Danger prompting method and device and storage medium

Abstract

The invention discloses a danger prompting method and device and a storage medium, and the method comprises the steps: obtaining environment information, extracting danger warning information including a danger direction, a danger distance and a danger type from the environment information, and generating a danger prompt according to the danger warning information, the danger prompt being an electric tactile signal based on a modulation signal, according to the dangerous orientation, an electric tactile signal based on a modulation signal is generated through an electrode in the signal generation module to realize dangerous orientation prompting; according to the danger distance and the danger type, prompting of the danger distance and the danger type is achieved by controlling the intensity and the frequency of an electric tactile signal which is generated by the electrode and based on the modulation signal. The danger source is determined through the obtained environment information, the user is reminded in the form of the electric tactile signal based on the modulation signal, the prompt of various touch and directions can be realized by controlling the micro-current energy signal, and the effective and economical danger prompt is realized corresponding to different types of dangers and danger directions, so that the visual impairment crowd is helped to avoid dangers.

Description

Technical Field

[0001] The present application relates to the field of blind guide technology, and in particular to a danger warning method, device and storage medium. Background Art

[0002] People with visual impairment include the blind, who have vision impairment so severe that they are unable to carry out most daily activities, and the low-vision group, which usually refers to people with amblyopia, an eye condition in which visual development in one or both eyes is affected, resulting in reduced vision that cannot be fully corrected even with glasses.

[0003] People with visual impairments face huge challenges in life, especially during daily activities and travel. Since they cannot directly observe the surrounding environment, they are prone to encounter potential dangers, which may lead to accidents. These dangers may include obstacles on the road, changes in traffic signals, the presence of stairs or steps, etc. At present, guide sticks can help blind people judge most obstacles, but they cannot inform people with visual impairments of road conditions and potential dangers based on actual conditions; guide dogs can help people with visual impairments judge most dangers, but the training cost of guide dogs is not trivial and many families cannot afford it. Summary of the invention

[0004] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0005] The embodiments of the present application provide a danger warning method, device and storage medium, which can provide an effective and economical danger warning method to help visually impaired people avoid danger in their daily lives.

[0006] In a first aspect, an embodiment of the present application provides a danger warning method, which is applied to a danger warning device, wherein the danger warning device comprises: a main control module, an information acquisition module, and a signal generation module provided with a plurality of electrodes, wherein the method comprises the following steps: Acquiring environmental information through the information acquisition module; Inputting the environmental information into a main control module, and extracting danger warning information from the environmental information through a preset visual model in the main control module, wherein the danger warning information includes danger direction, danger distance, and danger type; Based on the danger warning information, a danger prompt is generated, and the danger prompt is an electrotactile signal based on a modulated signal. The danger prompt is generated by the signal generating module and output through a plurality of the electrodes; wherein, the danger direction prompt is realized by outputting the electrotactile signal based on the modulated signal through the electrodes in corresponding positions in the signal generating module, and the danger distance and danger type prompt are realized by controlling the intensity and frequency of the electrotactile signal based on the modulated signal output by the electrodes.

[0007] According to some danger warning methods provided by embodiments of the present application, the output of the electrotactile signal based on the modulated signal by the electrodes in the corresponding positions in the signal generating module to realize the danger position warning includes: A first electrode is determined according to the dangerous position, the position of the first electrode in the signal generating module corresponds to the dangerous position, and the first electrode outputs an electrotactile signal based on a modulated signal to realize a dangerous position prompt.

[0008] According to some danger warning methods provided in embodiments of the present application, the method further includes: Extracting safety information according to the environmental information, the safety information including path information to avoid danger; Determine a second electrode according to the security information, where the second electrode is an electrode corresponding to the plurality of path information, wherein the second electrode adjacent to the first electrode is a starting second electrode, and the second electrode farthest from the first electrode is a terminal second electrode; Starting from the second electrode at the starting point to the second electrode at the ending point, electrotactile signals based on the modulation signal are sequentially output to realize danger avoidance prompt.

[0009] According to some danger warning methods provided by embodiments of the present application, the electrotactile signal based on the modulated signal is divided into at least a first signal, a second signal and a third signal according to its intensity, and the electrotactile signal based on the modulated signal with different intensities corresponds to different danger types; The method of realizing the prompt of the danger distance and the danger type by controlling the intensity and frequency of the electrotactile signal based on the modulation signal generated by the electrode according to the danger distance and the danger type includes: According to the danger type, an electrotactile signal based on a modulation signal corresponding to the danger type is output.

[0010] According to some danger prompting methods provided by embodiments of the present application, the prompting of the danger distance and the danger type is realized by controlling the intensity and frequency of the electrotactile signal based on the modulated signal generated by the electrode according to the danger distance and the danger type, including: According to the danger distance, the generation frequency of the electrotactile signal based on the modulation signal is controlled, and the generation frequency of the electrotactile signal based on the modulation signal increases as the danger distance decreases.

[0011] According to some danger warning methods provided by embodiments of the present application, the extracting danger warning information from the environmental information through a preset visual model in the main control module includes: Establishing a coordinate system according to the environmental information; Identify the risk factors in the environmental information, and determine the coordinate information and risk type of the risk factors; The dangerous direction and the dangerous distance are determined according to the coordinate information of the dangerous factor.

[0012] According to some danger warning methods provided by embodiments of the present application, the electrotactile signal based on the modulation signal is a bi-phase modulation signal.

[0013] In a second aspect, an embodiment of the present application provides a danger warning device, comprising: a main control module, an information acquisition module and a signal generation module, wherein the main control module is connected to the information acquisition module and the signal generation module respectively; The information acquisition module is used to acquire environmental information and input it into the main control module; The main control module includes a preset visual model, the main control module obtains the environmental information, and extracts danger warning information through the preset visual model, the danger warning information includes danger direction, danger distance and danger type; The signal generating module includes a signal generating component, a plurality of electrodes and a fixing module. The signal generating component is connected to the plurality of electrodes. A danger prompt is generated through the signal generating module. The danger prompt is an electrotactile signal based on a modulated signal, and the danger prompt is output through the plurality of electrodes.

[0014] According to some danger warning devices provided by embodiments of the present application, the signal generating module further includes a fixing module; The fixing module is used to fix the plurality of electrodes, and the user wears the plurality of electrodes through the fixing module.

