Near-electricity warning method and system based on intelligent safety helmet and medium

Abstract

The invention discloses a near-electricity warning method and system based on an intelligent safety helmet and a medium, and relates to the technical field of safety helmet warning. The method comprises the following steps: performing scene data acquisition on a target scene, and establishing a scene danger map; after the intelligent safety helmet is activated and started, updating the scene danger map to the intelligent safety helmet, and generating positioning data through a UWB positioning chip of the intelligent safety helmet; according to the positioning data and the scene danger map, carrying out near-electricity alarm identification, and generating first alarm information; activating an electric field sensing sensor group of the intelligent safety helmet to execute electric field direction identification, and establishing an electric field direction identification result; user motion trend analysis is carried out by using the electric field direction identification result, and second alarm information is established; and after carrying out alarm fusion on the first alarm information and the second alarm information, reporting an abnormal alarm. The technical problem of insufficient alarm accuracy and timeliness in the prior art is solved, and the technical effect of improving the alarm accuracy and timeliness is achieved.

Description

Technical Field

[0001] This invention relates to the field of safety helmet alarm technology, specifically to a proximity alarm method, system, and medium based on smart safety helmets. Background Technology

[0002] In high-voltage work scenarios such as power line inspection and construction maintenance, workers often face the risk of electric shock due to proximity to high-voltage power equipment or live conductors. To ensure operational safety, various proximity warning devices based on electric field sensing, wireless positioning, or audible and visual alarms have been proposed in existing technologies. However, these solutions often suffer from drawbacks such as limited alarm methods, low positioning accuracy, and insufficient directional sensing capabilities, making it difficult to identify the dangerous proximity relationship between personnel and power sources in a timely and accurate manner, and thus failing to effectively prevent accidents. Especially in dynamic and complex environments, the displacement trend of workers and the electric field distribution in hazardous areas cannot be fully perceived, leading to delayed alarms or frequent false alarms. Summary of the Invention

[0003] This application provides a proximity alarm method, system, and medium based on a smart safety helmet, which solves the technical problems of insufficient alarm accuracy and timeliness in the prior art.

[0004] The first aspect of this application provides a proximity alarm method based on a smart safety helmet, the method comprising:

[0005] Scene data is collected for the target scene to establish a scene hazard map, which includes location scene hazard value markers. When the smart safety helmet is activated, the scene hazard map is updated to the smart safety helmet, and positioning data is generated through the UWB positioning chip of the smart safety helmet. Based on the positioning data and the scene hazard map, a proximity alarm is identified, generating a first alarm message. The electric field sensing sensor group of the smart safety helmet is activated to perform electric field direction recognition, establishing an electric field direction recognition result. The electric field sensing sensor group includes at least three electric field sensing units and an attitude sensing unit, with the electric field sensing units equidistantly arranged on the circumferential structure of the smart safety helmet. The user's movement trend is analyzed using the electric field direction recognition result, establishing a second alarm message. After fusing the first and second alarm messages, an abnormal alarm is reported.

[0006] A second aspect of this application provides a proximity alarm system based on a smart safety helmet, the system comprising:

[0007] Map Building Module: Collects scene data of the target scene and builds a scene hazard map, which is set with location scene hazard value markers; Map Update Module: When the smart safety helmet is activated, it updates the scene hazard map to the smart safety helmet and generates positioning data through the UWB positioning chip of the smart safety helmet; Alarm Recognition Module: Based on the positioning data and the scene hazard map, it performs near-electric alarm recognition and generates a first alarm message; Electric Field Direction Recognition Module: Activates the electric field sensing sensor group of the smart safety helmet to perform electric field direction recognition and establishes an electric field direction recognition result, wherein the electric field sensing sensor group includes at least three electric field sensing units and an attitude sensing unit, and the electric field sensing units are equidistantly arranged on the circumferential structure of the smart safety helmet; Motion Trend Analysis Module: Analyzes the user's motion trend using the electric field direction recognition result and establishes a second alarm message; Anomaly Alarm Module: After fusing the first alarm message and the second alarm message, it reports an anomaly alarm.

