An AI vision-based dense personnel attendance passage

Abstract

The present invention provides a dense personnel attendance passage based on AI vision, which relates to the field of attendance registration. Through the settings of the self-check attendance passage and the attendance system and specific usage methods, it effectively encourages personnel to spontaneously queue up for attendance in an orderly manner, reducing behaviors such as queue-jumping and collisions caused by dense attendance personnel. At the same time, it can improve the enthusiasm of personnel to actively dissuade and resolve conflicts between others, reduce the probability of further intensification of personnel conflicts, and improve the safety and attendance efficiency during the dense personnel attendance process. This is the first self-discipline measure. Through two more self-discipline measures, namely, imposing an attendance penalty of delayed authentication on queue-jumping personnel and implementing a reward system of granting priority attendance times to all personnel, the occurrence of contradictions and conflicts during the attendance process can be further reduced. The people in need of care and those with priority attendance times can be exempted from queuing in the pedestrian passage and directly access the turnstile, improving the safety protection for the people in need of care.

Description

Technical Field

[0001] The present invention relates to the field of attendance registration, and in particular, to a dense personnel attendance channel based on AI vision. Background Art

[0002] Attendance is the record of employees' commuting times to determine whether there are phenomena such as being late, leaving early, or absent from work. Traditional attendance methods generally record attendance by collecting employees' fingerprints. With the rapid development of AI vision technology, attendance methods based on AI vision have been applied in the actual lives of the public.

[0003] For example, the specification of Chinese Patent CN109741476B discloses an attendance system, which includes a server, an image acquisition device, and at least one gate channel; the image acquisition device collects personnel face images in real time and sends the personnel face images to the server; the server receives the personnel face images, verifies the personnel face images according to the pre-stored employee information, if the verification is passed, records the attendance information of the employee corresponding to the personnel face image, and determines the first target gate channel according to the preset channel determination method, and sends the first opening instruction to the first target gate channel; the first target gate channel opens the gate when receiving the first opening instruction, and the image acquisition device can capture face images when personnel enter and exit, so only one image acquisition device can complete the collection of face images, and the cost is greatly reduced. And there is no need to output prompt information, and personnel do not need to wait for the collection of face images, and attendance records can be made without the perception of personnel.

[0004] Another example is that the specification of Chinese Patent CN118212704A discloses a method for on-site personnel attendance based on AI technology. A blockchain service center module, a monitoring service terminal module, and an intelligent detection and judgment module are established in the central system. The blockchain service center module includes a blockchain data system sub-module and a central processing sub-module. The intelligent detection and judgment module includes an Internet connection terminal sub-module and an intelligent maintenance monitoring sub-module. The data captured by face recognition during commuting is docked with the labor real-name system to complete attendance records, and an alarm is issued for personnel who are not in the face database during commuting, and the security guard will go immediately, improving the attendance efficiency of construction site personnel and solving the congestion phenomenon at the construction site entrance.

[0005] Existing methods that simply use AI vision to capture faces for attendance have certain inaccuracies. Especially in a crowded environment, there is a certain situation of missed detection. And the method of using an identity recognition device to authenticate personnel one by one is prone to congestion of people queuing densely. In this case, behaviors such as queue jumping and collisions are extremely likely to occur, thus threatening the safety of attendance personnel. Therefore, there is an urgent need for an attendance channel that can restrain personnel behaviors and improve attendance security. Summary of the Invention

[0006] In view of the above-mentioned prior art, the technical problem to be solved by the present invention is that in a dense personnel attendance environment, conflict behaviors such as personnel cutting in line and colliding with each other are likely to occur, thus threatening the safety of attendance personnel.

[0007] To solve the above problems, the present invention provides a dense personnel attendance passage based on AI vision, which includes an attendance system and a self-check attendance passage. The attendance system includes an attendance subsystem, a self-check subsystem and a priority subsystem. The self-check subsystem includes a air pressure monitoring module, a short shutdown module, a timing module and an alarm module. The priority subsystem includes a priority attendance module, a delayed attendance module and a special database. The special database stores information of people in need of care and information of personnel with priority attendance times and delayed attendance times;

[0008] The self-check attendance passage includes a top plate and a plurality of side plates fixedly connected to the lower end thereof. A pedestrian passage is formed between adjacent side plates. Gate machines are fixedly installed inside the pedestrian passage. A visual recognition device I is fixedly installed at the upper end of the gate machine. Induction capsules are connected to one end of adjacent side plates close to each other. An air chamber is formed between the induction capsule and the side plate. An air pressure sensor located in the air chamber is connected to the end face of the side plate, and the air pressure sensor is electrically connected to the air pressure monitoring module;

[0009] Electric doors are slidably connected to a pair of edge side plates. The electric doors are located between the gate machines and the induction capsules. Visual recognition devices II are fixedly connected to one end of a pair of edge side plates away from each other.

