Emergency rescue system and method based on brain-computer interface

Abstract

The invention relates to an emergency rescue method and system based on a brain-computer interface, electronic equipment and a storage medium. The method comprises the steps that a preset device is adopted, real-time telemetering rescue image data are displayed to rescue workers according to a preset mode, electroencephalogram EEG data of the rescue workers are collected, and event-related potential ERP components in the EEG data are extracted; the event-related potential ERP data and the electroencephalogram EEG data are preprocessed respectively and then serve as input of a double-end LSTM model, target classification and task load detection task processing are conducted on the event-related potential ERP data and the electroencephalogram EEG data, and target information and a task load state are generated; and after performing priority ranking on the target information, updating emergency rescue task allocation based on a task load state. The instruction set of a traditional emergency rescue command system can be expanded, the advantages of rapidness, high efficiency, optimal scheduling and the like are met based on the brain-computer interface technology, and emergency rescue becomes more flexible and rapid.

Description

Technical Field

[0001] The present disclosure relates to the field of brain-computer interface, and in particular to an emergency rescue method, device, electronic device and computer-readable storage medium based on a brain-computer interface. Background Art

[0002] In modern emergency rescue, the ability to quickly and accurately obtain information is crucial for improving rescue efficiency in the face of natural disasters or emergencies. Traditional manual search methods are not only time-consuming but also carry high risks in complex environments. In recent years, the development of brain-computer interface (BCI) technology, which assists or guides rescue operations by reading and analyzing brain signals, has provided new ideas and technical means for emergency rescue.

[0003] RSVP is a stimulus presentation paradigm widely used in EEG and psychology experiments. Its core is to present visual stimuli, such as text and images, in a rapid, continuous sequence at a specific screen location. These stimuli appear one after another at extremely short intervals (typically within a few hundred milliseconds), allowing users to quickly process and attend to each stimulus. This task is primarily designed to explore human attention, cognitive function, and information processing capabilities. By observing participants' responses to rapidly presented stimuli, we can gain insight into how the brain processes continuous information in a short period of time and how attention changes during this process.

[0004] To more deeply analyze brain activity patterns during RSVP tasks, brain imaging techniques such as electroencephalography (EEG) are often used to record event-related potentials (ERPs). ERPs refer to changes in electrical potential caused by neuronal activity in the brain in response to specific stimuli. Combining the RSVP task with ERP measurement effectively captures the brain's transient response to rapid, continuous stimulation, thereby revealing the user's observational goals.

[0005] In emergency rescue scenarios, an efficient rescue information processing system has been developed using RSVP-ERP technology. By presenting rescuers with a series of potential rescue target images (such as photos of trapped people and the location of rescue supplies) and monitoring their EEG activity, it can quickly determine which information has caught their attention.

[0006] There is no related technical solution in the prior art. Therefore, one or more methods are needed to solve the above problems.

[0007] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute prior art known to ordinary technicians in the field. Summary of the Invention

[0008] The purpose of the present disclosure is to provide an emergency rescue method, device, electronic device and computer-readable storage medium based on a brain-computer interface, thereby overcoming one or more problems caused by the limitations and defects of related technologies to at least a certain extent.

[0009] According to one aspect of the present disclosure, there is provided an emergency rescue method based on a brain-computer interface, comprising:

[0010] Using a preset device, real-time telemetry rescue image data is displayed to rescuers in a preset manner, EEG data of the rescuers is collected, and event-related potential (ERP) components are extracted therefrom;

[0011] After preprocessing the event-related potential (ERP) data and the electroencephalogram (EEG) data, the data are used as inputs of a two-headed LSTM model to perform target classification and task load detection on the event-related potential (ERP) data and the electroencephalogram (EEG) data to generate target information and task load status;

[0012] After prioritizing the target information, the emergency rescue task allocation is updated based on the task load status.

[0013] In an exemplary embodiment of the present disclosure, the method further includes:

[0014] Using AR glasses, real-time telemetry rescue image data is encoded into image sequences in chronological order and displayed to rescuers at a rate of 10 Hz.