[0008] A third aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the proximity alarm method based on a smart safety helmet provided in this application.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] First, scene data is collected for the target scenario to create a scene hazard map, which includes location hazard value markers. When the smart helmet is activated, the scene hazard map is updated to the helmet, and location data is generated using the helmet's UWB positioning chip. Next, based on the location data and the scene hazard map, a proximity alarm is identified, generating a first alarm message. The electric field sensing sensor group of the smart helmet is activated to perform electric field direction recognition, establishing an electric field direction recognition result. This electric field sensing sensor group includes at least three electric field sensing units and an attitude sensing unit, with the electric field sensing units equidistantly distributed on the circumferential structure of the smart helmet. Then, the user's movement trend is analyzed using the electric field direction recognition result, generating a second alarm message. Finally, the first and second alarm messages are fused to issue an abnormal alarm. This solves the technical problems of insufficient alarm accuracy and timeliness in existing technologies, achieving the technical effect of improving alarm accuracy and timeliness. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 A schematic flowchart of a proximity alarm method based on a smart safety helmet provided in this application embodiment;

[0013] Figure 2 This is a schematic diagram of the proximity alarm system based on a smart safety helmet provided in an embodiment of this application.

[0014] Figure labeling: Map creation module 11, Map update module 12, Alarm identification module 13, Electric field direction identification module 14, Motion trend analysis module 15, Anomaly alarm module 16. Detailed Implementation

[0015] This application solves the technical problems of insufficient accuracy and timeliness of alarms in the prior art by providing a proximity alarm method, system and medium based on smart safety helmets.

[0016] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0017] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0018] Example 1, as Figure 1 As shown, this application provides a proximity alarm method based on a smart safety helmet, wherein the method includes:

[0019] Scene data is collected from the target scene to create a scene hazard map, which is marked with location scene hazard value identifiers.

[0020] In this embodiment, multiple sensing devices are deployed in the target work area to comprehensively collect data on the target scene. These sensing devices include, but are not limited to, industrial cameras, LiDAR, and electric field monitoring sensors. Industrial cameras are used to collect image information of key areas in the scene, LiDAR is used to build a high-precision 3D spatial model, and electric field monitoring sensors are used to acquire electric field intensity distribution data at various sampling points within the space. Within a set periodic acquisition time window, the aforementioned sensing devices are controlled to work collaboratively to acquire a complete spatial scene dataset and a spatial electric field dataset. After data acquisition is completed, a spatial registration operation is performed to unify and fuse spatial scene information and electric field information from different sensor sources. By mapping the collected electric field intensity values ​​to corresponding spatial location points, a scene hazard map containing the spatial structure and electric field distribution relationship is established. Subsequently, based on a set safe electric field threshold, the mapped electric field intensity values ​​are compared to determine whether there are high-risk electric field areas exceeding the safe threshold at each location point, and corresponding location scene hazard value markers are added to these locations on the scene hazard map.

[0021] Furthermore, scene data is collected from the target scene to create a scene hazard map, including:

[0022] Install sensing devices for data acquisition, including industrial cameras, lidar, and electric field monitoring sensors; activate the sensing devices within a predetermined periodic window to perform data acquisition of the target scene, and establish a spatial scene dataset and a spatial electric field dataset; after spatial registration of the spatial scene dataset and the spatial electric field dataset, establish a scene hazard map.

[0023] First, sensing devices for environmental data acquisition are deployed in key areas of the target scene. These sensing devices include at least industrial cameras, LiDAR, and electric field monitoring sensors. The industrial cameras are used to collect image information from the target scene and identify visual reference objects such as fixed structures, equipment layouts, and personnel passageways. The LiDAR is used to acquire spatial structural information of the target scene and construct a 3D point cloud model. The electric field monitoring sensors are used to collect electric field intensity data at different spatial locations in the scene and construct an electric field distribution map.

[0024] Within the set periodic acquisition window, the system uniformly activates all the aforementioned sensing devices to collaboratively complete the multi-source data acquisition task of the target scene, and separately forms a spatial scene dataset and a spatial electric field dataset. The spatial scene dataset includes image information and three-dimensional structural information acquired by cameras and lidar; the spatial electric field dataset includes electric field intensity values ​​and their corresponding coordinates measured by electric field monitoring sensors at multiple spatial sampling points.

[0025] Next, spatial registration is performed on the spatial scene dataset and the spatial electric field dataset, mapping data from different sensors to a unified spatial coordinate system. During registration, the location information of the electric field monitoring points is geometrically aligned with the 3D scene model, thereby achieving the fusion of spatial electric field information and environmental structure information. Based on the fused data, the system divides the entire target area according to a spatial coordinate grid and classifies and quantifies the electric field intensity data within each grid cell.

[0026] Finally, a scene hazard map is built based on the registered data. Each spatial grid cell in the scene hazard map is equipped with a location scene hazard value identifier, which is used to characterize the electric field risk level corresponding to that spatial location.

