Device Safety Supervision Method, Device and Computer Device for Unmanned Operation Area

Abstract

The present invention discloses a method, device and computer device for equipment safety supervision in an unmanned operation area, belonging to the field of equipment monitoring. The present invention sends a data transmission request to a target Internet of Things to obtain operation equipment information of a target area through the target Internet of Things; uses a preset sensing device and a cloud image acquisition device connected in the target Internet of Things to obtain the working behavior and working image corresponding to each operation equipment in the operation equipment information; obtains the work log of each operation equipment and generates a safety score in combination with the working behavior and the working image; when it is detected that the safety score meets a preset early warning condition, takes the corresponding operation equipment as a target equipment; determines a target notification strategy according to the working behavior of the target equipment; and performs abnormal early warning on the target area according to the target notification strategy. The technical effects of monitoring equipment safety anomalies and safely supervising equipment in an unmanned operation area are achieved.

Description

Technical Field

[0001] The present invention relates to the field of equipment monitoring, and in particular to a method, device and computer equipment for equipment safety supervision in an unmanned operation area. Background Art

[0002] Currently, in multi-unmanned vehicle operations, such as mining, transportation, and dumping operations in mining areas, in order to enable multiple unmanned vehicles to execute operation tasks safely and efficiently in different operations.

[0003] The existing technical methods currently adopted are as follows: By executing independent non-overlapping routes for each unmanned vehicle, intervening manually or remotely when multiple vehicles meet during joint operation, staggering the operation times of multiple vehicles, etc., to ensure that when multiple unmanned vehicles meet in the same operation area (such as loading areas and unloading areas, etc.), there will be no dangerous driving behaviors or parking jams. The defects of the existing methods are as follows: With the increase in the number of unmanned vehicles, especially in narrow operation areas or intersection areas, it is impossible to ensure that non-overlapping paths can be allocated to each unmanned vehicle. At the same time, remote takeover and manual intervention still require a large number of human resources to ensure the execution of operations. And the method of staggering the operation times of multiple vehicles will inevitably lead to a decrease in operation efficiency, and at the same time, in the case of an increase in the number of vehicles, it will lead to traffic jams of multiple vehicles.

[0004] Therefore, how to supervise and warn the equipment safety in the unmanned operation area has become an urgent technical problem to be solved. Summary of the Invention

[0005] The main object of the present invention is to solve the technical problem of supervising and warning the equipment safety in the unmanned operation area.

[0006] To achieve the above object, the present invention provides a method for equipment safety supervision in an unmanned operation area, and the method for equipment safety supervision in the unmanned operation area includes the following steps:

[0007] Send a data transmission request to the target Internet of Things to obtain operation equipment information of the target area through the target Internet of Things;

[0008] Use the preset sensing devices and cloud image acquisition devices connected in the target Internet of Things to obtain the working behaviors and working images corresponding to each operation equipment in the operation equipment information;

[0009] Obtain the work log of each operation equipment and generate a safety score in combination with the working behavior and the working image;

[0010] When it is detected that the safety score meets the preset warning condition, use the corresponding operation equipment as the target equipment;

[0011] Determine a target notification policy according to the working behavior of the target device;

[0012] Perform abnormal early warning on the target area according to the target notification policy.

[0013] Optionally, the step of obtaining the work log of each working device and generating a safety score by combining the working behavior and the working image includes:

[0014] Obtain the work log of each working device;

[0015] Determine the work task information of each working device according to the work log to determine the current working stage;

[0016] Generate a safety score for each working device according to the current working stage, the working behavior, and the working image.

[0017] Optionally, the step of generating a safety score for each working device according to the current working stage, the working behavior, and the working image includes:

[0018] Match in a preset working behavior set according to the current working stage to obtain a set of standard actions;

[0019] Call an image recognition model to recognize and compare the working image to determine the image action difference information of each working device. The image recognition model is a deep learning model pre-trained with device working big data for comparing the similarity of working images;

[0020] Determine the image similarity according to the image action difference information;

[0021] Determine the action similarity according to the working behavior and the set of standard actions;

[0022] Determine the corresponding safety score according to the image similarity and the action similarity.

