Cigarette factory operation site behavior monitoring system and method, medium and program product

Abstract

The invention discloses a behavior monitoring system and method for a cigarette factory operation site, a medium and a program product, and the system comprises an image collection device which is used for collecting image data and transmitting the image data to a data processing device; the wind speed sensor is used for collecting and sending gas flow rate data to the data processing device; the data processing device is used for sending a prompt or warning instruction to the alarm device when the operator does not move within the first or second preset time; when the definition of the image is lower than a preset threshold value or the gas flow rate is higher than a preset threshold value, a prompt instruction is sent to an alarm device; and the alarm device responds to the prompting or warning instruction and sends out prompting or warning information. By monitoring the behavior mode of the operating personnel in real time and sending out a prompt or an alarm when the abnormal or dangerous behavior is detected, related personnel are reminded to take corresponding measures in time, so that the delay of the construction period due to abnormal operation is avoided, the risk that the personnel suffer from safety accidents is reduced, and the management level, efficiency and safety of operation are improved.

Description

Technical Field

[0001] The present invention relates to the field of digital management technology, and in particular to a behavior monitoring system, method, medium and program product for a cigarette factory operation site. Background Art

[0002] In the production environment of modern cigarette factories, the production links of cigarette factories are complex, involving multiple positions and processes. There are many safety risks in these production areas. Although dangerous behaviors occur in a short time, they may cause greater harm. Therefore, it is crucial to monitor the behavioral patterns at the work site in real time, detect abnormalities in time and issue alarms.

[0003] At present, the factory monitoring technology of cigarette factories mainly relies on traditional human monitoring and some intelligent equipment. For example, many cigarette factories have deployed high-definition cameras in the factory to monitor the production site in real time, but they lack intelligent analysis capabilities and still require operators to view and analyze, and rely on a large number of manpower for on-site inspections and data recording, which increases the labor cost of monitoring, fails to detect abnormal and dangerous behaviors at the work site in time, increases the risk of delays due to abnormal operations and safety accidents for operators, and reduces the management level, efficiency and safety of operations. Summary of the invention

[0004] The present invention provides a behavior monitoring system, method, medium and program product for a cigarette factory operation site, so as to solve the problems of high labor cost and low efficiency when monitoring the behavior patterns of the cigarette factory operation site, and the resulting problems of failure to timely discover and handle abnormal operation behaviors, low operation management level and low operation safety.

[0005] According to one aspect of an embodiment of the present invention, a behavior monitoring system for a cigarette factory operation site is provided, comprising: an image acquisition device, a wind speed sensor, an alarm device, and a data processing device; the image acquisition device is arranged on an operating table of a production line, the wind speed sensor is arranged on a roof of an operating area of ​​the production line, the alarm device is arranged on an operating table of an operating area of ​​the production line, the image acquisition device is electrically connected to the data processing device, the wind speed sensor is electrically connected to the data processing device, and the alarm device is electrically connected to the data processing device;

[0006] The image acquisition device is used to acquire real-time image data in the operation area of ​​the production line during the operation, and send the real-time image data to the data processing device;

[0007] The wind speed sensor is used to collect real-time gas flow rate data in the operation area of ​​the production line during operation, and send the real-time gas flow rate data to the data processing device;

[0008] The data processing device is used to receive real-time image data from an image acquisition device, and send a prompt instruction to an alarm device when the clarity of the real-time image data is lower than a preset clarity threshold; send a prompt instruction to the alarm device when it is identified in the real-time image data that the operator has not moved within a first preset time range; after sending the prompt instruction to the alarm device, when it is identified in the real-time image data that the operator has not moved within a second preset time range, send a warning instruction to the alarm device; and receive real-time gas flow rate data from a wind speed sensor, and send a prompt instruction to the alarm device when the real-time gas flow rate data is higher than a preset flow rate threshold;

[0009] The alarm device issues a prompt message in response to a received prompt instruction, or issues a warning message in response to a received warning instruction.

[0010] According to another aspect of an embodiment of the present invention, a behavior monitoring method at a cigarette factory operation site is provided, which is executed by a data processing device in a behavior monitoring system configured at the cigarette factory operation site, and includes:

[0011] receiving real-time image data from an image acquisition device, and sending a prompt instruction to an alarm device when the clarity of the real-time image data is lower than a preset clarity threshold;

[0012] When it is identified in the real-time image data that the operator has not moved within a first preset time range, sending a prompt instruction to the alarm device;

[0013] After sending the prompt instruction to the alarm device, when it is identified in the real-time image data that the operator has not moved within the second preset time range, sending a warning instruction to the alarm device;

[0014] as well as,

[0015] Receive real-time gas flow rate data from the wind speed sensor, and send a prompt instruction to the alarm device when the real-time gas flow rate data is higher than a preset flow rate threshold.

[0016] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the behavior monitoring method for a cigarette factory operation site described in any embodiment of the present invention when executed.

[0017] According to another aspect of an embodiment of the present invention, a computer program product is provided, comprising computer instructions, wherein when the computer instructions are executed by a processor, the steps of the method described in any embodiment of the present invention are implemented.

[0018] The behavior monitoring system of the cigarette factory operation site of the embodiment of the present invention includes: an image acquisition device for acquiring and sending real-time image data to a data processing device; a wind speed sensor for acquiring and sending real-time gas flow rate data to a data processing device; a data processing device for sending a prompt or warning instruction to an alarm device when the operator does not move within the first or second preset time; when the clarity of the real-time image is lower than the preset threshold or the real-time gas flow rate is higher than the preset threshold, a prompt instruction is sent to the alarm device; the alarm device responds to the prompt or warning instruction and issues a prompt or warning message. The behavior pattern of the operator and the state of the wind speed in the production environment are monitored in real time by the data processing device, and prompts or warnings are automatically issued when abnormal or dangerous behaviors are detected, reminding relevant personnel to take corresponding measures in time, avoiding delays in the construction period due to abnormal operations, reducing the risk of personnel suffering from safety accidents, reducing the human cost of behavior monitoring at the operation site, and improving the management level, efficiency and safety of the operation.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 is a schematic diagram of the structure of a behavior monitoring system for a cigarette factory operation site provided according to the first embodiment of the present invention;

[0022] Figure 2 is a flow chart of a behavior monitoring method for a cigarette factory operation site provided according to Embodiment 2 of the present invention;

[0023] Figure 3 It is a schematic diagram of a behavior monitoring system for a cigarette factory operation site to which an embodiment of the present invention is applicable. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] Embodiment 1

[0027] Figure 1 This is a schematic diagram of the structure of a behavior monitoring system for a cigarette factory operation site provided by Embodiment 1 of the present invention. This embodiment is applicable to monitoring the behavior patterns of a cigarette factory operation site.

