AI-based plant personnel safety monitoring method, device, equipment and medium
By using an AI-based method for monitoring personnel safety in factory areas, AI models are used to analyze equipment and environmental data, identify and handle anomalies, and overcome the limitations of existing technologies such as manual inspection and sensor monitoring. This enables efficient and accurate monitoring and management of factory safety.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ZHIWEISHI (TIANJIN) TECH CO LTD
- Filing Date
- 2026-03-05
- Publication Date
- 2026-06-12
Smart Images
Figure CN122198623A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of factory personnel safety monitoring, and in particular to an AI-based method, device, equipment and medium for factory personnel safety monitoring. Background Technology
[0002] In modern industrial production, personnel safety in the factory area is of paramount importance, affecting the continuous and stable operation of the enterprise and the health and lives of employees. With the continuous advancement of industrial automation and intelligence, equipment and processes within the factory area are becoming increasingly complex, leading to a rise in safety risks for personnel. Therefore, effective monitoring and management of personnel safety in the factory area has become a crucial issue that urgently needs to be addressed in the industrial sector. A sound personnel safety monitoring system can promptly identify potential safety hazards, reduce the probability of accidents, ensure smooth production, and also contribute to improving the company's social image and economic benefits.
[0003] Currently, the main methods used for safety monitoring in factory areas include manual inspections and traditional sensor monitoring. Manual inspections involve professionals conducting on-site checks of various areas of the factory at set time intervals and along designated routes, observing equipment operation status and personnel behavior to promptly identify, record, and address potential safety issues. Traditional sensor monitoring involves installing various types of sensors within the factory area, such as temperature sensors, pressure sensors, and smoke sensors, to collect real-time equipment operating parameters and environmental data. Alarms are triggered if the data exceeds preset ranges. In addition, video surveillance systems are used to monitor key areas of the factory in real time, allowing for timely on-site assessment in case of problems.
[0004] However, all these monitoring methods have certain drawbacks. Manual inspections are subjective and limited, making it difficult to achieve all-weather, all-round monitoring, and prone to missed or false detections, and they are also costly in terms of manpower. Traditional sensor monitoring can only monitor specific physical quantities and is unable to accurately identify abnormal human behavior or complex environmental changes. Video surveillance systems also rely mainly on manual review and cannot automatically and quickly analyze and judge abnormal situations in the footage, resulting in safety hazards not being detected and dealt with in a timely manner. Summary of the Invention
[0005] To improve the efficiency and reliability of personnel safety monitoring in factory areas, this application provides an AI-based method, device, equipment, and medium for personnel safety monitoring in factory areas.
[0006] Firstly, this application provides an AI-based method for monitoring the safety of personnel in factory areas, employing the following technical solution: An AI-based method for monitoring personnel safety in factory areas, comprising: Acquire current monitoring data and historical monitoring data, wherein the current monitoring data includes equipment operating status data and environmental monitoring data; The historical monitoring data is analyzed based on an AI model to determine the anomaly identification criteria; The anomaly identification criteria are matched based on the equipment operating status data to determine the current identification criteria for each workstation. The current monitoring data is analyzed based on the AI model to determine the current status information; The current anomaly information is determined based on the current status information, the current identification criteria, the environmental monitoring data, and the equipment operating status data; An anomaly management strategy is determined based on the current anomaly information.
[0007] By adopting the above technical solutions, using AI models to analyze historical monitoring data to derive anomaly identification standards, and then matching the current identification standards for each workstation with equipment operating status data, the applicable anomaly identification standards for different workstations can be accurately determined. Based on the analysis of current monitoring data using AI models to determine current status information, and further combining current identification standards, environmental monitoring data, and equipment operating status data to determine current anomaly information, anomaly situations within the factory area can be identified more comprehensively and accurately. Finally, based on the current anomaly information, anomaly management strategies can be determined, enabling effective monitoring and management of personnel safety in the factory area, and improving the efficiency and reliability of personnel safety monitoring in the factory area.
