capacity is huge.CN108830761 discloses a kind of campus based on recognition of face
Method for managing security seizes by force Ling Hangwei in order to prevent, initially sets up dangerous student database, is then identified using monitoring device same
When there are two crowd more than people, then carry out again it is facial it is nervous, fear or the analysis of the expressions such as indignation, then determine again wherein
Whether there is dangerous student, with this to determine whether there is despot Ling Hangwei.It is had the disadvantage in that in the above method first is that needing to locate
The information content of reason is very huge, and students in middle and primary schools are generally to go with to play after class, and institute in the above way actually needs to institute
There is student that will identify and calculate;Second is that existing Expression analysis method is not accurate enough, can accurately not identify tight
The expressions such as open, fear, especially in the case where remote distance camera;Third is that face recognition identifies in the case where remote distance camera
It spends not high;Fourth is that only by security personnel once expel behavior just will wherein to be added dangerous student database obviously improper by a side because
Whether belonging to despot Ling Bingfei security personnel at that time can simply determine, security personnel it is wrong student is included in dangerous student database it
Afterwards, the parents of student and student itself inherently generate strong conflict and discontented mood, or even can arrive school and create disturbances to and make trouble,
Seek justice.
The above prior art of comprehensive analysis is it can be found that in the prior art at least for the method for early warning campus despot Ling Hangwei
There are following several disadvantages: 1. information processing capacities are huge;2. video monitoring distance is remote, causing despot to insult Activity recognition rate is reduced;3.
It is easy to that parent is caused to misread and psychological unpleasantness;4. judge index be it is qualitative, judge not accurate enough, often judge by accident;5. at
This height.
Summary of the invention
In order to solve the above technical problems, the present invention provides a kind of completely new campus despots based on artificial intelligence technology to insult row
For early warning system and method, system and a method according to the invention can realize that Ling Hangwei is seized by force in campus under the premise of low cost
Accurate judgement.
According to one embodiment of the application, a kind of campus despot Ling Hangwei early warning system based on artificial intelligence technology is provided
System, it is characterised in that: including three processor, student terminal and teacher's terminal parts, wherein processor calculate for executing and
Artificial intelligence analysis, the student terminal carry out despot for student and insult alarm use, and teacher's terminal receives processor for teacher
The information of transmission simultaneously carries out subsequent processing according to transmitted information, and the processor includes memory, is stored in memory
Master database, master database include the information of all students, and each student is endowed a classification system according to usually performance
A possibility that number K, category COEFFICIENT K carries out assignment according to the daily performance of the student, insulted by despot, is bigger, and assignment is bigger,
A possibility that carrying out despot's icepro to other classmates is bigger, and assignment is smaller, builds between the processor and student terminal and teacher's terminal
Vertical to have communication connection, student terminal includes at least fingerprint identification module, photographing module and display panel module, and alarm student passes through hand
Referring to pressing fingerprint identification module, processor can quickly identify the identity information of alarm student, and read its classification coefficient value K, and
Student's expression is analyzed using photographing module, carries out expression assignment L based on the analysis results, it is two that the expression assignment L, which is divided to,
Class, is L1 and L2 respectively, if it is it is nervous, fear, indignation or serious class expression are then assigned a value of L2, if easily, it is glad or
The expression of pleasant class then assignment L1, wherein L1 < L2 and the two difference is greater than 0.3, it is described after completing Expression Recognition and judging
Display panel module shows the name of each student according to the size of this class of student's classification coefficient value K according to sequence from big to small,
Alarm student can click directly on corresponding name to confirm the student for implementing despot and insulting, student's name that processor is clicked according to alarm student
Word reads student's name in memory to transfer the classification coefficient value K for being clicked name student, and calculates 1 and subtract the quilt
The resulting difference of classification coefficient value K for clicking name student, which is indicated with M, finally, processor calculates J=K*M*L value
Size, processor compare the size relation of calculated result J value and preset threshold, if J value is greater than preset threshold, then it is assumed that alarm
Student receives despot Ling Hangwei, and corresponding information is sent teacher's terminal by processor, if J value is less than preset threshold, to report
Alert student's record spurious alarm is primary, when the spurious alarm number of a student is more than the preset times that the student is set, processing
Device also needs to send corresponding information to teacher's terminal, and above-mentioned K, L, the size of M value is greater than 0 less than 1.