[0028] At the operation site of a cigarette factory, the equipment, assembly lines and the behaviors of the staff are interrelated and together constitute a complex production system. The operation site of a cigarette factory usually includes multiple functional areas, such as the silk-making workshop, the rolling and packaging workshop, the high-bay warehouse and the energy and power workshop. Each area is equipped with specific equipment to complete different links of cigarette production. For example, the shredder, dryer and feeder in the silk-making workshop are used to process tobacco leaves into filamentary materials suitable for cigarette production; the cigarette-making machine, packaging machine and cartoning machine in the rolling and packaging workshop are used to package the tobacco into cigarette products. The high-bay warehouse realizes efficient storage and retrieval of materials through automated shelf systems and stackers, while the energy and power workshop provides power support such as electricity, steam and compressed air for the entire cigarette factory.

[0029] Among them, the operation of equipment in the tobacco workshop is more sensitive to the ambient wind speed. For example, the tobacco cutter, tobacco drying machine and feeder require a stable wind speed during operation to ensure the quality and efficiency of tobacco leaf processing. If the wind speed is too high or too low, it may affect the drying effect and conveying efficiency of tobacco leaves, thereby affecting product quality. The cigarette making and packaging machines in the rolling and packaging workshop also have certain requirements for wind speed. Stable wind speed helps to maintain air flow in the workshop and avoid smoke accumulation, thereby ensuring the normal operation of the equipment. Changes in wind speed may affect the packaging quality of cigarettes, such as the forming and sealing effects of cigarette boxes. In addition, at various operation sites in the cigarette factory, strict operating procedures are the key to ensuring production efficiency and operation safety. The behavior of staff not only directly affects production efficiency, but also affects the safety of the entire operation process. Therefore, the behavior of the cigarette factory operation site is monitored in real time to ensure that the operation of the operator meets the established safety and efficiency standards, thereby ensuring the smooth progress of the production process and the safety of personnel.

[0030] Correspondingly, such as Figure 1 As shown, the system includes:

[0031] An image acquisition device 110, a wind speed sensor 120, an alarm device 130 and a data processing device 140; the image acquisition device 110 is arranged on an operating table of a production line, the wind speed sensor 120 is arranged on a roof of an operating area of ​​the production line, the alarm device 130 is arranged on an operating table of an operating area of ​​the production line, the image acquisition device 110 is electrically connected to the data processing device 140, the wind speed sensor 120 is electrically connected to the data processing device 140, and the alarm device 130 is electrically connected to the data processing device 140;

[0032] The image acquisition device 110 is used to acquire real-time image data in the operation area of ​​the production line during the operation, and send the real-time image data to the data processing device 140;

[0033] The wind speed sensor 120 is used to collect real-time gas flow rate data in the operation area of ​​the production line during operation, and send the real-time gas flow rate data to the data processing device 140;

[0034] The data processing device 140 is used to receive the real-time image data from the image acquisition device 110, and send a prompt instruction to the alarm device 130 when the clarity of the real-time image data is lower than a preset clarity threshold; send a prompt instruction to the alarm device 130 when it is identified in the real-time image data that the operator has not moved within a first preset time range; after sending the prompt instruction to the alarm device 130, when it is identified in the real-time image data that the operator has not moved within a second preset time range, send a warning instruction to the alarm device 130; and receive the real-time gas flow rate data from the wind speed sensor 120, and send a prompt instruction to the alarm device 130 when the real-time gas flow rate data is higher than a preset flow rate threshold;

[0035] The alarm device 130 issues a prompt message in response to a received prompt instruction, or issues a warning message in response to a received warning instruction.

[0036] In the embodiment of the present invention, the image acquisition device can be specifically understood as: a device for monitoring the operating behavior of operators, the operating status of equipment and the working environment, which can be set at the operating table of the production line, especially at the key positions of production operations, such as the entrance and exit of the production line (used to monitor the behavior of operators, ensure the monitoring of the entry and exit of materials and the final quality of products), the cigarette machine and packaging machine operation area (used to monitor the operating status of equipment and the behavior of operators in real time) and high-risk areas (such as areas with mechanical injury risks, used to monitor whether operators have safety risks and accidents), etc. In addition, multiple image acquisition devices can be set at key positions to form cross coverage to ensure that there are no blind spots for monitoring and improve the comprehensiveness of monitoring. Image acquisition at different angles can reduce the image blur caused by occlusion or viewing angle limitation of a single camera, enhance the accuracy of image recognition and analysis, and quickly discover potential safety problems. Depending on the usage scenario, the image acquisition device can use an infrared camera (capable of working in low light or night environment, suitable for scenes requiring 24-hour monitoring), a high-definition camera (used to capture clear images, suitable for scenes requiring high-resolution monitoring) or a zoom lens camera (the focal length can be adjusted as needed, suitable for application scenarios with complex working environments and the need to monitor individuals at different distances) and other devices.

[0037] The wind speed sensor can be specifically understood as: a device for monitoring the ambient wind speed, especially when the ventilation system is running or under the influence of external wind, to ensure the safety of the working environment. It can be set on the roof of the production line operation area, especially at the key positions of production operations, such as the entrance and exit of the production line (used to monitor the ambient wind speed during material transportation and product output to ensure that the logistics process is not affected by wind speed) and the cigarette machine and packaging machine operation area (used to monitor the local wind speed during equipment operation to avoid the impact of wind speed changes on rolling and packaging quality). In addition, if the production line is long or the environment is complex, wind speed sensors can be set on the roof of each operation area to achieve accurate monitoring of wind speed in different areas and avoid safety problems caused by local wind speed changes. Multiple sensors can also be set at the same key position to form cross coverage, which can reduce monitoring blind spots and improve the comprehensiveness and accuracy of monitoring. If the production line is short and the environment is relatively simple, multiple operation areas can share a wind speed sensor to reduce costs while meeting basic wind speed monitoring needs.

[0038] The alarm device can be specifically understood as: a device used to alert operators or managers to potential safety issues, which can be set on the operating table in the production line operation area, especially at key locations of production operations, such as the entrance and exit of the production line and the cigarette machine and packaging machine operation area. In addition, in order to achieve accurate positioning and provide timely assistance after receiving a prompt or warning message, an alarm device can be set at each operating table position or on its roof to achieve accurate positioning of the area where abnormal behavior occurs. If the production line is short and the environment is relatively simple, a shared alarm device can be used to reduce costs while meeting basic alarm needs. The alarm device can use an alarm light, a speaker or a video monitoring device (such as a display screen). The display screen can be set in the common space of multiple operation areas to centrally display the monitoring screens of multiple operation areas. When the alarm is triggered, it automatically switches to the camera screen of the alarm area and displays the alarm location information on the display screen, such as the workstation number or the operation area number, which can not only improve the monitoring efficiency, but also ensure that the alarm location information is quickly and accurately located and displayed when the alarm is triggered, helping rescue personnel to quickly understand the situation on the scene.

