CN117636607A - Campus safety monitoring and early warning system based on artificial intelligence - Google Patents
Campus safety monitoring and early warning system based on artificial intelligence Download PDFInfo
- Publication number
- CN117636607A CN117636607A CN202410090153.3A CN202410090153A CN117636607A CN 117636607 A CN117636607 A CN 117636607A CN 202410090153 A CN202410090153 A CN 202410090153A CN 117636607 A CN117636607 A CN 117636607A
- Authority
- CN
- China
- Prior art keywords
- early warning
- module
- data
- campus
- police
- 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.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 23
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 22
- 238000007405 data analysis Methods 0.000 claims abstract description 57
- 238000012545 processing Methods 0.000 claims abstract description 42
- 238000005516 engineering process Methods 0.000 claims abstract description 13
- 230000002159 abnormal effect Effects 0.000 claims description 40
- 230000000875 corresponding effect Effects 0.000 claims description 34
- 238000011156 evaluation Methods 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 7
- 239000013598 vector Substances 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 5
- 230000008713 feedback mechanism Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000009471 action Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 3
- 238000000034 method Methods 0.000 description 24
- 230000008569 process Effects 0.000 description 14
- 230000010365 information processing Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 230000006378 damage Effects 0.000 description 5
- 238000012790 confirmation Methods 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000000391 smoking effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 208000027418 Wounds and injury Diseases 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 208000014674 injury Diseases 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000036626 alertness Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Alarm Systems (AREA)
Abstract
The invention discloses an artificial intelligence-based campus security monitoring and early warning system, which belongs to the field of security monitoring and comprises a campus data acquisition module, a cloud server, a data analysis module, an early warning pushing module, a campus management end module, a police management end module and a police user end module. The invention aims to provide an artificial intelligence-based campus security monitoring and early warning system, which utilizes an artificial intelligence technology to extract and classify the characteristics of data such as images and the like, thereby improving the recognition accuracy and efficiency; the campus management end module, the police management end module and the police user end module realize the processing, feedback and execution of the early warning information, and improve the treatment effect and quality.
Description
Technical Field
The invention relates to the field of safety monitoring, in particular to an artificial intelligence-based campus safety monitoring and early warning system.
Background
Campus security is an important issue for social and family concerns and is also an important content for school management. Therefore, how to effectively prevent and process campus security events and improve the level and efficiency of campus security management is a problem to be solved urgently.
In order to cope with the campus security problem, some campus security monitoring and early warning systems based on video monitoring systems are applied at present. The method comprises the steps that a camera and other devices are used for collecting data such as images of various areas and scenes in a campus, safety personnel monitor collected videos, and when safety risks or anomalies are found, the safety personnel process the safety risks or anomalies in a field processing mode, an evacuation mode, an alarming mode and the like.
However, due to the fact that the number of cameras is large, the required monitoring scenes are large, the number of personnel is large, and the safety risk or the abnormal recognition efficiency can be affected; meanwhile, effective communication with police systems and the like cannot be performed, so that quick response and effective treatment on safety risks or abnormal conditions cannot be realized. There is a need to further increase the level and efficiency of campus security management.
Disclosure of Invention
Aiming at the problems, the invention provides an artificial intelligence-based campus security monitoring and early warning system, which comprises:
the campus data acquisition module is used for acquiring image data in a campus and encrypting the data through the encryption module;
the cloud server receives the encrypted data transmitted by the campus data acquisition module in a wireless, wired and other modes, decrypts and restores the data through the decryption module, restores original image data, and is also responsible for reserving the data;
the data analysis module analyzes the image data received by the cloud server by using an artificial intelligence technology to identify the safety risk and abnormal conditions existing in the campus, such as a frame strike, a fire disaster, a rod-holding intrusion and the like, and generates corresponding early warning information;
the early warning pushing module receives the early warning information generated by the data analysis module and pushes the early warning information to the campus management end module so as to timely treat the safety risk or abnormal situation;
the campus management end module receives the early warning information sent by the early warning pushing module, displays the early warning information on an interface of the campus management end module, determines whether the safety risk or the abnormal situation can be automatically resolved according to the early warning information, and the automatic resolving mode can be used for closing the early warning information after resolving through teachers, security field processing, voice shouting and the like, and sends the early warning information to the police management end module if the early warning information cannot be resolved;
the police management end module receives the early warning information sent by the campus management end module, displays the early warning information on an interface of the police management end module, and forwards the early warning information to the corresponding police user end module according to the content and the emergency degree of the early warning information and the police information which is calculated based on big data and is most in line with the action;
the police user side module receives the early warning information forwarded by the police management side module and displays the early warning information on an interface of the police user side module, and corresponding actions such as movement, arrival, disposal and the like are taken according to the content and the emergency degree of the early warning information and responsibilities and authorities of the police user side module.
The modules are connected in a wireless mode, a wired mode and the like.
The beneficial effects that this scheme produced are: the comprehensive monitoring and intelligent analysis of each area and scene in the campus can be realized, and related personnel can be timely found and informed to process the safety risk and abnormal condition existing in the campus, so that the campus safety management level and efficiency are improved; meanwhile, the data analysis module is used for extracting and classifying the characteristics of complex image and other data by utilizing an artificial intelligence technology, so that the recognition accuracy and efficiency are improved; the campus management end module, the police management end module and the police user end module realize the processing, feedback and execution of the early warning information, and improve the treatment effect and quality.