[0015] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores a computer program executable by a processor, and the processor-executable computer program, when executed by the processor, is used to implement the method described in the first aspect of the embodiment of the present application.

[0016] The embodiments of the present application include at least the following beneficial effects: By acquiring environmental information and extracting danger warning information including danger direction, danger distance and danger type from it, and generating danger prompts according to the danger warning information, the danger prompts are electrotactile signals based on modulated signals, wherein the danger direction prompts are realized by generating electrotactile signals based on modulated signals through the electrodes in the signal generating module according to the danger direction, and the danger distance and danger type prompts are realized by controlling the intensity and frequency of the electrotactile signals based on modulated signals generated by the electrodes according to the danger distance and danger type. The danger source is determined by the environmental information acquired in real time, and the user is reminded in the form of electrotactile signals based on modulated signals. By controlling the microcurrent signal, a variety of tactile and direction prompts can be realized, corresponding to different types of dangers and danger directions, to realize effective and economical danger prompts, and help visually impaired people avoid danger.

[0017] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained through the structures particularly pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide further understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.

[0019] Figure 1 It is a structural schematic diagram of a danger warning device provided in an embodiment of the present application; Figure 2 It is a specific structural schematic diagram of a danger warning device provided in an embodiment of the present application; Figure 3 It is a schematic diagram of the wearing position of a fixing module of a danger warning device provided in an embodiment of the present application; Figure 4 It is a flowchart of a danger warning method provided in an embodiment of the present application; Figure 5 This is a schematic diagram of a danger avoidance prompt step provided by an embodiment of the present application; Figure 6 This is a schematic diagram of electrode changes when prompting avoidance provided in an embodiment of the present application; Figure 7 This is another schematic diagram of electrode changes when prompting avoidance provided by an embodiment of the present application. DETAILED DESCRIPTION

[0020] The present application is further described below in conjunction with the accompanying drawings and specific embodiments. The described embodiments should not be regarded as limiting the present application, and all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0021] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0023] Before further describing the embodiments of the present application in detail, the nouns and terms involved in the embodiments of the present application are explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations.

[0024] Electrotactile is a technology that transmits information by stimulating the skin with electric current. This technology uses the skin's electrical receptors to generate tactile feedback to convey information about the environment. The basic principle of electrotactile is to stimulate the receptors on the surface of the skin by applying a small electric current, so that the user can feel a sense of touch, which can simulate different textures, pressure or vibrations. When the current passes through the skin, it activates the nerve endings, which in turn makes the user feel a specific touch or vibration. Electrotactile can be achieved through electrotactile signals based on modulated signals. By controlling the size of the voltage, the intensity of the generated electrotactile signal can be controlled. As the voltage increases, the tactile sensation felt by the user becomes stronger, so that different prompt effects can be achieved through voltage control. Electrotactile technology has broad application prospects in the fields of human-computer interaction, rehabilitation engineering and assistive technology. Especially for the visually impaired, it provides a new way to perceive the environment.

[0025] Computer Science (CS) is a discipline that studies computing theory, algorithms, and information processing. It not only focuses on the design and implementation of computers themselves, but also includes software development, data structures, algorithm analysis, computational complexity theory, database management, network communications, and many other aspects. The core of computer science lies in problem-solving methods and techniques, as well as how to effectively use computing resources to implement these methods.

[0026] Artificial Intelligence (AI) is a broad discipline that covers technologies and methods that allow machines to simulate human intelligence. The research and application of AI aims to develop systems that can perform tasks that usually require human effort. These tasks include but are not limited to learning, reasoning, problem solving, knowledge representation, planning, language understanding, perception, and action.

[0027] In the field of computer science and artificial intelligence, visual models refer to algorithms and techniques used to process and understand image or video data. These models generally include but are not limited to: Deep learning models: such as Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), YOLO model (You Only Look Once), Transformer, etc., are mostly used for tasks such as image classification, object detection, semantic segmentation, style transfer, etc.

[0028] Feature extraction model: used to extract useful features from images, such as scale-invariant feature transform (SIFT), histogram of oriented gradient (HOG), etc.

[0029] Generative models: Such as Generative Adversarial Networks (GAN), Variational Auto-Encoder (VAE), etc. Generative models are used for image generation and editing.

[0030] By analyzing and understanding image or video data, visual models can help machines or systems accurately perceive and judge the environment. By identifying objects in the environment and determining their locations, they not only improve efficiency and accuracy, but also provide unprecedented convenience in many situations.

[0031] The YOLO model of the deep learning model is an advanced real-time target detection model. The 5th version of YOLO is famous for its efficient performance and flexibility. It can achieve real-time detection speed while maintaining high accuracy. The YOLOv5 model mainly consists of the following parts: Input: The model receives the original image as input and preprocesses it (such as resizing, normalizing, etc.); Backbone: This part is mainly used to extract image features. YOLOv5 adopts a design concept similar to CSPNet, which uses CSP (Cross Stage Partial Network) modules to optimize feature propagation and reduce information redundancy. The Backbone part also includes components such as Conv module, C3 module and SPPF module; Neck: Neck connects the Backbone and the Head. It is responsible for fusing feature maps at different levels to generate multi-scale feature representations. The Neck of YOLOv5 uses a combination of FPN (Feature Pyramid Network) and PAN (Path Aggregation Network), which enables the model to better detect objects of different sizes.

[0032] Head structure: The Head part is responsible for predicting the location, category and confidence of the target from the fused feature map. The Head of YOLOv5 contains three detection heads, corresponding to feature maps of different scales to adapt to the detection of targets of different sizes.

[0033] The YOLO model has the advantages of real-time detection, high flexibility, easy training and deployment, and high performance. It can achieve very high detection speed without sacrificing accuracy, has good training stability and robustness, and supports a variety of training techniques, such as mixed precision training, Mosaic data enhancement, etc. The model is also very easy to deploy. On multiple benchmark datasets, it has shown performance comparable to or even better than similar models, making it suitable for real-time applications.