[0027] Furthermore, establishing a scene hazard map includes:

[0028] Configure a safe electric field threshold; use the safe electric field threshold as a comparison standard value to perform an intensity comparison of the electric field at the location in the scene hazard map, and establish an intensity comparison result; set a location scene hazard value identifier based on the intensity comparison result.

[0029] During the process of establishing a scenario hazard map, a safe electric field threshold is configured for electric field risk assessment. This threshold can be set based on relevant electrical safety regulations, job type, voltage level, and worker protection level, and is used to determine whether a risk area with excessive electric field strength exists at a given spatial location. The safe electric field threshold can be a single fixed value, or it can be subdivided into multiple threshold levels according to the job scenario for more refined graded early warning.

[0030] Using a safe electric field threshold as the standard value for comparison, the electric field intensity values ​​at various spatial locations in the scene hazard map obtained through the aforementioned spatial registration process are compared and analyzed. The system traverses each spatial cell (or spatial sampling point), calculates whether its corresponding electric field intensity value exceeds the set threshold, and then establishes the intensity comparison result. The comparison result can be expressed using Boolean notation (safe / exceeding limit) or as a continuous expression using the ratio coefficient of electric field intensity to threshold.

[0031] Based on the comparison results, a corresponding location scene hazard value identifier is set for each location unit in the spatial coordinate grid of the scene hazard map. This identifier is used to describe the potential electric field risk level of the spatial location, and the identifier can be in the following forms: level type: such as "Level 0 (Safe)", "Level 1 (Warning)", "Level 2 (Danger)"; numerical type: such as a floating-point number with a risk index range of 0 to 1, or a multiple relationship between the compared electric field strength and the threshold.

[0032] Once the smart helmet is activated, the scene hazard map is updated to the smart helmet, and positioning data is generated through the UWB positioning chip of the smart helmet.

[0033] Once the smart safety helmet is activated, the control system synchronously updates a pre-built scene hazard map to the helmet's local processing unit via communication modules (such as Wi-Fi, Bluetooth, and UWB base station communication interfaces). After the scene hazard map is loaded locally, the smart safety helmet activates its built-in UWB positioning chip and uses high-precision distance measurement between itself and pre-deployed UWB anchor points or base stations within the target work area to achieve real-time location tracking of the worker. The positioning data includes three-dimensional spatial coordinate information (X, Y, Z) and a positioning timestamp, used to dynamically track the wearer's relative position in the hazardous scene.

[0034] Based on the location data and the scene hazard map, a near-electricity alarm is identified, and a first alarm message is generated.

[0035] The system spatially matches the 3D coordinates in the location data with the corresponding spatial units in the scene hazard map to obtain the location scene hazard value identifier corresponding to that unit. If the hazard value identifier of the matched location is in an unsafe state such as "warning" or "danger," it is determined that the current worker is in a high-risk area of ​​the electric field or close to a sensitive area of ​​high-voltage equipment. When the location coordinates are less than a preset distance threshold from the boundary of any high-risk area, it is determined that the worker has entered a high-risk state near electricity. At this time, the system generates a first alarm message, which includes the current location coordinates, hazard level, risk area identifier number, and timestamp, indicating the real-time status of the worker approaching the electrical hazard area.

[0036] The electric field sensing sensor group of the smart safety helmet is activated to perform electric field direction recognition and establish electric field direction recognition results. The electric field sensing sensor group includes at least three electric field sensing units and an attitude sensing unit. The electric field sensing units are equidistantly arranged on the circumferential structure of the smart safety helmet.

[0037] After the smart safety helmet is activated, the system initiates the electric field sensing sensor group integrated within the helmet to perform electric field direction identification. The electric field sensing sensor group includes at least three electric field sensing units and one attitude sensing unit. The multiple electric field sensing units employ high-sensitivity electric field sensor chips to collect electric field intensity information in different orientations of the worker's surrounding space. The attitude sensing unit includes inertial measurement components such as gyroscopes and accelerometers to monitor the smart safety helmet's spatial attitude in real time, including orientation, tilt angle, and rotational trend.

[0038] Multiple electric field sensing units are equidistantly arranged on the circumferential structure of the smart safety helmet. For example, three sensors are arranged at a 120° angle, or a four-point or six-point uniform arrangement is adopted to ensure that electric field information of the surrounding space can be obtained from multiple directions, forming a complete circumferential sensing capability.