According to one embodiment of the application, the initial K value of each student can be by teacher according to student in master database
Daily performance determines.
According to one embodiment of the application, the initial K value of each student can be obtained according to questionnaire in master database
Average value is obtained to determine.
According to one embodiment of the application, if what teacher's terminal received is that despot insults warning message, teacher goes existing
Field is verified, if confirmation belongs to despot's icepro event after verifying, despot's icepro confirmation is carried out in teacher's terminal, processor is according to really
Recognize results modification alarm student and implement the corresponding K value of despot Ling Hangwei student, increases by the K value of the student of despot Ling Hangwei,
The K value for implementing despot Ling Hangwei student becomes smaller.
According to one embodiment of the application, if what teacher's terminal received is that the number of some student's spurious alarm is more than
Preset times, then teacher also will go to scene to handle, and the multiple alarm for verifying student is spurious alarm on earth, if through
It crosses verification and really belongs to spurious alarm, then teacher belongs to spurious alarm in teacher's terminal check, and processor reduces according to confirmation result should
The K value of student belongs to processor misjudgment, then carries out true alarming determining, processor root if belonging to true alarm by verification
Increase the K value of the student according to confirmation result or increases the preset times of the student.
According to one embodiment of the application, despot is carried out to some student without student in the regular period and insults alarm, explanation
Student's sustained superior performance, then processor increases its K value.
According to one embodiment of the application, a kind of campus despot Ling Hangwei early warning system based on artificial intelligence technology is provided
System carries out the method that despot insults early warning, it is characterised in that: alarm student presses fingerprint identification module by finger, and processor can be quick
The identity information of identification alarm student, and its classification coefficient value K is read, and analyze student's expression using photographing module,
Carry out expression assignment L based on the analysis results, it is L1 and L2 respectively that the expression assignment L, which be divided to for two classes, if it is anxiety, fear,
Indignation or serious class expression are then assigned a value of L2, if easily, assignment L1 if the expression of glad or pleasant class, wherein L1 < L2 is simultaneously
And the two difference is greater than 0.3, after completion Expression Recognition judges, the display panel module is according to this class of student's classification coefficient value
The size of K shows the name of each student according to sequence from big to small, and alarm student can click directly on corresponding name to confirm
Implement the student that despot insults, processor reads student's name in memory according to student's name that alarm student clicks to transfer
This is clicked the classification coefficient value K of name student, and calculates 1 to subtract the classification coefficient value K for being clicked name student resulting
Difference indicates the difference with M, finally, processor calculates the size of J=K*M*L value, processor compares calculated result J value and pre-
If the size relation of threshold value, if J value is greater than preset threshold, then it is assumed that alarm student receives despot Ling Hangwei, and processor is by phase
Information is answered to be sent to teacher's terminal, it is primary to alarm student's record spurious alarm if J value is less than preset threshold, it is learned when one
When raw spurious alarm number is more than the preset times that the student is set, processor also needs to send teacher for corresponding information
Terminal, above-mentioned K, L, the size of M value are greater than 0 less than 1.
According to one embodiment of the application, of different sizes, class's order of the preset threshold of each class
Relatively good class, the preset threshold are set as relatively large, and processor is according to the history data in the regular period
To adjust the size of the preset threshold.
According to one embodiment of the application, if what teacher's terminal received is that despot insults warning message, teacher goes existing
Field is verified, if confirmation belongs to despot's icepro event after verifying, despot's icepro confirmation is carried out in teacher's terminal, processor is according to really
Recognize results modification alarm student and implement the corresponding K value of despot Ling Hangwei student, increases by the K value of the student of despot Ling Hangwei,
The K value for implementing despot Ling Hangwei student becomes smaller.