[0023] Optionally, the step of determining a target notification policy according to the working behavior of the target device includes:

[0024] Determine the cause of the failure according to the working behavior of the target device;

[0025] Query the historical record database according to the cause of the failure to obtain the abnormal record of the target device;

[0026] Determine the abnormal level of the target device according to the abnormal record, the cause of the failure, and a preset diagnosis threshold;

[0027] Match the corresponding target notification level according to the abnormal level;

[0028] Determine a target notification policy based on the target notification level in combination with the work behavior.

[0029] Optionally, the step of determining a target notification policy based on the target notification level in combination with the work behavior includes:

[0030] Obtain the work scenario mode corresponding to the target area;

[0031] Determine the notification content based on the work scenario mode in combination with the work behavior;

[0032] Generate a target notification policy based on the target notification level and the notification content.

[0033] Optionally, the step of performing abnormal early warning on the target area according to the target notification policy includes:

[0034] Obtain the notification restriction conditions of the target area;

[0035] Update the notification method in the target notification policy according to the notification restriction conditions;

[0036] Obtain the notification method and notification content in the current target notification policy;

[0037] Perform abnormal early warning on the target area according to the notification method and the notification content.

[0038] Optionally, after the step of performing abnormal early warning on the target area according to the target notification policy, it further includes:

[0039] Determine abnormal devices according to the target notification policy;

[0040] Obtain the working environment and working record data of the abnormal devices to generate an abnormal work analysis report;

[0041] Store the abnormal work analysis report in the historical abnormal table so that the historical abnormal table generates a fault record about the abnormal devices.

[0042] In addition, to achieve the above object, the present invention also proposes a device safety supervision device for an unmanned operation area, and the device safety supervision device for the unmanned operation area includes:

[0043] An information acquisition module, configured to send a data transmission request to a target Internet of Things to obtain operation device information of a target area through the target Internet of Things;

[0044] A behavior acquisition module, configured to use a preset sensing device and a cloud image acquisition device connected in the target Internet of Things to obtain the work behavior and work image corresponding to each operation device in the operation device information;

[0045] A safety score determination module, configured to obtain the work logs of each of the operation devices and generate a safety score in combination with the work behaviors and the work images;

[0046] A target device determination module, configured to use the corresponding operation device as a target device when it is detected that the safety score meets a preset warning condition;

[0047] A policy determination module, configured to determine a target notification policy according to the work behaviors of the target device;

[0048] An abnormal warning module, configured to perform an abnormal warning on the target area according to the target notification policy.

[0049] In addition, to achieve the above object, the present invention further provides a computer device, where the computer device includes: a memory and a processor, and when the processor runs computer instructions stored in the memory, the processor executes the method described above.

[0050] In addition, to achieve the above object, the present invention further provides a medium, including instructions, and when the instructions run on a computer device, the computer device is caused to execute the method described above.

[0051] The present invention sends a data transmission request to a target Internet of Things to obtain operation device information of a target area through the target Internet of Things; uses a preset sensing device and a cloud image acquisition device connected in the target Internet of Things to obtain work behaviors and work images corresponding to each operation device in the operation device information; obtains the work logs of each operation device and generates a safety score in combination with the work behaviors and the work images; uses the corresponding operation device as a target device when it is detected that the safety score meets a preset warning condition; determines a target notification policy according to the work behaviors of the target device; and performs an abnormal warning on the target area according to the target notification policy. By requesting operation device information from the Internet of Things and generating a safety score by combining feedback and the obtained work logs, work behaviors, and work images, monitoring of device safety anomalies is achieved. At the same time, a notification policy is determined according to work behaviors to achieve the technical effect of safely supervising devices in an unmanned operation area. Description of the Drawings

[0052] Figure 1 It is a schematic structural diagram of a computer device in a hardware operating environment related to the solution of an embodiment of the present application;

[0053] Figure 2 It is a schematic flowchart of a first embodiment of the device safety supervision method for an unmanned operation area of the present application;

[0054] Figure 3It is a schematic flowchart of the second embodiment of the device safety supervision method in the unmanned operation area of the present application;

[0055] Figure 4 It is a structural block diagram of the first embodiment of the device safety supervision device in the unmanned operation area of the present application. Detailed implementation manners

[0056] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] Refer to Figure 1 , Figure 1 It is a schematic structural diagram of a computer device for the hardware operating environment involved in the solution of the embodiment of the present invention.