Further, in order to avoid the false alarm condition, the waste of system performance and resources is avoided; the data analysis module can also judge the authenticity of the data acquired by the campus data acquisition module, the data judged to be the false alarm condition is recorded by the cloud server and then stops transmitting, and the data judged to be the true alarm condition is sent to the early warning pushing module.
The formula for judging true and false alarm conditions is as follows:
wherein, P represents the probability that the police condition corresponding to the data is true when the campus image data is given;representing model parameters; />Representing natural constants; />Representation->Is a transpose of (2); />Representation->And->Dot product of->Representing feature vectors in the image data of a given campus.
The true and false judgment of the data can effectively filter out some data which are not critical or maliciously manufactured, avoid unnecessary interference and burden on the system, and improve the response speed and processing capacity of the system.
Furthermore, the encryption module and the decryption module adopt a blockchain technology, and the characteristics of distributed, decentralised, non-tamperable and the like of the blockchain technology are utilized to ensure the safety and reliability in the data transmission process and prevent the data from being tampered or leaked.
Further, the campus data acquisition module acquires image data through a camera.
Further, the early warning information includes:
the early warning level is comprehensively calculated according to factors such as the influence range, duration, occurrence probability and the like of the safety risk or abnormal condition, wherein the influence range, the duration, the occurrence probability can be estimated according to the analysis result or the historical data of the data analysis module; the method can rapidly judge the severity of the safety risk or abnormal condition, and is convenient for taking corresponding measures; the early warning level adopts the following formula:
wherein L represents an early warning level, S represents an influence range of a safety risk or an abnormal condition, T represents duration of the safety risk or the abnormal condition, and C represents hazard degree of the safety risk or the abnormal condition. The function f is a nonlinear function and is used for comprehensively considering the influence of various factors on the early warning level. For example, if f (S, T, C) >0.8, the warning level is considered to be high; if f (S, T, C) <0.2, then the early warning level is considered to be low; if neither is satisfied, the early warning level is considered to be medium.
The early warning content is obtained by extracting and classifying the characteristics of the data such as images, videos, voices and the like according to the data analysis module and comprises information such as occurrence time, places, characters, objects, scenes and the like; the method can clearly know the specific conditions of safety risks or abnormal conditions, and is convenient for analyzing reasons and responsibilities; the generation process of the early warning content adopts the formula:
wherein N represents the early warning content,representing the place of occurrence of the event, t representing the time of occurrence of the event, R representing the primary participant of the event, and E representing the primary process of the event. The function h is a generating function for generating early warning content according to various factors.
Further, in order to improve the processing efficiency of the early warning information, the early warning information further includes: early warning advice for providing an emergency solution for a security risk or abnormal situation; the emergency scheme and the operation steps for processing the safety risk or the abnormal situation can be effectively guided, and the treatment efficiency and the treatment quality are improved.
Furthermore, the data analysis module adopts a deep learning technology, and utilizes a neural network to extract and classify the characteristics of the image data; and the data analysis module optimizes and adjusts the early warning information by using a feedback mechanism.
Further, the campus management end module includes:
the campus early warning data receiving sub-module is used for receiving the early warning information sent by the early warning pushing module and displaying the early warning information on an interface of the campus management end module, wherein the interface is displayed on a monitor, a mobile phone, a tablet and the like;
the campus early warning data processing sub-module is used for processing the received early warning information, including operations such as confirmation, neglect, forwarding and the like, wherein the confirmation operation indicates that the campus management end module can self-resolve the security risk or abnormal situation and execute corresponding operations; neglecting operation means that the campus management end module considers that the early warning information does not need to be processed or invalid, for example, when a performer in a campus activity holds a performance stick tool and the like, the early warning information can be considered that the early warning information does not need to be processed; the forwarding operation indicates that the campus management end module cannot self-solve the security risk or abnormal situation, and forwards the early warning information to the police management end module;
the campus early warning data feedback sub-module is used for communicating with the early warning pushing module and the data analysis module to send the processing result of the campus early warning data processing sub-module to the early warning pushing module and send the evaluation of the campus early warning data processing sub-module to the data analysis module; the processing result shows what operation is adopted by the campus management end module to the early warning information; the evaluation represents satisfaction or suggestion of the campus management end module to the early warning information, so as to be used for adjusting generation and pushing parameters of the early warning information.
The early warning information can be timely acquired through each sub-module of the campus management end module and displayed on the interface of the campus management end module, so that convenience and visibility of information acquisition are improved; then, corresponding processing operations such as confirmation, neglect, forwarding and the like can be performed according to the content and the grade of the early warning information, so that the flexibility and the efficiency of information processing are improved; meanwhile, the processing result and evaluation can be sent to the early warning pushing module and the data analysis module, so that closed-loop feedback of information processing is realized, and the quality and accuracy of the information processing are improved.