[0008] Optionally, the step of matching the anomaly identification criteria based on the equipment operating status data to determine the current identification criteria for each workstation includes: Obtain the continuous working hours and cumulative years of service for each employee at each workstation; The anomaly identification criteria are matched based on the continuous working time, the cumulative working years, and the equipment operating status data to determine the current identification criteria for each workstation.
[0009] By adopting the above technical solution and combining the continuous working hours, cumulative years of service, and equipment operating status data of employees to match the anomaly identification standards to determine the current identification standards for each workstation, the identification standards can be made more in line with the actual situation of each workstation, improve the accuracy of anomaly identification, thereby better monitoring the safety of personnel in the factory area, reducing the missed and false detection of safety hazards, and ensuring the smooth operation of production.
[0010] Optionally, the current monitoring data includes video data, audio data, and vibration data. The step of analyzing the current monitoring data based on the AI model to determine the current state information includes: The video data is analyzed based on the AI model to determine image recognition information; The AI model is used to analyze the sound data to determine sound recognition information; The vibration data is analyzed based on the AI model to determine vibration identification information; The current state information is determined based on the image recognition information, the sound recognition information, and the vibration recognition information.
[0011] By adopting the above technical solution, AI models are used to analyze video data, sound data, and vibration data to obtain image recognition information, sound recognition information, and vibration recognition information, thereby determining the current status information. This enables multi-dimensional monitoring of personnel safety in the factory area, more comprehensively and accurately identifying abnormal personnel behavior and complex environmental changes, improving the accuracy and timeliness of personnel safety monitoring in the factory area, and reducing the chances of missing safety hazards.
[0012] Optionally, the image recognition information includes employee identification information and group identification information, and the step of determining the current anomaly information based on the current status information, the current identification standard, the environmental monitoring data, and the equipment operating status data includes: The image recognition information is compared with the current recognition standard to determine image anomaly information; The sound recognition information is compared with the current recognition standard to determine sound anomaly information; The vibration identification information is compared with the current identification standard to determine the vibration anomaly information; Analyze the equipment's operating status data to determine any equipment malfunctions; The environmental monitoring data is analyzed to identify environmental anomalies. The current anomaly information is determined based on the image anomaly information, the sound anomaly information, the vibration anomaly information, the equipment anomaly information, and the environmental anomaly information. The current anomaly information includes anomaly type, anomaly range, and anomaly level. The anomaly range includes individual anomalies and group anomalies.
[0013] By adopting the above technical solution, image anomaly information, sound anomaly information, and vibration anomaly information are determined by comparing various identification information with the current identification standards. Equipment anomaly information and environmental anomaly information are obtained by analyzing equipment operating status data and environmental monitoring data. Then, the anomaly type, anomaly range, and anomaly level are determined by comprehensive analysis, and the current anomaly information is finally determined. This can more comprehensively and accurately identify abnormal behavior of personnel in the factory area and complex environmental changes, and promptly detect safety hazards.
[0014] Optionally, determining the anomaly management strategy based on the current anomaly information includes: If the scope of the anomaly is the individual anomaly, then the associated management factors are determined based on the anomaly type; The anomaly level is adjusted based on the aforementioned related management factors; The anomaly management strategy is determined based on the adjusted anomaly level and the current anomaly information.
[0015] By adopting the above technical solution, when the anomaly range is individual anomaly, the associated management factors are determined based on the anomaly type and the anomaly level is adjusted. Then, combined with the current anomaly information, an anomaly management strategy is determined. This enables the formulation of more accurate and effective management strategies for individual anomalies, thereby improving the targeting and management efficiency of safety monitoring of personnel in the factory area.
[0016] Optionally, determining the anomaly management strategy based on the current anomaly information includes: If the anomaly range is the group anomaly, then a control strategy is determined based on the anomaly level; Determine whether the anomaly level exceeds a preset anomaly level; If the anomaly level exceeds the preset anomaly level, a device shutdown strategy is determined. The anomaly management strategy is determined based on the control strategy and the equipment linkage shutdown strategy.