[0058] As Figure 1 shown, the computer device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0059] Those skilled in the art can understand that Figure 1 the structure shown in

[0060] does not constitute a limitation on the computer device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Figure 1 As

[0061] shown, the memory 1005, as a storage medium, may include an operating system, a network communication module, a user interface module, and a device safety supervision program for the unmanned operation area. Figure 1In the computer device shown, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the computer device of the present invention can be arranged in the computer device. The computer device calls, through the processor 1001, the device safety supervision program stored in the memory 1005 for the unmanned operation area, and executes the device safety supervision method for the unmanned operation area provided by the embodiments of the present invention.

[0062] Embodiments of the present invention provide a device safety supervision method for an unmanned operation area. Refer to Figure 2 , Figure 2 which is a schematic flowchart of the first embodiment of the device safety supervision method for the unmanned operation area of the present invention.

[0063] In this embodiment, the device safety supervision method for the unmanned operation area includes the following steps:

[0064] Step S10: Send a data transmission request to a target Internet of Things to obtain operation device information of a target area through the target Internet of Things.

[0065] It should be noted that in the solution of the present application, each operation device and various monitoring devices in the target area are connected to the target Internet of Things. Each device in the target Internet of Things is connected and data is transmitted through a wireless network, and manual-free data interaction can be achieved.

[0066] It can be understood that the operation device information refers to the correlation information of the devices corresponding to the devices in the target area. It includes the basic information of the operation devices and the working information of the operation devices. In the basic information, the mac address, model, and other characteristic information of the operation devices can be obtained; in the working information, the working data when the operation devices are working can be determined, including action behavior data, working energy consumption data, etc.

[0067] In a specific implementation, when obtaining the operation device information, a device blueprint of the target area can be generated, and the device basic information and the current working state of each operation device will be marked in the device blueprint.

[0068] Step S20: Use the preset sensing devices and cloud image acquisition devices connected in the target Internet of Things to obtain the working behaviors and working images corresponding to each operation device in the operation device information.

[0069] It should be noted that the preset sensing device refers to a related device with the function of obtaining information of the operating device. For example, an image monitoring device can obtain the working behavior of the operating device by means of image recording. The cloud image acquisition device refers to an image acquisition device that is also connected to the target Internet of Things, which can be any type of camera or monitor.

[0070] It can be understood that before obtaining the working behavior corresponding to each operating device in the operating device information, screening will also be performed according to the operating device information. The devices that are not working will be regarded as non-operating devices, and the working behaviors of the screened operating devices will be recorded.

[0071] In a specific implementation, the working behavior of the operating device refers to the corresponding working behavior during the working process of the operating device. For example: charging and discharging behavior, handling behavior or driving behavior, etc.

[0072] It should be noted that the way to obtain the working behavior is realized through the working data generated by the operating device during the working process. For example, the working behavior of the operating device is obtained by obtaining the control instruction signal in the operating device, or the working behavior can be determined by the image acquisition device recording the behavior information of the operating device.

[0073] In a specific implementation, after using the preset sensing device to obtain the working behavior corresponding to each operating device in the operating device information, the working behavior corresponding to each device will be recorded in the work log, and the working behavior information of each device will be determined by calling the work log.

[0074] Step S30: Obtain the work log of each operating device and generate a safety score by combining the working behavior and the working image.

[0075] It should be noted that after obtaining the work log, it will be judged whether it matches the current working behavior in the work log. If it matches, the safety score is zero; if it does not match, the safety score will be generated according to the actual action and the standard action.