Further, the police management end module includes:
the police early warning data receiving sub-module is used for receiving the early warning information sent by the campus management end module and displaying the early warning information on an interface of the police management end module, wherein the interface can be displayed through a monitor, a mobile phone, a tablet and the like;
the police early warning data distribution sub-module is used for distributing the received early warning information and forwarding the information to the corresponding police user terminal module according to the police information which is calculated based on big data and is most in line with the movement;
and the police early warning data feedback sub-module is used for sending the distribution result of the police early warning data distribution sub-module to the early warning pushing module and the campus management end module, sending the evaluation of the police early warning data distribution sub-module to the data analysis module and adjusting the generation and pushing parameters of the early warning information.
The early warning information can be timely acquired through each sub-module of the police management end module and displayed on the interface of the police management end module, so that the convenience and the visibility of information acquisition are improved; meanwhile, the distribution result can be sent to the early warning pushing module and the campus management end module, and the evaluation of the early warning information can be sent to the data analysis module, so that the closed-loop feedback of the information processing is realized, and the quality and the accuracy of the information processing are improved.
Further, the police client module includes:
the police early warning data receiving sub-module is used for receiving the early warning information forwarded by the police management end module and displaying the early warning information on an interface of the police user end module;
the police early warning data execution sub-module is used for executing the received early warning information, including operations such as running, arriving and disposing;
the police early warning data feedback sub-module is used for sending the execution result of the police early warning data execution sub-module to the police management end module and sending the evaluation of the police early warning data execution sub-module to the data analysis module and is used for adjusting the generation and pushing parameters of early warning information.
The early warning information can be timely acquired through each sub-module of the police user side module and displayed on the interface of the police user side module, so that the convenience and the visibility of information acquisition are improved; then, corresponding processing operations such as operation, arrival, treatment and the like can be performed according to the content, the grade and the like of the early warning information, so that the flexibility and the efficiency of information processing are improved; meanwhile, an execution result can be sent to the police management end module and evaluation of early warning information can be sent to the data analysis module, closed loop feedback of information processing is achieved, and quality and accuracy of information processing are improved.
Drawings
Fig. 1 is a flowchart of the operation of example 4.
Detailed Description
In order that those skilled in the art will better understand the technical solutions, the following detailed description of the technical solutions is provided with examples and illustrations only, and should not be construed as limiting the scope of the present application in any way.
Embodiment 1, a campus security monitoring and early warning system based on artificial intelligence includes: the system comprises a campus data acquisition module, a cloud server, a data analysis module, an early warning pushing module, a campus management end module, a police management end module and a police user end module.
The campus data acquisition module acquires image data through the camera and encrypts the data through the encryption module, and the encryption module adopts a blockchain technology to ensure the safety and the integrity of the data. And the cloud server receives the encrypted data transmitted by the campus data acquisition module and decrypts and restores the data through the decryption module. The data analysis module performs artificial intelligence technology analysis on the data received by the cloud server, can classify the acquired images through algorithms such as VGG, resNet, inception, determines data acquisition time through system time, determines event occurrence places through installation places of the campus data acquisition module, recognizes safety risks and abnormal conditions in the campus, and generates corresponding early warning information. The early warning pushing module receives the early warning information generated by the data analysis module and pushes the content of the early warning information to the campus management end module. The campus management end module receives the early warning information sent by the early warning pushing module, decides whether the safety risk or the abnormal situation can be resolved by self according to the content of the early warning information, and forwards the safety risk or the abnormal situation which cannot be resolved to the police management end module. The police management end module receives the early warning information sent by the campus management end module, and forwards the early warning information to the corresponding police user end module according to the content and the emergency degree of the early warning information and the police information which is calculated based on big data and is most in line with the movement. The police user side module receives the early warning information forwarded by the police management side module, and takes corresponding actions according to the content and the emergency degree of the early warning information and the responsibilities and authorities of the police user side module.
The early warning information comprises early warning grade and early warning content, and in order to generate the early warning grade, the data analysis module needs to consider the following three factors:
impact range S of security risk or abnormal situation: indicating how extensive the event may affect. For example, if the event occurs in a classroom, the impact range is small; if the event occurs on the playground, the impact range is large.
Duration T of security risk or abnormal situation: indicating the length of time the event has passed from start to end. For example, if the event lasts for a few minutes, the duration is shorter; if the event lasts for several hours, the duration is longer.
Degree of hazard C of safety risk or abnormal situation: indicating the extent of injury or loss that the event may cause. For example, if the event is just some verbal quarry, the hazard is less severe; if the event involves violence or weapons, the hazard is high.
The data analysis module calculates the early warning level by adopting the following formula：
Wherein:
。
the early warning content is used for describing specific situations of safety risks or abnormal situations. In order to generate the early warning content, the data analysis module needs to extract the following information: the place of occurrence of the event, the time of occurrence of the event, the primary participant of the event, the primary process of the event.
The generation process of the early warning content adopts the formula:where N represents the content of the early warning,representing the place of occurrence of the event, t representing the time of occurrence of the event, R representing the primary participant of the event, and E representing the primary process of the event. The function h is a generating function for generating early warning content according to various factors.
The specific working process comprises the following steps:
a person holding the stick is arranged to break the school gate, and the event is captured by the camera and transmitted to the cloud server. The data analysis module analyzes the event, identifies that the event belongs to safety risk or abnormal condition, and generates corresponding early warning information. In order to generate the early warning information, the data analysis module needs to calculate the early warning level and the early warning content.