[0017] By adopting the above technical solutions, not only can individual anomalies be handled in a timely manner, but also group anomalies can be handled in a timely manner, thus improving the comprehensiveness of anomaly management.
[0018] Optionally, the method further includes: Obtain historical anomaly information; The historical anomaly information is analyzed to identify high-frequency abnormal workstations and high-frequency abnormal time periods; The monitoring frequency of each workstation in each time period is determined based on the high-frequency abnormal workstation and the high-frequency abnormal time period.
[0019] By adopting the above technical solution, high-frequency abnormal workstations and high-frequency abnormal time periods can be identified by analyzing historical abnormal information. In turn, the monitoring frequency of each workstation in each time period can be determined. This can strengthen the monitoring of workstations and time periods prone to abnormalities, improve the pertinence and effectiveness of safety monitoring of personnel in the factory area, reduce the missed detection of safety hazards, and ensure the smooth operation of production.
[0020] Secondly, this application provides an AI-based factory personnel safety monitoring device, which adopts the following technical solution: An AI-based factory personnel safety monitoring device includes: The monitoring data acquisition module is used to acquire current monitoring data and historical monitoring data, wherein the current monitoring data includes equipment operating status data and environmental monitoring data; The identification standard determination module is used to analyze the historical monitoring data based on the AI model to determine the anomaly identification standard; The identification specification matching module is used to match the anomaly identification specification based on the equipment operating status data to determine the current identification specification for each workstation; The status information determination module is used to analyze the current monitoring data based on the AI model to determine the current status information; An anomaly information determination module is used to determine current anomaly information based on the current status information, the current identification standard, the environmental monitoring data, and the equipment operating status data. The management strategy determination module is used to determine the anomaly management strategy based on the current anomaly information.
[0021] By adopting the above technical solutions, using AI models to analyze historical monitoring data to derive anomaly identification standards, and then matching the current identification standards for each workstation with equipment operating status data, the applicable anomaly identification standards for different workstations can be accurately determined. Based on the analysis of current monitoring data using AI models to determine current status information, and further combining current identification standards, environmental monitoring data, and equipment operating status data to determine current anomaly information, anomaly situations within the factory area can be identified more comprehensively and accurately. Finally, based on the current anomaly information, anomaly management strategies can be determined, enabling effective monitoring and management of personnel safety in the factory area, and improving the efficiency and reliability of personnel safety monitoring in the factory area.
[0022] Thirdly, this application provides an electronic device that adopts the following technical solution: An electronic device includes a processor coupled to a memory; The memory stores a computer program that can be loaded by a processor and executed as described in any of the first aspects, namely, the AI-based factory personnel safety monitoring method.
[0023] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium storing a computer program capable of being loaded by a processor and executing the AI-based factory personnel safety monitoring method described in any of the first aspects. Attached Figure Description
[0024] Figure 1 This is a flowchart illustrating an AI-based method for monitoring the safety of personnel in a factory area, as provided in an embodiment of this application.
[0025] Figure 2This is a structural block diagram of an AI-based factory personnel safety monitoring device provided in an embodiment of this application.
[0026] Figure 3 This is a structural block diagram of the electronic device provided in the embodiments of this application. Detailed Implementation
[0027] The present application will be further described in detail below with reference to the accompanying drawings.
[0028] This application provides an AI-based method for monitoring the safety of personnel in a factory area. This method can be executed by an electronic device, which can be a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet, desktop computer, etc., but is not limited to these.
[0029] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0030] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.
[0031] like Figure 1 As shown, an AI-based method for monitoring the safety of personnel in a factory area is described in the following steps (S101-S106): Step S101: Obtain current monitoring data and historical monitoring data. Current monitoring data includes equipment operating status data and environmental monitoring data.