[0034] People with visual impairment include the blind, who have vision impairment so severe that they are unable to carry out most daily activities, and the low-vision group, which usually refers to people with amblyopia, an eye condition in which visual development in one or both eyes is affected, resulting in reduced vision that cannot be fully corrected even with glasses.

[0035] People with visual impairments face huge challenges in life, especially in daily activities and travel. Since they cannot directly observe the surrounding environment, they are prone to encounter potential dangerous situations, which may lead to accidents. These dangers may include obstacles on the road, changes in traffic signals, the presence of stairs or steps, etc. At present, guide sticks can help blind people judge most obstacles and terrains, but they cannot inform visually impaired people of road conditions and potential dangers according to actual conditions; and although guide dogs can help visually impaired people judge most dangers, the training cost of guide dogs is not trivial, and many families cannot afford it. Therefore, there is an urgent need to provide an effective and economical danger warning method to help people with visual impairments avoid danger.

[0036] Based on this, the embodiments of the present application provide a danger warning method, device and storage medium, which can observe the environment in real time, and provide danger warnings through electrotactile signals based on modulated signals, thereby realizing effective and economical danger warnings for people with visual impairments and helping people with physical disabilities avoid dangers in their daily lives.

[0037] First, accept the danger warning device that provides danger warning in the embodiment of the present application.

[0038] Please refer to Figure 1 , is a danger warning device provided by an embodiment of the present application, such as Figure 1 As shown, in an embodiment of the present application, a danger warning device 100 for implementing a danger warning method may include but is not limited to: a main control module 110, an information acquisition module 120 and a signal generation module 130, wherein the main control module 110 is connected to the information acquisition module 120 and the signal generation module 130 respectively.

[0039] The main control module 110 includes a preset visual model 111 . The main control module 110 obtains environmental information and extracts danger warning information through the preset visual model 111 . The danger warning information includes danger direction, danger distance and danger type.

[0040] It should be noted that in the embodiment of the present application, the visual model 111 included in the main control module 110 used in the proposed danger warning device 100 is used to realize the extraction of danger information. The visual model 111 used in the main control module 110 can adopt any visual model, and the adopted visual model 111 can complete feature extraction.

[0041] Exemplarily, in a feasible embodiment of the present application, the visual model 111 may adopt a YOLO model, and the visual model 111 is used to realize the function of extracting danger warning information from the obtained environmental information.

[0042] Specifically, in a feasible embodiment of the present application, the fifth generation YOLO model—YOLOv5 visual model is used as the visual model 111. Before using the visual model 111, it needs to be pre-trained. The visual model 111 obtained after pre-training can be used for information extraction, and the factors that may cause danger are extracted from the environmental information obtained by the information acquisition module 120, so as to generate danger warning information. The pre-training method of the visual model can use the model training method commonly used in the prior art, and the present application does not make too many restrictions on the model training method.

[0043] It should be noted that in the embodiment of the present application, if the environmental information includes various danger signs, the warning content in the signs can be recognized by text, and the visual model 111 can also use an optical character recognition (OCR) engine to assist in identifying the acquired environmental information. After the main control module 110 acquires the environmental information, the visual model 111 recognizes the text therein through the OCR engine and further uses it to generate danger warning information.

[0044] The main control module 110 provided in the embodiment of the present application can realize the function of obtaining danger warning information from environmental information, so that the signal generation module can issue danger prompts according to the danger warning information, thereby prompting people with physical disabilities to the danger and helping people with visual impairments avoid danger.

[0045] The information acquisition module 120 is used to acquire environmental information and input the environmental information into the main control module 110 .

[0046] It should be noted that, in the embodiment of the present application, the information acquisition module 120 is a module for acquiring environmental information, which may be a device capable of recording or photographing, including but not limited to: a camera and a video recorder. The information acquisition module can record the video of the user's current environment in real time as environmental information, and transmit the obtained environmental information to the main control module 110 to acquire danger warning information.

[0047] Exemplarily, in a feasible embodiment of the present application, the main control module 110 adopts the YOLOv5 model as the visual model 111 and uses Python's CV2 library. After the information acquisition module 120 obtains environmental information by real-time recording, the frame data in the environmental information is obtained through the CV2 library, and the frame data is input into the YOLOv5 model for recognition to obtain danger warning information.

[0048] It is understandable that CV2 is part of Python's OpenCV (Open Source Computer Vision Library) interface, an interface of the OpenCV library in Python, which is a very popular library in the field of computer vision and image processing. The environmental information is the video data recorded in real time by the information acquisition module 120. The CV2 library can better achieve real-time acquisition of frame data in the environmental information, and extract danger warning information through the acquired frame data.

[0049] In the embodiment of the present application, the environmental information can be acquired in real time through the information acquisition module 120 and transmitted to the main control module 110 to generate danger warning information.

[0050] The signal generating module 130 includes a signal generating component 131 and a plurality of electrodes 132 . The signal generating component 131 is connected to the plurality of electrodes 132 . A danger prompt is generated by the signal generating module 130 . The danger prompt is an electrotactile signal based on a modulated signal, and the danger prompt is output through the plurality of electrodes 132 .

[0051] It should be noted that in the embodiment of the present application, the signal generating component 131 is used to receive the danger warning information generated by the main control module 110, and multiple electrodes 132 are evenly distributed in various directions. The signal generating component 131 selects the corresponding electrode 132 according to the danger direction in the danger warning information, and generates an electrotactile signal based on the modulated signal with corresponding intensity and stimulation frequency according to the danger distance and danger type in the danger warning information, and outputs the electrotactile signal based on the modulated signal through the corresponding electrode 132 to prompt the user.

[0052] Exemplarily, in a feasible embodiment of the present application, when the danger direction in the danger warning information is 45° to the left front of the user and there is a danger that may cause minor injury, the signal generating component 131 selects the electrode 132 located 45° to the left front and generates a low-frequency, low-intensity electrotactile signal based on the modulated signal, and controls the electrode 132 to output a low-frequency, low-intensity electrotactile signal based on the modulated signal, so that a user with visual impairment can feel the low-frequency vibration 45° to the left front of the signal generating module 130, thereby avoiding obstacles. As the user approaches danger, the output frequency of the electrotactile signal based on the modulated signal is gradually increased to provide a prompt of the danger distance.