[0039] When the system performs electric field direction recognition, it first uses the attitude sensing unit to collect the current spatial attitude data of the smart helmet and establishes an attitude reference based on the geographic coordinate system or the head reference coordinate system. Then, it collects and compares the electric field intensity values ​​obtained by each electric field sensing unit, and performs direction vector analysis in conjunction with the attitude reference data. Specifically, based on the physical installation direction of each electric field sensing unit and the collected electric field intensity, it constructs a direction map of the electric field distribution, and further identifies the dominant direction of the current electric field through vector difference or principal direction extraction algorithms. Thus, the system establishes and outputs the electric field direction recognition result, which can be a spatial direction vector or direction angle information, used to characterize the direction of the electric field source relative to the wearer. For example, the recognition result can be expressed as "an enhanced electric field exists in a direction 30° to the left and 20° above the head relative to the front direction."

[0040] Furthermore, activating the electric field sensing sensor array of the smart helmet performs electric field direction recognition and establishes the electric field direction recognition results, including:

[0041] Data is collected using the gyroscope and accelerometer in the attitude sensing unit, and the orientation and rotation trend data of the smart safety helmet are identified using the data collection results. The orientation of the electric field sensing unit is initialized based on the orientation of the smart safety helmet. This initialization includes: establishing a calibration spatial coordinate system; establishing a sensing direction mapping between the electric field sensing unit and the calibration spatial coordinate system based on the orientation of the smart safety helmet; reading the position sensing data of the electric field sensing unit; and establishing an electric field direction recognition result based on the position sensing data and the sensing direction mapping.

[0042] Once the electric field sensing and recognition process is triggered, the system first activates the attitude sensing unit integrated inside the smart safety helmet. This unit includes a gyroscope and an accelerometer, used to collect real-time motion state data of the smart safety helmet in the current space. By jointly processing the collected data, the system extracts the current orientation attitude information of the smart safety helmet (such as the head's yaw angle, pitch angle, and roll angle) and rotation trend data (such as angular velocity and acceleration vector), which are used to characterize the spatial attitude and turning behavior of the worker's head.

[0043] Based on the identified orientation and posture information, the orientation initialization operation of the electric field sensing unit is performed. Specifically, a three-dimensional spatial coordinate system aligned with the work scene is constructed using the ground normal, the forward orientation of the human body, and the direction of gravity as reference axes. Based on the physical installation position of the electric field sensing unit on the smart safety helmet and its corresponding orientation vector, combined with the current orientation and posture angle, the orientation of each sensing unit is mapped to the calibration spatial coordinate system to form an orientation correspondence table.

[0044] The system reads the position sensing data output by each electric field sensing unit, which consists of electric field intensity values ​​collected in each sensing direction. Combining this with a sensing direction mapping table, the system vectorizes these intensity values, comprehensively calculates the differences in electric field distribution across different directions, and identifies the dominant direction of the electric field in space. Finally, the system constructs and outputs the electric field direction identification result, which can be in the form of a unit vector, polar coordinate direction angle, or direction offset data with the smart helmet body as a reference, used to describe the source direction of the current electric field change.

[0045] The electric field direction identification results are used to analyze user movement trends and establish a second alarm message.

[0046] Furthermore, the user's movement trend is analyzed using the electric field direction identification results to establish a second alarm message, including:

[0047] The orientation angle is identified based on the orientation of the smart safety helmet and the electric field direction recognition result; if the orientation angle recognition result meets the set angle threshold, orientation warning data is established; the mean intensity data of the electric field is obtained based on the position sensing data of the electric field sensing unit, and a position intensity warning is established based on the mean intensity data; the field strength gradient is identified based on the electric field direction recognition result and the position sensing data of the electric field sensing unit, and a gradient intensity warning is established using the field strength gradient recognition result per unit distance; a second alarm message is established based on the orientation warning data, the position intensity warning, and the gradient intensity warning.

[0048] First, based on the orientation posture data output by the smart safety helmet's posture sensing unit, the orientation vector information of the worker's current head is extracted. Simultaneously, the electric field direction recognition result is retrieved to extract the corresponding main electric field direction vector. The angle between these two vectors is calculated to obtain the orientation angle recognition result between the current orientation and the electric field direction. When the orientation angle recognition result is less than a preset angle threshold (e.g., 30°, 20°, etc., configurable parameters), it is determined that the worker is potentially approaching the electric field source, and the system establishes orientation warning data accordingly. Second, using the electric field strength value output by the electric field sensing unit at the current location, the average electric field strength data at the current point is calculated and compared with a set safe electric field strength threshold. If the average strength exceeds the set threshold, the system determines that the current location has a high electric field risk, and thus establishes location strength warning information. Next, based on the current positioning information, orientation posture information, and multi-point strength data from the electric field sensing unit, a field strength gradient recognition operation is performed, i.e., analyzing the rate of change of electric field strength per unit distance movement. If the gradient change rate reaches or exceeds a set threshold, it is determined that the worker is continuously approaching the electric field source, thus generating gradient intensity warning information. Finally, based on the warning information from the above three dimensions—orientation warning data, location intensity warning information, and gradient intensity warning information—the system performs a comprehensive evaluation and merges them to generate a second alarm message to characterize the worker's dynamic approach to the electric field source.