[0039] The data processing device can be specifically understood as a device for data analysis and instruction generation, which can receive data from the image acquisition device and the wind speed sensor, process and analyze the data, and send prompt instructions or warning instructions to the alarm device according to the analysis results. The data processing device can be specifically in the form of an integration of a PLC (Programmable Logic Controller) and an MES system (Manufacturing Execution System). The MES system obtains the operating data on the production line collected by each sensor and image acquisition device through the PLC, processes and analyzes the data, generates control instructions based on the analysis results, and sends them to the production equipment through the PLC to achieve automated control.

[0040] The first preset time can be specifically understood as: a preset time range used to determine whether the operator has not moved in a short period of time. If the operator has not moved in the first preset time, it means that his / her operation behavior may be abnormal, and the data processing device needs to send a prompt instruction to the alarm device. The second preset time can be specifically understood as: a longer preset time range used to further determine whether the operator has not moved for a long time. If the operator still has not moved in the second preset time, it means that his / her operation behavior may be dangerous, and the data processing device needs to send a warning instruction to the alarm device.

[0041] The preset clarity threshold can be specifically understood as: within a specific time range (such as 1 minute), if the clarity of the image data is lower than a set value (such as 10 pixels) for a cumulative time that reaches or exceeds a preset threshold (such as 10 seconds).

[0042] Specifically, during the operation, the image acquisition device 110 acquires real-time image data in the operation area and sends the data to the data processing device 140. During the operation, the wind speed sensor 120 acquires real-time gas flow rate data in the operation area and sends the data to the data processing device 140. The data processing device 140 receives real-time image data from the image acquisition device 110 (the real-time image data can be a real-time video stream or a single-frame image). If the real-time image data is a real-time video stream, the video stream is read frame by frame to obtain each frame of the image. If the original image is in color, it can be converted into a grayscale image. Grayscale images can reduce the amount of data while retaining the main structural information of the image, which is convenient for subsequent processing. The image is denoised (such as Gaussian filtering or median filtering, etc.), and the Brenner gradient is calculated, that is, for each row of pixels in the image, the horizontal gradient difference of adjacent pixels is calculated and the square sum of these gradient differences is calculated as the clarity index of the image. If the clarity of the image data is lower than the preset clarity threshold (for example, the clarity of the image data for 10 seconds or more within 1 minute is lower than the set value), it means that the operator may have abnormal behavior such as working too fast, which may easily cause damage to the workpiece and reduce construction quality. It is necessary to send a prompt instruction to the alarm device 130 for warning.

[0043] The average speed of the moving pixels or the number of moving pixels between consecutive frames is calculated by an image processing algorithm (such as an optical flow method) to detect whether there is effective movement. If it is identified that the operator has not moved within the first preset time (such as 30 seconds) (the number of moving pixels calculated is less than the preset corresponding threshold), the operator may take a temporary rest due to fatigue or be injured by objects in the working area, causing the construction personnel to pause. In order to ensure the safety of the operators during operation, the data processing device 140 sends a prompt instruction to the alarm device 130, thereby prompting the construction personnel. In order to avoid false alarms, the personnel taking a temporary rest only need to move slightly again or continue construction to stop triggering subsequent warning instructions. After sending the prompt instruction, if it is identified that the operator still has not moved within the second preset time (such as 60 seconds), it means that the operator may be in a dangerous situation, and the data processing device 140 sends a warning instruction to the alarm device 130.

[0044] The data processing device 140 receives real-time gas flow rate data from the wind speed sensor 120 , and sends a prompt instruction to the alarm device 130 if the gas flow rate data is higher than a preset flow rate threshold.

[0045] When the alarm device 130 receives a prompt instruction, it issues a prompt message (such as obtaining the location information and workstation number of the abnormal behavior operation area from the instruction and displaying it on the display screen); when it receives a warning instruction, it issues a warning message (such as obtaining the location information of the dangerous behavior operation area from the instruction and displaying it in real time, and automatically switching to the camera screen of the alarm area).

[0046] Generally speaking, in the behavior monitoring system at the operation site of the cigarette factory, the data processing device simultaneously receives real-time data from the wind speed sensor and the video monitoring system, and triggers the alarm instruction according to these data. If the alarm device 130 receives multiple prompt instructions at the same time, it can choose to trigger a comprehensive prompt instruction (such as obtaining the location information of all abnormal behavior operation areas from each instruction and displaying it on the display screen); if the prompt instruction and the warning instruction occur at the same time, the warning instruction is triggered first and the prompt instruction is suppressed; if multiple warning instructions occur at the same time, the warning instructions can be triggered one by one in the order of receiving the instructions (such as obtaining the location information of all dangerous behavior operation areas from each instruction for real-time display, and automatically switching to the camera screen of each alarm area, and displaying the screens of multiple alarm areas in blocks on the same screen) until all warning instructions are processed.

[0047] The behavior monitoring system for the cigarette factory operation site of the embodiment of the present invention includes: an image acquisition device for acquiring and sending real-time image data to a data processing device; a wind speed sensor for acquiring and sending real-time gas flow rate data to a data processing device; a data processing device for sending a prompt or warning instruction to an alarm device when the operator does not move within the first or second preset time; when the clarity of the real-time image is lower than the preset threshold or the real-time gas flow rate is higher than the preset threshold, a prompt instruction is sent to the alarm device; the alarm device, in response to the prompt or warning instruction, issues a prompt or warning message. By real-time monitoring of the behavior patterns of the operators and automatically issuing prompts or warnings when abnormal or dangerous behaviors are detected, the relevant personnel are reminded to take corresponding measures in a timely manner, thus avoiding delays in the construction period due to abnormal operations, reducing the risk of personnel suffering from safety accidents, reducing the labor cost of behavior monitoring at the operation site, and improving the management level, efficiency and safety of the operation.

[0048] Based on the above embodiments, the data processing device is specifically used for:

[0049] Receiving image data from an image acquisition device, identifying the outline of the operator, and analyzing the outline offset of the starting frame and each frame of the first preset time range, and sending a prompt instruction to the alarm device when the offset is less than a preset displacement threshold;

[0050] After sending the prompt instruction to the alarm device, the contour offset of the start frame and each frame in the second preset time range is analyzed, and when the offset is less than the preset displacement threshold, a warning instruction is sent to the alarm device.

