Campus security monitoring method and system based on AI

Abstract

The invention is suitable for the technical field of monitoring, and particularly relates to an AI-based campus security monitoring method and system, and the method comprises the steps: S100: constructing a campus security monitoring platform, constructing nodes corresponding to students one by one, integrating the nodes, generating a monitoring chain, and integrating the monitoring chain into the campus security monitoring platform, based on preset positioning equipment, position information of students is collected, and the position information is uploaded to nodes; and S200, establishing a communication link between the node and a preset contact person. By constructing an AI monitoring strategy, voice, conversation and physiological indexes of students can be monitored, abnormal behaviors of the students can occur in time, dangerous behavior occurrence sites are recorded at the same time, the self-protection ability of the students is greatly improved when the dangerous behaviors come, and by activating an emergency call mechanism, the safety of the students is improved. Campus dangerous behaviors are effectively avoided, and the personal safety of students is better protected.

Description

Technical Field

[0001] The present invention relates to the field of monitoring technology, and in particular to an AI-based campus security monitoring method and system. Background Art

[0002] Campus safety is an important issue in protecting students’ mental health and safety, and schools can take a variety of measures to prevent and respond to this issue; for example, conducting safety education courses to raise awareness among students and faculty and staff and teach them to identify dangerous behaviors.

[0003] However, the current monitoring of dangerous behaviors on campus still requires active discovery by faculty and staff, or active reporting by students, which results in large prevention and control loopholes. With the development of AI technology, a new approach has been provided for monitoring dangerous behaviors on campus. Therefore, “how to use AI technology for campus safety monitoring” is a technical problem that needs to be solved by the present invention. Summary of the invention

[0004] The purpose of the present invention is to provide an AI-based campus security monitoring method and system to solve the problem of "how to use AI technology for campus security monitoring" raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A campus safety monitoring method based on AI, the method comprising:

[0007] S100: construct a campus security monitoring platform, construct nodes corresponding to students one by one, integrate the nodes, generate a monitoring chain, and integrate the monitoring chain into the campus security monitoring platform, collect student location information based on a preset positioning device, and upload the location information to the node;

[0008] S200: Building a communication link between the node and a preset contact, integrating an emergency call mechanism into the communication link, and opening access rights of the node to the preset contact corresponding to each student based on the communication link;

[0009] S300: collecting behavior monitoring data of the node, wherein the behavior monitoring data at least includes: voice, call and physiological indicators, constructing an AI monitoring strategy consisting of several levels, and configuring a corresponding relationship between the AI ​​monitoring strategy and the monitoring data at each level;

[0010] S400: Using the AI ​​monitoring strategy, traverse the suspicious data in the monitoring chain, and use the pre-collected video monitoring data to verify the suspicious data to determine whether there is any dangerous behavior. If so, activate the emergency call mechanism.

[0011] Furthermore, the S100 includes:

[0012] When dangerous behavior is detected, an abnormal area is marked on campus, and based on the location information, it is determined whether the student has entered the abnormal area. If so, an alarm message is generated;

[0013] Based on the communication link, the alarm information is pushed to the preset contact.

[0014] Furthermore, the emergency call mechanism is: based on a preset communication device, obtaining the distress message sent by the student, integrating the location information into the distress message, and sending the distress message to the preset contact via the communication link.

[0015] Further, the 300 includes:

[0016] Find out the AI ​​monitoring strategy corresponding to the voice and the call, and identify the keywords in the voice and the call;

[0017] Compare with a preset comparison table to determine whether the keyword is in the comparison table;

[0018] If yes, the communication device is triggered to start, collect the real-time recording of the student, and upload the real-time recording to the node.

[0019] Furthermore, the S300 further includes:

[0020] Find out the AI ​​monitoring strategy corresponding to the speech, build an AI deep learning model, input the speech into the AI ​​deep learning model, extract the semantic information in the speech, perform sentiment analysis, and output abnormal information, wherein the abnormal information at least includes: negative emotions, offensive words, insulting words, ridicule topics, and fighting;

[0021] The student corresponding to the abnormal information is determined as a subject of concern.