[0049] Furthermore, a second alarm message is established based on the orientation warning data, location intensity warning, and gradient intensity warning, including:

[0050] Configure a sliding time window; perform temporal differential identification of electric field intensity for each electric field sensing unit within the sliding time window, and establish a position temporal differential identification result; perform a consistency evaluation of the continuous movement intention and electric field direction identification result based on the position temporal differential identification result, and establish a second alarm information based on the consistency evaluation result, the orientation warning data, the position intensity warning, and the gradient intensity warning.

[0051] A sliding time window is configured to dynamically analyze the electric field sensing data of the electric field sensing unit over a continuous time series. The sliding time window is a preset continuous time period (e.g., 2 seconds, 5 seconds, or other configurable lengths). The system updates the window with a fixed step size to ensure the continuity and timeliness of the electric field intensity data.

[0052] Within the sliding time window, for each electric field sensing unit deployed circumferentially on the smart safety helmet, a temporal differential identification operation of the electric field intensity is performed. This involves performing first-order differential processing on the electric field intensity data at consecutive sampling time points to extract the electric field intensity change trend and generate corresponding positional temporal differential identification results. These results characterize the rate and direction of electric field change in the corresponding direction of each sensing unit. Based on these positional temporal differential identification results, and combined with the orientation trend information provided by the attitude sensing unit and the identified main electric field direction, a consistency evaluation operation is performed between the continuous movement intention and the electric field direction identification results. Specifically, it determines whether the current user's movement trend is consistent with the direction of electric field enhancement, i.e., whether the worker is continuously approaching the electric field source. If the consistency evaluation result shows a continuous approaching trend, a second alarm message with a higher risk level is generated by combining previously acquired orientation warning data, position intensity warning information, and gradient intensity warning information.

[0053] After fusing the first alarm information and the second alarm information, an abnormal alarm is reported.

[0054] The system receives a first alarm message (identified based on a scene hazard map and location data) and a second alarm message (identified based on electric field direction identification and user movement trend analysis). It then comprehensively assesses the severity, triggering conditions, and temporal sequence of the two alarm messages according to fusion rules. During the fusion process, the system employs a multi-factor weighting mechanism to evaluate the location risk value in the first alarm message and the trend similarity level in the second alarm message. For example, if the electric field strength at the current location point exceeds a safety threshold, and the system simultaneously detects the user continuously moving towards the electric field direction, the system will classify the fusion as high-risk and generate an abnormal alarm flag. Based on the alarm level determined by the fusion result, the system generates a structured abnormal alarm message containing fields such as alarm level, alarm type, suggested action, and risk orientation information. This triggers the sound, light, and vibration-linked early warning unit in the smart safety helmet to provide an abnormal alert, reminding the wearer to stop approaching or evacuate the high-risk area immediately.

[0055] Furthermore, after fusing the first alarm information and the second alarm information, the abnormal alarm report also includes:

[0056] Activate the image acquisition device integrated in the smart safety helmet, use the image acquisition device to perform scene image acquisition, and establish scene image acquisition results; based on the scene image acquisition results, identify and locate key equipment, use the key equipment identification and location results and scene hazard map to perform map fusion identification, and establish auxiliary positioning information; establish third alarm information according to the auxiliary positioning information, and perform abnormal alarm compensation management through the third alarm information.

[0057] The system activates the image acquisition device integrated into the smart helmet, which includes a high-definition industrial camera or a miniature imaging module. Upon detecting that the fusion alarm trigger condition is met, the system automatically controls the image acquisition device to capture scene images and generate scene image acquisition results associated with the wearer's current location and orientation.

[0058] Based on scene image acquisition results, the system employs a pre-trained target recognition model or image segmentation algorithm to identify and locate key equipment such as industrial electrical facilities, power equipment, and warning signs in the images, determining the equipment bounding boxes, spatial distribution coordinates, and risk types. Through map fusion recognition with a scene hazard map, multimodal linkage between image information and spatial risk data is achieved, generating auxiliary positioning information with real-time and context-aware capabilities. This auxiliary positioning information is used to correct or enhance alarm judgment deviations caused by positioning errors, electric field interference, etc. Based on the key target distribution areas, risk levels, and current personnel behavior status marked in the auxiliary positioning information, the system comprehensively generates a third alarm information. This third alarm information has compensatory alarm capabilities and can serve as a basis for enhancing or correcting the first and second alarm information. The system uses the third alarm information as compensation input to participate in the final abnormal alarm level decision and management output. Through the abnormal alarm compensation management mechanism, the system significantly improves the response accuracy and robustness of the alarm system in scenarios with obstructed environments, multi-source interference from equipment, or dynamic electric field anomalies, ensuring more comprehensive near-electric safety protection for operators in complex scenarios.