[0051] Specifically, the outline of the operator is identified through an image processing algorithm (such as background subtraction method), the outline position of the operator is marked, and its coordinate information is recorded. Within the first preset time range (such as 30 seconds), the outline offset (i.e., the moving distance) of the starting frame and each frame is calculated. If the calculated offsets are all less than the preset threshold (such as 10 pixels), it means that the operator has almost no movement in this time period due to a temporary rest or a safety accident. The data processing device will send a prompt instruction to the alarm device. In order to avoid false alarms, the personnel who take a temporary rest only need to move slightly again or continue the construction to stop triggering subsequent warning instructions. After sending the prompt instruction, the data processing device continues to analyze the outline offsets of the starting frame and each frame within the second preset time range. If these offsets are still less than the preset displacement threshold, it means that the operator has not moved for a longer time. The data processing device will send a warning instruction to the alarm device to remind the relevant personnel to take further measures. By real-time monitoring of workers' long periods of inactivity, it is possible to effectively identify whether the workers may be in a safety accident, thereby improving the safety and management efficiency of the production site. Through the dual-stage early warning trigger mechanism of prompts and warnings, it is also possible to avoid interference with normal operations due to false alarms while ensuring safety, thereby improving production efficiency.

[0052] Furthermore, based on the above embodiments, the data processing device may also be used for:

[0053] When it is detected that the clarity of the real-time image data received from the image acquisition device is lower than a preset clarity threshold, a mode adjustment instruction is sent to the image acquisition device.

[0054] In the embodiment of the present invention, the mode adjustment instruction can be specifically understood as a control instruction for adjusting the working mode of the image acquisition device based on the quality (such as clarity) of the image data currently acquired by the image acquisition device. The instruction optimizes the image acquisition effect by dynamically adjusting the working parameters of the device.

[0055] Specifically, when the data processing device detects that the clarity of the real-time image data collected by the image acquisition device is lower than a preset threshold, the system will send a mode adjustment instruction to the image acquisition device. These instructions can adjust the working mode of the image acquisition device according to different environmental conditions and real-time image quality issues. For example, when the light intensity sensor finds that the image acquisition device is at night or in a poorly lit work site (the current light intensity is lower than the preset light intensity threshold), the data processing device can send a mode adjustment instruction to the image acquisition device to switch the image acquisition device to a low light mode (such as turning on a fill light or adjusting the exposure time) and adjust the focal length to improve the image quality; identify the outline of the operator through an image processing algorithm (such as background subtraction method), calculate the area of ​​the outline, and compare it with the preset threshold. If the outline area is less than the preset corresponding threshold, it means that the monitoring target is far away and the resolution needs to be increased to ensure that the target is clearly visible. The data processing device needs to send a mode adjustment instruction to the image acquisition device to increase the resolution to optimize the image quality.

[0056] Through mode adjustment instructions, the image acquisition device can dynamically adjust the working mode according to real-time environmental conditions, ensuring that the acquired images meet quality requirements, improving the adaptability and reliability of image acquisition, and reducing image quality problems caused by environmental changes, thereby improving the monitoring performance of the system, avoiding delays in construction due to abnormal operations, reducing the risk of personnel suffering safety accidents, reducing the manpower cost of on-site behavior monitoring, and improving the management level, efficiency and safety of operations.

[0057] Further, based on the above embodiments, the behavior monitoring system at the cigarette factory operation site may further include: a stop button;

[0058] Wherein, the stop button is arranged on the housing of the alarm device, and the stop button is electrically connected to the data processing device;

[0059] The stop button is used to send stop alarm indication information to the data processing device in response to a button pressing operation;

[0060] The data processing device is further configured to send an alarm stop instruction to the alarm device upon receiving the alarm stop instruction information;

[0061] The alarm device is also used to stop sending prompt information or warning information when receiving an alarm stop instruction.

[0062] Specifically, a stop button (which can be a mechanical button or a touch button) is installed on the housing of the alarm device and is electrically connected to the data processing device. When the operator or manager presses this button, the stop button will send stop alarm indication information (stop prompt indication information or stop warning indication information) to the data processing device. After receiving the stop alarm indication information, the data processing device sends a corresponding stop instruction (stop prompt instruction or stop warning instruction) to the alarm device according to the content of the stop alarm indication information, thereby stopping the alarm device from continuing to send prompt information or warning information. When a false alarm occurs or the alarm needs to be suspended in a non-emergency situation, the operator or manager can immediately press the stop button to stop the current alarm, thereby improving the flexibility and practicality of the monitoring system, reducing unnecessary interference caused by false alarms, ensuring the normal operation of the work site, and improving the management level and efficiency of the work site.

[0063] Optionally, based on the above embodiments, the alarm device is a warning light;

[0064] The alarm light is used to issue a light prompt in response to a received prompt instruction according to a preset prompt light display mode, or to issue a light warning in response to a received warning instruction according to a preset warning light display mode.

[0065] Specifically, the warning light is connected to the data processing device, and can issue prompts or warning information in different ways according to the received instructions. Among them, the warning light can use a multi-color light-emitting diode light, support the control of different colors and flashing frequencies, and can be specifically set to: when receiving a prompt instruction, control the warning light to flash with a yellow light and a lower frequency (such as flashing once per second); when receiving a warning instruction, control the warning light to flash with a red light and a higher frequency (such as flashing twice per second). Correspondingly, when the data processing device detects a potential risk (such as the operator does not move within the first preset time, there is abnormal behavior or abnormal wind speed), a prompt instruction is sent to the warning light, and the warning light issues a prompt message according to the preset prompt light display mode (such as flashing a yellow light with a lower frequency). If the risk escalates (such as the operator does not move within the second preset time), the data processing device sends a warning instruction to the warning light, and the warning light issues a warning message according to the preset warning light display mode (such as flashing a red light with a high frequency). By setting the color and flashing frequency of the warning light, the visibility and distinction of alarm information at different levels are improved, ensuring that operators can respond in a timely manner, thereby effectively preventing accidents, ensuring the safety of the work site, and improving the management level, efficiency and safety of the operation.

[0066] Further, based on the above embodiments, the alarm device may further include: a speaker;

[0067] The data processing device is further used to send a voice warning instruction to the speaker when it is detected that the duration of the light warning issued by the control warning light exceeds a preset time threshold;

[0068] The speaker is used to issue a voice warning according to the received voice warning instruction.