[0022] Furthermore, the S300 further includes:

[0023] Establishing a dialogue between the student and the communication device based on the AI ​​monitoring strategy;

[0024] The conversation is input into an AI deep learning model to obtain suggestions, which are integrated into the conversation.

[0025] Furthermore, the system comprises:

[0026] An upload module is used to construct a campus safety monitoring platform, construct nodes corresponding to students one by one, integrate the nodes, generate a monitoring chain, and integrate the monitoring chain into the campus safety monitoring platform, collect the location information of students based on a preset positioning device, and upload the location information to the node;

[0027] An open module, used to establish a communication link between the node and a preset contact person, integrate an emergency call mechanism into the communication link, and open access rights of the node to the preset contact person corresponding to each student based on the communication link;

[0028] A configuration module is used to collect behavior monitoring data of the node, wherein the behavior monitoring data includes at least: voice, call and physiological indicators, construct an AI monitoring strategy consisting of several levels, and configure the corresponding relationship between the AI ​​monitoring strategy and the monitoring data at each level;

[0029] The activation module is used to use the AI ​​monitoring strategy to traverse the suspicious data in the monitoring chain, and use the pre-collected video monitoring data to verify the suspicious data to determine whether there is any dangerous behavior. If so, activate the emergency call mechanism.

[0030] Furthermore, the upload module includes:

[0031] An alarm unit is used to mark an abnormal area on campus when a dangerous behavior is detected, and to determine whether a student has entered the abnormal area based on the location information, and to generate an alarm message if the student has entered the abnormal area;

[0032] A push unit is used to push the alarm information to the preset contact according to the communication link.

[0033] Furthermore, the configuration module includes:

[0034] A search unit, used to search for an AI monitoring strategy corresponding to the voice and call, and identify keywords in the voice and call;

[0035] The comparison unit is used to compare with a preset comparison table to determine whether the keyword is in the comparison table. If so, trigger the communication device to collect the real-time recording of the student and upload the real-time recording to the node.

[0036] Furthermore, the configuration module also includes:

[0037] An output unit, used to find out the AI ​​monitoring strategy corresponding to the voice, build an AI deep learning model, input the voice into the AI ​​deep learning model, extract the semantic information in the voice, perform sentiment analysis, and output abnormal information, wherein the abnormal information at least includes: negative emotions, offensive words, insulting words, ridicule topics, fighting, etc.;

[0038] A determination unit, used for determining the student corresponding to the abnormal information as a concerned object;

[0039] An establishing unit, configured to establish a dialogue between the student and the communication device based on the AI ​​monitoring strategy;

[0040] An integration unit is used to input the dialogue into an AI deep learning model, obtain suggestions, and integrate the suggestions into the dialogue.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] By building a campus security monitoring platform and generating a monitoring chain, the campus can be monitored for security and suspected dangerous behaviors can be found. By collecting students' location information, preset contacts can check students' whereabouts at any time. By building a communication link, connections can be established between students and preset contacts, and emotional channels can be established for students to talk in time. By building an AI monitoring strategy, students' voice, calls and physiological indicators can be monitored, and abnormal behaviors of students can be discovered in time. At the same time, the scene of dangerous behaviors can be recorded, which greatly improves students' self-protection ability when dangerous behaviors occur. By activating the emergency call mechanism, dangerous behaviors on campus can be effectively avoided, and students' personal safety can be better protected. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A flowchart of an AI-based campus safety monitoring method provided by an embodiment of the present invention;

[0044] Figure 2 A first sub-flow chart of the AI-based campus safety monitoring method provided in an embodiment of the present invention;

[0045] Figure 3 A second sub-flow diagram of the AI-based campus safety monitoring method provided in an embodiment of the present invention;

[0046] Figure 4 A block diagram of the AI-based campus security monitoring system provided by an embodiment of the present invention;

[0047] Figure 5 A block diagram of the composition of the upload module in the AI-based campus security monitoring system provided by an embodiment of the present invention;

[0048] Figure 6 A block diagram of the composition of the configuration module in the AI-based campus security monitoring system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0050] In Example 1, Figure 1 The implementation process of the AI-based campus security monitoring method provided by an embodiment of the present invention is shown and described in detail below:

[0051] S100: Build a campus security monitoring platform, build nodes corresponding to students one by one, integrate the nodes, generate a monitoring chain, and integrate the monitoring chain into the campus security monitoring platform, collect students' location information based on a preset positioning device, and upload the location information to the node.