[0059] Furthermore, reporting abnormal alarms also includes:

[0060] Configure the alarm intensity value of the abnormal alarm based on the proximity index, duration index, and action trend index; after configuring the abnormal alarm level using the alarm intensity value, call the sound, light, vibration linkage early warning unit mapped to the abnormal alarm level to execute the early warning.

[0061] Based on the fused alarm information, the system extracts proximity, duration, and action trend indicators related to the current alarm event. The proximity indicator measures the spatial distance and electric field strength between the user's current location and a hazardous location in the scene. The duration indicator represents the length of time the user is in a high-risk location or continuously near an electric field source. The action trend indicator reflects the change in the angle and consistency between the user's orientation, electric field direction, and movement trend. Based on these multiple risk characteristics, the system uses preset alarm intensity configuration rules to generate corresponding abnormal alarm intensity values, which quantify the severity of the current risk level. Next, the system configures the abnormal alarm level according to the risk level corresponding to the alarm intensity value and, based on this level, invokes the integrated audio-visual vibration warning unit in the smart safety helmet to issue an early warning. The warning unit includes a buzzer, warning light, and miniature vibration motor, which can trigger audio-visual vibration outputs of different frequencies, durations, and combinations according to different alarm intensity levels, achieving multimodal warning prompts for workers.

[0062] In summary, the embodiments of this application have at least the following technical effects:

[0063] First, scene data is collected for the target scenario to create a scene hazard map, which includes location hazard value markers. When the smart helmet is activated, the scene hazard map is updated to the helmet, and location data is generated using the helmet's UWB positioning chip. Next, based on the location data and the scene hazard map, a proximity alarm is identified, generating a first alarm message. The electric field sensing sensor group of the smart helmet is activated to perform electric field direction recognition, establishing an electric field direction recognition result. This electric field sensing sensor group includes at least three electric field sensing units and an attitude sensing unit, with the electric field sensing units equidistantly distributed on the circumferential structure of the smart helmet. Then, the user's movement trend is analyzed using the electric field direction recognition result, generating a second alarm message. Finally, the first and second alarm messages are fused to issue an abnormal alarm. This solves the technical problems of insufficient alarm accuracy and timeliness in existing technologies, achieving the technical effect of improving alarm accuracy and timeliness.

[0064] Example 2, based on the same inventive concept as the proximity alarm method based on a smart safety helmet in the previous examples, such as... Figure 2 As shown, this application provides a proximity alarm system based on a smart safety helmet, wherein the system includes:

[0065] Map building module 11: Collects scene data of the target scene and builds a scene hazard map, which is set with location scene hazard value markers; Map updating module 12: When the smart safety helmet is activated, updates the scene hazard map to the smart safety helmet and generates positioning data through the UWB positioning chip of the smart safety helmet; Alarm identification module 13: Based on the positioning data and the scene hazard map, performs near-electric alarm identification and generates a first alarm message; Electric field direction identification module 14: Activates the electric field sensing sensor group of the smart safety helmet to perform electric field direction identification and establishes an electric field direction identification result, wherein the electric field sensing sensor group includes at least three electric field sensing units and an attitude sensing unit, and the electric field sensing units are equidistantly arranged on the circumferential structure of the smart safety helmet; Motion trend analysis module 15: Analyzes user motion trends using the electric field direction identification result and establishes a second alarm message; Abnormal alarm module 16: After fusing the first alarm message and the second alarm message, reports an abnormal alarm.

[0066] Furthermore, the electric field direction recognition module 14 is used to perform the following method:

[0067] Data is collected using the gyroscope and accelerometer in the attitude sensing unit, and the orientation and rotation trend data of the smart safety helmet are identified using the data collection results. The orientation of the electric field sensing unit is initialized based on the orientation of the smart safety helmet. This initialization includes: establishing a calibration spatial coordinate system; establishing a sensing direction mapping between the electric field sensing unit and the calibration spatial coordinate system based on the orientation of the smart safety helmet; reading the position sensing data of the electric field sensing unit; and establishing an electric field direction recognition result based on the position sensing data and the sensing direction mapping.