[0076] It should be noted that in this embodiment, the higher the safety score, the more serious the abnormal situation of the corresponding operating device.

[0077] It can be understood that when the safety score exceeds the preset threshold, it will be judged that the current working behavior of the operating device is abnormal.

[0078] Further, to generate the safety score, the steps of obtaining the work log of each operating device and generating the safety score in combination with the work behavior and the work image include: obtaining the work log of each operating device; determining the work task information of each operating device according to the work log to determine the current work stage; and generating the safety score of each operating device according to the current work stage, the work behavior, and the work image.

[0079] It should be noted that the work task information of each operating device is determined according to the work log, and the current work stage is determined in the work task information to determine the corresponding standard work behavior. The safety score is obtained by comparing the work behavior with the standard work behavior and combining the work image.

[0080] Further, the steps of generating the safety score of each operating device according to the current work stage, the work behavior, and the work image include: matching in the preset work behavior set according to the current work stage to obtain the set of standard actions; calling an image recognition model to recognize and compare the work image to determine the image action difference information of each operating device, where the image recognition model is a deep learning model pre-trained with device work big data for comparing the similarity of work images; determining the image similarity according to the image action difference information; and determining the corresponding safety score according to the image similarity and the action similarity.

[0081] It should be noted that the image recognition model is a deep learning model trained and optimized with device work big data. Specifically, after the work image is input into the image recognition model, it can automatically output the work behavior corresponding to the work image and the similarity between the work image of the current operating device's behavior and the standard behavior image. Among them, device work big data refers to the work images collected and stored when each operating device is working normally, which can be used as standard images for comparison and recognition. The standard behavior images are pre-stored and maintained in the database of the image recognition model for image comparison and recognition. The higher the image similarity, the more normal the working state of the operating device. On the contrary, the lower the image similarity, the more abnormal the working state of the operating device.

[0082] It can be understood that the action similarity refers to the degree of difference between the work behavior and the set of standard actions. For example, in a certain work stage, the scraper A needs to drive straight at a speed of 20 kilometers per hour. Currently, when obtaining the work behavior of the scraper A, it is found that the current speed of A is 40 kilometers per hour, which does not conform to the normal work behavior, and it can be known that the action similarity is -200.

[0083] It should be noted that action similarity does not necessarily refer to specific action behaviors. When the working behavior of some operating equipment has a small action amplitude or no action amplitude, it will be judged by the working signal data of the equipment, including electrical signals and other generated working signals.

[0084] It is understandable that after the image similarity and action similarity are determined, the safety score corresponding to each operating device can be generated by calculation, specifically: A=q / p. Among them, A is the safety score, q is the action similarity, and p is the image similarity. Therefore, the smaller the value of action similarity, the lower the safety score, and the larger the value of image similarity, the lower the safety score.

[0085] Step S40: When it is detected that the safety score meets the preset warning condition, the corresponding operating equipment is used as the target equipment.

[0086] It should be noted that the preset warning condition is a condition pre-set by the background administrator of this embodiment according to actual usage, and whether the preset warning condition is met is judged by the safety score threshold in the preset warning condition.

[0087] Step S50: Determine the target notification strategy according to the working behavior of the target device.

[0088] It should be noted that the current abnormal situation is determined according to the working behavior of the target device, and the corresponding notification strategy is matched in the preset strategy set according to the abnormal situation. For example: it is currently determined that the operating equipment is traveling too fast, so the preset strategy set will be traversed with the traveling speed being too fast as the traversal condition to determine the corresponding notification strategy, which includes the notification method and notification content and other notification remarks information. The notification method is determined by the corresponding method such as radio broadcast or background information prompt, and the notification content is the content generated specifically for the working behavior. In the case of excessive driving speed, the corresponding notification content can be set to: XXX equipment has exceeded the speed limit, please slow down.

[0089] Step S60: issuing an abnormal warning to the target area according to the target notification strategy.