[0052] Build a campus security monitoring platform and create a node for each student. After the creation is completed, integrate all the nodes to generate a monitoring chain, and deploy the monitoring chain to the campus security monitoring platform; use the preset positioning device to collect the student's location information, where the preset positioning device can be a smart device worn by the student, or a smart student ID card with a positioning function, etc., and upload the location information to the node.

[0053] S200: Building a communication link between the node and a preset contact person, integrating an emergency call mechanism into the communication link, and opening access rights of the node to the preset contact person corresponding to each student based on the communication link.

[0054] Build a communication link between the node and the preset contacts, where the preset contacts are parents and teachers, etc., integrate an emergency call mechanism into the communication link, establish a one-to-one correspondence between the preset contacts and the nodes, and open the corresponding node viewing rights to the preset contacts.

[0055] S300: Collecting behavior monitoring data of the node, wherein the behavior monitoring data includes at least: voice, call and physiological indicators, constructing an AI monitoring strategy consisting of several levels, and configuring the correspondence between the AI ​​monitoring strategy and the monitoring data of each level.

[0056] Collect the behavior monitoring data of the nodes and build an AI monitoring strategy for each behavior monitoring data.

[0057] S400: Using the AI ​​monitoring strategy, traverse the suspicious data in the monitoring chain, and use the pre-collected video monitoring data to verify the suspicious data to determine whether there is any dangerous behavior. If so, activate the emergency call mechanism.

[0058] Activate the AI ​​monitoring strategy to find suspicious data in the monitoring chain and verify the suspicious data using video surveillance data, where the video surveillance data is collected by video surveillance equipment on campus; if after verification, it is determined that dangerous behavior has occurred based on suspicious behavior, the emergency call mechanism is immediately activated.

[0059] In Example 2, Figure 2 The implementation process of the AI-based campus security monitoring method provided by an embodiment of the present invention is shown, and S100 is described in detail below, as follows:

[0060] S101: When a dangerous behavior is detected, an abnormal area is marked on campus, and based on the location information, it is determined whether the student has entered the abnormal area. If so, an alarm message is generated.

[0061] When dangerous behavior is detected, an abnormal area is marked for each student in danger. If a student enters the corresponding abnormal area, an alarm message is generated.

[0062] S102: Pushing the alarm information to the preset contact based on the communication link.

[0063] In Example 3, the implementation process of the AI-based campus safety monitoring method provided by the embodiment of the present invention is as follows:

[0064] The emergency call mechanism is: based on the preset communication device, obtain the distress information sent by the student, integrate the location information into the distress information, and send the distress information to the preset contact via the communication link.

[0065] The communication device can be a smart wearable device or a home-school interconnection device such as the school communication system on campus. When a student sends a distress message to the campus security monitoring platform through the physical buttons on the communication device, the student's location information is obtained and integrated into the distress message, and then the distress message is sent to the preset contact.

[0066] In Example 4, Figure 3 The implementation process of the AI-based campus security monitoring method provided by an embodiment of the present invention is shown, and S300 is described in detail below, as follows:

[0067] S301: Find out the AI ​​monitoring strategy corresponding to the voice and the call, and identify the keywords in the voice and the call.

[0068] According to the AI ​​monitoring strategy, keywords in voice and calls are identified, where the keywords may be "slip" and "physical discomfort".

[0069] S302: Compare with a preset comparison table to determine whether the keyword is in the comparison table. If yes, trigger the communication device to start, collect the real-time recording of the student, and upload the real-time recording to the node.

[0070] A keyword comparison table is constructed to determine whether the keywords in the student's voice and conversation are in the comparison table, where the student's voice and conversation are obtained through the communication device; after the keyword is identified, the recording function integrated in the communication device is started to collect the student's real-time recording, and the real-time recording is uploaded to the node.