[0068] Furthermore, the motion trend analysis module 15 is used to perform the following methods:

[0069] The orientation angle is identified based on the orientation of the smart safety helmet and the electric field direction recognition result; if the orientation angle recognition result meets the set angle threshold, orientation warning data is established; the mean intensity data of the electric field is obtained based on the position sensing data of the electric field sensing unit, and a position intensity warning is established based on the mean intensity data; the field strength gradient is identified based on the electric field direction recognition result and the position sensing data of the electric field sensing unit, and a gradient intensity warning is established using the field strength gradient recognition result per unit distance; a second alarm message is established based on the orientation warning data, the position intensity warning, and the gradient intensity warning.

[0070] Furthermore, the motion trend analysis module 15 is used to perform the following methods:

[0071] Configure a sliding time window; perform temporal differential identification of electric field intensity for each electric field sensing unit within the sliding time window, and establish a position temporal differential identification result; perform a consistency evaluation of the continuous movement intention and electric field direction identification result based on the position temporal differential identification result, and establish a second alarm information based on the consistency evaluation result, the orientation warning data, the position intensity warning, and the gradient intensity warning.

[0072] Furthermore, the map building module 11 is used to perform the following methods:

[0073] Install sensing devices for data acquisition, including industrial cameras, lidar, and electric field monitoring sensors; activate the sensing devices within a predetermined periodic window to perform data acquisition of the target scene, and establish a spatial scene dataset and a spatial electric field dataset; after spatial registration of the spatial scene dataset and the spatial electric field dataset, establish a scene hazard map.

[0074] Furthermore, the map building module 11 is used to perform the following methods:

[0075] Configure a safe electric field threshold; use the safe electric field threshold as a comparison standard value to perform an intensity comparison of the electric field at the location in the scene hazard map, and establish an intensity comparison result; set a location scene hazard value identifier based on the intensity comparison result.

[0076] Furthermore, the anomaly alarm module 16 is used to perform the following method:

[0077] Activate the image acquisition device integrated in the smart safety helmet, use the image acquisition device to perform scene image acquisition, and establish scene image acquisition results; based on the scene image acquisition results, identify and locate key equipment, use the key equipment identification and location results and scene hazard map to perform map fusion identification, and establish auxiliary positioning information; establish third alarm information according to the auxiliary positioning information, and perform abnormal alarm compensation management through the third alarm information.

[0078] Furthermore, the anomaly alarm module 16 is used to perform the following method:

[0079] Configure the alarm intensity value of the abnormal alarm based on the proximity index, duration index, and action trend index; after configuring the abnormal alarm level using the alarm intensity value, call the sound, light, vibration linkage early warning unit mapped to the abnormal alarm level to execute the early warning.

[0080] Example 3: Based on the same inventive concept as the proximity alarm method based on a smart helmet in the previous examples, this example provides a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the proximity alarm method based on a smart helmet in this application. The processor executes the software programs, instructions, and modules stored in the memory to perform various functional applications and data processing of the computer device, thereby implementing the aforementioned proximity alarm method based on a smart helmet.

[0081] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0082] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0083] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A proximity alarm method based on a smart safety helmet, characterized in that, include: Scene data is collected from the target scene to create a scene hazard map, which is marked with location scene hazard value identifiers; When the smart safety helmet is activated, the scene hazard map is updated to the smart safety helmet, and positioning data is generated through the UWB positioning chip of the smart safety helmet; Based on the location data and the scene hazard map, a near-electric alarm is identified, and a first alarm message is generated; The electric field sensing sensor group of the smart safety helmet is activated to perform electric field direction recognition and establish electric field direction recognition results. The electric field sensing sensor group includes at least three electric field sensing units and an attitude sensing unit. The electric field sensing units are equidistantly arranged on the circumferential structure of the smart safety helmet. The electric field direction identification results are used to analyze user movement trends and establish a second alarm message. After fusing the first alarm information and the second alarm information, an abnormal alarm is reported.

2. The proximity alarm method based on a smart safety helmet according to claim 1, characterized in that, The electric field sensing sensor group activated by the smart safety helmet performs electric field direction recognition and establishes the electric field direction recognition result, including: Data is collected using the gyroscope and accelerometer in the attitude sensing unit, and the data collection results are used to identify the orientation and rotation trend data of the smart safety helmet. The electric field sensing unit is initialized according to the orientation of the smart safety helmet, and the orientation initialization includes: Establish a calibration spatial coordinate system, and establish a sensing direction mapping between the electric field sensing unit and the calibration spatial coordinate system based on the orientation of the smart safety helmet; Read the position sensing data of the electric field sensing unit, and establish the electric field direction recognition result based on the position sensing data and sensing direction mapping of the electric field sensing unit.