According to one embodiment of the application, if what teacher's terminal received is that the number of some student's spurious alarm is more than
Preset times, then teacher also will go to scene to handle, and the multiple alarm for verifying student is spurious alarm on earth, if through
It crosses verification and really belongs to spurious alarm, then teacher belongs to spurious alarm in teacher's terminal check, and processor reduces according to confirmation result should
The K value of student belongs to processor misjudgment, then carries out true alarming determining, processor root if belonging to true alarm by verification
Increase the K value of the student according to confirmation result or increases the preset times of the student.
Detailed description of the invention
Attached drawing 1 is the schematic diagram of campus despot Ling Hangwei early warning system of the application based on artificial intelligence technology;
Attached drawing 2 is the schematic diagram of early warning system middle school student's terminal.
Specific embodiment
As shown in Figure 1, it is of the invention based on artificial intelligence technology campus despot Ling Hangwei early warning system include processor 1,
2 three parts of student terminal 3 and teacher's terminal, wherein processor can be total processor of campus intelligent network, be mainly used for
Calculating and artificial intelligence analysis are executed, it can be fixed terminal or mobile terminal, the multiple student is whole that student terminal, which includes multiple,
It include at least one mobile terminal in end, the student terminal carries out despot's icepro alarm for student and uses.Teacher's terminal is for old
Teacher receives the information that processor is sent and carries out subsequent processing, settable one of each Staff Room according to transmitted information
Teacher's terminal.
The method that early warning system of the invention carries out despot's Ling Hangwei early warning is specifically described below.It is to establish master data first
Library, the master database can be obtained by the method for carrying out anonymous statistics in student and teacher, and main purpose is in class
Student classify, typically, the student in class can substantially be divided into three classes, the first kind be especially it is naughty love stir up trouble love beat
Frame love bullies people, and the second class is that self-disciplining is preferable, does not like generally and quarrels and fights noisily with others, will not actively go to bully other classmates,
Also less simultaneously to will receive what other classmates bullied, third class is exactly somewhat naughty but own strength is not enough easy by other
What classmate bullied.Can be completed by way of student in class and teacher send anonymous questionnaire class student just
Classification is walked to obtain master database, it is excessively conscientious careful that the establishment process of this master database can not have to, namely is not required to
Conscientiously to screen which classification each student belongs on earth, as long as substantially suitable.On this basis, each student is according to flat
When performance be endowed a classification COEFFICIENT K, category COEFFICIENT K carries out assignment according to the daily performance of the student, is insulted by despot
A possibility that it is bigger, assignment is bigger, to other classmates carry out despot insult a possibility that it is bigger, assignment is smaller, although student substantially divides
For three classes, but not only 3 numerical value, the classification coefficient value of each student can be different with other classmates to classification coefficient
's.Other than the form of above-mentioned questionnaire, the initial value of K can also be determined by teacher according to the daily performance of student, equally
Reason, it is especially accurate which does not need, as long as conforming generally to, there is no problem there is biggish deviation, this Shen
The intelligent algorithm that please be arranged below, namely the K value of each student can be constantly modified according to the historical data of student, eventually
It is revised as the initial K value of mistake accurately to meet actual numerical value.
Establishing between the processor and student terminal and teacher's terminal has communication connection, and this communication connection can be wired
Or wireless mode.Student terminal may include it is multiple, multiple places in school are respectively set, some students are bullied or seized by force icepro
Later may dare not carry out in public despot insult alarm, the student terminal of settable some movements, student can carry to
It alarms covered place.Or the student terminal fixed in more hidden place setting.As shown in Fig. 2, student terminal is extremely
Less include fingerprint identification module 5, photographing module 6 and display panel module 4, insults report when carrying out despot using student terminal by despot Ling student
When alert, fingerprint module is pressed by finger, processor can quickly identify the identity information of alarm student, and read its classification coefficient
Value K.After identifying identity information, student's expression is analyzed using photographing module, carries out expression assignment based on the analysis results
L, if it is it is nervous, fear, indignation or serious class expression are then assigned a value of L2, if easily, if the expression of glad or pleasant class
Assignment L1, wherein L1 < L2.Wherein the difference of L1 and L2 is greater than 0.3, we are by a large amount of numerical simulation calculation, when difference is big
Preferable discrimination could be generated when 0.3, conducive to the judgement of result, otherwise may result in the increase of rate of false alarm.It takes the photograph herein
As module has been mounted on student terminal, the camera distance of student's facial expression is greatly shortened, very good solution camera shooting
The problem of misjudgment of expression caused by distance is remote, and due to being to carry out expression point only for the student for pressing student terminal
Analysis, information processing capacity are greatly reduced, and more complicated and more accurate algorithm can be used on this basis, to further increase
The accuracy of expression judgement.