[0032] The current monitoring data includes video data, audio data, and vibration data. The historical monitoring data includes historical normal monitoring data (e.g., videos of excellent employees' operations) and historical abnormal monitoring data (e.g., videos of incorrect operations). Both historical normal monitoring data and historical abnormal monitoring data include various types of data such as video data, audio data, vibration data, equipment operating status data, and environmental monitoring data.
[0033] The factory area is equipped with various monitoring devices, including sensors such as temperature sensors, pressure sensors, smoke sensors, and vibration sensors, used to collect equipment operating status data, environmental monitoring data, and vibration data; it also includes cameras and microphones for collecting video and audio data. Current monitoring data is obtained from these devices, and historical monitoring data is retrieved from a database.
[0034] Step S102: Analyze historical monitoring data based on AI models to determine anomaly identification standards.
[0035] Historical normal monitoring data and historical abnormal monitoring data labeled "normal" or "abnormal" are input into the AI model for analysis to identify patterns and characteristics. The AI model can then output anomaly identification specifications, which include the standard operating procedures for each workstation, the operation time for each procedure, action specifications, abnormal behaviors, and prohibited areas. For example, the standard operating procedure for the welding workstation is "take the part (no more than 2 seconds, elbow bent at 60-91 degrees) - align the position - weld - release the part", and the standard operating procedure for the assembly workstation is "take the screw - tighten it - check". Abnormal behaviors include playing with a mobile phone, making or receiving phone calls, etc. The AI model can be a pre-trained deep learning model, such as a convolutional neural network (CNN) or a recurrent neural network (RNN).
[0036] Step S103: Match the anomaly identification specifications based on the equipment operating status data to determine the current identification specifications for each workstation.
[0037] Different equipment operating states correspond to different anomaly identification standards. For example, when a machine tool is running, the safe distance between the employee and the machine tool is 1.5 meters; when the machine tool is stopped for changeover, the safe distance between the employee and the machine tool is 0.5 meters, allowing the employee to operate it at a closer distance. The current equipment operating status data is used to match the current identification standards for each workstation from the anomaly identification standards.
[0038] Specifically, the anomaly identification criteria are matched based on equipment operating status data to determine the current identification criteria for each workstation, including: obtaining the continuous working hours and cumulative years of service of the employees corresponding to each workstation; and matching the anomaly identification criteria based on the continuous working hours, cumulative years of service, and equipment operating status data to determine the current identification criteria for each workstation.
[0039] The anomaly identification criteria are related not only to equipment operating status data, but also to employees' continuous working hours and cumulative years of service. For example, the operation time of new employees in each process step is longer than that of experienced employees in the corresponding process steps. In this embodiment, the cumulative years of service of employees corresponding to each workstation are obtained from the employee file, and the continuous working hours of employees corresponding to each workstation are obtained from the attendance data. The current continuous working hours, cumulative years of service, and the anomaly identification criteria corresponding to the equipment operating status data are matched from the anomaly identification criteria, that is, the current identification criteria of each workstation.
[0040] Step S104: Analyze the current monitoring data based on the AI model to determine the current status information.
[0041] Specifically, the current monitoring data is analyzed based on the AI model to determine the current status information, including: analyzing video data based on the AI model to determine image recognition information; analyzing sound data based on the AI model to determine sound recognition information; analyzing vibration data based on the AI model to determine vibration recognition information; and determining the current status information based on image recognition information, sound recognition information, and vibration recognition information.
[0042] In this embodiment, the current video data, audio data, and vibration data are respectively input into the AI model for analysis to obtain image recognition information (including the employee's skeletal movements, posture angles, operating behavior, wearing of equipment such as safety helmets, and location information), audio recognition information (including the operating sound of the equipment and the voices of the employees), and vibration recognition information (including the vibration frequency and amplitude of the equipment). The image recognition information, audio recognition information, and vibration recognition information are jointly determined as the current state information, wherein the AI model is the same as the AI model in step S102 above.
[0043] Step S105: Determine the current abnormal information based on the current status information, current identification specifications, environmental monitoring data, and equipment operating status data.