[0053] It can be understood that when the danger may cause serious harm, the signal generating component generates high-intensity microcurrent information, which is output through the corresponding electrodes so that users with visual impairments can feel the burning, tingling or numbness of the signal generating module 130, allowing users to distinguish the damage caused by the danger and choose whether to take emergency avoidance.

[0054] It should be noted that the signal generating module 130 in the embodiment of the present application further includes a fixing module 133 , which is used to fix the plurality of electrodes 132 , and the user wears the plurality of electrodes 132 on the fingers through the fixing module 133 .

[0055] By wearing it on the fingers, it will not affect the user's daily life. At the same time, since electrodes can be arranged in all directions at the fingertips, danger warnings can be provided in most positions, realizing a convenient and lightweight wearable device.

[0056] For example, please refer to Figure 2 , is a schematic diagram of a specific structure of a danger warning device provided in an embodiment of the present application, such as Figure 2 As shown, in the embodiment of the present application, the main control module 110 includes a visual model 111 for extracting danger warning information from environmental information. The main control module 110 can be any terminal, which is convenient for users to carry; the information acquisition module 120 is a camera, which can obtain environmental information of the user's environment in real time, and transmit the obtained environmental information to the main control module 110; the signal generation module 130 includes a signal generation component 131, a plurality of electrodes 132 and a fixing module 133, wherein the signal generation component includes a dual-channel signal generator, an amplifier and a monitoring component, the monitoring component is used to monitor and record current and voltage in real time, the dual-channel signal generator outputs two signals of opposite phases to the amplifier, and the dual-channel amplifier is used to amplify the input signal to provide sufficient stimulation voltage, and the monitoring component can be used to detect data, so that the user can adjust the device according to the recorded information later; Figure 2 The electrodes 132 in the figure are part of the electrodes shown. In actual use, more electrodes can be set to cover all directions to ensure that the user can be accurately prompted for the orientation. The fixing module 133 is also a planar expansion diagram. In actual application, the fixing module 133 can be used to fix multiple electrodes 132 on the user's fingers (such as Figure 2 As shown in the shadow of the fingers on the middle palm), it can prompt the user by stimulating the fingers without affecting the user's daily life.

[0057] It should be noted that in a feasible embodiment of the present application, the fixing module 133 fixes the plurality of electrodes 132 so that the user can wear it, and can be adapted to be worn in a position that does not affect the user's daily life by setting different shapes, such as Figure 3 As shown, in addition to the finger position (position 3 in the figure), it can also be worn on the arm (position 1 in the figure) or wrist (position 2 in the figure). The specific position can be designed according to actual needs. This application does not impose too many restrictions on the specific shape and fixed position of the fixing module 133.

[0058] The various devices in the embodiments of the present application can be connected via a wired connection or a wireless connection. The wireless connection can be achieved through WiFi or Bluetooth. Each device can be equipped with an independent power supply for wireless use or share a power supply when connected by wire. The specific selection can be set according to the actual needs of the user, and the present application does not impose too many restrictions on this.

[0059] Next, the danger warning method proposed in the embodiment of the present application is described in combination with the danger warning device described above.

[0060] Please refer to Figure 4 , is a flow chart of a danger warning method provided in an embodiment of the present application, such as Figure 4 As shown, the danger warning method applied to the danger warning device provided in the embodiment of the present application may include but is not limited to steps S110 to S130: Step S110: Acquire environmental information through an information acquisition module.

[0061] It should be noted that, in the embodiment of the present application, the information acquisition module is a module for acquiring environmental information, which may be a device capable of recording or photographing, including but not limited to: a camera and a video recorder. The environmental information acquired by the information acquisition module is a real-time recorded video. When a danger warning is required, the environmental information is obtained by real-time video recording of the user's environment through the information acquisition module.

[0062] In the embodiment of the present application, the information of the environment in which the user is located is obtained through the information acquisition module, and the environmental information is used to judge the dangerous situation of the environment to realize the subsequent danger warning function.

[0063] Step S120: input the environmental information into the main control module, and extract danger warning information from the environmental information through a preset visual model in the main control module, where the danger warning information includes danger direction, danger distance and danger type.

[0064] It should be noted that in the embodiment of the present application, the danger warning information extracted through environmental information needs to determine the danger direction, danger distance and danger type. Among them, the danger direction indicates the position of the danger relative to the user. By referring to the danger direction, the danger direction reminder can be made to inform the user of the location of the danger; the danger distance indicates the distance between the danger and the user. The user is reminded according to the danger distance so that the user can determine whether emergency avoidance is required; the danger type indicates the type of danger that occurs, and different reminders can be made according to different danger types.

[0065] In the embodiment of the present application, the main control module can control the generation of danger prompts through danger warning information, thereby reminding the user, so that the user can understand the dangers in the environment and take corresponding evasive actions to avoid them.

[0066] For example, in the embodiment of the present application, step S120 extracting danger warning information from environmental information may include but is not limited to: Establish a coordinate system based on environmental information; Identify the risk factors in the environmental information, determine the coordinate information of the risk factors and the risk type; Determine the danger direction and distance based on the coordinate information of the danger factors.

[0067] It can be understood that, as described above, in the embodiment of the present application, the main control module includes a visual model for realizing danger information extraction. The visual model can adopt any visual model, and the acquired environmental information is extracted through the visual model to obtain danger warning information.

[0068] Specifically, in a feasible embodiment of the present application, the YOLOv5 model is used as a visual model, and extracting danger information from environmental information may include: After obtaining the environmental information, extract the video frames for recognition, and establish a coordinate system centered on the user based on the extracted video frames; When the identified environmental information contains a risk factor, the coordinate information of the risk factor in the coordinate system is determined according to the identified risk factor, and the risk type of the risk factor is determined; for example, when an obstacle appears 100 meters to the left of the user, which may cause a tripping hazard, the coordinate information of the obstacle is determined, and the risk type is determined as an obstacle tripping. At this time, only the obstacle is identified, and the risk distance and risk direction need to be determined according to the specific coordinate information; After determining the coordinate information of the danger, the direction and distance of the danger are determined based on the obtained coordinate information. Specifically, the danger is determined to be in the left front, and the corresponding distance is 100 meters.