[0071] In Example 5, Figure 3 The implementation process of the AI-based campus security monitoring method provided by an embodiment of the present invention is shown, and S300 is further described in detail below, as follows:

[0072] S303: Find out the AI ​​monitoring strategy corresponding to the voice, build an AI deep learning model, input the voice into the AI ​​deep learning model, extract the semantic information in the voice, perform sentiment analysis, and output abnormal information, wherein the abnormal information at least includes: negative emotions, offensive words, insulting words, ridicule topics and fighting, etc.

[0073] Build an AI deep learning model, transfer the collected students' voices into the AI ​​deep learning model, extract the semantic information, perform sentiment analysis on the students' voices, and obtain abnormal information, where the abnormal information is the negative emotions contained in the students' voices, or the offensive and insulting words in the students' voices.

[0074] S304: Determine the student corresponding to the abnormal information as a focus object.

[0075] Identify students whose voice contains abnormal information as subjects of concern, and increase the frequency of monitoring of subjects of concern.

[0076] In Example 6, Figure 3 The implementation process of the AI-based campus security monitoring method provided by an embodiment of the present invention is shown, and S300 is further described in detail below, as follows:

[0077] S305: Based on the AI ​​monitoring strategy, establish a dialogue between the student and the communication device.

[0078] Establish a dialogue between students and communication devices, integrate a chatbot with an AI deep learning model as the core into the communication device, and use the chatbot to reply to the dialogue.

[0079] S306: Input the conversation into an AI deep learning model to obtain suggestions, and integrate the suggestions into the conversation.

[0080] Use chatbots to receive students' messages and provide them with psychological support and advice.

[0081] Figure 4 The structure diagram of the AI-based campus security monitoring system provided in an embodiment of the present invention is shown. The AI-based campus security monitoring system 1 includes:

[0082] The uploading module 11 is used to construct a campus safety monitoring platform, construct nodes corresponding to students one by one, integrate the nodes, generate a monitoring chain, and integrate the monitoring chain into the campus safety monitoring platform, collect the location information of students based on a preset positioning device, and upload the location information to the node;

[0083] An open module 12 is used to establish a communication link between the node and a preset contact person, and integrate an emergency call mechanism into the communication link, and based on the communication link, open the access rights of the node to the preset contact person corresponding to each student;

[0084] A configuration module 13 is used to collect behavior monitoring data of the node, wherein the behavior monitoring data includes at least: voice, call and physiological indicators, construct an AI monitoring strategy consisting of several levels, and configure the corresponding relationship between the AI ​​monitoring strategy and the monitoring data at each level;

[0085] The activation module 14 is used to use the AI ​​monitoring strategy to traverse the suspicious data in the monitoring chain, and use the pre-collected video monitoring data to verify the suspicious data to determine whether there is any dangerous behavior. If so, activate the emergency call mechanism.

[0086] Figure 5 The structure diagram of the AI-based campus security monitoring system provided by an embodiment of the present invention is shown, and the uploading module 11 includes:

[0087] The alarm unit 111 is used to mark an abnormal area on campus when a dangerous behavior is detected, and determine whether the student has entered the abnormal area based on the location information, and if so, generate an alarm message;

[0088] The push unit 112 is used to push the alarm information to the preset contact according to the communication link.

[0089] Figure 6 The structure diagram of the AI-based campus security monitoring system provided by an embodiment of the present invention is shown, and the configuration module 13 includes:

[0090] A search unit 131 is used to search for an AI monitoring strategy corresponding to the voice and call, and identify keywords in the voice and call;

[0091] The comparison unit 132 is used to compare the preset comparison table to determine whether the keyword is in the comparison table. If yes, trigger the communication device to collect the real-time recording of the student and upload the real-time recording to the node.