[0044] Specifically, image recognition information includes employee identification information and group identification information. Based on current status information, current identification standards, environmental monitoring data, and equipment operating status data, current anomaly information is determined, including: comparing image recognition information with current identification standards to determine image anomalies; comparing sound recognition information with current identification standards to determine sound anomalies; comparing vibration recognition information with current identification standards to determine vibration anomalies; analyzing equipment operating status data to determine equipment anomalies; analyzing environmental monitoring data to determine environmental anomalies; and determining current anomaly information based on image anomaly information, sound anomaly information, vibration anomaly information, equipment anomaly information, and environmental anomaly information. Current anomaly information includes anomaly type, anomaly scope, and anomaly level. The anomaly scope includes individual anomalies and group anomalies.
[0045] In this embodiment, when the AI model identifies the current video data, it can not only identify each employee's skeletal movements, posture angles, operating behaviors, wearing of equipment such as safety helmets, and location information, but also identify the overall state (orderly or chaotic) of all employees in the factory area. That is, the image recognition information includes employee identification information and group identification information, which can make more effective anomaly judgments.
[0046] Image recognition information, sound recognition information, and vibration recognition information are compared with the corresponding current recognition standards to determine abnormal information of employees and equipment, namely image abnormal information, sound abnormal information, and vibration abnormal information. Equipment operating status data are compared with preset status thresholds to determine equipment abnormal information. Environmental monitoring data are compared with preset environmental thresholds to determine environmental abnormal information. Each of the above abnormal information includes an abnormality type and an abnormality level. Image abnormal information, sound abnormal information, vibration abnormal information, equipment abnormal information, and environmental abnormal information are collectively determined as the current abnormal information.
[0047] If the current abnormal information includes personnel abnormalities, the scope of the abnormality will be further determined. If the abnormal image information includes employees in a chaotic state, the scope of the abnormality is a group abnormality. If the abnormal image information includes employees in an orderly state, the scope of the abnormality is an individual abnormality.
[0048] Step S106: Determine the exception management strategy based on the current exception information.
[0049] Specifically, determining the anomaly management strategy based on the current anomaly information includes: if the anomaly scope is an individual anomaly, determining the associated management factors based on the anomaly type; adjusting the anomaly level based on the associated management factors; and determining the anomaly management strategy based on the adjusted anomaly level and the current anomaly information.
[0050] In this embodiment, for personnel anomalies within the factory area, if the anomaly is an individual anomaly, then related management factors are retrieved from the database based on the anomaly type. For example, if the anomaly type is an operational timing deviation anomaly, then the related management factors include the risk status of the abnormal workstation and the risk status of the abnormal time period. Preset anomaly level adjustment rules are retrieved from the database, and the anomaly level is adjusted using the related management factors and the preset anomaly level adjustment rules. For example, if the anomaly type is an operational timing deviation anomaly, and the abnormal workstation is a high-risk workstation or the abnormal time period is a high-risk time period, then the anomaly level is increased by one level. The database stores anomaly management strategies corresponding to various anomaly information (anomaly type, anomaly range, anomaly level). Based on the adjusted anomaly level and the anomaly type and anomaly range in the current anomaly information, anomaly management strategies are matched from the database. For example, voice reminders are given for anomalies, and team leaders coordinate the handling of anomalies.
[0051] Specifically, the anomaly management strategy is determined based on the current anomaly information, including: if the anomaly range is a group anomaly, then the control strategy is determined based on the anomaly level; it is determined whether the anomaly level exceeds the preset anomaly level; if the anomaly level exceeds the preset anomaly level, then the equipment linkage shutdown strategy is determined; and the anomaly management strategy is determined based on the control strategy and the equipment linkage shutdown strategy.