[0090] Furthermore, in order to implement abnormal warning for the target area, the step of carrying out abnormal warning for the target area according to the target notification strategy includes: obtaining notification restriction conditions for the target area; updating the notification method in the target notification strategy according to the notification restriction conditions; obtaining the notification method and notification content in the current target notification strategy; and carrying out abnormal warning for the target area according to the notification method and the notification content.

[0091] Further, after the step of performing abnormal early warning on the target area according to the target notification policy, the method further includes: determining abnormal devices according to the target notification policy; obtaining the working environment and working record data of the abnormal devices to generate an abnormal work analysis report; and storing the abnormal work analysis report in a historical abnormality table so that the historical abnormality table generates a fault record regarding the abnormal devices.

[0092] In this embodiment, a data transmission request is sent to a target Internet of Things to obtain job device information of a target area through the target Internet of Things; preset sensing devices and cloud image acquisition devices connected in the target Internet of Things are used to obtain the working behaviors and working images corresponding to each job device in the job device information; the work log of each job device is obtained and a safety score is generated in combination with the working behaviors and the working images; when it is detected that the safety score meets a preset early warning condition, the corresponding job device is used as a target device; a target notification policy is determined according to the working behaviors of the target device; and abnormal early warning is performed on the target area according to the target notification policy. By requesting job device information from the Internet of Things and generating a safety score in combination with feedback and the obtained work log, working behaviors, and working images, monitoring of device safety anomalies is achieved. At the same time, a notification policy is determined according to the working behaviors to achieve the technical effect of safely supervising the devices in the unmanned operation area.

[0093] Reference Figure 3 , Figure 3 is a schematic flowchart of the second embodiment of the method for safely supervising devices in an unmanned operation area of the present invention.

[0094] Based on the above first embodiment, step S50 of the method for safely supervising devices in an unmanned operation area of this embodiment further includes:

[0095] Step S501: Determine the cause of the fault according to the working behaviors of the target device.

[0096] It should be noted that the working behaviors of the target device are analyzed, abnormal information is obtained, and the cause of the abnormality is generated in combination with the abnormal information.

[0097] Step S502: Query the historical record database according to the cause of the fault to obtain the abnormal records of the target device.

[0098] It can be understood that the historical record database is a data storage of the work logs / images / data, etc. of each job device stored during the operation of the target Internet of Things. The abnormal records of the target device refer to the records of the abnormal conditions that have been reported by the target device and stored in the background.

[0099] Step S503: Determine the abnormal level of the target device according to the abnormal records, the cause of the fault, and a preset diagnosis threshold.

[0100] It should be noted that the number of faults caused by the fault cause from the last repair or maintenance to the current time is first determined based on the abnormal record, and then the preset diagnostic threshold corresponding to the fault cause is determined based on the fault cause, so as to determine the abnormal level based on the difference between the number of faults caused by the fault cause and the preset diagnostic threshold combined with the weight of the fault cause itself. Among them, different fault causes can correspond to different preset diagnostic thresholds, and the weight of the fault cause itself refers to the pre-set urgency of different fault causes for each individual weight and weight, and the more dangerous the fault cause, the higher the corresponding weight.

[0101] It should be noted that different levels of situations will be generated according to different fault causes, so the abnormality level will be determined according to the specific abnormality cause. In this embodiment, the abnormality levels from low to high correspond to the urgency of the situations that need to be solved from low to high.

[0102] Step S504: Match the corresponding target notification level according to the abnormal level.

[0103] It should be noted that the target notification level refers to the notification efficiency level at the time of notification. The higher the notification level, the more complex the notification channels and notification presentation methods used.

[0104] Step S505: Determine the target notification strategy according to the target notification level and the work behavior.

[0105] Furthermore, in order to improve the rationality of the generation of the target notification strategy, the step of determining the target notification strategy based on the target notification level in combination with the work behavior includes: obtaining the work scene mode corresponding to the target area; determining the notification content based on the work scene mode in combination with the work behavior; generating the target notification strategy based on the target notification level and the notification content.