[0015] In an exemplary embodiment of the present disclosure, the method further includes:

[0016] Collecting EEG data of the rescuer based on Neuroscan 64-lead EEG instrument and extracting event-related potential (ERP) components therefrom;

[0017] Based on the MQTT communication protocol, the real-time collected event-related potential ERP data and electroencephalogram (EEG) data are sent to the rescue information comprehensive processing system.

[0018] In an exemplary embodiment of the present disclosure, the method further includes:

[0019] After preprocessing of EEG data by removing artifacts and filtering, time-frequency analysis was performed, and the energy characteristics of the α-wave, β-wave and γ-wave frequency bands were extracted based on wavelet transform and short-time Fourier transform.

[0020] In an exemplary embodiment of the present disclosure, the method further includes:

[0021] The P300 features of event-related potential ERP data are extracted and the extracted features are fused to generate a high-dimensional feature vector.

[0022] In an exemplary embodiment of the present disclosure, the dual-headed LSTM model of the method further includes:

[0023] The target classification head is used to identify target stimuli in the input signal. The network structure includes a preset number of LSTM layers, followed by a fully connected layer and a softmax activation function, and outputs the probability distribution of each category;

[0024] The load detection head is used to evaluate the user's cognitive load level. The network structure includes a preset number of LSTM layers, followed by a fully connected layer, and an output layer regression method to predict the load score.

[0025] In an exemplary embodiment of the present disclosure, the method further includes:

[0026] Prioritizing the target information;

[0027] Filter target information based on preset task load status thresholds;

[0028] The emergency rescue task allocation is updated based on the priority sorting and screening results.

[0029] In one aspect of the present disclosure, there is provided an emergency rescue system based on a brain-computer interface, comprising:

[0030] An EEG data acquisition module is used to display real-time telemetry rescue image data to rescuers in a preset manner using a preset device, collect EEG data of the rescuers, and extract event-related potential (ERP) components therefrom;

[0031] An EEG data analysis module is used to pre-process the event-related potential (ERP) data and the electroencephalogram (EEG) data, respectively, and use them as inputs of a two-headed LSTM model to perform target classification and task load detection on the event-related potential (ERP) data and the electroencephalogram (EEG) data, thereby generating target information and task load status.

[0032] The rescue mission update module is used to update the emergency rescue mission allocation based on the mission load status after prioritizing the target information.

[0033] In one aspect of the present disclosure, there is provided an electronic device, comprising:

[0034] processor; and

[0035] A memory having computer-readable instructions stored thereon, wherein the computer-readable instructions, when executed by the processor, implement the method according to any one of the above items.

[0036] In one aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method according to any one of the above items is implemented.

[0037] An emergency rescue method based on a brain-computer interface in an exemplary embodiment of the present disclosure, wherein the method includes: using a preset device to display real-time telemetry rescue image data to rescue personnel in a preset manner, collecting electroencephalogram (EEG) data of the rescue personnel, and extracting event-related potential (ERP) components therefrom; pre-processing the event-related potential (ERP) data and electroencephalogram (EEG) data respectively, and using them as inputs of a dual-headed LSTM model to perform target classification and task load detection task processing on the event-related potential (ERP) data and electroencephalogram (EEG) data, generating target information and task load status; after prioritizing the target information, updating the emergency rescue task allocation based on the task load status. The present disclosure can expand the instruction set of the traditional emergency rescue command system, and based on the brain-computer interface technology, meet the advantages of fast, efficient, and optimized scheduling, making emergency rescue more flexible and rapid.

[0038] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The above and other features and advantages of the present disclosure will become more apparent by describing in detail example embodiments thereof with reference to the accompanying drawings.

[0040] Figure 1 A flowchart of an emergency rescue method based on a brain-computer interface according to an exemplary embodiment of the present disclosure is shown;

[0041] Figure 2 A flowchart of an implementation of an emergency rescue system based on a brain-computer interface according to an exemplary embodiment of the present disclosure is shown;

[0042] Figure 3 A structural block diagram of an emergency rescue system based on a brain-computer interface according to an exemplary embodiment of the present disclosure is shown;

[0043] Figure 4 A block diagram schematically illustrates an electronic device according to an exemplary embodiment of the present disclosure;

[0044] Figure 5A schematic diagram schematically illustrates a computer-readable storage medium according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0045] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art. Like reference numerals in the drawings represent like or similar parts, and thus repetitive description thereof will be omitted.