[0052] In this embodiment, for personnel anomalies within the factory area, if the anomaly involves a group anomaly (e.g., employees running around in panic), a control strategy is matched from the database based on the anomaly level. For example, the system may repeatedly broadcast messages such as "Please keep order and do not panic, and evacuate according to the rules in area XX," or notify security personnel to provide on-site guidance. If the anomaly level exceeds a preset anomaly level (pre-set, not specifically limited here), a preset equipment shutdown strategy is activated to stop equipment operation and reduce the possibility of further risk spread. The anomaly management strategy includes controlling personnel according to the control strategy and stopping equipment operation according to the equipment shutdown strategy.
[0053] Furthermore, for equipment and environmental anomalies within the factory area, corresponding anomaly management strategies are matched from the database based on the anomaly type and level.
[0054] Specifically, the method also includes: acquiring historical anomaly information; analyzing the historical anomaly information to determine high-frequency anomaly workstations and high-frequency anomaly time periods; and determining the monitoring frequency of each workstation in each time period based on the high-frequency anomaly workstations and high-frequency anomaly time periods.
[0055] In this embodiment, historical anomaly information is obtained from the database; the historical anomaly information is analyzed using a data analysis tool (e.g., EXCEL), and workstations with anomaly frequency higher than a first preset frequency are identified as high-frequency anomaly workstations, and time periods with anomaly frequency higher than a second preset frequency are identified as high-frequency anomaly time periods; wherein, the first preset frequency and the second preset frequency are both preset by the staff and are not specifically limited here.
[0056] The database stores the monitoring frequencies corresponding to high-frequency abnormal workstations and high-frequency abnormal time periods, as well as the monitoring frequencies corresponding to ordinary workstations (workstations other than high-frequency abnormal workstations) and ordinary time periods (time periods other than high-frequency abnormal time periods). Based on whether a workstation is a high-frequency abnormal workstation or whether a time period is a high-frequency abnormal time period, the corresponding monitoring frequency is retrieved from the database, thereby obtaining the monitoring frequency of each workstation in each time period. Among them, the monitoring frequency corresponding to high-frequency abnormal workstations is higher than the monitoring frequency corresponding to ordinary workstations, and the monitoring frequency corresponding to high-frequency abnormal time periods is higher than the monitoring frequency corresponding to ordinary time periods.
[0057] Figure 2 This is a structural block diagram of an AI-based factory personnel safety monitoring device 200 provided in an embodiment of this application.
[0058] like Figure 2 As shown, the AI-based factory personnel safety monitoring device 200 mainly includes: The monitoring data acquisition module 201 is used to acquire current monitoring data and historical monitoring data. The current monitoring data includes equipment operating status data and environmental monitoring data. The identification specification determination module 202 is used to analyze historical monitoring data based on an AI model to determine the anomaly identification specifications; The identification specification matching module 203 is used to match the anomaly identification specifications based on the equipment operating status data to determine the current identification specifications for each workstation. The status information determination module 204 is used to analyze the current monitoring data based on the AI model and determine the current status information; The anomaly information determination module 205 is used to determine the current anomaly information based on the current status information, the current identification standard, environmental monitoring data, and equipment operating status data. The management strategy determination module 206 is used to determine the exception management strategy based on the current exception information.
[0059] As an optional implementation of this embodiment, the identification specification matching module 203 is specifically used to match the anomaly identification specification based on the equipment operation status data to determine the current identification specification of each workstation, including: obtaining the continuous working time and cumulative working years of the employees corresponding to each workstation; matching the anomaly identification specification based on the continuous working time, cumulative working years and equipment operation status data to determine the current identification specification of each workstation.
[0060] As an optional implementation of this embodiment, the current monitoring data includes video data, sound data, and vibration data. The status information determination module 204 is specifically used to analyze the current monitoring data based on an AI model to determine the current status information, including: analyzing video data based on an AI model to determine image recognition information; analyzing sound data based on an AI model to determine sound recognition information; analyzing vibration data based on an AI model to determine vibration recognition information; and determining the current status information based on image recognition information, sound recognition information, and vibration recognition information.