[0010] Further, the attendance subsystem includes an identity recognition module, a passage module and a personnel database. Both the visual recognition device I and the visual recognition device II are electrically connected to the identity recognition module. The gate machine is electrically connected to the passage module. The passage module is connected to the short shutdown module. The personnel database is used to store information of all personnel using the self-check attendance passage.

[0011] A method for using a dense personnel attendance passage based on AI vision includes the following steps:

[0012] S1. Personnel queue up along the pedestrian passage. When reaching the gate machine, they perform identity recognition through the visual recognition device I. People in need of care and personnel with priority attendance times can choose to perform the first identity recognition on the visual recognition device II. After successful recognition, the electric door automatically opens, and the personnel directly reach the gate machine without queuing. Subsequently, they perform secondary identity recognition through the visual recognition device I. After successful recognition by the visual recognition device I, the passage module controls the gate machine to open for the personnel to pass through;

[0013] S2. When a person cuts in line or rushes in the pedestrian passage, due to the size limitation in the pedestrian passage, the cut-in operation will cause collisions and squeezes between the person and the induction bladder, resulting in obvious changes in the monitoring data of the air pressure sensor. At this time, the short shutdown module is activated to control the access module to close the turnstile and suspend the passage of people within the next T seconds.

[0014] S3. When there is no secondary obvious change in the data of the air pressure sensor within T seconds, the normal use of the turnstile is restored. When there is again an obvious data change in the air pressure sensor within T seconds, the turnstile remains closed, and at the same time, the alarm module is activated to notify the management staff to conduct on-site handling.

[0015] Further, a camera is provided inside the pedestrian passage. The camera is fixedly connected to the inner top end of the top plate. The self-checking subsystem further includes an AI monitoring module electrically connected to the camera. The on-site handling in step S3 includes the following operations:

[0016] The management staff confirms the person A who cuts in line based on the image information collected by the camera and the testimony information of the surrounding people, and then enters the information of the person A who cuts in line into the special database, giving him a once delayed attendance penalty. The operation of the delayed attendance penalty is: when the person A who cuts in line passes through the self-checking attendance passage next time, he needs to complete the identity recognition operation on any two different visual recognizers I. And after the identity recognition is first completed on one visual recognizer I, the corresponding turnstile does not open. After the identity recognition is completed on another visual recognizer I for the second time, the corresponding turnstile opens for people to pass.

[0017] Further, the electric door is electrically connected to the priority attendance module, and the delayed attendance module is connected to the identity recognition module.

[0018] A method for using a dense personnel attendance passage based on AI vision further includes the following steps: When the short shutdown module has not been activated for N consecutive days, all personnel in the personnel database are given the right to use priority attendance once.

[0019] Further, the width between a pair of induction bladders in the initial inflated state is 60 - 100 cm.

[0020] Further, the induction bladder includes a return frame. The inner end face of the return frame is fixedly connected to the edge end of the air bladder. One end of the return frame away from the air bladder is fixedly connected with a sealing gasket. The return frame and the side plate are detachably connected through a plurality of bolts.

[0021] Further, an installation groove is formed on the end face of the side plate, and the air pressure sensor is adhesively bonded to the inside of the installation groove.

[0022] In summary, through the settings of the self-check attendance channel, the attendance system, and the specific usage method, this application effectively encourages personnel to queue up for attendance spontaneously and in an orderly manner, effectively reducing conflict behaviors such as queue-jumping and collisions caused by crowded attendance personnel, reducing the occurrence of personnel safety accidents. At the same time, it can also improve the enthusiasm of personnel to spontaneously dissuade and resolve conflicts between others, reduce the probability of further intensification of personnel conflicts, and further improve the safety and attendance efficiency during the attendance of crowded personnel. This is the first self-regulatory measure. By means of the delayed attendance penalty of double-channel authentication for queue-jumping personnel and the reward system of granting priority attendance times to all personnel, the occurrence of personnel conflicts during attendance can be further reduced. These are the second and third self-regulatory measures. The people in need of care and those with priority attendance times can avoid queuing in the pedestrian passage and go directly to the turnstile, improving the safety protection for the people in need of care. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is the three-dimensional view of the device according to the first and second embodiments of this application Figure 1 ;