After completion Expression Recognition judges, display panel module shows each student's according to this class of student's K value size order
Name namely the big student of K value are shown in front, and K value is small to be shown in below, since student is set as movably, institute
It should not be too large with the volume of mobile terminal, a display screen can not all show the name of all students in class, and such as
The student of fruit alarm is boy student, then preferentially shows the big boy student of K value in front, such as the name for requiring display screen first page to show
All boy students in word are directly arranged according to K value size order if the student of alarm is schoolgirl.Alarming student can
Corresponding name is clicked directly on to confirm the student for implementing despot and insulting.Student's name that processor is clicked according to alarm student is in memory
It is interior to read student's name to transfer the K value of the student, and calculate 1 and subtract the classification coefficient value K institute for being clicked name student
The difference is indicated (namely calculating M=1-K) with M, finally, processor calculates the size of J=K*M*L value, processor by the difference obtained
Compare the size of J value and preset threshold, if J value is greater than preset threshold value, sends teacher's terminal for corresponding information, if
J value is less than preset threshold, then primary to alarm student's record spurious alarm, when the spurious alarm number of a student reaches certain amount
After, processor also needs to send corresponding information to teacher's terminal.Above-mentioned K, L, the size of M value are greater than 0 less than 1.
Teacher's terminal needs to carry out actual treatment to corresponding event after receiving the information that processor is sent, if sent
What is come is that despot insults warning message, then teacher should go to scene to verify, if confirmation belongs to despot's icepro event after verifying, teach
Despot is carried out in teacher's terminal and insults confirmation, and processor is according to confirmation as a result, modifying alarm student and reality based on intelligent algorithm
The corresponding K value for applying despot Ling Hangwei student increases by the K value of the student of despot Ling Hangwei, and the K value for implementing despot Ling Hangwei student becomes
It is small.If the number that the information that processor is sent is some student's spurious alarm has been more than preset times, teacher will also go existing
Field is handled, and the multiple alarm for verifying student is on earth spurious alarm, if really belonging to spurious alarm by verification, for institute
It states carried out by student deliberately makes fun of, then teacher belongs to spurious alarm in teacher's terminal check, and processor reduces according to confirmation result
Raw K value belongs to processor misjudgment, then carries out true alarming determining if belonging to true alarm by verification, processor according to
Confirmation result increases the K value of the student or increases the preset times of the student.The situation for changing student K value further includes one
Despot is carried out to it without student in the timing phase and insults alarm, such as in three months or half a year, year, none student couple
It carries out despot and insults alarm, illustrates student's sustained superior performance, when the conditions are satisfied, then processor can suitably increase its K
Value.
Above-mentioned K and L and the initial value of the preset threshold can be by teachers determines according to actual conditions, which generally conforms to
Actual conditions, it is not required that completely true, post processor can be adjusted constantly according to the actual operation, to change
Into judging result.The difference of class and class namely the preset threshold of each class are reflected for the size of preset threshold
Size be it is different, preferable for class's order, less generation student, which fights, seizes by force the class of Ling Hangwei, and preset threshold can be set
Set it is big a little and the class bad for class's order, the value can be set a little bit smaller, processor can be according to three months or half
Year history data adjust the size of its value, the adjustment of above-mentioned several parameter values can be based entirely on existing artificial intelligence
Technology, reduction are thought to intervene, and realize the correctly predicted of result and judgement.