[0106] It should be noted that different notification methods correspond to different work scenario modes. In the default scenario mode, the default matching logic will be adopted. For example, in the process of dangerous goods production, a dangerous production scenario will be entered and the corresponding notification content will be upgraded.

[0107] It is understandable that driverless technology is a combination of many cutting-edge disciplines such as sensors, computers, artificial intelligence, communications, navigation and positioning, pattern recognition, machine vision, and intelligent control.

[0108] In this embodiment, compared with the open outdoor environment, the underground environment is relatively closed and complex, and GPS technology cannot work in the underground environment. Therefore, there are many solutions to the wireless positioning needs of mines, and the main technical means used include the following:

[0109] ① WiFi technology. In WiFi positioning applications, wireless base stations are installed in an area. According to the signal characteristics of the WiFi device to be located and combined with the topological structure of the wireless base stations, the coordinates of the WiFi device to be located are comprehensively determined. WiFi positioning technology facilitates the realization of the positioning function using existing wireless devices. However, WiFi positioning has natural defects such as poor security, high power consumption, low positioning accuracy, and the spectrum resources are approaching saturation.

[0110] ② Radio frequency identification technology. It is a technology that uses the principle of electromagnetic induction to wirelessly activate a short-range wireless tag and realize information reading. The radio frequency identification distance ranges from a few centimeters to more than a dozen meters. The typical application of RFID for personnel positioning comes from the expansion of the personnel attendance system, mainly for identifying whether a person exists in a certain area, and it cannot achieve real-time tracking and precise positioning. Moreover, there is no standard network system for positioning applications. Therefore, if the continuous positioning requirements in a mine are to be met, the network establishment cost and difficulty are relatively large.

[0111] ③ UWB long-distance positioning technology. UWB (Ultra Wideband) is a carrierless communication technology that uses non-sinusoidal narrow pulses in the nanosecond to microsecond level to transmit data. UWB modulation uses fast-rising and falling pulses with a pulse width in the ns level. The spectrum covered by the pulse ranges from DC to GHz, without the need for the RF frequency conversion required by conventional narrowband modulation. After pulse shaping, it can be directly sent to the antenna for transmission. The spectrum shape can be adjusted through the shape of very narrow continuous single pulses and the characteristics of the antenna load. The radiation of UWB signals is very low, usually only one-thousandth of the radiation of a mobile phone. Therefore, when applied industrially, there is no problem of interfering with other instruments and meters.

[0112] In this embodiment, the fault cause is determined according to the working behavior of the target device; the abnormal level is determined according to the fault cause; the corresponding target notification level is matched according to the abnormal level; and the target notification strategy is determined according to the target notification level combined with the working behavior, achieving the technical effect of accurately generating the target notification strategy and further improving the effectiveness of abnormal warning in the process of safety supervision.

[0113] In addition, an embodiment of the present invention also proposes a medium. A program for device safety supervision in an unmanned operation area is stored on the storage medium. When the program for device safety supervision in the unmanned operation area is executed by a processor, the steps of the method for device safety supervision in the unmanned operation area as described above are implemented.

[0114] Refer to Figure 4 , Figure 4 which is the structural block diagram of the first embodiment of the device safety supervision device in the unmanned operation area of the present invention.

[0115] As Figure 4As shown in the figure, the device safety supervision device for unmanned operation areas proposed in the embodiments of the present invention includes:

[0116] An information acquisition module 10, configured to acquire operation device information of a target area through a preset port;

[0117] A behavior acquisition module 20, configured to acquire the working behavior corresponding to each operation device in the operation device information by using a preset sensing device;

[0118] A safety score determination module 30, configured to acquire the work log of each operation device and generate a safety score in combination with the working behavior;

[0119] A target device determination module 40, configured to use the corresponding operation device as a target device when it is detected that the safety score meets a preset warning condition;

[0120] A policy determination module 50, configured to determine a target notification policy according to the working behavior of the target device;

[0121] An abnormal warning module 60, configured to perform abnormal warning on the target area according to the target notification policy.