[0024] Figure 2 is the system diagram according to the first and second embodiments of this application;

[0025] Figure 3 is the three-dimensional view of the device according to the first and second embodiments of this application Figure 2 ;

[0026] Figure 4 is the three-dimensional view of the device according to the first and second embodiments of this application Figure 3 ;

[0027] Figure 5 is the three-dimensional view of the device when the induction capsule is disassembled in the second embodiment of this application;

[0028] Figure 6 is the three-dimensional view of the device according to the first and second embodiments of this application Figure 4 ;

[0029] Figure 7 is the schematic top view of the device according to the first and second embodiments of this application;

[0030] Figure 8 is the three-dimensional view of the induction capsule in the second embodiment of this application.

[0031] Description of the reference numerals in the drawings:

[0032] 1 top plate, 2 side plates, 201 installation groove, 3 camera, 4 turnstile, 5 first visual recognition device, 6 induction capsule, 61 return frame, 62 airbag, 63 sealing gasket, 7 air pressure sensor, 8 electric door, 9 second visual recognition device. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] The following will describe in detail two embodiments of the present invention with reference to the accompanying drawings.

[0034] The first embodiment:

[0035] The present invention provides a dense personnel attendance passage based on AI vision, which is applicable to personnel attendance-intensive places such as company buildings and factories. Please refer to Figure 1 and Figure 2 , including an attendance system and a self-check attendance passage. The attendance system includes an attendance subsystem, a self-check subsystem, and a priority subsystem.

[0036] The attendance subsystem includes an identity recognition module, a passage module, and a personnel database;

[0037] The self-check subsystem includes a pressure monitoring module, a short shutdown module, a timing module, an AI monitoring module, and an alarm module. The short shutdown module is connected to the passage module;

[0038] The priority subsystem includes a priority attendance module, a delayed attendance module, and a special database. The special database stores information about people in need of care and information about personnel with priority attendance times and delayed attendance times.

[0039] The self-check attendance passage includes a top plate 1 and a plurality of side plates 2 fixedly connected to the lower end thereof. A pedestrian passage is formed between adjacent side plates 2. A turnstile 4 is fixedly installed inside the pedestrian passage. A visual recognizer 5 is fixedly installed at the upper end of the turnstile 4. The visual recognizer 5 is electrically connected to the identity recognition module. The turnstile 4 is electrically connected to the passage module. The personnel database is used to store information about all personnel using the self-check attendance passage. During the attendance time period with dense personnel, people should line up orderly in the pedestrian passage and arrive at the turnstile 4 in sequence. Subsequently, identity recognition is performed on the visual recognizer 5. When the facial data collected by the visual recognizer 5 corresponds to the facial information of a certain person in the personnel database, the identity recognition module sends an instruction to allow passage to the passage module, and the passage module controls the turnstile 4 to open for people to pass through and complete the attendance.

[0040] One end of adjacent side plates 2 close to each other is connected with an induction bladder 6. A closed air cavity is formed between the induction bladder 6 and the side plate 2. The end face of the side plate 2 is connected with a pressure sensor 7 located in the air cavity, and the pressure sensor 7 is electrically connected to the pressure monitoring module. In this embodiment, both the induction bladder 6 and the pressure sensor 7 are fixedly connected to the side plate 2. A camera 3 is provided inside the pedestrian passage. The camera 3 is fixedly connected to the inner top end of the top plate 1. The camera 3 is electrically connected to the AI monitoring module. The camera 3 is used to automatically collect and record the facial and morphological information of on-site attendance personnel for later query.

[0041] On both sides of the pair of side plates 2 at the edge, there is a sliding connection with an electric door 8. The electric door 8 is located between the turnstile 4 and the induction bladder 6. At the mutually remote ends of the pair of side plates 2 at the edge, there is a fixed connection with a second visual recognition device 9. The second visual recognition device 9 is also electrically connected to the identity recognition module. The electric door 8 is electrically connected to the priority attendance module. The second visual recognition device 9 can be used by the people to be cared for and those with priority attendance times. The people to be cared for include pregnant women, people with inconvenient mobility, etc. Since the personnel are densely crowded during the attendance period, in order to improve the safety of the attendance of the people to be cared for, a priority attendance channel can be set for them. When the facial information collected by the second visual recognition device 9 corresponds to a certain facial information in the special database, the priority attendance module controls the electric door 8 to open for this person to pass through. This person can directly reach the turnstile 4 and then perform identity recognition on the first visual recognition device 5, so that they do not need to queue in the pedestrian passage.