Wherein the data analysis module judges the influence range of the eventDuration->Degree of hazardEarly warning level->The method comprises the following steps:
according to the set threshold value, ifThe early warning level is considered to be high; if->The early warning level is considered to be low; if neither is satisfied, the early warning level is considered to be medium. Therefore, in this data case, the early warning level is medium.
The early warning content N is as follows: "10 am, one person holds the stick to break the school gate at the school gate. "
The data analysis module combines the early warning level and the early warning content into a complete early warning message and sends the complete early warning message to the early warning pushing module. In this data case, the early warning information is:
"early warning grade: in (a) and (b); the early warning content is as follows: at 10 am, at the gate of school, one holds the stick and runs the gate of school.
At the moment, the campus management end module receives the early warning information sent by the early warning pushing module, and the campus management end module sends out teachers and security guards to evacuate and close the school gate. Meanwhile, the campus management end module sends the early warning information to the police management end module, the police management end module pushes the early warning information to the police on duty closest to the school gate and having no task, after receiving the early warning information, the police on duty carries the apparatus to drive to the school gate, meanwhile, the police on duty registers in the police early warning data execution sub-module, the police on duty closes the early warning information after processing the event, and then sends an execution result to the police management end module and an evaluation aiming at the early warning information to the data analysis module.
Example 2: in a campus, a student smokes in a classroom, and the event is captured by a camera and transmitted to a cloud server. The data analysis module analyzes the event, identifies that the event belongs to safety risk or abnormal condition, and generates corresponding early warning information. The early warning information comprises early warning grades and early warning contents.
In this embodiment, the early warning level uses the formula of embodiment 1 to determine the influence range of the eventDuration->Degree of hazard->Early warning level->The method comprises the following steps:
according to the set threshold value, ifThe early warning level is considered to be high; if->The early warning level is considered to be low; if neither is satisfied, the early warning level is considered to be medium. Therefore, in this data case, the early warning level is low.
In this embodiment, the early warning content N is:
"10 am, a smoking together event occurs in a classroom, and a person smokes in the classroom. "
And finally, the data analysis module combines the early warning grade and the early warning content into complete early warning information and sends the complete early warning information to the early warning pushing module. In this data case, the early warning information is:
"early warning grade: low; the early warning content is as follows: at 10 am, a smoking together event occurs in the classroom and one person smokes in the classroom. "
At the moment, the campus management end module receives the early warning information sent by the early warning pushing module and judges that the event can be automatically resolved, and then the campus management module informs the teaching department or the class owner corresponding to the classroom to go to the scene to persuade and educate the students. And after the campus management end module finishes processing the event, closing the early warning information, and sending a processing result and evaluation to the early warning pushing module and the data analysis module.
The duration T value is determined based on the event identified by the camera.
The influence range S in embodiment 1 and embodiment 2 mainly has influence parameters of the area where the event occurs and the total area of the campus, and the following formula may be adopted:
erf is an error function, and a and B represent the area of the area where the event occurs and the total area of the campus, respectively. As in example 1, the campus area was 10000 square meters, the doorway area was 500 square meters, and the classroom area was 100 square meters, and the influence range s=0.5 in example 1 and the influence range s=0.1 in example 2 were obtained by substituting the formula.
The degree of damage C in examples 1 and 2 mainly affects the degree of loss that may be caused by the parameter, and the following formula may be used:
wherein the method comprises the steps ofRepresents a natural constant, approximately equal to 2.71828, D represents the degree of maximum damage or loss that an event may cause, and d represents the damage actually caused by the eventOr the degree of loss, the k value is constant, the set value is 0.55, and the d value is preset according to the situation possibly faced by campus management. Assuming that the maximum injury or loss degree caused by the event is 10, the person may be injured by the stick-holding and the door-checking, so the D value in the embodiment 1 is set to 8, and the person is not easily injured by smoking, so the D value in the embodiment 2 is set to 2, and the D value in the embodiment 1 are brought into the formula, so that the following results are obtained:
solving for the hazard level c=0.8 in example 1, bringing the D and D values in example 2 into the formula gives:
solving for c=0.8, and bringing the D and D values in example 2 into the formula gives the hazard level c=0.2 in example 2.
Embodiment 3, other structures and working procedures of this embodiment can be obtained by referring to embodiment 1 or 2, but in this embodiment, in order to avoid wasting system performance and resources due to false alarm conditions; the data analysis module can also judge the authenticity of the data acquired by the campus data acquisition module, the data judged to be the false alarm condition is recorded by the cloud server and then stops transmitting, and the data judged to be the true alarm condition is sent to the early warning pushing module. For this reason, the following formula is adopted in this embodiment to determine true and false alarm conditions.
Wherein, P represents the probability that the police condition corresponding to the data is true when the campus image data is given;representing model parameters, which may be learned by training data; />Representing a natural constant, approximately equal to 2.71828; />Representation->Transpose of (i.e. add->To obtain a new vector; />Representation->And->Dot product of (i.e. handle +)>And->Multiplication and addition of corresponding elements of (2) to obtain a scalar,/->Representing feature vectors in the image data of a given campus.
