Operation risk management and control method and device based on image recognition, electronic equipment and storage medium

Abstract

The invention discloses an operation risk management and control method and device based on image recognition, electronic equipment and a storage medium. The method comprises the steps that an operation site video of a current operation site is acquired; inputting the operation site video into a preset operation risk type identification model, so that the operation risk type identification model extracts image frames of the operation site video, sequentially performing image feature extraction on the image frames, and performing identification on the extracted image features according to the identification result of the operation site video; comparing the operation risk characteristics with operation risk characteristics of different operation risk types in a preset image characteristic library one by one, and when the operation risk characteristics consistent with the image characteristics are detected, taking the corresponding operation risk type as the operation risk type of the current operation site and outputting the operation risk type; and matching a corresponding operation risk management and control scheme according to the output operation risk type, and then performing risk management and control on the current operation site according to the operation risk management and control scheme. According to the invention, the operation risk management and control efficiency can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of operation risk management and control, and in particular to an operation risk management and control method, device, electronic equipment and storage medium based on image recognition. Background Art

[0002] Operation risk assessment and control is a core component of the safety production risk management system and an important support for ensuring operation safety. The power grid company has established a long-term mechanism for operation risk assessment and control, and has formulated a unified operation risk assessment method. Each work team must conduct an operation risk assessment in advance before each operation task begins, and take corresponding control measures based on the operation risk assessment results.

[0003] In the prior art, a unified risk category benchmark library for operating tasks can be established through historical data on operating risks, so that automatic sorting of operating risk levels can be achieved, and risk categories with higher risk values ​​and corresponding operating links can be screened and customized; at the same time, corresponding matching monitoring measures are formulated for risk categories with higher risk values; then, based on the real-time operating task data on site, the risk category benchmark values ​​of the "risk category benchmark library" are associated and matched, and high-risk operating risk categories are screened and customized; finally, the corresponding monitoring measures are matched and enabled according to the operating risk categories with higher risk values ​​that need to be monitored, so as to achieve key monitoring of operating tasks with higher risk values.

[0004] However, in actual on-site operations, some operations may include dozens of high-risk operations, and the operation time of most operations may last for several hours, or even dozens of hours. The time periods when high-risk operations occur in the operations are relatively random and difficult to determine. Operation risk monitoring personnel cannot set the time in advance and it is difficult to intervene in time. They can only start to use corresponding monitoring measures to intervene in operation risk monitoring after long-term follow-up confirmation by personnel at the corresponding high-risk operation links. This will consume a lot of unnecessary manpower time and is not conducive to improving the effectiveness of operation risk management. Summary of the invention

[0005] The present invention provides an operation risk management method, device, electronic device and storage medium based on image recognition to solve the technical problem that the prior art requires personnel to follow up for a long time to confirm that the corresponding high-risk operation link has been reached, and then the corresponding monitoring measures are started to intervene in the operation risk monitoring, which will consume a lot of unnecessary manpower time and is not conducive to improving the efficiency of operation risk management.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides an operation risk management method based on image recognition, comprising:

[0007] Get the job site video of the current job site;

[0008] The operation site video is input into a preset operation risk type recognition model, so that the operation risk type recognition model extracts image frames of the operation site video, extracts image features from each of the image frames in turn, and compares the extracted image features with operation risk features of different operation risk types in a preset image feature library one by one. When an operation risk feature consistent with the image feature is detected, the corresponding operation risk type is used as the operation risk type of the current operation site and outputted;

[0009] The corresponding operation risk management plan is matched according to the output operation risk type, and then the risk management of the current operation site is carried out according to the operation risk management plan.

[0010] As a preferred solution, the generation of the operation risk characteristics includes:

[0011] Obtaining the work site images corresponding to each work risk type;

[0012] Extracting the work site elements in the work site image and marking the relative positions of the work site elements; wherein the work site elements include: the body shape of a person, the face shape of a person, a safety helmet, a safety belt, a grounding wire, electrical equipment, a base plane, a ladder, and a tunnel;

[0013] According to the operation site elements and the relative positions of the operation site elements, operation risk features corresponding to each operation risk type are generated.