[0122] In this embodiment, a data transmission request is sent to a target Internet of Things to acquire operation device information of a target area through the target Internet of Things; a preset sensing device and a cloud image acquisition device connected in the target Internet of Things are used to acquire the working behavior and working image corresponding to each operation device in the operation device information; the work log of each operation device is acquired and a safety score is generated in combination with the working behavior and the working image; when it is detected that the safety score meets a preset warning condition, the corresponding operation device is used as a target device; a target notification policy is determined according to the working behavior of the target device; and an abnormal warning is performed on the target area according to the target notification policy. By requesting operation device information from the Internet of Things and generating a safety score in combination with the feedback and the acquired work log, working behavior and working image, the monitoring of device safety anomalies is realized. At the same time, a notification policy is determined according to the working behavior, thereby achieving the technical effect of safely supervising the devices in the unmanned operation area.

[0123] In one embodiment, the safety score determination module 30 is further configured to acquire the work log of each operation device; determine the work task information of each operation device according to the work log to determine the current working stage; and generate a safety score for each operation device according to the current working stage, the working behavior and the working image.

[0124] In one embodiment, the safety score determination module 30 is further configured to match the current working stage in a preset set of working behaviors to obtain a set of standard actions; call an image recognition model to recognize and compare the working image to determine the image action difference information of each working device, where the image recognition model is a deep learning model pre-trained with device working big data for comparing the similarity of working images; determine the image similarity according to the image action difference information; determine the action similarity according to the working behavior and the set of standard actions; and determine the corresponding safety score according to the image similarity and the action similarity.

[0125] In one embodiment, the policy determination module 50 is further configured to determine the cause of the failure according to the working behavior of the target device; query the historical record database according to the cause of the failure to obtain the abnormal record of the target device; determine the abnormal level of the target device according to the abnormal record, the cause of the failure, and a preset diagnosis threshold; match the corresponding target notification level according to the abnormal level; and determine the target notification policy according to the target notification level and the working behavior.

[0126] In one embodiment, the policy determination module 50 is further configured to obtain the working scenario mode corresponding to the target area; determine the notification content according to the working scenario mode and the working behavior; and generate the target notification policy according to the target notification level and the notification content.

[0127] In one embodiment, the abnormal warning module 60 is further configured to obtain the notification restriction conditions of the target area; update the notification method in the target notification policy according to the notification restriction conditions; obtain the notification method and the notification content in the current target notification policy; and perform abnormal warning on the target area according to the notification method and the notification content.

[0128] In one embodiment, the abnormal warning module 60 is further configured to determine the abnormal device according to the target notification policy; obtain the working environment and the working record data of the abnormal device to generate an abnormal work analysis report; and store the abnormal work analysis report in the historical abnormal table so that the historical abnormal table generates a failure record about the abnormal device.

[0129] It should be understood that the above is only for illustration and does not constitute any limitation to the technical solution of the present invention. In specific applications, those skilled in the art can set according to needs, and the present invention does not limit this.

[0130] It should be noted that the workflow described above is only illustrative and does not limit the protection scope of the present invention. In actual applications, those skilled in the art can select some or all of them according to actual needs to achieve the purpose of the solution of this embodiment, and no limitation is made here.

[0131] In addition, for the technical details not described in detail in this embodiment, reference can be made to the device safety supervision method for unmanned operation areas provided in any embodiment of the present invention, and no further elaboration will be made here.

[0132] In addition, it should be noted that in this article, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or system. Without further limitation, the element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or system including the element.

[0133] The serial numbers of the above embodiments of the present invention are only for description and do not represent the superiority or inferiority of the embodiments.