[0046] In addition, the described features, structures or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure can be practiced without one or more of the specific details, or other methods, components, materials, systems, steps, etc. can be adopted. In other cases, well-known structures, methods, systems, implementations, materials or operations are not shown or described in detail to avoid blurring various aspects of the present disclosure.

[0047] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. Specifically, these functional entities may be implemented in software, or in one or more software-hardened modules, or in different networks and / or processor systems and / or microcontroller systems.

[0048] In this exemplary embodiment, a brain-computer interface-based emergency rescue method is first provided; Figure 1 As shown in , the emergency rescue method based on brain-computer interface may include the following steps:

[0049] Step S110: using a preset device, displaying the real-time telemetry rescue image data to the rescuer in a preset manner, collecting the EEG data of the rescuer, and extracting the event-related potential (ERP) component therefrom;

[0050] Step S120, after pre-processing the event-related potential (ERP) data and the electroencephalogram (EEG) data, the data are used as inputs of a two-headed LSTM model to perform target classification and task load detection on the event-related potential (ERP) data and the electroencephalogram (EEG) data to generate target information and task load status;

[0051] Step S130: After prioritizing the target information, the emergency rescue task allocation is updated based on the task load status.

[0052] An emergency rescue method based on a brain-computer interface in an exemplary embodiment of the present disclosure, wherein the method includes: using a preset device to display real-time telemetry rescue image data to rescue personnel in a preset manner, collecting electroencephalogram (EEG) data of the rescue personnel, and extracting event-related potential (ERP) components therefrom; pre-processing the event-related potential (ERP) data and electroencephalogram (EEG) data respectively, and using them as inputs of a dual-headed LSTM model to perform target classification and task load detection task processing on the event-related potential (ERP) data and electroencephalogram (EEG) data, generating target information and task load status; after prioritizing the target information, updating the emergency rescue task allocation based on the task load status. The present disclosure can expand the instruction set of the traditional emergency rescue command system, and based on the brain-computer interface technology, meet the advantages of fast, efficient, and optimized scheduling, making emergency rescue more flexible and rapid.

[0053] Below, an emergency rescue method based on a brain-computer interface in this example embodiment will be further described.

[0054] Example 1:

[0055] In step S110, a preset device may be used to display the real-time telemetry rescue image data to the rescuer in a preset manner, collect the EEG data of the rescuer, and extract the event-related potential (ERP) component therefrom.

[0056] In this exemplary embodiment, the method further includes:

[0057] Using AR glasses, real-time telemetry rescue image data is encoded into image sequences in chronological order and displayed to rescuers at a rate of 10 Hz.

[0058] In this exemplary embodiment, the method further includes:

[0059] Collecting EEG data of the rescuer based on Neuroscan 64-lead EEG instrument and extracting event-related potential (ERP) components therefrom;

[0060] Based on the MQTT communication protocol, the real-time collected event-related potential ERP data and electroencephalogram (EEG) data are sent to the rescue information comprehensive processing system.

[0061] In step S120, the event-related potential ERP data and electroencephalogram EEG data can be preprocessed separately and used as input of a two-headed LSTM model to perform target classification and task load detection task processing on the event-related potential ERP data and electroencephalogram EEG data to generate target information and task load status.

[0062] In this exemplary embodiment, the method further includes:

[0063] After preprocessing of EEG data by removing artifacts and filtering, time-frequency analysis was performed, and the energy characteristics of the α-wave, β-wave and γ-wave frequency bands were extracted based on wavelet transform and short-time Fourier transform.

[0064] In this exemplary embodiment, the method further includes:

[0065] The P300 features of event-related potential ERP data are extracted and the extracted features are fused to generate a high-dimensional feature vector.