According to the system and method for the application, it while solving the problems, such as background technique, advantage is obtained that: 1) being not required to
Smart phone is wanted, processor, teacher's terminal and student terminal may be coupled directly in the intelligent network of campus, it is only necessary to existing
There is campus intelligent network be simply transformed, does not need in addition to increase processor, required teacher's terminal and student terminal
Quantity it is few, it is required at low cost;2) student's facial expression camera distance is close, improves accuracy of analysis, while using fingerprint
It carries out just carrying out Expression analysis on the basis of identification, information processing capacity is greatly reduced, simultaneously because student's initiative alarming
The judgement of alarm behavior greatly improved in the intervention of behavior;3) despot Ling Hangwei judgement uses quantitative manner, changes previous list
The simple judgment mode of an only factor or a certain individual, judging result are more acurrate;4) artificial intelligence technology gets involved in parameter tune
In whole, system may make the more to run the more perfect, more using more accurate;5) not deliberately some or certain students are classified as danger
Dangerous student will not cause the dislike and unpleasantness of student.
Illustrating just for the invention above, but limitation of the present invention can not be interpreted as.This field skill
The deformation of art personnel precognition is in protection scope of the present invention.
Claims (10)
1. Ling Hangwei early warning system is seized by force in a kind of campus based on artificial intelligence technology, it is characterised in that: whole including processor, student
End and three parts of teacher's terminal, wherein processor is for executing calculating and artificial intelligence analysis, and the student terminal is for learning
Raw to carry out despot's icepro alarm use, teacher's terminal receives the information of processor transmission for teacher and is carried out according to transmitted information
Subsequent processing, the processor include memory, and master database is stored in memory, and master database includes all students
Information, each student is endowed a classification COEFFICIENT K according to usually performance, and category COEFFICIENT K is according to the daily table of the student
A possibility that a possibility that now carrying out assignment, being insulted by despot is bigger, and assignment is bigger, carries out despot's icepro to other classmates is bigger, assigns
It is worth smaller, establishing between the processor and student terminal and teacher's terminal has a communication connection, and student terminal includes at least fingerprint
Identification module, photographing module and display panel module, alarm student press fingerprint identification module by finger, and processor can quickly be known
Not Bao Jing student identity information, and read its classification coefficient value K, and analyze using photographing module student's expression, root
Expression assignment L is carried out according to analysis result, it is two classes that the expression assignment L, which is divided to, is L1 and L2 respectively, if it is anxiety, fears, anger
Anger or serious class expression are then assigned a value of L2, if easily, assignment L1 if the expression of glad or pleasant class, wherein L1 < L2 and
The two difference is greater than 0.3, and after completion Expression Recognition judges, the display panel module is according to this class of student's classification coefficient value K
Size the name of each student is shown according to sequence from big to small, alarm student can click directly on corresponding name to confirm reality
The student that despot insults is applied, processor reads student's name in memory according to student's name that alarm student clicks to transfer this
It is clicked the classification coefficient value K of name student, and calculates 1 and subtracts the resulting difference of classification coefficient value K for being clicked name student,
The difference is indicated with M, finally, processor calculates the size of J=K*M*L value, processor compares calculated result J value and default threshold
The size relation of value, if J value is greater than preset threshold, then it is assumed that alarm student receives despot Ling Hangwei, and processor will accordingly be believed
Breath is sent to teacher's terminal, if J value is less than preset threshold, records that spurious alarm is primary to alarm student, when student's
When spurious alarm number is more than the preset times that the student is set, processor also needs to send corresponding information to teacher's end
End, above-mentioned K, L, the size of M value are greater than 0 less than 1.
2. Ling Hangwei early warning system is seized by force in the campus according to claim 1 based on artificial intelligence technology, it is characterised in that: base
The initial K value of each student can be determined by teacher according to the daily performance of student in database.
3. Ling Hangwei early warning system is seized by force in the campus according to claim 1 based on artificial intelligence technology, it is characterised in that: base
The initial K value of each student can obtain average value according to questionnaire to determine in database.
4. Ling Hangwei early warning system is seized by force in the campus according to claim 1 based on artificial intelligence technology, it is characterised in that: such as
What fruit teacher's terminal received is that despot insults warning message, then teacher goes to scene to verify, and is insulted if confirming after verifying and belonging to despot
Event then carries out despot's icepro in teacher's terminal and confirms, processor is according to confirmation results modification alarm student and implements to seize by force icepro row
For the corresponding K value of student, increase by the K value of the student of despot Ling Hangwei, the K value for implementing despot Ling Hangwei student becomes smaller.