[0069] The danger warning information obtained in the embodiment of the present application is used to generate danger prompts based on the danger type, danger direction and danger distance included therein, so as to facilitate the user to avoid danger.

[0070] Step S130, generating a danger prompt based on the danger warning information, the danger prompt being an electrotactile signal based on a modulated signal, the danger prompt being generated by a signal generating module and outputted through a plurality of electrodes; wherein, the danger direction prompt is realized by outputting an electrotactile signal based on the modulated signal through electrodes in corresponding positions in the signal generating module, and the danger distance and danger type prompt are realized by controlling the intensity and frequency of the electrotactile signal based on the modulated signal outputted by the electrodes.

[0071] It should be noted that in the embodiment of the present application, the generated electrotactile signal based on the modulated signal is directly used to remind the user of the danger. Since the electric current can cause pain, it may cause discomfort, and the high-intensity current may even cause harm to the human body. Therefore, in the embodiment of the present application, it is necessary to control the current and use the electrotactile signal based on the modulated signal.

[0072] Exemplarily, in an embodiment of the present application, the electrotactile signal based on the modulation signal used is a bi-phase modulation signal, and the implementation method is to adjust different signal parameters, including signal type (DC, AC), signal waveform (square wave, sine wave, pulse wave, amplitude modulation wave, frequency modulation wave, etc.), voltage size, frequency, phase, etc.

[0073] Specifically, in a feasible embodiment of the present application, a local high-frequency vibration tactile sensation is generated by using a signal generating component to generate a biphase modulated signal, wherein the signal generating component includes a dual-channel signal generator of two channels, channel 1 and channel 2, and outputs two signals of opposite phases. The signal of channel 1 uses a square wave of 1KHz, 1Vrms as a carrier, a sine wave of 40Hz as a modulating wave, and a phase setting of 0°; the signal of channel 2 uses a square wave of 1KHz, 1Vrms as a carrier, a sine wave of 40Hz as a modulating wave, and a phase setting of 180°. When the signal adjusts the frequency to a lower frequency (i.e., 500HZ), a wide range of low-frequency vibrations can be generated in the human body without causing pain or harm. When the signal further increases the voltage on the basis of the voltage of the aforementioned example signal that can generate local high-frequency vibrations, the vibration tactile sensation generated can be gradually enhanced, that is, the intensity of the stimulation can be adjusted by controlling the intensity of the voltage; as the voltage continues to increase, the human body can also gradually produce a transition from vibration to numbness to burning and tingling, and different sensations can be achieved to remind the user.

[0074] In addition to controlling the parameters of the signal, changing the signal type can also achieve a variety of tactile sensations including vibration, tingling, numbness, and burning.

[0075] The embodiment of the present application uses a bi-phase modulation signal to control an electrotactile signal based on a modulation signal, so that while achieving a tactile prompt, it is possible to avoid harm to the human body caused by electric current, thereby providing effective danger prompts to visually impaired users.

[0076] It should be noted that in the embodiment of the present application, the dangerous position prompt is realized by outputting an electrotactile signal based on a modulated signal through electrodes at corresponding positions in the signal generating module, including: The first electrode is determined according to the danger direction, the position of the first electrode in the signal generation module corresponds to the danger direction, and the danger direction prompt is realized by outputting an electrotactile signal based on the modulated signal through the first electrode.

[0077] It can be understood that the first electrode directly corresponds to the danger position, and the first electrode outputs an electrotactile signal based on the modulated signal so that the user can directly sense the danger position.

[0078] It should be noted that in the embodiment of the present application, on the one hand, when there are multiple risk factors in the environmental information, the nearest risk factor is given priority for risk warning; on the other hand, when two risk factors with the same distance from the user are found, the user is given a risk warning at the same time.

[0079] Exemplarily, in a feasible embodiment of the present application, when it is identified that there are danger factors both 50 meters to the left of the user and 100 meters directly in front of the user, the first danger warning information is first determined, that is, the danger warning information corresponding to the danger factor 50 meters to the left of the user, and the user is warned of the danger according to the first danger warning information; when the user avoids the danger in the left front, the second danger warning information is determined, that is, the danger warning information corresponding to the danger factor 100 meters directly in front of the user. The user is warned of the danger through the first danger warning information and the second danger warning information.

[0080] In another feasible embodiment of the present application, when it is identified that there are dangerous factors 100 meters to the left and 100 meters to the right of the user, and it is determined that the two dangerous factors are at equal distances from the user, a first danger warning message and a second danger warning message are determined at the same time. The first danger warning message corresponds to the dangerous factor to the left of the user, and the second danger warning message corresponds to the dangerous factor to the right of the user. Since the two dangerous factors are at equal distances from the user, it is necessary to provide the user with danger warnings at the same time.

[0081] It is understandable that if multiple dangerous factors appear at different distances from the user but the distances between the dangerous factors are close, it is also necessary to simultaneously warn the user of the danger to prevent the user from being injured because the next danger is too close after avoiding the nearest danger.

[0082] Through danger prompts, users with visual impairments can understand the dangers in their environment and choose corresponding measures to avoid danger.

[0083] It should be noted that in the embodiment of the present application, in addition to reminding the user of the location of the danger, the user will also be prompted to avoid the danger. Figure 5 , is a schematic diagram of a danger avoidance prompt step provided in an embodiment of the present application, such as Figure 5 As shown, the danger avoidance prompting method in the embodiment of the present application may include but is not limited to steps S210 to S230: Step S210: extracting safety information based on environmental information, where the safety information includes path information for avoiding danger.

[0084] It should be noted that after the dangerous factors are identified, the area information where there are no dangerous factors is a safe area. At this time, it is necessary to determine the path information that can avoid the danger from the safe area, and then the safety information is obtained; the extraction of safety information is also completed through the visual model used in the embodiment of the present application. Please refer to the previous description for the description of the visual model, which will not be repeated here.

[0085] Exemplarily, in an embodiment of the present application, security information is extracted through the YOLOv5 model. After the dangerous factors in the environmental information are identified, the safe area in the environmental information that does not contain the dangerous factors is determined, and the security information is extracted based on the dangerous factors and the safe area in the environmental information.