The formula adopts a logistic regression model and utilizes a classification algorithm. In this embodiment, the alertness is divided into two categories: true alarm conditions and false alarm conditions. Training a logistic regression model by using the campus image and the corresponding false and true warning label and using the data to obtain the optimal valueValues. When new campus image data exists, the model can be used for calculating the probability that the police condition corresponding to the data is true. If the probability is greater than a certain threshold (e.g., 0.5), we judge that the alarm is true; otherwise, we judge the false alarm condition. After training, the person is added with->The values are:
the formula for judging true and false alarm conditions is introduced into embodiment 1, the campus data acquisition module acquires an image, and a person holding a stick makes a correction on the door, so that the feature vector corresponding to the condition is determined firstI.e. the characteristic values of the number of persons, the number of weapons and the escape gesture in the image. The feature vectors that correspond to this identified case are:
wherein the first element represents a constant term and the last three elements represent a person, a weapon and no escape gesture in the image, respectively. Then, the previously given is usedThe value, the probability that the corresponding alert condition is true is:
since this probability is greater than 0.5, a true alarm condition is judged. And then the data analysis module early warning information is sent to the early warning pushing module.
If the campus data acquisition module acquires an image, a male student holds a stick for performance in the campus. After encryption and decryption, the image is sent to a cloud server and analyzed by a data analysis module. Then the corresponding feature vector for this image is:
wherein the first element represents a constant term and the last three elements represent a person, a weapon and a no escape gesture in the image, respectively. Then, the probability that the alarm corresponding to the image is true is:
because the probability is smaller than 0.5, the false alarm condition is judged, and the information is recorded in the cloud server and then is stopped from being transmitted.
Example 4: as shown in fig. 1, other structures and working processes of the present embodiment are implemented 1-3 at the same time, but in the present embodiment, in order to improve accuracy of information identification, etc., a data analysis module adopts a deep learning technology, and uses a neural network to perform feature extraction and classification on image data; and the data analysis module optimizes and adjusts the early warning information by using a feedback mechanism.
For this purpose, the campus management end module comprises:
the campus early warning data receiving sub-module is used for receiving the early warning information sent by the early warning pushing module and displaying the early warning information on an interface of the campus management end module;
the campus early warning data processing sub-module is used for processing the received early warning information, such as checking, confirming, forwarding and the like;
and the campus early warning data feedback sub-module is used for sending the processing result of the campus early warning data processing sub-module to the early warning pushing module and sending the evaluation of the campus early warning data processing sub-module to the data analysis module and used for adjusting the generation and pushing parameters of the early warning information.
The police management end module comprises:
the police early warning data receiving sub-module is used for receiving the early warning information sent by the campus management end module and displaying the early warning information on an interface of the police management end module;
the police early warning data distribution sub-module is used for distributing the received early warning information and forwarding the information to the corresponding police user terminal module according to the police information which is calculated based on big data and is most in line with the movement;
and the police early warning data feedback sub-module is used for sending the distribution result of the police early warning data distribution sub-module to the early warning pushing module and the campus management end module, sending the evaluation of the police early warning data distribution sub-module to the data analysis module and adjusting the generation and pushing parameters of the early warning information.
The police user side module comprises:
the police early warning data receiving sub-module is used for receiving the early warning information forwarded by the police management end module and displaying the early warning information on an interface of the police user end module;
the police early warning data execution sub-module is used for executing received early warning information, such as checking, confirming, feeding back, completing and the like;
the police early warning data feedback sub-module is used for sending the execution result of the police early warning data execution sub-module to the police management end module and sending the evaluation of the police early warning data execution sub-module to the data analysis module and is used for adjusting the generation and pushing parameters of early warning information.
The specific working process comprises the following steps: the campus data acquisition module may be any device capable of acquiring campus image data, such as a camera, an unmanned aerial vehicle, a smart phone, etc. To take pictures or record pictures of personnel, vehicles, facilities and the like in the campus, and to acquire image data. The image data may be still pictures or dynamic video. The campus data acquisition module may perform preprocessing, such as compression, clipping, filtering, enhancement, correction, transformation, encoding, etc., on the image data as needed to facilitate subsequent transmission and analysis.
The cloud server may be any server capable of receiving, storing, processing, and transmitting image data, such as a cloud computing server, an edge computing server, a distributed computing server, and the like. The cloud server can store, backup, delete and other management operations on the image data according to the requirements.
The data analysis module may employ deep learning, machine learning, computer vision, natural language processing, etc. to perform artificial intelligence technical analysis on the image data. The data analysis module may utilize a neural network to perform feature extraction and classification on the image data, such as a convolutional neural network, a cyclic neural network, and the like. The data analysis module can detect, identify, track, analyze, judge and the like personnel, vehicles, facilities and the like in the image data according to preset safety rules and abnormal standards, such as face recognition, license plate recognition, behavior recognition, scene recognition, abnormal detection and the like. The data analysis module can generate early warning information according to the analysis result. The data analysis module can optimize and adjust the early warning information by using a feedback mechanism, such as increasing or decreasing the early warning threshold value, modifying or updating the early warning rule, increasing or deleting the early warning type, and the like. The data analysis module can be integrated with the cloud server or can be independently arranged.
The early warning pushing module can be any module capable of receiving, processing and sending early warning information, such as pushing the early warning information through an APP. The early warning pushing module is used for pushing the content of early warning information to the campus management end module so that campus management personnel can know the safety condition in the campus in time and take corresponding measures. The early warning pushing module can be integrated with the cloud server and can be independently arranged.