5. Ling Hangwei early warning system is seized by force in the campus according to claim 1 based on artificial intelligence technology, it is characterised in that: such as
It has been more than preset times that fruit teacher's terminal received, which is the number of some student's spurious alarm, then teacher will also go at scene
Reason, the multiple alarm for verifying student is on earth spurious alarm, if really belonging to spurious alarm by verification, teacher is in teacher
Terminal check belongs to spurious alarm, and processor reduces the K value of the student according to confirmation result, if belonging to true alarm by verification,
Belong to processor misjudgment, then carry out true alarming determining, processor increases the K value or increase of the student according to confirmation result
The preset times of the student.
6. Ling Hangwei early warning system is seized by force in the campus according to claim 1 based on artificial intelligence technology, it is characterised in that: one
Despot is carried out to some student without student in the timing phase and insults alarm, illustrates student's sustained superior performance, then processor increases its K
Value.
7. a kind of, any campus despot's Ling Hangwei early warning system based on artificial intelligence technology is seized by force in -6 according to claim 1
The method for insulting early warning, it is characterised in that: alarm student presses fingerprint identification module by finger, and processor can quickly identify alarm
The identity information of student, and its classification coefficient value K is read, and analyze student's expression using photographing module, according to analysis
As a result expression assignment L is carried out, it is two classes that the expression assignment L, which is divided to, is L1 and L2 respectively, if it is anxiety, fears, angry or tight
Respectful class expression is then assigned a value of L2, if easily, assignment L1 if the expression of glad or pleasant class, wherein L1 < L2 and the two is poor
Value is greater than 0.3, and after completing Expression Recognition and judging, the display panel module is according to the size of this class of student's classification coefficient value K
The name of each student is shown according to sequence from big to small, alarm student can click directly on corresponding name to confirm that implementing despot insults
Student, processor reads student's name in memory and is clicked to transfer this according to student's name that alarm student clicks
The classification coefficient value K of name student, and calculate 1 and subtract the resulting difference of classification coefficient value K for being clicked name student, by the difference
Value indicates with M, finally, processor calculates the size of J=K*M*L value, processor compares the big of calculated result J value and preset threshold
Small relationship, if J value is greater than preset threshold, then it is assumed that alarm student receives despot Ling Hangwei, and processor sends corresponding information
It is primary to alarm student's record spurious alarm if J value is less than preset threshold to teacher's terminal, when the spurious alarm of a student
When number is more than the preset times that the student is set, processor also needs to send corresponding information to teacher's terminal, above-mentioned
The size of K, L, M value is greater than 0 less than 1.
8. according to the method described in claim 7, it is characterized by: the size of the preset threshold of each class not
Together, the relatively good class of class's order, the preset threshold are set as relatively large, and processor is according to going through in the regular period
History operation data adjusts the size of the preset threshold.
9. according to the method described in claim 7, it is characterized by: if teacher's terminal receive be despot insult warning message,
Then teacher goes to scene to verify, if confirmation belongs to despot's icepro event after verifying, despot is carried out in teacher's terminal and insults confirmation, place
Device is managed according to the corresponding K value of confirmation results modification alarm student and implementation despot Ling Hangwei student, by the student of despot Ling Hangwei
K value increase, implement despot Ling Hangwei student K value become smaller.