[0086] Specifically, in a feasible embodiment of the present application, when the dangerous factor in the identified environmental information is 100 meters in front of the left, the safety information is extracted; if it is determined in the environmental information that the area 100 meters in front of and right of the user is a safe area that does not include dangerous factors, then the front and right front are determined to be safe areas. At this time, the dangerous factor in front of the left of the user is used as the starting point of the path information, and the right front of the user is used as the end point of the path information to determine the safety information.

[0087] The embodiment of the present application determines safety information for controlling the output of the electrotactile signal based on the modulation signal, and performs step S220.

[0088] Step S220: Determine a second electrode according to the security information, the second electrode being an electrode corresponding to the plurality of path information, the second electrode adjacent to the first electrode being the starting second electrode, and the second electrode farthest from the first electrode being the ending second electrode.

[0089] It should be noted that in the embodiment of the present application, since the path information represents a route that avoids dangerous factors, when reminding the user, multiple electrodes are required to output electrotactile signals based on the modulated signal, and the multiple electrodes that output safety information are the second electrodes.

[0090] It can be understood that the first electrode corresponds to the dangerous direction, that is, it indicates the position of the dangerous factor in the environment relative to the user, and the starting point of the path information is the dangerous factor, and the focus of the path information is the point in the safe area. Therefore, the starting point second electrode in the embodiment of the present application is adjacent to the first electrode, and at the same time, the starting point second electrode corresponds to the starting point of the path information, and the end point second electrode corresponds to the end point of the path information. The middle second electrode is the electrode selected according to the path information.

[0091] Illustratively, in an embodiment of the present application, the danger factor is located in front of the left of the user, and the first electrode corresponds to the danger factor located in front of the left. After the path information is determined, the starting second electrode is adjacent to the first electrode and corresponds to the starting point of the path information. The remaining second electrodes correspond to the path information, and all the second electrodes are determined to be used to prompt the user.

[0092] Illustratively, in another embodiment of the present application, on the one hand, when there are multiple risk factors in the environmental information, the nearest risk factor is given priority, and the safety information determines the path information based on the risk factor closest to the user; on the other hand, when two risk factors are found to be at the same distance from the user, the user is given a risk warning at the same time, and the optimal safe path is selected according to the safety information to prompt the user.

[0093] Specifically, in a feasible embodiment of the present application, when it is identified that there are dangerous factors both 50 meters to the left of the user and 100 meters directly in front of the user, firstly, the first safety information is determined, that is, the safety information corresponding to the path information including the dangerous factors 50 meters to the left of the user is avoided; after the user avoids the danger in the left front, the second safety information is determined, that is, the safety information corresponding to the path information including the dangerous factors 100 meters directly in front of the user is avoided. The first safety information and the second safety information are used to help the user avoid danger.

[0094] In another feasible embodiment of the present application, when it is identified that there are danger factors 100 meters to the left and 100 meters to the right of the user, and it is determined that the two danger factors are at equal distances from the user, the user is prompted with danger according to the first danger warning information and the second danger warning information at the same time. At this time, it is necessary to determine the distance between the danger factors and determine the safe path according to the danger type: When the distance between two dangerous factors is large and the dangerous type is not likely to cause serious harm to the user, a safe path can be selected that passes through the middle of the two dangerous factors to guide the user through. For example, if there are large rubber barriers between the two dangerous factors, even if the user accidentally bumps against them from the side, they will not fall or get hurt. In this case, a safe path can be selected to guide the user through the middle. When two dangerous factors are close to each other or the type of danger is one that may cause serious injury, it is necessary to select a safe path that allows the user to dodge. In this case, the safe path is a path that bypasses the danger to prevent the user from being hurt.

[0095] By selecting a safe path, users are prompted so that they can avoid dangers ahead according to the prompts and avoid harm caused by the dangers.

[0096] Step S230, starting from the second electrode at the starting point to the second electrode at the ending point, sequentially outputting electrotactile signals based on the modulation signal to implement a danger avoidance prompt.

[0097] It can be understood that after the second electrode is determined, an electrotactile signal based on the modulated signal can be output according to the second electrode to implement a danger avoidance prompt, prompting the user to avoid the danger.

[0098] In an embodiment of the present application, when a dangerous factor that needs to be avoided appears in front of the left side of the user, the second electrode sequentially outputs electrotactile signals based on the modulated signal from left to right to inform the user of the avoidance direction. Similarly, in other cases, when there is only one dangerous factor in the environmental information or there are multiple dangerous factors that are at different distances from the user and far away from each other, multiple second electrodes sequentially output electrotactile signals based on the modulated signal to provide danger avoidance prompts, prompting the user to avoid.

[0099] For example, please refer to Figure 6 , is a schematic diagram of electrode changes during avoidance prompting provided in an embodiment of the present application, such as Figure 6 As shown, in the embodiment of the present application, there may be two ways to prompt avoidance.

[0100] Reference Figure 6 Mode 1, in a feasible embodiment of the present application, the electrodes are worn on the fingertips of the user, fit on the fingers of the user, and two second electrodes are used to provide danger avoidance prompts; When it is determined that there is danger in front of the left of the user, safety information is extracted based on environmental information, and the safety information includes path information for avoiding the danger, which is to dodge to the right; at this time, the number of second electrodes confirmed according to the safety information is 2, of which the starting second electrode is in the front left, and the ending second electrode is in the front right; starting from the starting second electrode to the ending second electrode, electrotactile signals based on the modulated signal are output sequentially to realize danger avoidance prompts. Since only 2 second electrodes are used at this time, the ending second electrode directly outputs after the starting second electrode outputs (the arrows in the figure indicate the activation sequence direction).

[0101] pass Figure 6 Method 1, which uses only two second electrodes to complete the danger avoidance prompt, is more suitable for saving power and achieving long-term prompting when the user needs to use it for a long time.