[0014] As a preferred solution, the types of operation risks include: electric shock, falling, power transmission with grounding wires, and poisoning in confined spaces;

[0015] The extracted image features are compared one by one with the operation risk features of different operation risk types in the preset image feature library. When the operation risk features consistent with the image features are detected, the corresponding operation risk type is used as the operation risk type of the current operation site and output, including:

[0016] The extracted image features are compared one by one with the operation risk features of different operation risk types in the preset image feature library;

[0017] When it is detected that the image feature is consistent with the operation risk feature of the electric shock operation risk in the image feature library, the electric shock operation risk is taken as the operation risk type of the current operation site and outputted;

[0018] When it is detected that the image feature is consistent with the operation risk feature of the falling operation risk in the image feature library, the falling operation risk is taken as the operation risk type of the current operation site and outputted;

[0019] When it is detected that the image feature is consistent with the operation risk feature of the power transmission operation with grounding wire in the image feature library, the risk of the power transmission operation with grounding wire is output as the operation risk type of the current operation site;

[0020] When it is detected that the image feature is consistent with the operation risk feature of the confined space poisoning operation risk in the image feature library, the confined space poisoning operation risk is taken as the operation risk type of the current operation site and outputted.

[0021] As a preferred solution, the operational risk characteristics of the electric shock operational risk are: the minimum distance between the person's body and the electrical equipment is less than a preset distance threshold;

[0022] When it is detected that the image feature is consistent with the operation risk feature of the electric shock operation risk in the image feature library, the electric shock operation risk is used as the operation risk type of the current operation site and outputted, including:

[0023] When it is detected that the minimum distance between the person's body and the electrical equipment in the image feature is less than a preset distance threshold, it is determined that the image feature is consistent with the operational risk feature of the electric shock operational risk, and the electric shock operational risk is taken as the operational risk type of the current operational site and output.

[0024] As a preferred solution, the operational risk characteristics of the falling operational risk are: the minimum vertical distance between the personnel's body shape and the base plane is not greater than a preset vertical distance threshold;

[0025] When it is detected that the image feature is consistent with the operation risk feature of the falling operation risk in the image feature library, the falling operation risk is used as the operation risk type of the current operation site and outputted, including:

[0026] When it is detected that the minimum vertical distance between the person's body shape and the base plane in the image feature is not greater than the preset vertical distance threshold, it is determined that the image feature is consistent with the operation risk feature of the falling operation risk, and the falling operation risk is taken as the operation risk type of the current operation site and output.

[0027] As a preferred solution, the risk characteristics of the operation of power transmission with grounding wire are: the personnel hold an insulating rod;

[0028] When it is detected that the image feature is consistent with the operation risk feature of the power transmission operation with grounding wire in the image feature library, the risk of the power transmission operation with grounding wire is used as the operation risk type of the current operation site and outputted, including:

[0029] When it is detected in the image feature that a person is holding an insulating rod, it is determined that the image feature is consistent with the operation risk feature of the operation risk of power transmission with a grounding wire, and the operation risk of power transmission with a grounding wire is taken as the operation risk type of the current operation site and output.

[0030] As a preferred solution, the operational risk characteristics of the confined space poisoning operational risk are: the body proportion of the person entering the tunnel is greater than a preset body proportion threshold;

[0031] When it is detected that the image feature is consistent with the operation risk feature of the confined space poisoning operation risk in the image feature library, the confined space poisoning operation risk is used as the operation risk type of the current operation site and outputted, including:

[0032] When it is detected in the image feature that the body proportion of the person entering the tunnel is greater than a preset body proportion threshold, it is determined that the image feature is consistent with the operational risk feature of the confined space poisoning operation risk, and the confined space poisoning operation risk is taken as the operational risk type of the current work site and output.

[0033] On the basis of the above-mentioned embodiment, another embodiment of the present invention provides a work risk management and control device based on image recognition, comprising: a work site video acquisition module, a work risk type identification module and a current work site risk management and control module;

[0034] The work site video acquisition module is used to acquire the work site video of the current work site;

[0035] The operation risk type identification module is used to input the operation site video into a preset operation risk type identification model, so that the operation risk type identification model extracts image frames of the operation site video, extracts image features from each of the image frames in turn, and compares the extracted image features with operation risk features of different operation risk types in a preset image feature library one by one. When an operation risk feature consistent with the image feature is detected, the corresponding operation risk type is used as the operation risk type of the current operation site and outputted;

[0036] The current operation site risk management and control module is used to match the corresponding operation risk management and control plan according to the output operation risk type, and then perform risk management and control on the current operation site according to the operation risk management and control plan.

[0037] Based on the above embodiments, another embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the operation risk management method based on image recognition described in the above invention embodiment is implemented.

[0038] Based on the above embodiments, another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the operation risk management method based on image recognition described in the above invention embodiment.

[0039] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0040] The present invention provides a method for operation risk control based on image recognition. Compared with the method in the prior art in which personnel continuously follow up to confirm that the corresponding high-risk operation link has been reached, and then the corresponding operation risk control scheme is activated for operation risk control, the present invention does not require personnel to follow up on site, but only needs to obtain the operation site video of the current operation site, and then input the operation site video into a preset operation risk type recognition model. The operation risk type recognition model can extract the image frame of the operation site video, extract image features from each of the image frames in turn, and compare the extracted image features with the operation risk features of different operation risk types in the preset image feature library one by one. When the operation risk features consistent with the image features are detected, it means that the operation site has reached the high-risk operation link at this time, and the corresponding operation risk type is used as the operation risk type of the current operation site and output. Finally, the corresponding operation risk control scheme is matched according to the output operation risk type, and the current operation site is risk controlled.

[0041] The present invention can perform image recognition on the video of the operation site, realize automatic recognition of high-risk operation links, and when the operation risk features consistent with the image features of the video image frame of the operation site are detected, it means that the operation site has reached the high-risk operation link at this time, and the start implementation time of the high-risk operation link can be accurately determined, and then the operation risk management and control scheme corresponding to the high-risk operation link can be automatically matched and called in time to perform risk management. The present invention can realize risk management and control of high-risk operation links in a timely and accurate manner, greatly improving the efficiency of operation risk management and control. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flowchart of an operation risk management method based on image recognition provided by an embodiment of the present invention;

[0043] Figure 2 It is a structural schematic diagram of an operation risk management device based on image recognition provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0046] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0047] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0048] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0049] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0050] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0051] Embodiment 1

[0052] Please refer to Figure 1 , is a flow chart of a method for operation risk management and control based on image recognition provided by an embodiment of the present invention, comprising the following specific steps:

[0053] S1. Obtaining a video of the current operation site;

[0054] Specifically, the present invention provides an operation risk management method based on image recognition. In view of the problems that the high-risk operation links in the past appeared randomly and the time was difficult to determine, the monitoring measures could not be set in advance manually to intervene in the monitoring time, and the operation risk management was time-consuming, labor-intensive and inefficient. In the process of implementing key monitoring of high-risk operation links, based on the screened high-risk operation links, the pre-trained operation risk type recognition model is innovatively used to perform image recognition on the on-site operation video, determine the implementation time of the high-risk operation link, and then automatically match and automatically enable the corresponding monitoring measures, so as to timely and accurately realize the key monitoring of the high-risk operation links, greatly improving the efficiency of operation risk management. Its specific implementation steps include:

[0055] 1. Video acquisition of the operation site:

[0056] For the high-risk work tasks that have been screened out, such as those involving work links with higher risk values ​​such as electric shock, falling, power transmission with grounding wires, and poisoning in confined spaces, cameras are set up to record the entire process of the work site (from starting work to finishing work) to obtain the work site video of the current work site, and transmit the work site video to the smart safety monitoring system of the power grid through the mobile communication system.

[0057] S2. Input the operation site video into a preset operation risk type recognition model, so that the operation risk type recognition model extracts image frames of the operation site video, extracts image features from each of the image frames in turn, and compares the extracted image features with operation risk features of different operation risk types in a preset image feature library one by one. When an operation risk feature consistent with the image feature is detected, the corresponding operation risk type is used as the operation risk type of the current operation site and outputted;

[0058] Preferably, the generation of the operation risk characteristics includes: obtaining the operation site image corresponding to each operation risk type; extracting the operation site elements in the operation site image, and marking the relative position of each of the operation site elements; wherein the operation site elements include: personnel body shape, personnel face shape, safety helmet, safety belt, grounding wire, electrical equipment, base plane, ladder and tunnel; generating the operation risk characteristics corresponding to each operation risk type according to the operation site elements and the relative position of the operation site elements.

[0059] Preferably, the operation risk types include: electric shock, falling, power supply with grounding wire and poisoning in confined space; the extracted image features are compared one by one with the operation risk features of different operation risk types in the preset image feature library, and when the operation risk features consistent with the image features are detected, the corresponding operation risk type is used as the operation risk type of the current operation site and output, including: the extracted image features are compared one by one with the operation risk features of different operation risk types in the preset image feature library; when it is detected that the image features are consistent with the operation risk features of electric shock operation risk in the image feature library, the electric shock operation risk is used as the current operation site. The operation risk type of the previous operation site is determined and output; when it is detected that the image feature is consistent with the operation risk feature of the falling operation risk in the image feature library, the falling operation risk is used as the operation risk type of the current operation site and output; when it is detected that the image feature is consistent with the operation risk feature of the power transmission operation risk with a grounding wire in the image feature library, the power transmission operation risk with a grounding wire is used as the operation risk type of the current operation site and output; when it is detected that the image feature is consistent with the operation risk feature of the confined space poisoning operation risk in the image feature library, the confined space poisoning operation risk is used as the operation risk type of the current operation site and output.

[0060] Preferably, the operating risk characteristic of the electric shock operating risk is: the minimum distance between the person's body and the electrical equipment is less than a preset distance threshold; when it is detected that the image feature is consistent with the operating risk characteristic of the electric shock operating risk in the image feature library, the electric shock operating risk is used as the operating risk type of the current operating site and outputted, including: when it is detected that the minimum distance between the person's body and the electrical equipment in the image feature is less than a preset distance threshold, it is determined that the image feature is consistent with the operating risk characteristic of the electric shock operating risk, and the electric shock operating risk is used as the operating risk type of the current operating site and outputted.

[0061] Preferably, the operation risk characteristic of the falling operation risk is: the minimum vertical distance between the person's body shape and the base plane is not greater than a preset vertical distance threshold; when it is detected that the image feature is consistent with the operation risk characteristic of the falling operation risk in the image feature library, the falling operation risk is used as the operation risk type of the current operation site and output, including: when it is detected that the minimum vertical distance between the person's body shape and the base plane in the image feature is not greater than the preset vertical distance threshold, it is determined that the image feature is consistent with the operation risk characteristic of the falling operation risk, and the falling operation risk is used as the operation risk type of the current operation site and output.

[0062] Preferably, the operation risk feature of the operation risk of power transmission with a grounding wire is: a person holding an insulating rod; when it is detected that the image feature is consistent with the operation risk feature of the operation risk of power transmission with a grounding wire in the image feature library, the operation risk of power transmission with a grounding wire is used as the operation risk type of the current operation site and outputted, including: when it is detected that a person is holding an insulating rod in the image feature, it is determined that the image feature is consistent with the operation risk feature of the operation risk of power transmission with a grounding wire, and the operation risk of power transmission with a grounding wire is used as the operation risk type of the current operation site and outputted.

[0063] Preferably, the operational risk characteristic of the operational risk of poisoning in a confined space is: the body proportion of the person entering the tunnel is greater than a preset body proportion threshold; when it is detected that the image feature is consistent with the operational risk characteristic of the operational risk of poisoning in a confined space in the image feature library, the operational risk of poisoning in a confined space is taken as the operational risk type of the current work site and output, including: when it is detected that the body proportion of the person entering the tunnel in the image feature is greater than a preset body proportion threshold, it is determined that the image feature is consistent with the operational risk characteristic of the operational risk of poisoning in a confined space, and the operational risk of poisoning in a confined space is taken as the operational risk type of the current work site and output.

[0064] 2. Image recognition:

[0065] After transmitting the operation site video to the smart safety monitoring system of the power grid, the system uses large model scene understanding + video labeling technology to perform image recognition on the on-site operation video, realize automatic identification of high-risk operation links, and then accurately determine the start time of high-risk operation links, including:

[0066] The operation site video is input into a preset operation risk type recognition model, so that the operation risk type recognition model extracts the image frames of the operation site video, extracts image features from each of the image frames in turn, and compares the extracted image features with the operation risk features of different operation risk types in the preset image feature library one by one. Once an operation risk feature consistent with the image feature is detected, the corresponding operation risk type is used as the operation risk type of the current operation site and output. When the model outputs the identified operation risk type (label), such as the risk of preventing electric shock, the risk of preventing poisoning in a confined space, etc., it can be determined that it is the start time of the high-risk operation link.

[0067] Among them, the generation of operation risk features of different operation risk types in the image feature library includes: using a recognition model with a model function similar to that of a face recognition system, first manually screening the operation site images of known high-risk operation types, and identifying the features of the operation site elements such as the body shape and face of the personnel in the operation site images, safety helmets, safety belts, grounding wires, electrical equipment, base planes, ladders, tunnels, etc. For example, through face recognition technology, faces can be identified and marked, and then customized as identification names according to the relative positions and position changes between images with different names, to generate operation risk features corresponding to each operation risk type.

[0068] The following is a detailed description of the identification process of the four types of work risks: electric shock, falling, power transmission with grounding wires, and poisoning in confined spaces:

[0069] (1) Identification of anti-electric shock operation links:

[0070] In the video image frame, the minimum distance between the human figure and the electrical equipment (such as transformers, switches, mutual inductors, lightning arresters, line conductors, etc.) is identified. When the minimum distance between the human figure and the electrical equipment in the image feature is less than a preset distance threshold, the image feature is determined to be consistent with the operational risk feature of the electric shock operation risk, and a label of "anti-electric shock operation risk" is output. In a specific embodiment, according to the distance threshold between the human figure and the electrical equipment in the following table 1, when the minimum distance between the human figure and the electrical equipment is close to the value in the following table, a label of "anti-electric shock operation risk" is output.

[0071]

[0072]

[0073] Table 1 Distance thresholds between human figures and electrical equipment

[0074] (2) Identification of fall prevention operations:

[0075] In the video image frame, when it is detected that the minimum vertical distance between the figure of the person and the base plane in the image feature is not greater than the preset vertical distance threshold, it is determined that the image feature is consistent with the operation risk feature of the falling operation risk, and the label of "anti-falling operation risk" is output. In a specific embodiment, when it is detected that the minimum vertical distance between the portrait and the base plane is close to 0.5 times the portrait height, the label of "anti-falling operation risk" can be output.

[0076] (3) Identification of power transmission operation links with grounding wires:

[0077] In the video image frame, when it is detected that a person is holding an insulating rod in the image feature, it is determined that the image feature is consistent with the risk feature of the operation risk of power transmission with grounding wire, and a label of "preventing the risk of power transmission with grounding wire" is output. In a specific embodiment, when it is detected that the electrical equipment is connected with a flexible wire and an insulating rod, and the person is holding the insulating rod, the label of "preventing the risk of power transmission with grounding wire" can be output.

[0078] (4) Identification of anti-poisoning operations in confined spaces:

[0079] In the video image frame, when it is detected that the body proportion of the person entering the tunnel in the image feature is greater than a preset body proportion threshold, the image feature is determined to be consistent with the operation risk feature of the confined space poisoning operation risk, and a label of "preventing confined space poisoning operation risk" is output. In a specific embodiment, when it is detected that 1 / 3 of the human figure has entered the tunnel, the label of "preventing confined space poisoning operation risk" can be output.

[0080] S3. Match the corresponding operation risk management plan according to the output operation risk type, and then perform risk management on the current operation site according to the operation risk management plan.

[0081] 3. On-site operation risk control:

[0082] Based on the image recognition results, the risk types of operations with higher risks are automatically identified for on-site operations, and the risk management and control plans for high-risk operations are automatically matched and called to conduct risk management and control on the current operation site. The monitoring data can be called to implement timely intervention in the case of alarm signals, ensuring that the risks of on-site operations are controllable and under control.

[0083] Embodiment 2

[0084] Please refer to Figure 2 , is a schematic diagram of the structure of an operation risk management and control device based on image recognition provided by an embodiment of the present invention, the device comprising: an operation site video acquisition module, an operation risk type identification module and a current operation site risk management and control module;

[0085] The work site video acquisition module is used to acquire the work site video of the current work site;

[0086] The operation risk type identification module is used to input the operation site video into a preset operation risk type identification model, so that the operation risk type identification model extracts image frames of the operation site video, extracts image features from each of the image frames in turn, and compares the extracted image features with operation risk features of different operation risk types in a preset image feature library one by one. When an operation risk feature consistent with the image feature is detected, the corresponding operation risk type is used as the operation risk type of the current operation site and outputted;

[0087] The current operation site risk management and control module is used to match the corresponding operation risk management and control plan according to the output operation risk type, and then perform risk management and control on the current operation site according to the operation risk management and control plan.

[0088] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0089] Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0090] Embodiment 3

[0091] Accordingly, an embodiment of the present invention provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the image recognition-based operation risk management method described in the above-mentioned embodiment of the invention is implemented.

[0092] The electronic device may be a computing device such as a desktop computer, a notebook, a palmtop computer, a cloud server, etc. The device may include, but is not limited to, a processor and a memory.

[0093] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the device, and various interfaces and lines are used to connect various parts of the entire device.

[0094] Embodiment 4

[0095] Accordingly, an embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the job risk management method based on image recognition described in the above-mentioned embodiment of the invention.

[0096] The memory can be used to store the computer program, and the processor realizes various functions of the device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0097] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the steps of each method embodiment described above can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0098] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for operation risk management based on image recognition, characterized in that: include: Get the job site video of the current job site; The operation site video is input into a preset operation risk type recognition model, so that the operation risk type recognition model extracts image frames of the operation site video, extracts image features from each of the image frames in turn, and compares the extracted image features with operation risk features of different operation risk types in a preset image feature library one by one. When an operation risk feature consistent with the image feature is detected, the corresponding operation risk type is used as the operation risk type of the current operation site and outputted; The corresponding operation risk management plan is matched according to the output operation risk type, and then the risk management of the current operation site is carried out according to the operation risk management plan.

2. The method for controlling operational risks based on image recognition according to claim 1, characterized in that: The generation of the operational risk characteristics includes: Obtaining the work site images corresponding to each work risk type; Extracting the work site elements in the work site image and marking the relative positions of the work site elements; wherein the work site elements include: the body shape of a person, the face shape of a person, a safety helmet, a safety belt, a grounding wire, electrical equipment, a base plane, a ladder, and a tunnel; According to the operation site elements and the relative positions of the operation site elements, operation risk features corresponding to each operation risk type are generated.

3. The method for controlling operation risks based on image recognition according to claim 2, characterized in that: The types of work risks include: electric shock, falling, power transmission with grounding wires, and poisoning in confined spaces; The extracted image features are compared one by one with the operation risk features of different operation risk types in the preset image feature library. When the operation risk features consistent with the image features are detected, the corresponding operation risk type is used as the operation risk type of the current operation site and output, including: The extracted image features are compared one by one with the operation risk features of different operation risk types in the preset image feature library; When it is detected that the image feature is consistent with the operation risk feature of the electric shock operation risk in the image feature library, the electric shock operation risk is taken as the operation risk type of the current operation site and outputted; When it is detected that the image feature is consistent with the operation risk feature of the falling operation risk in the image feature library, the falling operation risk is taken as the operation risk type of the current operation site and outputted; When it is detected that the image feature is consistent with the operation risk feature of the power transmission operation with grounding wire in the image feature library, the risk of the power transmission operation with grounding wire is taken as the operation risk type of the current operation site and outputted; When it is detected that the image feature is consistent with the operation risk feature of the confined space poisoning operation risk in the image feature library, the confined space poisoning operation risk is taken as the operation risk type of the current operation site and outputted.