[0134] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as Read Only Memory (ROM) / RAM, magnetic disk, optical disc), and includes several instructions to enable a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0135] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied to other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for equipment safety supervision in an unmanned operation area, characterized in that, The device safety supervision method for the unmanned operation area includes: Sending a data transmission request to the target Internet of Things to obtain the operation device information of the target area through the target Internet of Things; Using the preset sensing devices and cloud image acquisition devices connected in the target Internet of Things to obtain the working behavior and working image corresponding to each operation device in the operation device information; Obtaining the work log of each operation device and generating a safety score in combination with the working behavior and the working image; When it is detected that the safety score meets the preset warning condition, using the corresponding operation device as the target device; Determining a target notification strategy according to the working behavior of the target device; performing an abnormal warning on the target area according to the target notification strategy; Among them, the step of determining the target notification strategy according to the working behavior of the target device includes: Determining the cause of the failure according to the working behavior of the target device; Querying the historical record database according to the cause of the failure to obtain the abnormal record of the target device; Determining the abnormal level of the target device according to the abnormal record, the cause of the failure and the preset diagnosis threshold; Matching the corresponding target notification level according to the abnormal level; determining the target notification strategy according to the target notification level in combination with the working behavior; Among them, the step of determining the target notification strategy according to the target notification level in combination with the working behavior includes: Obtaining the working scenario mode corresponding to the target area; determining the notification content according to the working scenario mode in combination with the working behavior; Generating a target notification strategy according to the target notification level and the notification content.

2. The device safety supervision method for an unmanned operation area according to claim 1, wherein The step of obtaining the work log of each operation device and generating a safety score in combination with the working behavior and the working image includes: Obtaining the work log of each operation device; Determining the work task information of each operation device according to the work log to determine the current working stage; Generating a safety score for each operation device according to the current working stage, the working behavior and the working image.

3. The device safety supervision method for the unmanned operation area according to claim 2, wherein The step of generating a safety score for each operation device according to the current working stage, the working behavior and the working image includes: Performing matching in the preset working behavior set according to the current working stage to obtain a set of standard actions; Invoking an image recognition model to recognize and compare the working image to determine the image action difference information of each operation device, and the image recognition model is a deep learning model pre-trained by device operation big data for comparing the similarity of working images; Determining the image similarity according to the image action difference information; Determining the action similarity according to the working behavior and the set of standard actions; determining the corresponding safety score according to the image similarity and the action similarity.

4. The method for equipment safety supervision in an unmanned operation area according to claim 1, characterized in that The step of performing an abnormal warning on the target area according to the target notification strategy includes: Obtaining the notification restriction conditions of the target area; Updating the notification method in the target notification strategy according to the notification restriction conditions; obtaining the notification method and notification content in the current target notification strategy; Perform anomaly warning on the target area according to the notification method and the notification content.

5. The method for equipment safety supervision in an unmanned operation area according to claim 1, wherein After the step of performing anomaly warning on the target area according to the target notification strategy, the following steps are further included: Determine abnormal devices according to the target notification strategy; Obtain the working environment and working record data of the abnormal devices to generate an abnormal work analysis report; Store the abnormal work analysis report in the historical anomaly table so that the historical anomaly table generates a fault record about the abnormal devices.

6. An equipment safety supervision device for an unmanned operation area, characterized in that, Execute the method according to claim 1, and the device safety supervision device in the unmanned operation area includes: An information acquisition module, configured to send a data transmission request to a target Internet of Things to acquire operation device information of a target area through the target Internet of Things; A behavior acquisition module, configured to use preset sensing devices and cloud image acquisition devices connected in the target Internet of Things to acquire the working behaviors and working images corresponding to each operation device in the operation device information; A safety score determination module, configured to acquire the work log of each operation device and generate a safety score in combination with the working behaviors and the working images; A target device determination module, configured to use the corresponding operation device as a target device when it is detected that the safety score meets a preset warning condition; A strategy determination module, configured to determine a target notification strategy according to the working behaviors of the target devices; An anomaly warning module, configured to perform anomaly warning on the target area according to the target notification strategy.

7. A computer device, characterized in that, The computer device includes: a memory and a processor, and when the processor runs computer instructions stored in the memory, it executes the method according to any one of claims 1 to 5.

8. A medium, characterized in that, Includes instructions that, when run on a computer device, cause the computer device to execute the method according to any one of claims 1 to 5.

Images