[0102] Reference Figure 6 Mode 2, in another feasible embodiment of the present application, the electrodes are worn between the user and fit on the user's fingers, and at this time, more than two electrodes are used to provide danger avoidance prompts; When it is determined that there is danger in front of the left of the user, safety information is extracted according to the environmental information, and the safety information includes path information for avoiding the danger, which is to dodge to the right; different from method 1, the number of second electrodes confirmed according to the safety information is 5, among which the starting second electrode is in the front left (shaded by a left slash), the ending second electrode is in the front right, and the electrode between the starting second electrode and the ending second electrode is the middle second electrode (shaded by a right slash); starting from the starting second electrode to the ending second electrode, electrotactile signals based on the modulated signal are output sequentially to realize danger avoidance prompts, that is, starting from the starting second electrode, passing through the middle second electrode, and finally to the ending second electrode, electrotactile signals based on the modulated signal are output sequentially in the direction indicated by the arrows of method two to realize danger avoidance prompts.

[0103] pass Figure 6 Method 2 can more clearly inform the user of the direction to avoid danger and help the user to avoid danger.

[0104] It should be noted that when there are two or more dangerous factors at the same distance from the user, the user is warned of danger at the same time, and the optimal safe path is selected according to the safety information to warn the user. The safe path at this time is as described above. When the dangerous factors are far apart, the user is guided to pass through the middle. At this time, there are multiple starting second electrodes corresponding to the starting points of the path information. The electrotactile signals based on the modulated signals are output sequentially from the starting second electrodes. The second electrode corresponding to the end point of the path information is located in the safe zone between the dangerous factors. In the embodiment of the present application, Figure 7 As shown in the figure, the electrode positions before and after the electrode indication changes correspond one to one.

[0105] On the one hand, when guiding the user to pass through the middle, the end point of the path information can be fixed, and the starting point of the path can be changed in real time to remind the user which side of the dangerous factor the user is approaching when changing direction, thereby achieving guidance, that is, Figure 7 Mode 1 includes two cases, Mode 1a and Mode 1b. In this case, there are second electrodes at both ends. The second electrodes at the starting point change as the user's position changes. Electrotactile signals based on the modulated signal are sequentially outputted from the second electrodes at the starting point to remind the user of the direction to avoid. It should be noted that in the embodiment of the present application, in method 1a, there are two obstacles in the same plane in the direction of the user's advance. When the user moves forward, the safety distance of the obstacle in the left front of the user's advance (i.e., the upper part in the figure) changes greatly as the user moves forward, while the safety distance of the obstacle in the right front of the user's advance (i.e., the lower part in the figure) changes less as the user moves forward. At this time, as the user moves, the second electrode at the starting point in front of the left of the user will change, while the second electrode at the starting point in front of the right will not change. Different from method 1a, in method 1b, when the safety distance of the obstacles in the left front (i.e., the upper part in the figure) and the right front (i.e., the lower part in the figure) in the direction of the user's advance both change greatly as the user moves, the second electrode at the starting point in front of the left of the user and the second electrode at the starting point in front of the right will both change as the user moves, thereby prompting the user to pass the obstacle safely.

[0106] On the other hand, the starting point can be fixed, and the end point prompt can be changed as the user moves to achieve guidance, that is, Figure 7 In method 2, there are also starting second electrodes at both ends. The difference from method 1 is that the starting second electrode in method 2 does not change with the change of the user's position, but the ending second electrode changes with the change of the user's position, and the electrotactile signal based on the modulated signal is output sequentially starting from the starting second electrode to remind the user of the direction to avoid.

[0107] In an embodiment of the present application, in the danger warning based on the danger type, there is also a safe path judgment of the traffic light. If the danger type is that the traffic light turns red, the user needs to be guided to stop moving forward through safety information. Exemplarily, at this time, a special electrode output method can be used for prompting, such as continuously outputting electrotactile signals based on modulated signals through all electrodes, and reminding the user to stop moving forward through large-area output.

[0108] The electrotactile signals based on the modulated signals are outputted through the multiple second electrodes to give the user a prompt to avoid danger, thereby realizing the function of avoiding danger.

[0109] It should be noted that in the embodiment of the present application, the electrotactile signal based on the modulated signal is divided into at least a first signal, a second signal and a third signal according to the intensity, and the electrotactile signals based on the modulated signal of different intensities correspond to different danger types; It can be understood that, as mentioned above, the higher the intensity of the electrotactile signal based on the modulated signal, the sensation produced will gradually change from vibration to tingling. In the embodiment of the present application, in order to distinguish different types of dangers so that users can distinguish the dangers and take different countermeasures, a method of controlling the intensity of the electrotactile signal based on the modulated signal is adopted. The electrotactile signal based on the modulated signal is divided into at least a first signal, a second signal and a third signal according to the intensity. At each level of intensity, the electrotactile signal based on the modulated signal is output through the electrodes so that the user can feel different sensations.

[0110] It is understandable that the intensity of the electrotactile signal is achieved by controlling the magnitude of the voltage, as described above.

[0111] Therefore, by controlling the intensity of the electrotactile signal based on the modulation signal, a method for distinguishing the types of dangers is implemented, so that the user can understand the types of dangers in the environment by relying on the output electrotactile signal based on the modulation signal.

[0112] According to the danger distance and the danger type, the intensity and frequency of the electrotactile signal based on the modulated signal generated by the control electrode are controlled to realize the prompt of the danger distance and the danger type, including: Depending on the danger type, an electrotactile signal based on the modulation signal corresponding to the danger type is output.

[0113] It should be noted that the types of danger in the embodiments of the present application can be divided into types according to the degree of danger, and different types of dangers can be matched with electrotactile signals based on the modulation signal.

[0114] Illustratively, in one embodiment of the present application, a danger that may cause minor injury is corresponded to a first signal, and the danger that may cause minor injury may include but is not limited to: protruding corners that may cause bumps, etc.; a danger that may cause moderate injury is corresponded to a second signal, and the danger that may cause moderate injury may include but is not limited to: steps and roadblocks that may cause tripping, etc.; a danger that may cause serious injury is corresponded to a third signal, and the danger that may cause serious injury may include but is not limited to: sinking ground that may cause falling or sewers without manhole covers, roads with red lights, etc.

[0115] When the danger type is obtained, the corresponding signal strength is selected according to the danger type, and the corresponding electrotactile signal based on the modulated signal is output through the electrode, so as to realize the prompt of the danger type.

[0116] It should be noted that in the embodiment of the present application, in addition to the prompt of the danger type, it is also necessary to remind the user of the danger distance to avoid the danger caused by the user's failure to avoid it in time.