[0066] In the embodiment of this example, the dual-headed LSTM model of the method further includes:

[0067] The target classification head is used to identify target stimuli in the input signal. The network structure includes a preset number of LSTM layers, followed by a fully connected layer and a softmax activation function, and outputs the probability distribution of each category;

[0068] The load detection head is used to evaluate the user's cognitive load level. The network structure includes a preset number of LSTM layers, followed by a fully connected layer, and an output layer regression method to predict the load score.

[0069] In step S130, after the target information is prioritized, the emergency rescue task allocation may be updated based on the task load status.

[0070] In this exemplary embodiment, the method further includes:

[0071] Prioritizing the target information;

[0072] Filter target information based on preset task load status thresholds;

[0073] The emergency rescue task allocation is updated based on the priority sorting and screening results.

[0074] In this exemplary embodiment, the disclosed emergency rescue system and method based on brain-computer interface (BCI) technology addresses the problems of slow information acquisition, inefficient decision-making, and high safety risks for rescuers in existing rescue processes. RSVP technology is used to quickly present images of rescue targets, combined with electroencephalogram (EEG) recording of rescuers' brain activity, enabling efficient processing and screening of large amounts of information, ensuring that key information can be quickly identified. At the same time, the system can intelligently recommend optimal rescue paths and strategies based on the rescuer's attention state and environmental information, rationally allocate rescue resources, and improve overall rescue efficiency.

[0075] In this exemplary embodiment, the EEG data collection step includes:

[0076] This invention proposes encoding real-time telemetry rescue image data into an image sequence in chronological order and presenting it in AR glasses at a rate of 10Hz. The user wears AR glasses and a Neuroscan 64-lead EEG device. The electrodes used are all Ag / AgCl electrodes, and conductive paste or hydrogel electrodes are used to ensure good skin contact and signal conduction. The corresponding image-EEG data pairs are induced by observing the image sequence. This process uses edge computing devices to stimulate the presentation of images and collect EEG data. The real-time collected EEG data is sent to the rescue information integrated processing system for data analysis based on the MQTT communication protocol.

[0077] In this exemplary embodiment, the EEG data analysis step includes:

[0078] During EEG data preprocessing, the EEG signal is first de-artifacted using independent component analysis to remove artifacts such as eye movements and electromyography. This is crucial for improving the accuracy of subsequent analysis. Next, a bandpass filter (0.1-40 Hz) is applied to eliminate low-frequency drift and high-frequency noise. This process ensures the clarity of the EEG signal and provides a good foundation for feature extraction. The core of the feature extraction stage is to extract features related to target classification and cognitive load. We will perform time-frequency analysis, using wavelet transforms (such as Morlet wavelets) and short-time Fourier transforms (STFTs) to extract energy features in different frequency bands (such as alpha, beta, and gamma waves). Simultaneously, we will calculate event-related potentials (ERPs), such as the amplitude and latency of the P300 wave. After extraction, the resulting features will be formed into a high-dimensional feature vector, which will serve as input for subsequent models. For the classifier, we will construct a two-headed LSTM model for result recognition. In this model design, the two-headed LSTM architecture will simultaneously handle target classification and task load detection. The input of the model is the extracted EEG feature sequence, and the model will consist of two branches:

[0079] Object Classification Head: This part is responsible for identifying target stimuli in the input signal. The network structure consists of multiple LSTM layers followed by a fully connected layer and a softmax activation function, outputting a probability distribution for each category. The main purpose of object classification is to identify which stimulus images are rescue targets and their categories.

[0080] The basic calculation formula of LSTM unit is as follows:

[0081] Forget Gate f t :

[0082] f t =σ(W f ·[h t-1 ,xt ]+b f )

[0083] Input gate i t :

[0084] i t =σ(W i ·[h t-1 ,x t ]+b i )

[0085] Candidate cell states

[0086]

[0087] Cell state update C t :

[0088]

[0089] Output Gate O t :

[0090] O t =σ(W o ·[h t-1 ,x t ]+b o )

[0091] Hidden state update h t :

[0092] C t =O t tanh(C t )

[0093] Finally, the output of the target classification is calculated through the softmax function:

[0094]

[0095] where h T is the hidden state of the last time step, which represents the information summary of the entire sequence, W target and b target are the weights and biases of the classification head.