[0042] In the initial inflated state, the width between the pair of induction bladders 6 is 60 - 100 cm. The channel within this size range not only meets the normal walking needs of an adult, but also is not easily wide enough for two people to pass through (the normal passing width for two people is generally 120 cm or more). When a certain person cuts in and passes through in the pedestrian passage, it is easy to cause some people (the person cutting in or the people queuing) to squeeze and collide with one side of the induction bladder 6, resulting in a change in the air pressure in the air chamber. Therefore, the change in the monitoring data of the air pressure sensor 7 can effectively reflect whether there are behaviors such as attendance personnel cutting in line or having conflicts.

[0043] A dense personnel attendance channel based on AI vision, and its usage method includes the following steps:

[0044] S1. Personnel queue along the pedestrian passage. When they reach the turnstile 4, they perform identity recognition through the first visual recognition device 5. The people to be cared for and those with priority attendance times can choose to perform the first identity recognition on the second visual recognition device 9. After successful recognition, the electric door 8 automatically opens, and the personnel directly reach the turnstile 4 without queuing. Subsequently, they perform secondary identity recognition through the first visual recognition device 5. After successful recognition by the first visual recognition device 5, the access module controls the turnstile 4 to open for the personnel to pass through;

[0045] S2. When personnel perform behaviors such as cutting in line or colliding in the pedestrian passage, due to the size limitation in the pedestrian passage, the cutting-in operation will cause collisions and squeezes between the personnel and the induction bladder 6, resulting in a significant change in the monitoring data of the air pressure sensor 7. At this time, the short shutdown module is activated to control the access module to close the turnstile 4 and suspend the passage of personnel within the next T seconds;

[0046] S3. When there is no obvious secondary change in the data of the air pressure sensor 7 within T seconds, the normal use of the turnstile 4 is restored. When there is an obvious change in the data of the air pressure sensor 7 again within T seconds, the turnstile 4 remains closed, and at the same time, the alarm module is activated to notify the management personnel to conduct on-site handling.

[0047] Through steps S2 and S3, conflict behaviors such as queue jumping and ramming by personnel can be effectively reduced. At the same time, the enthusiasm of personnel to spontaneously dissuade and resolve conflicts among others can also be improved, as follows: First, when a certain person engages in behaviors such as queue jumping and ramming, causing the short-term shutdown of the turnstile 4, all personnel in the passage cannot continue to pass through this turnstile 4, and the attendance progress is delayed. Therefore, from the perspective of their own interests, through this operation method, it is not easy for personnel to actively engage in behaviors such as queue jumping and conflicts with others. Second, when there is a situation where queue jumping conflicts at the scene cause the short-term shutdown of the turnstile 4, in order to restore the use of the turnstile 4 as soon as possible, the conflicting personnel will tend to actively reconcile with others, reduce the intensification of contradictions, and reduce the probability of hitting the induction capsule 6 again. At the same time, other queuing personnel will also tend to abandon the attitude of having nothing to do with it, actively dissuade both parties of the incident, resolve the conflicts between the two parties, and enable the turnstile 4 to resume use on time, facilitating the smooth completion of their own attendance process.

[0048] Therefore, through the self-check of the attendance passage, the setting of the attendance system, and the specific usage method of this application, to a certain extent, it can prompt personnel to spontaneously queue up for attendance in an orderly manner, effectively reduce behaviors such as queue jumping and ramming caused by dense attendance personnel, reduce the occurrence of personnel safety accidents, and at the same time, it can also improve the enthusiasm of personnel to spontaneously dissuade and resolve queue jumping, conflicts and other behaviors, reduce the probability of further intensification of personnel conflicts, and further improve the safety and attendance efficiency during the attendance process of dense personnel. This is the first self-restraint measure.

[0049] The on-site handling in step S3 includes the following operations: The management personnel confirm the queue jumper A according to the image information collected by the camera 3 and the testimony information of the surrounding personnel, and then enter the information of the queue jumper A into the special database, giving him a delay in attendance penalty.