The campus manager module may be any device capable of receiving, processing, and sending the early warning information, such as a computer, tablet, etc. The campus management end module is used for enabling campus management personnel to timely know the safety condition in the campus, determining whether the safety risk or the abnormal condition can be resolved by self according to the content of the early warning information, and forwarding the safety risk or the abnormal condition which cannot be resolved to the police management end module so as to facilitate timely intervention processing of police authorities.
The police management end module can be any device capable of receiving, processing and sending early warning information, such as a computer and the like. The police management end module is used for enabling police authorities to timely know the safety condition in campuses, and forwarding police information which is calculated based on big data and is most in line with the movements to the corresponding police user end module according to the content of early warning information, so that the police can arrive at the site in time for processing.
The police client module can be any device capable of receiving, processing and sending early warning information, such as a mobile phone, a tablet and the like. The police user side module is used for enabling police to timely know the safety condition in the campus, and taking corresponding actions such as rush to the scene, investigation and evidence obtaining, illegal prevention, crime capture and the like according to the content and the emergency degree of early warning information and the responsibilities and authorities of the police user side module.
In this embodiment, a plurality of cameras are arranged in the campus as campus data acquisition modules, and are respectively arranged in areas such as teaching buildings, dormitory buildings, canteens, playgrounds and the like to acquire image data of the campus in real time. The campus data acquisition module sends the image data to the encryption module through the network, and the encryption module encrypts the image data to protect the privacy and safety of the data. The encrypted data is transmitted to a cloud server through a network, and after the cloud server receives the encrypted data, the encrypted data is decrypted and restored through a decryption module, so that the original image data is restored.
The decrypted image data is input into a data analysis module, the data analysis module adopts a deep learning technology, the neural network is utilized to conduct feature extraction and classification on the image data, safety risks and abnormal conditions existing in a campus, such as fire, frame construction, intrusion, theft and the like, are identified, and corresponding early warning information is generated. The early warning information comprises early warning grade, early warning content and early warning suggestion, wherein the early warning suggestion provides an emergency scheme according to other safety risks or abnormal conditions, if the emergency scheme is identified as fire, an evacuation scheme and an alarm telephone are provided, the emergency scheme and operation steps for processing the safety risks or abnormal conditions can be effectively guided, and the treatment efficiency and quality are improved.
The early warning information is output to an early warning pushing module, the early warning pushing module pushes the content of the early warning information to a campus management end module, and after the campus management end module receives the early warning information, the early warning information is displayed on an interface of the campus management end module through a campus early warning data receiving sub-module for viewing and processing by campus management staff. And the campus manager processes the information through the campus early warning data processing sub-module according to the content of the early warning information, such as calling a relevant video monitoring picture, contacting a relevant teacher or student, or sending a relevant staff to the scene, etc., so as to solve the security risk or abnormal situation. The processing result is sent to the early warning pushing module through the campus early warning data feedback sub-module, and the data analysis module is used for adjusting generation and pushing parameters of early warning information, such as increasing or decreasing early warning level, increasing or decreasing early warning frequency and the like.
If campus manager judges that security risk or abnormal situation can not be resolved by oneself or criminal case is involved, the intervention of police authorities is needed, then campus manager can forward early warning information to police manager module through campus early warning data processing submodule, after the early warning information is received by police manager module, the early warning information is displayed on the interface of police manager module through police early warning data receiving submodule for viewing and processing by police manager. Police manager distributes according to the content and the emergency of early warning information through police early warning data distribution submodule, and according to the police information that accords with the play that calculates based on big data, transmits corresponding police user side module with early warning information, and distribution result is sent early warning pushing module and campus management side module through police early warning data feedback submodule to make things convenient for managers and campus personnel to know out the police condition.
After the police user side module receives the early warning information forwarded by the police management side module, the early warning information is displayed on an interface of the police user side module through the police early warning data receiving sub-module for viewing and executing by a police. The police performs the execution, such as police outputting, investigation, capturing and the like, through the police early warning data execution submodule according to the content and the emergency degree of the early warning information and the responsibilities and authorities of the police so as to maintain the safety and the order of the campus. The execution result is sent to the police management end module through the police early warning data feedback sub-module, so that police management personnel can know real-time conditions conveniently, and the police user end module can be integrated at a mobile phone or a tablet and the like.
Meanwhile, the campus early warning data feedback sub-module, the police early warning data feedback sub-module and the police early warning data feedback sub-module send the evaluation of the early warning information to the data analysis module for adjusting the generation and pushing parameters of the early warning information; the evaluation comprises satisfaction degree of the early warning information content and suggestion of the early warning information, and the early warning information is optimized and adjusted through a feedback mechanism of the data analysis module, so that the accuracy and the effectiveness of the early warning information are improved.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Specific examples are used herein to illustrate the principles and embodiments of the technical solutions of the present application, and the above examples are only used to help understand the methods of the present application and the core ideas thereof. The foregoing is merely a preferred embodiment of the present application, and it should be noted that, due to the limited text expressions, there is virtually no limit to the specific structure, and that, for a person skilled in the art, several modifications, adaptations, or variations may be made without departing from the principles of the present application, and the above-described features may be combined in any suitable manner; such modifications, variations, or combinations, or direct application of the concepts and aspects of the invention in other applications without modification, are intended to be within the scope of the present application.