[0092] The output unit 133 is used to find out the AI ​​monitoring strategy corresponding to the voice, build an AI deep learning model, input the voice into the AI ​​deep learning model, extract the semantic information in the voice, perform sentiment analysis, and output abnormal information, wherein the abnormal information at least includes: negative emotions, offensive words, insulting words, ridicule topics, fighting, etc.;

[0093] A determination unit 134, configured to determine the student corresponding to the abnormal information as an object of concern;

[0094] An establishing unit 135, configured to establish a dialogue between the student and the communication device based on the AI ​​monitoring strategy;

[0095] The integration unit 136 is used to input the dialogue into the AI ​​deep learning model, obtain suggestions, and integrate the suggestions into the dialogue.

[0096] The upload module 11 is mainly used to complete step S100, the open module 12 is mainly used to complete step S200, the configuration module 13 is mainly used to complete step S300, and the activation module 14 is mainly used to complete step S400;

[0097] The alarm unit 111 is mainly used to complete step S101, and the push unit 112 is mainly used to complete step S102;

[0098] The search unit 131 is mainly used to complete step S301, the comparison unit 132 is mainly used to complete step S302, the output unit 133 is mainly used to complete step S303, the determination unit 134 is mainly used to complete step S304, the establishment unit 135 is mainly used to complete step S305, and the integration unit 136 is mainly used to complete step S306.

[0099] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0100] The functions that can be achieved by the AI-based campus security monitoring method are all completed by a computer device, which includes one or more processors and one or more memories, and at least one program code is stored in the one or more memories. The program code is loaded and executed by the one or more processors to achieve the functions of the AI-based campus security monitoring method.

[0101] The processor takes out instructions from the memory one by one, analyzes the instructions, and then completes the corresponding operations according to the instruction requirements, generating a series of control commands, so that the various parts of the computer can automatically, continuously and coordinately move to become an organic whole, realize the input of programs, the input of data, and the calculation and output of results. The arithmetic operations or logical operations generated in this process are all completed by the operator; the memory includes a read-only memory, which is used to store computer programs, and a protection device is provided outside the memory.

[0102] Exemplarily, the computer program may be divided into one or more modules, one or more modules are stored in a memory and executed by a processor to implement the present invention. One or more modules may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in a terminal device.

[0103] Those skilled in the art will understand that the description of the above service equipment is merely an example and does not constitute a limitation on the terminal equipment. It may include more or fewer components than described above, or a combination of certain components, or different components, for example, it may include input and output devices, network access equipment, buses, etc.

[0104] The processor may be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire user terminal.

[0105] The above-mentioned memory can be used to store computer programs and / or modules. The above-mentioned processor realizes various functions of the above-mentioned terminal device by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as an information collection template display function, a product information release function, etc.), etc.; the data storage area can store data created according to the use of the berth status display system (such as product information collection templates corresponding to different product types, product information that different product providers need to release, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card, a secure digital card, a flash memory card, at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0106] If the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the modules / units in the above-mentioned embodiment system, and can also be completed by instructing the relevant hardware through a computer program. The above-mentioned computer program can be stored in a computer-readable storage medium, and the computer program can realize the functions of the above-mentioned various system embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0107] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0108] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A campus security monitoring method based on AI, characterized in that: The method comprises: S100: construct a campus security monitoring platform, construct nodes corresponding to students one by one, integrate the nodes, generate a monitoring chain, and integrate the monitoring chain into the campus security monitoring platform, collect student location information based on a preset positioning device, and upload the location information to the node; S200: Building a communication link between the node and a preset contact, integrating an emergency call mechanism into the communication link, and opening access rights of the node to the preset contact corresponding to each student based on the communication link; S300: collecting behavior monitoring data of the node, wherein the behavior monitoring data at least includes: voice, call and physiological indicators, constructing an AI monitoring strategy consisting of several levels, and configuring a corresponding relationship between the AI ​​monitoring strategy and the monitoring data at each level; S400: Using the AI ​​monitoring strategy, traverse the suspicious data in the monitoring chain, and use the pre-collected video monitoring data to verify the suspicious data to determine whether there is any dangerous behavior. If so, activate the emergency call mechanism.