[0096] Load detection: This component assesses the user's cognitive load. The network architecture also consists of an LSTM layer followed by a fully connected layer, but the output layer uses regression techniques (such as a linear activation function) to predict the load score. Load detection helps understand how the user's cognitive load changes under different stimulation conditions, allowing for more effective task allocation during rescue information dispatch.

[0097]

[0098] Similarly, h T is the hidden state of the last time step, W load and b load are the weight and bias of the load detection head.

[0099] In the calculation of LSTM unit, t represents the current time step. t Represents the input feature vector of the current time step. h t-1 Represents the hidden state vector of the previous time step. W f , W i , W c , W o is the weight matrix of the forget gate, input gate, candidate cell state and output gate. f , b i , b c , b o is the bias vector of the forget gate, input gate, candidate cell state and output gate. t The output of the forget gate determines how much information about the previous cell state is retained. t The output of the input gate determines the extent to which the current input affects the cell state. Candidate cell state, representing the new information generated by the current input and the previous hidden state. t-1 is the cell state at the previous time step. C t is the cell state at the current time step, which is updated by the forget gate and input gate. t The output of the output gate determines the degree of influence of the current cell state on the hidden state. t is the hidden state of the current time step, which contains a comprehensive representation of the current input and past information.

[0100] In this exemplary embodiment, the rescue information comprehensive dispatch step includes:

[0101] By comprehensively identifying RSVP target information and task load status, the rescue information generation part uses mathematical models to automatically form effective rescue strategies and task allocation. First, the identified target information is prioritized. Let G be the target information set, g i For each target in the set, the priority can be expressed by the function P(g i ) indicates that the priority and the importance of the target I(g i ), position L(g i ) and state S(g i ). The following formula can be defined:

[0102] P(g i )=α·I(g i )+β·L(gi )+γ·S(g i )

[0103] Among them, α, β, and γ are weight coefficients, reflecting the relative importance of each factor to the priority. The system sorts the goals according to the calculated priority value to ensure that urgent tasks are processed first. Next, the system also needs to monitor the cognitive load status of the participants in real time. Let L p The task load of the participants can be represented by the LSTM model output:

[0104]

[0105] When assigning tasks, the system will give priority to the load status below a certain threshold T. Finally, the task assignment will be dynamically adjusted according to the priority and load status. Let T n For the current task set, update the task allocation T′ by the following formula n :

[0106] T′ n ={g i ∈G|P(g i )is high&L p <T}

[0107] All generated rescue information is displayed through a situational interface, helping decision-makers quickly access real-time data and mission progress. This mechanism not only optimizes resource allocation, but also ensures the flexibility and efficiency of rescue operations, supporting more accurate decision-making through scientific mathematical models.

[0108] In the embodiment of this example, the emergency rescue system and method based on brain-computer interface (BCI) and rapid continuous visual presentation (RSVP) technology disclosed in the present invention has the following significant beneficial effects compared with the existing technology: (1) Improve information processing speed and quickly identify key information: By quickly presenting the rescue target image through RSVP technology and combining it with electroencephalogram (EEG) to record the brain activity of the rescuer, key information can be quickly identified and the information processing speed can be improved. (2) Reduce information omission and enhance decision accuracy: The system can automatically detect the attention state of the rescuer to ensure that important information is not ignored, thereby improving the comprehensiveness and accuracy of information processing. Based on the machine learning algorithm LSTM, a classification model is constructed to identify the attention state of the rescuer to a specific stimulus based on the ERP (event-related potential) waveform of the rescuer, thereby improving the accuracy and reliability of decision-making. (3) Intelligently recommend the optimal strategy and optimize resource allocation: The system can intelligently recommend the optimal rescue path and strategy based on the attention state of the rescuer and environmental information, reduce human errors, and improve the quality of decision-making. The system can intelligently allocate rescue resources based on the load status of the rescuer, improve resource utilization efficiency, and ensure the smooth progress of the rescue operation. (4) Wide applicability and strong scalability: The system is not only suitable for rescue in natural disasters such as earthquakes and fires, but can also be extended to other emergency situations such as traffic accidents and landslides. It has wide applicability and flexibility. It can be customized and expanded according to different rescue needs to meet diverse application scenarios.