Claims (10)
1. Campus security monitoring and early warning system based on artificial intelligence, characterized by comprising:
the campus data acquisition module is used for acquiring the image data of the campus and encrypting the data through the encryption module;
the cloud server is used for receiving the encrypted data transmitted by the campus data acquisition module and decrypting and restoring the data through the decryption module;
the data analysis module is used for carrying out artificial intelligence technology analysis on the data received by the cloud server, identifying the safety risk and abnormal condition existing in the campus, and generating corresponding early warning information;
the early warning pushing module is used for receiving the early warning information generated by the data analysis module and pushing the content of the early warning information to the campus management end module;
the campus management end module is used for receiving the early warning information sent by the early warning pushing module, determining whether the safety risk or the abnormal situation can be resolved by self according to the content of the early warning information, and forwarding the safety risk or the abnormal situation which cannot be resolved to the police management end module;
the police management end module is used for receiving the early warning information sent by the campus management end module, and forwarding the early warning information to the corresponding police user end module according to the content and the emergency degree of the early warning information and the police information which is calculated based on big data and is most in line with the action;
the police user side module is used for receiving the early warning information forwarded by the police management side module and taking corresponding actions according to the content and the emergency degree of the early warning information and the responsibilities and authorities of the police user side module.
2. The campus security monitoring and early warning system based on artificial intelligence according to claim 1, wherein the data analysis module carries out true and false judgment on the data acquired by the campus data acquisition module, the data judged to be false alarm is recorded by the cloud server and then stops transmission, and the data judged to be true alarm is sent to the early warning pushing module;
the formula for judging true and false alarm conditions is as follows:
wherein, P represents the probability that the police condition corresponding to the data is true when the campus image data is given;representing model parameters;representing natural constants; />Representation->Is a transpose of (2); />Representation->And->Is a dot product of (2); />Representing feature vectors in the image data of a given campus.
3. The campus security monitoring and early warning system based on artificial intelligence of claim 1, wherein the encryption module and decryption module employ blockchain technology.
4. The campus security monitoring and early warning system based on artificial intelligence of claim 1, wherein the campus data acquisition module acquires image data through a camera.
5. The campus security monitoring and early warning system based on artificial intelligence of claim 1, wherein the early warning information includes:
the early warning level is used for representing the severity of the safety risk or abnormal condition;
the early warning content is used for describing specific situations of safety risks or abnormal situations.
6. The system of claim 4, wherein the pre-warning information further comprises pre-warning advice for providing an emergency plan for a security risk or abnormal situation.
7. The campus security monitoring and early warning system based on artificial intelligence according to claim 1, wherein the data analysis module adopts a deep learning technology, and performs feature extraction and classification on image data by using a neural network; and the data analysis module optimizes and adjusts the early warning information by using a feedback mechanism.
8. The campus security monitoring and early warning system based on artificial intelligence of claim 7, wherein the campus management side module comprises:
the campus early warning data receiving sub-module is used for receiving the early warning information sent by the early warning pushing module and displaying the early warning information on an interface of the campus management end module;
the campus early warning data processing sub-module is used for processing the received early warning information;
and the campus early warning data feedback sub-module is used for sending the processing result of the campus early warning data processing sub-module to the early warning pushing module and sending the evaluation of the campus early warning data processing sub-module to the data analysis module and used for adjusting the generation and pushing parameters of the early warning information.
9. The campus security monitoring and early warning system based on artificial intelligence of claim 7, wherein the police management side module comprises:
the police early warning data receiving sub-module is used for receiving the early warning information sent by the campus management end module and displaying the early warning information on an interface of the police management end module;
the police early warning data distribution sub-module is used for distributing the received early warning information and forwarding the information to the corresponding police user terminal module according to the police information which is calculated based on big data and is most in line with the movement;
and the police early warning data feedback sub-module is used for sending the distribution result of the police early warning data distribution sub-module to the early warning pushing module and the campus management end module, sending the evaluation of the police early warning data distribution sub-module to the data analysis module and adjusting the generation and pushing parameters of the early warning information.