2. The AI-based campus safety monitoring method according to claim 1 is characterized in that: The S100 includes: When dangerous behavior is detected, an abnormal area is marked on campus, and based on the location information, it is determined whether the student has entered the abnormal area. If so, an alarm message is generated; Based on the communication link, the alarm information is pushed to the preset contact.

3. The AI-based campus safety monitoring method according to claim 1 is characterized in that: The emergency call mechanism is: based on the preset communication device, obtain the distress information sent by the student, integrate the location information into the distress information, and send the distress information to the preset contact via the communication link.

4. The AI-based campus safety monitoring method according to claim 1 is characterized in that: The 300 includes: Find out the AI ​​monitoring strategy corresponding to the voice and the call, and identify the keywords in the voice and the call; Compare with a preset comparison table to determine whether the keyword is in the comparison table; If yes, the communication device is triggered to start, collect the real-time recording of the student, and upload the real-time recording to the node.

5. The AI-based campus security monitoring method according to claim 4 is characterized in that: The 300 further includes: Find out the AI ​​monitoring strategy corresponding to the speech, build an AI deep learning model, input the speech into the AI ​​deep learning model, extract the semantic information in the speech, perform sentiment analysis, and output abnormal information, wherein the abnormal information at least includes: negative emotions, offensive words, insulting words, ridicule topics, and fighting; The student corresponding to the abnormal information is determined as a subject of concern.

6. The AI-based campus safety monitoring method according to claim 5 is characterized in that: The 300 further includes: Establishing a dialogue between the student and the communication device based on the AI ​​monitoring strategy; The conversation is input into an AI deep learning model to obtain suggestions, which are integrated into the conversation.

7. An AI-based campus security monitoring system, characterized in that: The system comprises: An upload module is used to construct a campus safety monitoring platform, construct nodes corresponding to students one by one, integrate the nodes, generate a monitoring chain, and integrate the monitoring chain into the campus safety monitoring platform, collect the location information of students based on a preset positioning device, and upload the location information to the node; An open module, used to establish a communication link between the node and a preset contact person, integrate an emergency call mechanism into the communication link, and open access rights of the node to the preset contact person corresponding to each student based on the communication link; A configuration module is used to collect behavior monitoring data of the node, wherein the behavior monitoring data includes at least: voice, call and physiological indicators, construct an AI monitoring strategy consisting of several levels, and configure the corresponding relationship between the AI ​​monitoring strategy and the monitoring data at each level; The activation module is used to use the AI ​​monitoring strategy to traverse the suspicious data in the monitoring chain, and use the pre-collected video monitoring data to verify the suspicious data to determine whether there is any dangerous behavior. If so, activate the emergency call mechanism.

8. The AI-based campus security monitoring system according to claim 7 is characterized in that: The upload module includes: An alarm unit is used to mark an abnormal area on campus when a dangerous behavior is detected, and to determine whether a student has entered the abnormal area based on the location information, and to generate an alarm message if the student has entered the abnormal area; A push unit is used to push the alarm information to the preset contact according to the communication link.

9. The AI-based campus security monitoring system according to claim 7 is characterized in that: The configuration module includes: A search unit, used to search for an AI monitoring strategy corresponding to the voice and call, and identify keywords in the voice and call; The comparison unit is used to compare with a preset comparison table to determine whether the keyword is in the comparison table. If so, trigger the communication device to collect the real-time recording of the student and upload the real-time recording to the node.

10. The AI-based campus security monitoring system according to claim 9 is characterized in that: The configuration module also includes: An output unit, used to find out the AI ​​monitoring strategy corresponding to the voice, build an AI deep learning model, input the voice into the AI ​​deep learning model, extract the semantic information in the voice, perform sentiment analysis, and output abnormal information, wherein the abnormal information at least includes: negative emotions, offensive words, insulting words, ridicule topics, fighting, etc.; A determination unit, used for determining the student corresponding to the abnormal information as a concerned object; An establishing unit, configured to establish a dialogue between the student and the communication device based on the AI ​​monitoring strategy; An integration unit is used to input the dialogue into an AI deep learning model, obtain suggestions, and integrate the suggestions into the dialogue.

Images