[0061] As an optional implementation of this embodiment, the image recognition information includes employee identification information and group identification information. The anomaly information determination module 205 is specifically used to determine the current anomaly information based on the current status information, the current identification standard, environmental monitoring data, and equipment operating status data. This includes: comparing the image recognition information with the current identification standard to determine image anomaly information; comparing the sound recognition information with the current identification standard to determine sound anomaly information; comparing the vibration recognition information with the current identification standard to determine vibration anomaly information; analyzing the equipment operating status data to determine equipment anomaly information; analyzing the environmental monitoring data to determine environmental anomaly information; and determining the current anomaly information based on the image anomaly information, sound anomaly information, vibration anomaly information, equipment anomaly information, and environmental anomaly information. The current anomaly information includes anomaly type, anomaly range, and anomaly level. The anomaly range includes individual anomalies and group anomalies.
[0062] As an optional implementation of this embodiment, the management strategy determination module 206 is specifically used to determine an anomaly management strategy based on the current anomaly information, including: if the anomaly scope is an individual anomaly, then determine the associated management factors based on the anomaly type; adjust the anomaly level based on the associated management factors; and determine the anomaly management strategy based on the adjusted anomaly level and the current anomaly information.
[0063] As an optional implementation of this embodiment, the management strategy determination module 206 is specifically used to determine an anomaly management strategy based on the current anomaly information, including: if the anomaly range is a group anomaly, then determine the control strategy based on the anomaly level; determine whether the anomaly level exceeds the preset anomaly level; if the anomaly level exceeds the preset anomaly level, then determine the equipment linkage shutdown strategy; and determine the anomaly management strategy based on the control strategy and the equipment linkage shutdown strategy.
[0064] As an optional implementation of this embodiment, the AI-based factory personnel safety monitoring device 200 is also specifically used for: acquiring historical abnormal information; analyzing the historical abnormal information to determine high-frequency abnormal workstations and high-frequency abnormal time periods; and determining the monitoring frequency of each workstation in each time period based on the high-frequency abnormal workstations and high-frequency abnormal time periods.
[0065] In one example, the module in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.
[0066] For example, when modules in a device can be implemented via a processing element scheduler, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor capable of calling programs. Alternatively, these modules can be integrated together as a system-on-a-chip (SOC).
[0067] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device and module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0068] Figure 3 This is a structural block diagram of an electronic device 300 provided in an embodiment of this application.
[0069] like Figure 3 As shown, the electronic device 300 includes a processor 301 and a memory 302, and may further include one or more of an information input / output (I / O) interface 303, a communication component 304, and a communication bus 305.
[0070] The processor 301 controls the overall operation of the electronic device 300 to complete all or part of the steps of the AI-based factory personnel safety monitoring method described above. The memory 302 stores various types of data to support the operation of the electronic device 300. This data may include, for example, instructions for any application or method operating on the electronic device 300, as well as application-related data. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as one or more of Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.
[0071] I / O interface 303 provides an interface between processor 301 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 304 is used for wired or wireless communication between electronic device 300 and other devices. Wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 304 may include a Wi-Fi component, a Bluetooth component, and an NFC component.
[0072] The electronic device 300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the AI-based factory personnel safety monitoring method given in the above embodiments.
[0073] The communication bus 305 may include a path for transmitting information between the aforementioned components. The communication bus 305 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 305 may be divided into an address bus, a data bus, a control bus, etc.
[0074] Electronic device 300 may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers, and may also be servers.
[0075] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the AI-based factory personnel safety monitoring method described above.
[0076] The computer-readable storage medium may include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0077] The terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.
[0078] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing application concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions claimed in this application.
Claims
1. An AI-based method for monitoring personnel safety in factory areas, characterized in that, include: Acquire current monitoring data and historical monitoring data, wherein the current monitoring data includes equipment operating status data and environmental monitoring data; The historical monitoring data is analyzed based on an AI model to determine the anomaly identification criteria; The anomaly identification criteria are matched based on the equipment operating status data to determine the current identification criteria for each workstation. The current monitoring data is analyzed based on the AI model to determine the current status information; The current anomaly information is determined based on the current status information, the current identification criteria, the environmental monitoring data, and the equipment operating status data; An anomaly management strategy is determined based on the current anomaly information.