[0069] Specifically, when the system detects a potential risk and triggers the warning light to issue a warning message, if the risk duration exceeds the set time threshold, the data processing device sends a voice warning instruction to the speaker, and the speaker plays a preset voice content or makes a real-time call according to the voice warning instruction to remind the operator and the manager to pay attention to safety or provide support. Among them, the preset voice content can include location information (such as "operating station 1 has an abnormality, please pay attention"), or the speaker can provide a real-time call function, allowing the manager to send voice instructions directly to the work site through the microphone. By integrating a speaker in the alarm device and playing a voice warning when the warning light issues a warning message exceeding the preset time threshold, the system can more effectively remind the operator to pay attention to safety or provide support. The preset voice content can include specific location information or real-time calls to ensure the accuracy and timeliness of information transmission, improve the visibility and differentiation of the alarm, and enhance the flexibility and practicality of the system, so as to provide timely support to the site where there is an operation risk, ensure the safety of the operation site, and improve the management level, efficiency and safety of the operation.

[0070] Further, based on the above embodiments, the data processing device is further used for:

[0071] At least one of the preset first preset time, the second preset time and the preset flow rate threshold is updated according to the real-time image data and / or the real-time gas flow rate data when the stop alarm indication information is received.

[0072] Specifically, the data processing device receives the real-time image data from the image acquisition device and the real-time gas flow rate data from the wind speed sensor. When receiving the stop command, the data processing device records the clarity of the current real-time image and the real-time gas flow rate, analyzes whether the clarity of the real-time image data is less than the preset clarity threshold, and analyzes whether the real-time gas flow rate exceeds the preset flow rate threshold. If the real-time gas flow rate exceeds the preset flow rate threshold, the preset flow rate threshold is appropriately expanded. If the clarity of the real-time image data is less than the threshold, the working mode of the image acquisition device is adjusted. If the clarity of the real-time image data is greater than or equal to the threshold, the first preset time and the second preset time are appropriately adjusted according to the actual operation time. For example, if the system detects that the operator has not moved for a long time, but the actual operation time is long (that is, the operation behavior needs to remain stationary for a long time for processing), the first preset time and the second preset time can be appropriately increased. The actual operation time can be the preset time of triggering the alarm + the alarm duration (the time from receiving the prompt instruction or warning instruction to receiving the stop instruction), that is, if the stop instruction is received after issuing the warning instruction, then the actual operation time = the second preset time + the alarm duration; if the stop instruction is received after issuing the prompt instruction and no warning instruction is issued, then the actual operation time = the first preset time + the alarm duration. Typically, the preset time can be dynamically adjusted by an adaptive control algorithm (such as an adaptive PID proportional integral differential controller). If the real-time gas flow rate exceeds the preset flow rate threshold, the flow rate threshold is appropriately increased by an adaptive control algorithm (such as an adaptive PID controller) to reduce false alarms.

[0073] Among them, the initial proportional coefficient, initial integral coefficient and initial differential coefficient of the PID controller can be set to 1, 0.1 and 0.01 respectively, and the PID parameters are adjusted in real time according to the system performance using an adaptive algorithm (such as the gradient descent method) based on the error and the error change rate.

[0074] After adjusting the corresponding parameters, the quality inspection and acceptance of the operation process can be carried out regularly to verify whether the adjusted parameters meet the design requirements and quality specifications. If quality problems of the product are found after the adjustment, the parameters should be readjusted and verified again. By dynamically adjusting at least one of the first preset time, the second preset time and the preset flow rate threshold, the system can automatically optimize the alarm triggering conditions according to the data feedback in the actual operation, reduce false alarms caused by environmental changes or equipment status changes, improve the adaptability and reliability of the system, and ensure the safety of operators and production efficiency.

[0075] Embodiment 2

[0076] Figure 2This is a flow chart of a behavior monitoring method for a cigarette factory operation site provided in the second embodiment of the present invention. This embodiment can be applied to the situation of monitoring the behavior pattern of a cigarette factory operation site. The method can be executed by a data processing device in a behavior monitoring system configured at the cigarette factory operation site. The data processing device can be implemented in the form of hardware, specifically in the form of: a terminal device (such as a computer), a server or a cloud computing device.

[0077] Correspondingly, such as Figure 2 As shown, the method includes:

[0078] S210, receiving real-time image data from an image acquisition device, and when the clarity of the real-time image data is lower than a preset clarity threshold, sending a prompt instruction to an alarm device.

[0079] Specifically, the data processing device receives real-time image data, and if the real-time image data is a real-time video stream, the video stream is read frame by frame to obtain real-time image data of each frame, and if the original image is in color, it can be converted into a grayscale image. The clarity of the real-time image is calculated by the Brenner gradient method, and when the clarity of the real-time image data is lower than a preset clarity threshold, a prompt instruction is sent to the alarm device.

[0080] Optionally, based on the above embodiments, when the clarity of the real-time image data is lower than a preset clarity threshold, the data processing device may also send a mode adjustment instruction to the image acquisition device according to on-site operation conditions.

[0081] S220: When it is identified in the real-time image data that the operator has not moved within a first preset time range, a prompt instruction is sent to an alarm device.

[0082] S230: After sending the prompt instruction to the alarm device, when it is identified in the real-time image data that the operator has not moved within a second preset time range, sending a warning instruction to the alarm device.

[0083] Specifically, the data processing device calculates the average speed of moving pixels or the number of moving pixels between consecutive frames by the optical flow method, and detects whether the operator moves within the first preset time range. If the operator does not move within the first preset time, the data processing device sends a prompt instruction to the alarm device. In order to avoid false alarms, the personnel who have not moved within the first preset time due to temporary rest only need to move slightly again or continue construction to stop triggering subsequent warning instructions. If the operator still does not move within the second preset time after sending the prompt instruction, a warning instruction is sent to the alarm device.

[0084] S240, receiving real-time gas flow rate data from the wind speed sensor, and sending a prompt instruction to the alarm device when the real-time gas flow rate data is higher than a preset flow rate threshold.

[0085] Specifically, the data processing device receives the real-time gas flow rate data and evaluates whether the flow rate exceeds a preset flow rate threshold. If the real-time gas flow rate exceeds the preset flow rate threshold, a prompt instruction is sent to the alarm device.

[0086] The technical solution of the embodiment of the present invention receives real-time image data from an image acquisition device, and sends a prompt instruction to an alarm device when the clarity of the real-time image data is lower than a preset clarity threshold; sends a prompt instruction to an alarm device when it is identified in the real-time image data that the operator has not moved within a first preset time range; after sending the prompt instruction to the alarm device, when it is identified in the real-time image data that the operator has not moved within a second preset time range, sends a warning instruction to the alarm device; receives real-time gas flow rate data from a wind speed sensor, and sends a prompt instruction to the alarm device when the real-time gas flow rate data is higher than a preset flow rate threshold. By real-time monitoring of the behavior patterns of operators, and automatically issuing prompts or warnings when abnormal or dangerous behaviors are detected, relevant personnel are reminded to take corresponding measures in a timely manner, thereby avoiding delays in construction due to abnormal operations, reducing the risk of personnel suffering from safety accidents, reducing the labor cost of on-site behavior monitoring, and improving the management level, efficiency and safety of operations.