10. The campus security monitoring and early warning system based on artificial intelligence of claim 7, wherein the police user side module comprises:
the police early warning data receiving sub-module is used for receiving the early warning information forwarded by the police management end module and displaying the early warning information on an interface of the police user end module;
the police early warning data execution sub-module is used for executing the received early warning information;
the police early warning data feedback sub-module is used for sending the execution result of the police early warning data execution sub-module to the police management end module and sending the evaluation of the police early warning data execution sub-module to the data analysis module and is used for adjusting the generation and pushing parameters of early warning information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410090153.3A CN117636607B (en) | 2024-01-23 | 2024-01-23 | Campus safety monitoring and early warning system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410090153.3A CN117636607B (en) | 2024-01-23 | 2024-01-23 | Campus safety monitoring and early warning system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117636607A true CN117636607A (en) | 2024-03-01 |
| CN117636607B CN117636607B (en) | 2024-04-26 |
Family
ID=90016581
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410090153.3A Active CN117636607B (en) | 2024-01-23 | 2024-01-23 | Campus safety monitoring and early warning system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117636607B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105388826A (en) * | 2015-12-11 | 2016-03-09 | 中国环境科学研究院 | Method for establishing hybrid type rare earth mining area water environment quality monitoring and early warning system |
| CN105405150A (en) * | 2015-10-21 | 2016-03-16 | 东方网力科技股份有限公司 | Abnormal behavior detection method and abnormal behavior detection device based fused characteristics |
| CN107134112A (en) * | 2017-06-08 | 2017-09-05 | 安徽和力成信息科技有限公司 | A kind of multi-faceted safety defense monitoring system for campus |
| CN108416715A (en) * | 2018-05-11 | 2018-08-17 | 长江大学 | A kind of Campus security management system based on intelligent video camera head |
| US20180247382A1 (en) * | 2015-01-29 | 2018-08-30 | Jtb Corp. | Risk information distribution device and risk information distribution method |
| CN110363098A (en) * | 2019-06-24 | 2019-10-22 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of act of violence method for early warning, device, readable storage medium storing program for executing and terminal device |
| CN115035439A (en) * | 2022-05-30 | 2022-09-09 | 广州交信投科技股份有限公司 | Campus abnormal event monitoring system based on deep network learning |
| CN116502818A (en) * | 2023-02-13 | 2023-07-28 | 深圳天域世界科技有限公司 | Dynamic GIS geographic information monitoring system for emergency command |
| CN116895128A (en) * | 2023-05-08 | 2023-10-17 | 广州博音信息技术有限公司 | Campus behavior comprehensive early warning system |
| KR20230167549A (en) * | 2022-06-02 | 2023-12-11 | 전민호 | The apparatus and method of monitoring cctv with control moudule |
-
2024
- 2024-01-23 CN CN202410090153.3A patent/CN117636607B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180247382A1 (en) * | 2015-01-29 | 2018-08-30 | Jtb Corp. | Risk information distribution device and risk information distribution method |
| CN105405150A (en) * | 2015-10-21 | 2016-03-16 | 东方网力科技股份有限公司 | Abnormal behavior detection method and abnormal behavior detection device based fused characteristics |
| CN105388826A (en) * | 2015-12-11 | 2016-03-09 | 中国环境科学研究院 | Method for establishing hybrid type rare earth mining area water environment quality monitoring and early warning system |
| CN107134112A (en) * | 2017-06-08 | 2017-09-05 | 安徽和力成信息科技有限公司 | A kind of multi-faceted safety defense monitoring system for campus |
| CN108416715A (en) * | 2018-05-11 | 2018-08-17 | 长江大学 | A kind of Campus security management system based on intelligent video camera head |
| CN110363098A (en) * | 2019-06-24 | 2019-10-22 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of act of violence method for early warning, device, readable storage medium storing program for executing and terminal device |
| CN115035439A (en) * | 2022-05-30 | 2022-09-09 | 广州交信投科技股份有限公司 | Campus abnormal event monitoring system based on deep network learning |
| KR20230167549A (en) * | 2022-06-02 | 2023-12-11 | 전민호 | The apparatus and method of monitoring cctv with control moudule |
| CN116502818A (en) * | 2023-02-13 | 2023-07-28 | 深圳天域世界科技有限公司 | Dynamic GIS geographic information monitoring system for emergency command |
| CN116895128A (en) * | 2023-05-08 | 2023-10-17 | 广州博音信息技术有限公司 | Campus behavior comprehensive early warning system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117636607B (en) | 2024-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7036186B2 (en) | Video processing system, video processing method and video processing program | |
| JP7160154B2 (en) | System, abnormality determination device and method | |
| CN111414873B (en) | Alarm prompting method, device and alarm system based on wearing state of safety helmet | |
| CN108039008B (en) | Intelligent video monitoring method, device and system | |
| CN111131771B (en) | Video monitoring system | |
| CN109426798A (en) | A kind of border intrusion detection method, apparatus and system | |
| CN113011833A (en) | Safety management method and device for construction site, computer equipment and storage medium | |
| CN108200405A (en) | A kind of video monitoring system based on recognition of face | |
| US20210350256A1 (en) | Measuring risk within a media scene | |
| US20220198895A1 (en) | Frictionless security processing | |
| CN112419639A (en) | Video information acquisition method and device | |
| CN116129490A (en) | Monitoring device and monitoring method for complex environment behavior recognition | |
| KR102676020B1 (en) | Interaction behavior detection apparatus between objects in the image and, method thereof | |
| Bushra et al. | Predicting Anomalous and Consigning Apprise During Heists | |
| CN108833383B (en) | Linkage defense system based on deep learning and agent | |
| CN117636607B (en) | Campus safety monitoring and early warning system based on artificial intelligence | |
| CN113011300A (en) | Method, system and equipment for AI visual identification of violation behavior | |
| CN109460714A (en) | Identify the mthods, systems and devices of object | |
| Villegas-Ch et al. | Authentication, access, and monitoring system for critical areas with the use of artificial intelligence integrated into perimeter security in a data center | |
| CN112419638B (en) | Method and device for acquiring alarm video | |
| CN115100572A (en) | System and method for analyzing abnormal behaviors of campus | |
| CN110519562B (en) | Motion detection method, device and system | |
| CN114390260A (en) | Hazardous area and important place monitoring platform applied to smart city | |
| US20210158055A1 (en) | Frictionless and Autonomous Activity and Behavioral Monitoring | |
| CN115205724A (en) | Alarming method and device based on abnormal behavior and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |