Hidden health hazard identification method for power grid operating personnel

Abstract

The invention discloses a potential health hazard identification method for power grid operating personnel, and the method comprises the following steps: obtaining the information of the power grid operating personnel based on the power grid operating personnel distributed by an operation work order; acquiring first state information of the power grid operating personnel through face recognition equipment, and acquiring second state information of the power grid operating personnel through wearable equipment; constructing a first judgment model, and obtaining a first judgment result by taking the first state information as the input of the first judgment model; and constructing a second judgment model, and obtaining a second judgment result based on the second state information and the power grid operator information as input of the second judgment model.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power personnel monitoring, and in particular to a method for identifying health hazards of power grid operators. Background Art

[0002] As power companies are constantly developing and innovating in management. The work site is a place where operators directly contact electrical equipment and carry out various inspections and maintenance. How to further improve the work quality and work efficiency at the work site and ensure personal safety during operations has become a hot issue of common concern to many power supply companies. The existing safety management system and methods have always remained at the level of eliminating hidden dangers. Generally, on-site personnel inspections or remote monitoring through on-site monitoring equipment are used to remind and intervene when problems or possible problems are found. It can be seen that the existing safety management is mostly managed for equipment, but the current attention to the health and safety monitoring of operators themselves is still not enough. When power grid operators perform power operations, they are usually dangerous and usually have special power actions such as climbing and falling. If power operators suddenly lose consciousness due to their own health problems when performing special power actions, it is very easy to miss the rescue time. Summary of the invention

[0003] In view of the above-mentioned prior art, the present invention provides a method for identifying health risks of power grid workers, mainly to solve the technical problems existing in the above-mentioned background technology.

[0004] To achieve the above object, the technical solution of the embodiment of the present invention is implemented as follows: a method for identifying health hazards of power grid operators, the method comprising the following steps:

[0005] Based on the grid operation personnel assigned by the work order, obtain the grid operation personnel information;

[0006] Acquire first status information of the power grid operator through a facial recognition device, and acquire second status information of the power grid operator through a wearable device;

[0007] Constructing a first judgment model, taking the first state information as input of the first judgment model, and obtaining a first judgment result;

[0008] A second judgment model is constructed, and a second judgment result is obtained based on the second state information and the power grid operator information as inputs of the second judgment model.

[0009] Optionally, based on the grid operator assigned by the work order, the grid operator information is obtained, specifically including: based on the grid operator list determined by the work order, the corresponding personnel's pre-stored facial information and basic information are obtained from the list library.

[0010] Optionally, the first status information of the power grid operator is obtained through facial device recognition, and the power grid operator information is verified, specifically including: when the power grid worker arrives at the work place, the facial image is obtained through facial device recognition, and the facial image is compared and reviewed with the pre-stored facial information. After the comparison and review is passed, the power grid operator performs the work normally.

[0011] Optionally, constructing a first judgment model, taking the first state information as an input of the first judgment model, and obtaining a first judgment result, specifically comprising: the first judgment model comprises a recognition part, a cutting part, and a health recognition part, wherein the recognition part constructs a portrait recognition network, and the pre-stored facial information and the facial image are simultaneously input into the portrait recognition network, and the portrait recognition network is used to judge whether the facial image is consistent with the pre-stored facial information, thereby outputting a first comparison result;

[0012] The cutting part constructs a portrait cutting network, inputs the face image into the portrait cutting network, and outputs an eye state image and a mouth state image in the face image;

[0013] The health recognition part constructs a first health judgment network and a second health judgment network. The eye status picture and the mouth status picture are input into the first health judgment network to obtain a first health result, and the face image is input into the second health judgment network to obtain a second health result.

[0014] Optionally, an encoder and a decoder are constructed in the second health judgment network, and a block fusion unit is constructed in the encoder to perform auxiliary feature extraction. The block fusion unit extracts a feature map containing only red light, green light, and blue light from the input face image, and the decoder outputs a second health result based on the extracted feature map of red light, green light, and blue light.

[0015] Optionally, the wearable device includes a left-hand positioning bracelet and a right-hand positioning bracelet with heart rate and blood pressure collection functions, and the left-hand positioning bracelet and the right-hand positioning bracelet are both connected to the mobile terminal signal, and the heart rate and blood pressure information and the left hand three-dimensional position coordinates and the right hand three-dimensional position coordinates at different time nodes are collected by the left-hand positioning bracelet and the right-hand positioning bracelet. The mobile terminal sends the collected heart rate and blood pressure information and the left hand three-dimensional position coordinates and the right hand three-dimensional position coordinates at different time nodes to the second judgment model located in the cloud

[0016] Optionally, a second judgment result is obtained based on the second state information and the power grid operation personnel information as inputs of the second judgment model, specifically including: based on the work task corresponding to the work order, obtaining the left-hand coordinate difference threshold and the right-hand coordinate difference threshold corresponding to the work task from the position coordinate library, and obtaining the coordinate change of the left-hand three-dimensional position according to the left-hand three-dimensional position coordinates at different time nodes, obtaining the coordinate change of the right-hand three-dimensional position according to the right-hand three-dimensional position coordinates at different time nodes, comparing the coordinate change of the left-hand three-dimensional position with the left-hand coordinate difference threshold, and comparing the coordinate change of the right-hand three-dimensional position with the right-hand coordinate difference threshold.

[0017] Optionally, a heart rate difference is obtained based on the acquired heart rate information, and the heart rate difference is compared with a heart rate difference threshold in a heart rate database; if the difference between two heart rate data at different times is within the heart rate difference threshold, the average of the heart rate monitoring results of the two is taken as the heart rate of the operator; if the difference between the two heart rate data is above a set value, a potential abnormal reading risk warning is issued.

[0018] Optionally, if the coordinate change of the three-dimensional position of the right hand, the coordinate change of the three-dimensional position of the left hand, the heart rate difference and the blood pressure data all exceed the corresponding thresholds, it is determined that the operator is in danger.

[0019] The beneficial effects of the present invention are as follows: the method for identifying health hazards of power grid workers provided in the present application combines the content of the work ticket, on-site operation risks, and personnel status information to realize the identity recognition of the workers before the power operation, and during the operation, the health status can be judged by the portrait information of the workers, and the changes in the coordinate positions of the left and right hands recorded by the wearable device can be used to judge whether the workers themselves are in an abnormal state or a normal state. In addition, when the workers are in an abnormal state, the mobile terminal worn by the workers can send out an alarm signal in time, and provide medical services to the corresponding location through medical institutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 Schematic diagram of a flow chart of a method for identifying health hazards for power grid operators in an embodiment of the present application. DETAILED DESCRIPTION

[0021] The technical solution of the present invention is further elaborated in detail below in conjunction with the drawings and specific embodiments of the specification. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention. In the following description, the expression "some embodiments" is related to a subset of all possible embodiments, but it should be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0022] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is apparent to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features well known in the art are not described.

[0023] It should be understood that the present invention can be implemented in different forms and should not be interpreted as being limited to the embodiments proposed herein. On the contrary, providing these embodiments will make the disclosure thorough and complete, and the scope of the present invention will be fully conveyed to those skilled in the art. And the purpose of the terms used herein is only to describe specific embodiments and is not intended to be a limitation of the present invention. When used herein, the singular forms of "one", "one" and "said / the" are also intended to include plural forms, unless the context clearly indicates another way. It should also be understood that the terms "compose" and / or "include" when used in this specification determine the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, parts and / or groups. When used herein, the term "and / or" includes any and all combinations of the relevant listed items.

[0024] It should also be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "inside", "outside", "left", "right" and similar expressions used herein are for illustrative purposes only and are not intended to be the only implementation method.

[0025] In order to fully understand the present invention, a detailed structure will be proposed in the following description to illustrate the technical solution proposed by the present invention. The optional embodiments of the present invention are described in detail as follows, but in addition to these detailed descriptions, the present invention may also have other implementations.

[0026] Please refer to the attached Figure 1 The present application provides a method for identifying health hazards of power grid operators, the method comprising the following steps:

[0027] S1. Based on the power grid operator assigned by the work order, obtain the power grid operator information.

[0028] During the specific implementation, the facial information and basic information of all power grid operators in a certain area are first collected and pre-stored. When the power grid work order distribution system distributes work orders, it will send the corresponding operator's facial information and basic information, and task work orders to the corresponding power grid operator's mobile terminal.

[0029] S2. Obtaining first status information of the power grid operator through a facial recognition device, and obtaining second status information of the power grid operator through a wearable device;

[0030] The first state information includes facial image information of the power grid operator, and the second state information includes left hand coordinate information, right hand coordinate information, heart rate information and blood pressure information;

[0031] The wearable device includes a left-hand positioning bracelet and a right-hand positioning bracelet with heart rate and blood pressure collection functions. The left-hand positioning bracelet and the right-hand positioning bracelet are both connected to the mobile terminal signal. The left-hand positioning bracelet and the right-hand positioning bracelet collect heart rate, blood pressure information and the three-dimensional position coordinates of the left hand and the three-dimensional position coordinates of the right hand at different time nodes.

[0032] S3, constructing a first judgment model, using the first state information as input of the first judgment model, and obtaining a first judgment result;

[0033] The first judgment model constructed by it includes an identification part, a cutting part and a health identification part, wherein the identification part constructs a portrait recognition network. In specific implementation, when the power grid operator arrives at the work site, the facial recognition device on the mobile terminal collects his own facial image information, and the pre-stored facial information and facial image are simultaneously input into the portrait recognition network. The portrait recognition network determines whether the facial image is consistent with the pre-stored facial information. If the comparison is consistent, it means that after the comparison review is passed, the identity verification of the operator is correct, and the power grid operator can perform the work normally.

[0034] Furthermore, the cutting part constructs a portrait cutting network, inputs the face image into the portrait cutting network, and outputs an eye state picture and a mouth state picture in the face image;

[0035] A first health judgment network and a second health judgment network are constructed in the health identification part, and the eye status picture and the mouth status picture are input into the first health judgment network to obtain a first health result. Exemplarily, the length of the human eye is determined by the eye status picture, the width of the human eye is determined according to the eye status picture, or the eye closure degree, pupil dilation degree, eyebrow curvature, etc. are obtained. The first health judgment network obtains and outputs different health scores based on the above characteristics. When the health score is lower than the first preset health value, the judgment result output by the first health judgment network is a first-level unhealthy state. When the health score is lower than the second preset health value, the judgment result output by the first health judgment network is a second-level unhealthy state. When the health score is lower than the third preset health value, the judgment result output by the first health judgment network is a third-level unhealthy state. When the health score is greater than the third preset health value, the judgment result output by the first health judgment network is a healthy state.

[0036] Furthermore, an encoder and a decoder are constructed in the second health judgment network, and a block fusion unit is constructed in the encoder to perform auxiliary feature extraction. The block fusion unit extracts a feature map containing only red light, green light, and blue light from the input face image, and the decoder outputs a second health result based on the extracted feature map of red light, green light, and blue light. Specifically, the facial skin color will change slightly with the heartbeat. That is, in the microvessels of human skin tissue, the blood flow will change periodically with the heartbeat. The hemoglobin in the blood has a strong absorption of green light, so the skin's reflection of green light will also change periodically. Therefore, the decoder outputs a second health result based on the extracted feature map of red light, green light, and blue light.

[0037] S4. Construct a second judgment model, and obtain a second judgment result based on the second state information and the power grid operator information as inputs of the second judgment model.

[0038] When the mobile terminal sends the above-mentioned collected heart rate, blood pressure information and the left hand three-dimensional position coordinates and right hand three-dimensional position coordinates at different time nodes to the second judgment model located in the cloud, the left hand coordinate difference threshold and the right hand coordinate difference threshold corresponding to the work task are obtained from the position coordinate library, and the coordinate change of the left hand three-dimensional position is obtained according to the left hand three-dimensional position coordinates at different time nodes, and the coordinate change of the right hand three-dimensional position is obtained according to the right hand three-dimensional position coordinates at different time nodes. The coordinate change of the left hand three-dimensional position is compared with the left hand coordinate difference threshold, and the coordinate change of the right hand three-dimensional position is compared with the right hand coordinate difference threshold.

[0039] Furthermore, a heart rate difference is obtained based on the acquired heart rate information, and the heart rate difference is compared with the heart rate difference threshold in the heart rate database. If the difference between two heart rate data at different times is within the heart rate difference threshold, the average of the heart rate monitoring results of the two is taken as the heart rate of the operator; if the difference between the two heart rate data is above the set value, a potential abnormal reading risk warning is issued.

[0040] Furthermore, if the coordinate change of the three-dimensional position of the right hand, the coordinate change of the three-dimensional position of the left hand, the heart rate difference and the blood pressure data all exceed the corresponding thresholds, it is judged that the operator is in danger. At this time, the mobile terminal worn by the power operator will promptly send an alarm signal and provide medical services to the corresponding location through medical institutions.

[0041] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. The protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for identifying health hazards of power grid workers, characterized in that: The method comprises the following steps: Based on the grid operation personnel assigned by the work order, obtain the grid operation personnel information; Acquire first status information of the power grid operator through a facial recognition device, and acquire second status information of the power grid operator through a wearable device; Constructing a first judgment model, taking the first state information as input of the first judgment model, and obtaining a first judgment result; A second judgment model is constructed, and a second judgment result is obtained based on the second state information and the power grid operator information as inputs of the second judgment model.

2. A method for identifying health hazards of power grid workers according to claim 1, characterized in that: Based on the power grid operation personnel assigned by the work order, the power grid operation personnel information is obtained, specifically including: based on the list of power grid operation personnel determined by the work order, the pre-stored facial information and basic information of the corresponding personnel are obtained from the list library.

3. A method for identifying health risks of power grid workers according to claim 1, characterized in that: The first status information of the power grid operator is obtained through facial device recognition, and the information of the power grid operator is verified, specifically including: when the power grid worker arrives at the work place, the facial image is obtained through facial device recognition, and the facial image is compared and reviewed with the pre-stored facial information. After the comparison and review is passed, the power grid operator performs the work normally.

4. A method for identifying health hazards of power grid operators according to claim 1, characterized in that: Constructing a first judgment model, taking the first state information as an input of the first judgment model, and obtaining a first judgment result, specifically comprising: the first judgment model comprises a recognition part, a cutting part, and a health recognition part, wherein the recognition part constructs a portrait recognition network, inputs the pre-stored facial information and the facial image into the portrait recognition network at the same time, and judges through the portrait recognition network whether the facial image is consistent with the pre-stored facial information, thereby outputting a first comparison result; The cutting part constructs a portrait cutting network, inputs the face image into the portrait cutting network, and outputs an eye state image and a mouth state image in the face image; The health recognition part constructs a first health judgment network and a second health judgment network. The eye status picture and the mouth status picture are input into the first health judgment network to obtain a first health result, and the face image is input into the second health judgment network to obtain a second health result.

5. A method for identifying health hazards of power grid workers according to claim 4, characterized in that: An encoder and a decoder are constructed in the second health judgment network. A block fusion unit is constructed in the encoder to perform auxiliary feature extraction. The block fusion unit extracts a feature map containing only red light, green light, and blue light from the input face image. The decoder outputs a second health result based on the extracted feature map of red light, green light, and blue light.

6. A method for identifying health hazards of power grid operators according to claim 1, characterized in that: The wearable device includes a left-hand positioning bracelet and a right-hand positioning bracelet with heart rate and blood pressure collection functions. The left-hand positioning bracelet and the right-hand positioning bracelet are both connected to the mobile terminal signal. The heart rate and blood pressure information as well as the three-dimensional position coordinates of the left hand and the three-dimensional position coordinates of the right hand at different time nodes are collected through the left-hand positioning bracelet and the right-hand positioning bracelet. The mobile terminal sends the aforementioned collected heart rate and blood pressure information as well as the three-dimensional position coordinates of the left hand and the three-dimensional position coordinates of the right hand at different time nodes to a second judgment model located in the cloud.

7. A method for identifying health hazards of power grid workers according to claim 6, characterized in that: A second judgment result is obtained based on the second state information and the power grid operation personnel information as inputs of the second judgment model, specifically including: based on the work task corresponding to the work order, obtaining the left-hand coordinate difference threshold and the right-hand coordinate difference threshold corresponding to the work task from the position coordinate library, and obtaining the coordinate change of the left-hand three-dimensional position according to the left-hand three-dimensional position coordinates at different time nodes, obtaining the coordinate change of the right-hand three-dimensional position according to the right-hand three-dimensional position coordinates at different time nodes, comparing the coordinate change of the left-hand three-dimensional position with the left-hand coordinate difference threshold, and comparing the coordinate change of the right-hand three-dimensional position with the right-hand coordinate difference threshold.

8. A method for identifying health hazards of power grid workers according to claim 7, characterized in that: The heart rate difference is obtained based on the acquired heart rate information, and the heart rate difference is compared with the heart rate difference threshold in the heart rate database. If the difference between the two heart rate data at different times is within the heart rate difference threshold, the average of the heart rate monitoring results of the two is taken as the heart rate of the operator; if the difference between the two heart rate data is above the set value, a potential abnormal reading risk warning is issued.

9. A method for identifying health hazards of power grid workers according to claim 8, characterized in that: If the coordinate change of the three-dimensional position of the right hand, the coordinate change of the three-dimensional position of the left hand, the heart rate difference and the blood pressure data all exceed the corresponding thresholds, it is determined that the operator is in danger.

Images