3. The proximity alarm method based on a smart safety helmet according to claim 2, characterized in that, The step of using the electric field direction identification result to analyze user movement trends and establish a second alarm message includes: The orientation angle is identified based on the orientation of the smart safety helmet and the electric field direction recognition results. If the orientation angle recognition result meets the set orientation angle threshold, then orientation warning data is established; The mean intensity data of the electric field is obtained based on the position sensing data of the electric field sensing unit, and a position intensity early warning is established based on the mean intensity data. Based on the electric field direction identification result and the position sensing data of the electric field sensing unit, the field strength gradient is identified, and a gradient intensity warning is established using the field strength gradient identification result per unit distance. A second alarm message is established based on the orientation warning data, location intensity warning, and gradient intensity warning.

4. The proximity alarm method based on a smart safety helmet according to claim 3, characterized in that, The establishment of the second alarm information based on the orientation warning data, location intensity warning, and gradient intensity warning includes: Configure a sliding time window; Within the sliding time window, the electric field intensity of each electric field sensing unit is identified by temporal differential recognition, and the position temporal differential recognition result is established. Based on the location time-series differential identification results, a consistency evaluation is performed between the continuous movement intention and the electric field direction identification results. A second alarm message is established based on the consistency evaluation results, the orientation warning data, the location intensity warning, and the gradient intensity warning.

5. The proximity alarm method based on a smart safety helmet according to claim 1, characterized in that, The process of collecting scene data from the target scene and establishing a scene hazard map includes: Install sensing devices for data acquisition, including industrial cameras, lidar, and electric field monitoring sensors; Within a predetermined periodic window, the sensing device is activated to perform data acquisition of the target scene, and to establish a spatial scene dataset and a spatial electric field dataset. After spatial registration of the spatial scene dataset and the spatial electric field dataset, a scene hazard map is established.

6. The proximity alarm method based on a smart safety helmet according to claim 5, characterized in that, The creation of the scene hazard map includes: Configure a safe electric field threshold; Using the aforementioned safe electric field threshold as the comparison standard, the intensity comparison of the electric field at the location in the scene hazard map is performed, and the intensity comparison results are established. Based on the intensity comparison results, set the location scene hazard value identifier.

7. The proximity alarm method based on a smart safety helmet according to claim 1, characterized in that, The step of fusing the first alarm information and the second alarm information to report an abnormal alarm also includes: Activate the image acquisition device integrated in the smart safety helmet, use the image acquisition device to perform scene image acquisition, and establish the scene image acquisition results; Based on the scene image acquisition results, key equipment is identified and located. The key equipment identification and location results and the scene hazard map are used to perform map fusion identification to establish auxiliary positioning information. A third alarm message is established based on the auxiliary positioning information, and abnormal alarm compensation management is performed through the third alarm message.

8. The proximity alarm method based on a smart safety helmet according to claim 1, characterized in that, The reported abnormal alarm also includes: Configure the alarm intensity value for abnormal alarms based on proximity indicators, duration indicators, and action trend indicators; After configuring the abnormal alarm level using the alarm intensity value, the sound, light and vibration linkage early warning unit mapped to the abnormal alarm level is invoked to issue an early warning.

9. A proximity alarm system based on a smart safety helmet, characterized in that, For implementing the proximity alarm method based on a smart safety helmet according to any one of claims 1-8, the system comprises: Map building module: Collects scene data of the target scene and builds a scene hazard map, which is set with location scene hazard value indicators; Map update module: When the smart safety helmet is activated, it updates the scene hazard map to the smart safety helmet and generates positioning data through the UWB positioning chip of the smart safety helmet; Alarm identification module: Based on the location data and the scene hazard map, it identifies near-electric alarms and generates the first alarm information; Electric field direction recognition module: Activate the electric field sensing sensor group of the smart safety helmet to perform electric field direction recognition and establish electric field direction recognition results. The electric field sensing sensor group includes at least three electric field sensing units and an attitude sensing unit. The electric field sensing units are equidistantly arranged on the circumferential structure of the smart safety helmet. Motion trend analysis module: Utilizes the electric field direction identification results to analyze user motion trends and establish a second alarm message; Anomaly Alarm Module: After fusing the first alarm information and the second alarm information, an anomaly alarm is reported.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the proximity alarm method based on a smart safety helmet as described in any one of claims 1-8.

Images