[0050] The operation of the delay in attendance penalty is as follows: When the queue jumper A passes through the self-check attendance passage next time, he needs to complete the identity recognition operation on any two different visual recognition devices 5. The delay in attendance module is connected to the identity recognition module, and it sends the personnel information with the number of times of delay in attendance in the special database to the identity recognition module. Thus, after the personnel completes the identity recognition on a visual recognition device 5 for the first time, the identity recognition module does not send an instruction to allow passage to the passage module, that is, the corresponding turnstile 4 does not open. After the second identity recognition is completed on another visual recognition device 5, the corresponding turnstile 4 opens for the personnel to pass through.

[0051] By delaying the operation of attendance punishment, when personnel go through the next attendance process, they need to queue up and identify their identities in two pedestrian channels in sequence, which will greatly increase the time required for their next attendance. Therefore, considering their own interests and effectively avoiding being punished by delayed attendance, personnel are not likely to take the initiative to cut in line, rush, etc. Thus, the safety and attendance efficiency during the attendance process of dense personnel are further improved. This is the second self-restraint measure.

[0052] In addition, when the short shutdown module has not been started for N consecutive days (that is, no personnel collision events have occurred for N consecutive days), all personnel in the personnel database are given the right to use priority attendance once. Personnel with priority attendance times can choose to directly identify their identities through the vision recognizer II 9 at any time, and after passing through the electric door 8, they can directly reach the corresponding turnstile 4, that is, they obtain the right to avoid queuing in the pedestrian channel once. Personnel can choose to use it when their own attendance time is insufficient. Through this reward operation, the occurrence of behaviors such as cutting in line and rushing during the attendance process can be further reduced. This is the third self-restraint measure.

[0053] The second implementation method:

[0054] Based on the first implementation method, the following specific settings are made for the induction bladder 6 and the air pressure sensor 7 in this implementation method: Please refer to Figure 8 , the induction bladder 6 includes a loop frame 61. The inner end face of the loop frame 61 is fixedly connected to the edge end of the air bladder 62. One end of the loop frame 61 away from the air bladder 62 is fixedly connected to a sealing gasket 63. As shown in combination with Figure 5 , the loop frame 61 and the side plate 2 are detachably connected by a plurality of bolts. An air cavity is formed between the air bladder 62 and the side plate 2. The sealing gasket 63 is made of elastic rubber material and is in contact with the end face of the side plate 2, which can improve the sealing performance between the loop frame 61 and the side plate 2, making the gas in the air cavity not easily escape to the outside and maintaining the air pressure stability in the air cavity. A charging pipe (not shown in the figure) extending into the air cavity is fixedly connected to the loop frame 61, which is convenient for filling an appropriate amount of gas into the air cavity after installation, so that the air bladder 62 is in a moderately inflated state (the inflation saturation is 60%-80%), and is not easily broken due to personnel squeezing. An installation groove 201 is opened on the end face of the side plate 2, and the air pressure sensor 7 is adhesively bonded to the inside of the installation groove 201.

[0055] The air pressure sensor 7 adopts a hidden installation method placed inside the installation groove 201, which can effectively reduce the physical damage such as extrusion and collision of the air pressure sensor 7 by the attendance personnel. Through the setting of the above structure, both the sensing bladder 6 and the air pressure sensor 7 are detachably connected to the side plate 2, replacing the fixed connection method in Embodiment 1. When the air bladder 62 is damaged such as leaking or broken, or the air pressure sensor 7 is insensitive to monitoring, the disassembly and replacement of both can be realized. In addition, when this application is used in a non-dense area and there is no need to consider safety accidents such as queuing and jumping in line, the use mode of not installing the sensing bladder 6 and the air pressure sensor 7 can be selected, and this application can be used as an ordinary attendance device, reducing the consumption of equipment and power costs such as the sensing bladder 6 and the air pressure sensor 7.

[0056] Combined with the current actual needs, the above-mentioned implementation method adopted by this application, the protection scope is not limited to this. Within the knowledge scope of those skilled in the art, various changes made without departing from the concept of this application still fall within the protection scope of the present invention.