10. according to the method described in claim 7, it is characterized by: if what teacher's terminal received is some student's vacation report
Alert number has been more than preset times, then teacher also will go to scene to handle, and the multiple alarm for verifying student is on earth
Spurious alarm, if really belonging to spurious alarm by verification, teacher belongs to spurious alarm in teacher's terminal check, and processor is according to really
Recognize result and reduce the K value of the student, if belonging to true alarm by verification, belongs to processor misjudgment, then really alarmed
Confirmation, processor increase the K value of the student according to confirmation result or increase the preset times of the student.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910641993.3A CN110348754A (en) | 2019-07-16 | 2019-07-16 | A kind of campus despot's Ling Hangwei early warning system and method based on artificial intelligence technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910641993.3A CN110348754A (en) | 2019-07-16 | 2019-07-16 | A kind of campus despot's Ling Hangwei early warning system and method based on artificial intelligence technology |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110348754A true CN110348754A (en) | 2019-10-18 |
Family
ID=68174846
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910641993.3A Pending CN110348754A (en) | 2019-07-16 | 2019-07-16 | A kind of campus despot's Ling Hangwei early warning system and method based on artificial intelligence technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110348754A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111210591A (en) * | 2019-12-30 | 2020-05-29 | 江西理工大学 | Artificial intelligence early warning system |
CN117237155A (en) * | 2023-10-28 | 2023-12-15 | 南京达尔晟信息科技有限公司 | Intelligent campus student behavior analysis system based on artificial intelligence |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202110631U (en) * | 2011-06-13 | 2012-01-11 | 山东中创软件工程股份有限公司 | Electronic student identity card and alarm system |
CN102473257A (en) * | 2009-07-31 | 2012-05-23 | 东屋株式会社 | Information collection system |
CN107590953A (en) * | 2017-09-27 | 2018-01-16 | 广东小天才科技有限公司 | Alarm method and system of intelligent wearable device and terminal device |
-
2019
- 2019-07-16 CN CN201910641993.3A patent/CN110348754A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102473257A (en) * | 2009-07-31 | 2012-05-23 | 东屋株式会社 | Information collection system |
CN202110631U (en) * | 2011-06-13 | 2012-01-11 | 山东中创软件工程股份有限公司 | Electronic student identity card and alarm system |
CN107590953A (en) * | 2017-09-27 | 2018-01-16 | 广东小天才科技有限公司 | Alarm method and system of intelligent wearable device and terminal device |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111210591A (en) * | 2019-12-30 | 2020-05-29 | 江西理工大学 | Artificial intelligence early warning system |
CN117237155A (en) * | 2023-10-28 | 2023-12-15 | 南京达尔晟信息科技有限公司 | Intelligent campus student behavior analysis system based on artificial intelligence |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107358555A (en) | Teaching monitoring and managing method and system | |
DE60204292T2 (en) | AUTOMATIC MONITORING SYSTEM FOR A PATIENT AND HOSPITAL | |
CN111260314A (en) | Wisdom campus security situation perception system | |
CN110910549A (en) | Campus personnel safety management system based on deep learning and face recognition features | |
CN107730681A (en) | A kind of Campus Security ensures intelligent supervision early warning system | |
CN110097283B (en) | Teaching management system and method based on face recognition | |
CN108399190A (en) | A kind of panorama image space method applied to prison convict | |
CN107590953B (en) | Alarm method and system of intelligent wearable device and terminal device | |
CN111429321A (en) | Wisdom campus management system based on thing networking | |
CN110348754A (en) | A kind of campus despot's Ling Hangwei early warning system and method based on artificial intelligence technology | |
CN111985807A (en) | Campus security remote monitoring management system based on big data | |
CN116563797B (en) | Monitoring management system for intelligent campus | |
CN111370113A (en) | Remote psychological counseling system and method based on Internet of things cloud | |
CN112967487A (en) | System for preventing, controlling, detecting and reporting data of campus infectious disease epidemic situation, monitoring and early warning | |
CN112102129A (en) | Intelligent examination cheating identification system based on student terminal data processing | |
CN112085883A (en) | Intelligent invigilation anti-cheating system | |
CN115330568A (en) | Intelligent classroom teaching quality evaluation system and method | |
CN109886850A (en) | A kind of data comprehensive management system and management method for smart classroom | |
CN112488888A (en) | Wisdom campus safety early warning system based on thing networking and big data technology | |
CN115331346B (en) | Campus access control management method and device, electronic equipment and storage medium | |
JP2021096836A (en) | Bullying indication determination program and system, and bullying determination program and system | |
CN114822143B (en) | Military training intelligent examination management system and method | |
CN107483544A (en) | A kind of intelligent movable monitoring system and monitoring method | |
CN110148234A (en) | Campus brush face picks exchange method, storage medium and system | |
CN110458260A (en) | A kind of method, apparatus and computer memory device for supervising school bus |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191018 |