[0087] Optionally, based on the above embodiments, detecting that the operator in the image data has not moved within a first preset time range may include:

[0088] Identify the outline of the operator in the real-time image data, and analyze the outline offset of the starting frame and each frame of the first preset time range;

[0089] When the offset is less than the preset displacement threshold, a prompt instruction is sent to the alarm device.

[0090] Specifically, the data processing device identifies the outline of the operator in the real-time image data through an image processing algorithm (such as background subtraction method), marks the outline position of the operator, and records its coordinate information. Within the first preset time range (such as 30 seconds), the outline offset (i.e., the moving distance) of the starting frame and each frame is calculated. If the calculated offsets are all less than the preset threshold (such as 10 pixels), it means that the operator has almost no movement in this time period due to a temporary rest or a safety accident. The data processing device will send a prompt instruction to the alarm device. In order to avoid false alarms, the personnel who take a temporary rest only need to move slightly again or continue the construction to stop triggering subsequent warning instructions. After sending the prompt instruction, the data processing device continues to analyze the outline offsets of the starting frame and each frame within the second preset time range. If these offsets are still less than the preset displacement threshold, it means that the operator has not moved for a longer time. The data processing device will send a warning instruction to the alarm device to remind the relevant personnel to take further measures. By real-time monitoring of workers' long periods of inactivity, it is possible to effectively identify whether the workers are in a safety accident, thereby improving the safety and management efficiency of the production site. Through the dual early warning trigger mechanism of prompts and warnings, it is also possible to avoid interference with normal operations due to false alarms while ensuring safety, thereby improving production efficiency.

[0091] Further, based on the above embodiments, after sending the warning instruction to the alarm device, the following steps may be further included:

[0092] At least one of the preset first preset time, the second preset time and the preset flow rate threshold is updated according to the real-time image data and / or the real-time gas flow rate data when the stop alarm indication information sent via the stop button is received.

[0093] Specifically, the data processing device receives the image data from the image acquisition device and the gas flow rate data from the wind speed sensor. When receiving the stop alarm indication information, the data processing device records the clarity of the current real-time image data and the real-time gas flow rate, analyzes whether the clarity of the real-time image data is less than the preset clarity threshold, and analyzes whether the real-time gas flow rate exceeds the preset flow rate threshold. If the real-time gas flow rate exceeds the preset flow rate threshold, the preset flow rate threshold is appropriately expanded. If the clarity of the real-time image data is less than the preset clarity threshold, the working mode of the image acquisition device is adjusted. If the clarity of the real-time image data is greater than or equal to the preset clarity threshold, the first preset time and the second preset time are appropriately adjusted according to the actual operation time. For example, if the system detects that the operator has not moved for a long time, but the actual operation time is long (that is, the operation behavior needs to remain stationary for a long time for processing), the first preset time and the second preset time can be appropriately increased. Among them, the actual operation time can be the preset time of triggering the alarm + the duration of the alarm. If the stop instruction is received after the warning instruction is issued, then the actual operation time = the second preset time + the duration of the alarm; if the stop instruction is received after the prompt instruction is issued and the warning instruction is not issued, then the actual operation time = the first preset time + the duration of the alarm. Typically, the preset time can be dynamically adjusted by an adaptive control algorithm (such as an adaptive PID proportional integral derivative controller). If the real-time gas flow rate exceeds the threshold, the flow rate threshold is appropriately increased by an adaptive control algorithm (such as an adaptive PID controller) to reduce false alarms.

[0094] Among them, the initial proportional coefficient, initial integral coefficient and initial differential coefficient of the PID controller can be set to 1, 0.1 and 0.01 respectively, and the PID parameters are adjusted in real time according to the system performance using an adaptive algorithm (such as the gradient descent method) based on the error and the error change rate.

[0095] After adjusting the corresponding parameters, the quality inspection and acceptance of the operation process can be carried out regularly to verify whether the adjusted parameters meet the design requirements and quality specifications. If the adjusted parameters are found to have product quality problems, the parameters should be readjusted and verified again. By dynamically adjusting at least one of the first preset time, the second preset time and the preset flow rate threshold, the system can automatically optimize the alarm triggering conditions based on the data feedback in actual operation, reduce false alarms caused by environmental changes or equipment status changes, improve the adaptability and reliability of the system, and ensure the safety of operators and production efficiency.

[0096] Specific application scenarios

[0097] At present, the safety risks of construction projects, dangerous operations and illegal operations in the cigarette factory area are characterized by multiple time periods, multiple regions, multiple positions and multiple scenarios. Dangerous behaviors often occur in a short time, but may cause greater harm. The general monitoring risk assessment and decision-making methods cannot effectively detect the abnormalities of construction workers. Therefore, during the construction process, construction workers want to shorten the construction time and carry out continuous and fast operations. Not only are defects in construction easy to occur, but also illegal construction is easy to cause dangerous conditions. At the same time, when construction workers encounter accidents, they cannot be discovered and rescued in time. By deploying cameras, the monitoring system can record video data in real time, but lacks intelligent analysis capabilities. For example, the traditional monitoring system cannot automatically identify abnormal behaviors or dangerous operations. It can only serve as a basis for post-analysis and cannot issue warnings in advance. Human on-site inspections are required to make up for the shortcomings of the monitoring system in real-time analysis and warning. This monitoring method increases the labor cost of monitoring, fails to detect abnormal and dangerous behaviors at the operation site in time, increases the risk of delays in construction due to abnormal operations and safety accidents for operators, and reduces the management level, efficiency and safety of operations.

[0098] To solve the above problems, the present invention proposes a behavior monitoring system for a cigarette factory operation site. Figure 3 Schematic diagram of a behavior monitoring system for a cigarette factory operation site applicable to an embodiment of the present invention. The process of behavior monitoring at a cigarette factory operation site through the system may specifically include:

[0099] 1. Real-time monitoring and collection of images and wind speed information

[0100] Cameras, warning lights, loudspeakers and wind speed sensors are installed at appropriate locations (such as around key operating locations in the production line) to monitor the locations to be evaluated through cameras.

[0101] Wind speed sensors are installed on the top of the factory buildings in the operating areas of each production line. The wind speed sensors can detect the surrounding gas flow rate.