Claims

1. An attendance passage for dense personnel based on AI vision, characterized in that: It includes an attendance system and a self-check attendance passage. The attendance system includes an attendance subsystem, a self-check subsystem, and a priority subsystem. The self-check subsystem includes a air pressure monitoring module, a short shutdown module, a timing module, and an alarm module. The priority subsystem includes a priority attendance module, a delayed attendance module, and a special database. The special database stores information about people in need of care and information about personnel with priority attendance times and delayed attendance times; The self-check attendance passage includes a top plate (1) and a plurality of side plates (2) fixedly connected to the lower end thereof. A pedestrian passage is formed between adjacent side plates (2). A turnstile (4) is fixedly installed inside the pedestrian passage. A first visual recognition device (5) is fixedly installed at the upper end of the turnstile (4). Induction capsules (6) are connected to one end of adjacent side plates (2) close to each other. An air cavity is formed between the induction capsule (6) and the side plate (2). A air pressure sensor (7) located inside the air cavity is connected to the end face of the side plate (2), and the air pressure sensor (7) is electrically connected to the air pressure monitoring module; Electric doors (8) are slidably connected to a pair of edge side plates (2). The electric doors (8) are located between the turnstile (4) and the induction capsule (6). Second visual recognition devices (9) are fixedly connected to one end of a pair of edge side plates (2) away from each other; The usage method of the above-mentioned dense personnel attendance passage based on AI vision includes the following steps: S1. Personnel queue along the pedestrian passage. When reaching the turnstile (4), they are identified by the first visual recognition device (5). People in need of care and those with priority attendance times are identified for the first time by the second visual recognition device (9). After successful identification, the electric door (8) automatically opens, and the personnel directly reach the turnstile (4) without queuing. Subsequently, they are identified for the second time by the first visual recognition device (5). After successful identification by the first visual recognition device (5), the access module controls the turnstile (4) to open for the personnel to pass through; S2. When personnel cut in line or collide in the pedestrian passage, due to the size limitation in the pedestrian passage, the cut-in operation will cause collision and extrusion between the personnel and the induction capsule (6), resulting in a significant change in the monitoring data of the air pressure sensor (7). At this time, the short shutdown module is activated to control the access module to close the turnstile (4) and suspend personnel from passing through for the next T seconds; S3. When there is no second significant change in the data of the air pressure sensor (7) within T seconds, the normal use of the turnstile (4) is restored. When there is a significant data change in the air pressure sensor (7) again within T seconds, the turnstile (4) remains closed, and at the same time, the alarm module is activated to notify the management personnel to handle the scene.

2. The dense personnel attendance passage based on AI vision according to claim 1, wherein: The attendance subsystem includes an identity recognition module, an access module, and a personnel database. The first visual recognition device (5) and the second visual recognition device (9) are both electrically connected to the identity recognition module. The turnstile (4) is electrically connected to the access module. The access module is connected to the short shutdown module. The personnel database is used to store information about all personnel using the self-check attendance passage.

3. The dense personnel attendance passage based on AI vision according to claim 2, characterized in that: A camera (3) is provided inside the pedestrian passage, and the camera (3) is fixedly connected to the inner top end of the top plate (1). The self-checking subsystem further includes an AI monitoring module electrically connected to the camera (3). The on-site processing in step S3 includes the following operations: According to the image information collected by the camera (3) and the testimony information of the surrounding personnel, the management personnel confirm the queue-jumping person A, and then enter the information of the queue-jumping person A into the special database, and give him a delay in attendance punishment. The operation of the delay in attendance punishment is as follows: when the queue-jumping person A passes through the self-checking attendance passage next time, he needs to complete the identity recognition operation on any two different visual recognition devices one (5). And after the identity recognition is completed on a visual recognition device one (5) for the first time, the corresponding gate (4) is not opened. After the identity recognition is completed on another visual recognition device one (5) for the second time, the corresponding gate (4) is opened for personnel to pass through.

4. The intensive personnel attendance passage based on AI vision according to claim 2, characterized in that: The electric door (8) is electrically connected to the priority attendance module, and the delay attendance module is connected to the identity recognition module.

5. The intensive personnel attendance passage based on AI vision according to claim 2, wherein: Its usage method further includes the following steps: when the short shutdown module has not been started for N consecutive days, grant all personnel in the personnel database the right to use priority attendance once.

6. The dense personnel attendance passage based on AI vision according to claim 1, wherein: The width between a pair of the induction sacs (6) in the initial inflation state is 60-100 cm.

7. An intensive personnel attendance passage based on AI vision according to claim 1, characterized in that: The induction sac (6) includes a return frame (61). The inner end face of the return frame (61) is fixedly connected to the edge end of an airbag (62). One end of the return frame (61) away from the airbag (62) is fixedly connected to a sealing gasket (63). The return frame (61) and the side plate (2) are connected by a plurality of bolts.

8. A dense personnel attendance passage based on AI vision according to claim 1, characterized in that: An installation groove (201) is formed in the end face of the side plate (2), and the air pressure sensor (7) is adhered to the inside of the installation groove (201) by an adhesive.

Images