2. The method according to claim 1, characterized in that, The process of matching the anomaly identification criteria based on the equipment operating status data to determine the current identification criteria for each workstation includes: Obtain the continuous working hours and cumulative years of service for each employee at each workstation; The anomaly identification criteria are matched based on the continuous working time, the cumulative working years, and the equipment operating status data to determine the current identification criteria for each workstation.
3. The method according to claim 1, characterized in that, The current monitoring data includes video data, audio data, and vibration data. The analysis of the current monitoring data based on the AI model to determine the current state information includes: The video data is analyzed based on the AI model to determine image recognition information; The AI model is used to analyze the sound data to determine sound recognition information; The vibration data is analyzed based on the AI model to determine vibration identification information; The current state information is determined based on the image recognition information, the sound recognition information, and the vibration recognition information.
4. The method according to claim 3, characterized in that, The image recognition information includes employee identification information and group identification information. The step of determining the current anomaly information based on the current status information, the current identification criteria, the environmental monitoring data, and the equipment operating status data includes: The image recognition information is compared with the current recognition standard to determine image anomaly information; The sound recognition information is compared with the current recognition standard to determine sound anomaly information; The vibration identification information is compared with the current identification standard to determine the vibration anomaly information; Analyze the equipment's operating status data to determine any equipment malfunctions; The environmental monitoring data is analyzed to identify environmental anomalies. The current anomaly information is determined based on the image anomaly information, the sound anomaly information, the vibration anomaly information, the equipment anomaly information, and the environmental anomaly information. The current anomaly information includes anomaly type, anomaly range, and anomaly level. The anomaly range includes individual anomalies and group anomalies.
5. The method according to claim 4, characterized in that, The step of determining the anomaly management strategy based on the current anomaly information includes: If the scope of the anomaly is the individual anomaly, then the associated management factors are determined based on the anomaly type; The anomaly level is adjusted based on the aforementioned related management factors; The anomaly management strategy is determined based on the adjusted anomaly level and the current anomaly information.
6. The method according to claim 4, characterized in that, The step of determining the anomaly management strategy based on the current anomaly information includes: If the anomaly range is the group anomaly, then a control strategy is determined based on the anomaly level; Determine whether the anomaly level exceeds a preset anomaly level; If the anomaly level exceeds the preset anomaly level, a device shutdown strategy is determined. The anomaly management strategy is determined based on the control strategy and the equipment linkage shutdown strategy.
7. The method according to claim 1, characterized in that, The method further includes: Obtain historical anomaly information; The historical anomaly information is analyzed to identify high-frequency abnormal workstations and high-frequency abnormal time periods; The monitoring frequency of each workstation in each time period is determined based on the high-frequency abnormal workstation and the high-frequency abnormal time period.
8. An AI-based factory personnel safety monitoring device, characterized in that, include: The monitoring data acquisition module is used to acquire current monitoring data and historical monitoring data, wherein the current monitoring data includes equipment operating status data and environmental monitoring data; The identification standard determination module is used to analyze the historical monitoring data based on the AI model to determine the anomaly identification standard; The identification specification matching module is used to match the anomaly identification specification based on the equipment operating status data to determine the current identification specification for each workstation; The status information determination module is used to analyze the current monitoring data based on the AI model to determine the current status information; An anomaly information determination module is used to determine current anomaly information based on the current status information, the current identification standard, the environmental monitoring data, and the equipment operating status data. The management strategy determination module is used to determine the anomaly management strategy based on the current anomaly information.
9. An electronic device, characterized in that, Includes a processor, which is coupled to a memory; The processor is configured to execute a computer program stored in the memory to cause the electronic device to perform the method as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, It includes a computer program or instructions that, when run on a computer, cause the computer to perform the method as described in any one of claims 1 to 7.