[0102] 2. Monitor data analysis and issue prompts or warnings

[0103] The video monitoring data and gas flow rate data are transmitted to the data processing device for recording and analysis, so as to assess and make decisions on risks. The analysis of gas flow rate data and the issuance of prompts or warning information may specifically include:

[0104] The gas flow rate data is obtained. When the gas flow rate suddenly increases, the data processing device will mark and prompt. When the wind speed is abnormal (the gas flow rate is greater than the preset flow rate threshold), the warning light will flash yellow continuously to warn, indicating that the weather outside the factory is relatively bad, which may cause abnormal phenomena in the factory. For example, strong winds outside the factory will affect the phenomenon of external objects hitting the factory, thereby distracting the attention of the construction workers, that is, the construction at this time will affect the construction workers; when people or objects in the factory move close to the construction location, it will also cause abnormal wind speed. Based on this, the warning light will flash yellow continuously to warn, thereby warning of abnormal phenomena at the work site. For example, during the transportation of materials near the production line, the wind speed exceeding the specified value will also cause material scattering and aggravate dust flying, affecting the air quality of the workshop, and then affecting product quality and the operating stability of transportation equipment (such as conveyor belts and forklifts), increasing the risk of equipment failure.

[0105] Record and analyze the video monitoring data to determine whether the operator has moved, which may include:

[0106] Obtain image data from video surveillance, use background subtraction to identify the outline of the operator, mark the outline position of the operator in each frame of the image, and record its coordinate information. Set the first preset time range to 30 seconds, that is, within 30 seconds, compare the offset of the operator's outline in the starting frame and each frame. If the offset is less than 10 cm (the preset displacement threshold), it means that the operator has hardly moved during this period, and the data processing device needs to send a prompt instruction to the alarm device. After sending the prompt instruction, continue to analyze the outline offset within the next 1 minute (the second preset time range). If the offset is still less than 10 cm within this 1 minute, it means that the operator has not moved. The data processing device needs to send a warning instruction to the alarm device.

[0107] When the risk of an operating behavior is assessed as abnormal through video data, the user will be warned through a warning light; and when the abnormal operation lasts for a long time or dangerous behavior occurs, a loudspeaker will be used to warn and notify surrounding people.

[0108] There are two types of warning lights: yellow and red. The yellow light is a reminder light, which means that the construction environment is not optimal at this time, but construction can be carried out and safety needs to be paid attention to; the red light is a warning light, which means that construction needs to be stopped at this time.

[0109] In a specific example, during the construction process, different cameras are used to monitor the location and construction process of the construction workers. When it is detected that the construction workers have not moved for 20-60 seconds during the construction process, that is, the construction workers may take a temporary rest due to fatigue or be injured by objects in the construction location, causing the construction workers to pause, the warning light will continuously flash yellow to alert the construction workers. The personnel taking a temporary rest only need to move slightly again or continue the construction, and the warning light will stop working, thereby ensuring the safety of the construction workers during construction and reminding the construction workers at the same time.

[0110] During the construction process, if it is detected that the construction workers have not moved for more than 60 seconds, it means that the construction workers may be in a dangerous situation, such as inhaling something that can cause a person to become comatose or being exposed to electric current and becoming comatose. At this time, the warning light flashes red. If the construction workers just need to rest for a long time, they can stop the flashing of the warning light through the stop button attached to the warning light housing, thereby manually stopping the warning light from continuing to flash and avoiding misjudgment caused by an alarm; after the warning light flashes red for 30 seconds, the loudspeaker will make a sound to prompt, and the personnel in the factory can hear the sound through the loudspeaker and can arrive at the construction site for support, or control the loudspeaker through the data processing device to shout to the construction workers, which helps to wake up the construction workers and avoid danger to the construction workers.

[0111] During the construction process, when it is detected that the construction workers are working continuously at a high speed, such as when the camera is unclear for 10 seconds or more within 1 minute during the construction process (the Brenner gradient method can be used to calculate the clarity value of the image, and when the clarity value is lower than the preset clarity threshold, the camera is unclear), it means that the construction workers are working too fast, which may easily cause damage to the workpiece and poor work quality during the construction process. At this time, the warning light can flash yellow 5 times intermittently to warn the construction workers to be more careful during the construction process, thereby increasing the quality of construction. The construction speed can be adjusted according to the actual situation to ensure the normal progress of the construction work.

[0112] 3. Adaptive adjustment of camera shooting mode

[0113] When it is detected that the clarity of the image data received from the image acquisition device is lower than the preset clarity threshold, the data processing device can automatically send a mode adjustment instruction to the image acquisition device according to the conditions of the work site. After receiving the adjustment instruction, the image acquisition device adjusts its own parameters to the preset parameters of the adaptation scene according to the instruction content. For example, if the light intensity sensor finds that the camera is at night or in a low-light work site (the current light intensity is lower than the preset light intensity threshold), the data processing device can send an instruction to the image acquisition device to switch the image acquisition device to low-light mode (such as turning on the fill light or adjusting the exposure time) and adjust the focal length to improve the image quality.

[0114] 4. Adaptive optimization prompt and warning mechanism

[0115] Furthermore, when the construction personnel trigger the alarm for reasonable reasons (such as a long break), they manually intervene and avoid false alarms. At the same time, the system will automatically update the preset time threshold, displacement threshold or velocity threshold according to the image data and gas flow rate data when the stop command is received, so as to optimize the subsequent monitoring and alarm mechanism. For example, if the current operation area is manually stopped after the alarm is triggered multiple times, the system will adjust the preset time threshold corresponding to the current operation area according to these data (for example, adjust the first preset time from 30 seconds to 45 seconds). If the gas flow rate data in the current operation area is manually stopped after the alarm is triggered multiple times, the system will adjust the preset threshold of the gas flow rate corresponding to the current operation area (for example, from 8 meters / second to 10 meters / second). In addition, the first preset time, the second preset time and the preset threshold of the gas flow rate can also be dynamically adjusted by an adaptive control algorithm (such as an adaptive PID controller). After adjusting the corresponding parameters, the quality inspection and acceptance of the operation process can be carried out regularly to verify whether the adjusted parameters meet the design requirements and quality specifications. If it is found that there are quality problems with the adjusted parameters, the parameters should be readjusted and verified again.

[0116] The behavior monitoring system for the cigarette factory work site proposed in the embodiment of the present invention can monitor the work behavior of construction personnel at the work site, so as to determine whether the construction personnel have abnormal work behavior phenomena such as too fast construction or stopping construction during the construction process, and automatically issue prompts or warnings when abnormal work behavior is monitored, reminding relevant personnel to take corresponding measures in time, so as to effectively ensure the construction progress. At the same time, it can timely discover the dangerous work behaviors and safety accidents of construction personnel during the construction process, and when the construction personnel are unable to move due to injuries, etc., the monitoring device can automatically alarm in time, so as to timely discover the abnormality of the construction personnel and rescue them, thereby reducing the manpower cost of behavior monitoring at the work site and improving the management level, efficiency and safety of the operation.