[0117] Exemplarily, in an embodiment of the present application, the intensity and frequency of the electrotactile signal based on the modulated signal generated by the control electrode are controlled according to the danger distance and the danger type to realize the prompt of the danger distance and the danger type, and further includes: According to the danger distance, the generation frequency of the electrotactile signal based on the modulation signal is controlled, and the generation frequency of the electrotactile signal based on the modulation signal increases as the danger distance decreases.

[0118] It can be understood that the closer the user is to the dangerous factor, the higher the frequency of generating the electrotactile signal based on the modulated signal, and at the same time, the frequency of the electrotactile signal based on the modulated signal output by the electrode increases at the same time. Therefore, the user can clearly know the distance between himself and the danger through the stimulation frequency of the electrotactile signal based on the modulated signal, thereby realizing the notification of the dangerous distance.

[0119] The danger warning method, device and storage medium provided in the embodiments of the present application determine the danger source through the acquired environmental information, and remind the user in the form of an electrotactile signal based on a modulated signal. By controlling the micro-current energy signal, multiple touch and orientation prompts can be achieved, corresponding to different types of dangers and danger orientations, to achieve effective and economical danger warnings, helping people with visual impairments avoid danger. At the same time, the current acts directly on the user's body, avoiding the problem of needing to control the volume when using voice reminders.

[0120] The embodiment of the present application further discloses a computer-readable storage medium, which stores a computer program executable by a processor. When the computer program executable by the processor is executed by the processor, it is used to implement the danger warning method as described above.

[0121] An embodiment of the present application also discloses a computer program product, including a computer program or computer instructions, wherein the computer program or computer instructions are stored in a computer-readable storage medium, a processor of an electronic device reads the computer program or computer instructions from the computer-readable storage medium, and the processor executes the computer program or computer instructions, so that the electronic device executes the danger warning method as described above.

[0122] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0123] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0124] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0125] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories), or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0126] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0128] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program codes.

[0129] The step numbers in the above method embodiment are only provided for the convenience of explanation and description, and no limitation is imposed on the order of the steps. The execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

Claims

1. A danger warning method, characterized in that: Applied to a danger warning device, the danger warning device comprises: a main control module, an information acquisition module and a signal generation module provided with a plurality of electrodes, the method comprises the following steps: Acquiring environmental information through the information acquisition module; Inputting the environmental information into a main control module, and extracting danger warning information from the environmental information through a preset visual model in the main control module, wherein the danger warning information includes danger direction, danger distance, and danger type; Based on the danger warning information, a danger prompt is generated, and the danger prompt is an electrotactile signal based on a modulated signal. The danger prompt is generated by the signal generating module and output through a plurality of the electrodes; wherein, the danger direction prompt is realized by outputting the electrotactile signal based on the modulated signal through the electrodes in corresponding positions in the signal generating module, and the danger distance and danger type prompt are realized by controlling the intensity and frequency of the electrotactile signal based on the modulated signal output by the electrodes.

2. The method according to claim 1, characterized in that The outputting of the electrotactile signal based on the modulated signal by the electrodes at the corresponding positions in the signal generating module to realize the danger position prompt includes: A first electrode is determined according to the dangerous position, the position of the first electrode in the signal generating module corresponds to the dangerous position, and the first electrode outputs an electrotactile signal based on a modulated signal to realize a dangerous position prompt.

3. The method according to claim 2, characterized in that The method further comprises: Extracting safety information according to the environmental information, the safety information including path information to avoid danger; Determine a second electrode according to the security information, where the second electrode is an electrode corresponding to the plurality of path information, wherein the second electrode adjacent to the first electrode is a starting second electrode, and the second electrode farthest from the first electrode is a terminal second electrode; Starting from the second electrode at the starting point to the second electrode at the ending point, electrotactile signals based on the modulation signal are sequentially output to realize danger avoidance prompt.

4. The method according to claim 1, characterized in that: The electrotactile signal based on the modulated signal is divided into at least a first signal, a second signal and a third signal according to its intensity, and the electrotactile signal based on the modulated signal with different intensities corresponds to different danger types; The method of realizing the prompt of the danger distance and the danger type by controlling the intensity and frequency of the electrotactile signal based on the modulation signal generated by the electrode according to the danger distance and the danger type includes: According to the danger type, an electrotactile signal based on a modulation signal corresponding to the danger type is output.

5. The method according to claim 1, characterized in that The method of realizing the prompt of the danger distance and the danger type by controlling the intensity and frequency of the electrotactile signal based on the modulation signal generated by the electrode according to the danger distance and the danger type includes: According to the danger distance, the generation frequency of the electrotactile signal based on the modulation signal is controlled, and the generation frequency of the electrotactile signal based on the modulation signal increases as the danger distance decreases.

6. The method according to claim 1, characterized in that The extracting danger warning information from the environmental information by using a preset visual model in the main control module includes: Establishing a coordinate system according to the environmental information; Identify the risk factors in the environmental information, and determine the coordinate information and risk type of the risk factors; The dangerous direction and the dangerous distance are determined according to the coordinate information of the dangerous factor.

7. The method according to claim 1, characterized in that The electrotactile signal based on the modulation signal is a bi-phase modulation signal.

8. A danger warning device, characterized in that: include: A main control module, an information acquisition module and a signal generation module, wherein the main control module is connected to the information acquisition module and the signal generation module respectively; The information acquisition module is used to acquire environmental information and input it into the main control module; The main control module includes a preset visual model, the main control module obtains the environmental information, and extracts danger warning information through the preset visual model, the danger warning information includes danger direction, danger distance and danger type; The signal generating module includes a signal generating component, a plurality of electrodes and a fixing module. The signal generating component is connected to the plurality of electrodes. A danger prompt is generated through the signal generating module. The danger prompt is an electrotactile signal based on a modulated signal, and the danger prompt is output through the plurality of electrodes.

9. The device according to claim 8, characterized in that The signal generating module further comprises a fixing module; The fixing module is used to fix the plurality of electrodes, and the user wears the plurality of electrodes through the fixing module.

10. A computer-readable storage medium, characterized in that: A computer program executable by a processor is stored therein, and when the computer program executable by the processor is executed by the processor, it is used to implement the method according to any one of claims 1 to 7.

Images