4. The method for controlling operation risks based on image recognition according to claim 3, characterized in that: The operational risk characteristics of the electric shock operation risk are: the minimum distance between the person's body and the electrical equipment is less than a preset distance threshold; When it is detected that the image feature is consistent with the operation risk feature of the electric shock operation risk in the image feature library, the electric shock operation risk is used as the operation risk type of the current operation site and outputted, including: When it is detected that the minimum distance between the person's body and the electrical equipment in the image feature is less than a preset distance threshold, it is determined that the image feature is consistent with the operational risk feature of the electric shock operational risk, and the electric shock operational risk is taken as the operational risk type of the current operational site and output.

5. The method for controlling operation risks based on image recognition according to claim 3, characterized in that: The operational risk characteristics of the falling operational risk are: the minimum vertical distance between the personnel's body shape and the base plane is not greater than a preset vertical distance threshold; When it is detected that the image feature is consistent with the operation risk feature of the falling operation risk in the image feature library, the falling operation risk is used as the operation risk type of the current operation site and outputted, including: When it is detected that the minimum vertical distance between the person's body shape and the base plane in the image feature is not greater than the preset vertical distance threshold, it is determined that the image feature is consistent with the operation risk feature of the falling operation risk, and the falling operation risk is taken as the operation risk type of the current operation site and output.

6. The method for controlling operation risks based on image recognition according to claim 3, characterized in that: The operational risk characteristics of the risk of power transmission operation with grounding wire are: personnel holding an insulating rod; When it is detected that the image feature is consistent with the operation risk feature of the power transmission operation with grounding wire in the image feature library, the risk of the power transmission operation with grounding wire is used as the operation risk type of the current operation site and outputted, including: When it is detected in the image feature that a person is holding an insulating rod, it is determined that the image feature is consistent with the operation risk feature of the operation risk of power transmission with a grounding wire, and the operation risk of power transmission with a grounding wire is taken as the operation risk type of the current operation site and output.

7. The method for controlling operation risks based on image recognition according to claim 3, characterized in that: The operational risk characteristics of the confined space poisoning operational risk are: the body proportion of the person entering the tunnel is greater than a preset body proportion threshold; When it is detected that the image feature is consistent with the operation risk feature of the confined space poisoning operation risk in the image feature library, the confined space poisoning operation risk is used as the operation risk type of the current operation site and outputted, including: When it is detected in the image feature that the body proportion of the person entering the tunnel is greater than a preset body proportion threshold, it is determined that the image feature is consistent with the operational risk feature of the confined space poisoning operational risk, and the confined space poisoning operational risk is taken as the operational risk type of the current work site and output.

8. An operation risk management and control device based on image recognition, characterized in that: include: Operation site video acquisition module, operation risk type identification module and current operation site risk management and control module; The operation site video acquisition module is used to acquire the operation site video of the current operation site; The operation risk type identification module is used to input the operation site video into a preset operation risk type identification model, so that the operation risk type identification model extracts image frames of the operation site video, extracts image features from each of the image frames in turn, and compares the extracted image features with operation risk features of different operation risk types in a preset image feature library one by one. When an operation risk feature consistent with the image feature is detected, the corresponding operation risk type is used as the operation risk type of the current operation site and outputted; The current operation site risk management and control module is used to match the corresponding operation risk management and control plan according to the output operation risk type, and then perform risk management and control on the current operation site according to the operation risk management and control plan.

9. An electronic device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the operation risk management method based on image recognition as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the operation risk management method based on image recognition as described in any one of claims 1 to 7.

Images