[0117] Embodiment 3

[0118] In some embodiments, the behavior monitoring method of a cigarette factory operation site can be implemented as a computer program, that is:

[0119] Receiving image data from an image acquisition device, and sending a prompt instruction to an alarm device when the clarity of the image data is lower than a preset clarity threshold;

[0120] When it is detected in the image data that the operator has not moved within a first preset time range, sending a prompt instruction to the alarm device;

[0121] After sending the prompt instruction to the alarm device, when the operator does not move within the second preset time range in the image data, sending a warning instruction to the alarm device;

[0122] as well as,

[0123] Receive gas flow rate data from the wind speed sensor, and send a prompt instruction to the alarm device when the gas flow rate data is higher than a preset flow rate threshold.

[0124] It is tangibly contained in a computer-readable storage medium, such as a storage unit. In some embodiments, part or all of the computer program can be loaded and / or installed on the behavior monitoring system of the cigarette factory operation site via the ROM and / or the communication unit. When the computer program is loaded into the RAM and executed by the processor, one or more steps of the behavior monitoring method of the cigarette factory operation site described above can be executed. Alternatively, in other embodiments, the processor can be configured to execute the behavior monitoring method of the cigarette factory operation site by any other appropriate means (for example, by means of firmware).

[0125] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0126] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0127] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0128] In order to provide interaction with the user, the systems and techniques described herein can be implemented on a behavior monitoring system at a cigarette factory operation site, which has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball), through which the user can provide input to the behavior monitoring system at the cigarette factory operation site. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and the input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0129] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0130] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0131] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0132] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A behavior monitoring system for a cigarette factory operation site, characterized in that: include: An image acquisition device, a wind speed sensor, an alarm device and a data processing device; the image acquisition device is arranged on an operating table of a production line, the wind speed sensor is arranged on a roof of an operating area of ​​the production line, the alarm device is arranged on an operating table of an operating area of ​​the production line, the image acquisition device is electrically connected to the data processing device, the wind speed sensor is electrically connected to the data processing device, and the alarm device is electrically connected to the data processing device; The image acquisition device is used to acquire real-time image data in the operation area of ​​the production line during the operation, and send the real-time image data to the data processing device; The wind speed sensor is used to collect real-time gas flow rate data in the operation area of ​​the production line during operation, and send the real-time gas flow rate data to the data processing device; The data processing device is used to receive real-time image data from an image acquisition device, and send a prompt instruction to an alarm device when the clarity of the real-time image data is lower than a preset clarity threshold; send a prompt instruction to the alarm device when it is identified in the real-time image data that the operator has not moved within a first preset time range; after sending the prompt instruction to the alarm device, when it is identified in the real-time image data that the operator has not moved within a second preset time range, send a warning instruction to the alarm device; and receive real-time gas flow rate data from a wind speed sensor, and send a prompt instruction to the alarm device when the real-time gas flow rate data is higher than a preset flow rate threshold; The alarm device issues a prompt message in response to a received prompt instruction, or issues a warning message in response to a received warning instruction.

2. The system according to claim 1, characterized in that The data processing device is specifically used for: Receive image data from the image acquisition device, identify the outline of the operator, and analyze the outline offset of the starting frame and each frame of the first preset time range, and when the offset is less than the preset displacement threshold, send a prompt instruction to the alarm device; After sending the prompt instruction to the alarm device, the contour offset of the start frame and each frame in the second preset time range is analyzed, and when the offset is less than the preset displacement threshold, a warning instruction is sent to the alarm device.

3. The system according to claim 1, characterized in that The data processing device is further used for: When it is detected that the clarity of the real-time image data received from the image acquisition device is lower than a preset clarity threshold, a mode adjustment instruction is sent to the image acquisition device.

4. The system according to claim 1, characterized in that Also includes: Stop button; Wherein, the stop button is arranged on the housing of the alarm device, and the stop button is electrically connected to the data processing device; The stop button is used to send stop alarm indication information to the data processing device in response to a button pressing operation; The data processing device is further configured to send an alarm stop instruction to the alarm device upon receiving the alarm stop instruction information; The alarm device is also used to stop sending prompt information or warning information when receiving an alarm stop instruction.

5. The system according to any one of claims 1 to 4, characterized in that: The alarm device is a warning light; The alarm light is used to issue a light prompt in response to a received prompt instruction according to a preset prompt light display mode, or to issue a light warning in response to a received warning instruction according to a preset warning light display mode.

6. The system according to claim 5, characterized in that The alarm device also includes: a speaker; The data processing device is further used to send a voice warning instruction to the speaker when it is detected that the duration of the light warning issued by the control warning light exceeds a preset time threshold; The speaker is used to issue a voice warning according to the received voice warning instruction.

7. The system according to claim 4, characterized in that The data processing device is further used for: At least one of the preset first preset time, the second preset time and the preset flow rate threshold is updated according to the real-time image data and / or the real-time gas flow rate data when the stop alarm indication information is received.

8. A behavior monitoring method for a cigarette factory operation site, characterized in that: The method is performed by a data processing device configured in the behavior monitoring system of the cigarette factory operation site according to any one of claims 1 to 7, and comprises: receiving real-time image data from an image acquisition device, and sending a prompt instruction to an alarm device when the clarity of the real-time image data is lower than a preset clarity threshold; When it is identified in the real-time image data that the operator has not moved within a first preset time range, sending a prompt instruction to the alarm device; After sending the prompt instruction to the alarm device, when it is identified in the real-time image data that the operator has not moved within the second preset time range, sending a warning instruction to the alarm device; as well as, Receive real-time gas flow rate data from the wind speed sensor, and send a prompt instruction to the alarm device when the real-time gas flow rate data is higher than a preset flow rate threshold.

9. The method according to claim 8, characterized in that The identifying that the operator has not moved within a first preset time range in the real-time image data specifically includes: Identify the outline of the operator in the real-time image data, and analyze the outline offset of the starting frame and each frame of the first preset time range; When the offset is less than the preset displacement threshold, a prompt instruction is sent to the alarm device.

10. The method according to claim 8, characterized in that After sending a warning instruction or a prompt instruction to the alarm device, it also includes: At least one of the preset first preset time, the second preset time and the preset flow rate threshold is updated according to the real-time image data and / or the real-time gas flow rate data when the stop alarm indication information sent via the stop button is received.

Images