[0109] It should be noted that although the steps of the method disclosed herein are depicted in a particular order in the accompanying drawings, this does not require or imply that the steps must be performed in that particular order, or that all steps must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one, and / or one step may be decomposed into multiple steps.

[0110] In addition, in this exemplary embodiment, an emergency rescue system based on a brain-computer interface is also provided. Figure 3 As shown, the emergency rescue system 300 based on brain-computer interface may include: an EEG data acquisition module 310, an EEG data analysis module 320 and a rescue mission update module 330.

[0111] The EEG data acquisition module 310 is used to display the real-time telemetry rescue image data to the rescue personnel in a preset manner using a preset device, collect the EEG data of the rescue personnel, and extract the event-related potential (ERP) component therefrom;

[0112] The EEG data analysis module 320 is configured to pre-process the ERP data and the EEG data and use them as inputs to a two-headed LSTM model, perform target classification and task load detection on the ERP data and the EEG data, and generate target information and task load status;

[0113] The rescue mission update module 330 is configured to update the emergency rescue mission allocation based on the mission load status after prioritizing the target information.

[0114] The specific details of each of the above-mentioned brain-computer interface-based emergency rescue system modules have been described in detail in the corresponding brain-computer interface-based emergency rescue method, so they will not be repeated here.

[0115] It should be noted that although several modules or units of a brain-computer interface-based emergency rescue system 300 are mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units for concretization.

[0116] In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0117] Those skilled in the art will appreciate that various aspects of the present invention may be implemented as systems, methods, or program products. Accordingly, various aspects of the present invention may be implemented as a complete hardware embodiment, a complete software embodiment (including firmware, microcode, etc.), or a combination of hardware and software embodiments, which may be collectively referred to herein as "circuits," "modules," or "systems."

[0118] Refer to the following Figure 4 An electronic device 400 according to such an embodiment of the present invention will be described. Figure 4 The electronic device 400 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0119] like Figure 4 As shown, electronic device 400 is implemented as a general-purpose computing device. Components of electronic device 400 may include, but are not limited to, the aforementioned at least one processing unit 410, the aforementioned at least one storage unit 420, a bus 430 connecting various system components (including storage unit 420 and processing unit 410), and a display unit 440.

[0120] The storage unit stores program codes that can be executed by the processing unit 410, so that the processing unit 410 performs the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Methods” section of this specification. For example, the processing unit 410 may perform the following steps: Figure 1 Steps S110 to S130 shown in FIG.

[0121] The storage unit 420 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 4201 and / or a cache memory unit 4202 , and may further include a read-only memory unit (ROM) 4203 .

[0122] The storage unit 420 may also include a program / utility 4204 having a set (at least one) of program modules 4205, such program modules 4205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0123] Bus 430 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0124] The electronic device 400 can also communicate with one or more external devices 470 (e.g., a keyboard, a pointing device, a Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 400, and / or any device that enables the electronic device 400 to communicate with one or more other computing devices (e.g., a router, a modem, etc.). Such communication can occur via an input / output (I / O) interface 450. Furthermore, the electronic device 400 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 460. As shown, the network adapter 460 communicates with other modules of the electronic device 400 via a bus 430. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 400, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0125] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal system, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0126] In exemplary embodiments of the present disclosure, a computer-readable storage medium is also provided, storing a program product capable of implementing the aforementioned methods of this specification. In some possible embodiments, various aspects of the present invention may also be implemented in the form of a program product comprising program code. When the program product is executed on a terminal device, the program code is configured to cause the terminal device to perform the steps according to various exemplary embodiments of the present invention described in the "Exemplary Methods" section of this specification.

[0127] refer to Figure 5 As shown, a program product 500 for implementing the above method according to an embodiment of the present invention is described. The program product 500 may be a portable compact disk read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device.

[0128] The program product may be implemented in any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0129] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, system, or device.

[0130] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0131] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and the like, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0132] Furthermore, the above-described figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention and are not intended to be limiting. It is readily understood that the processes illustrated in the above-described figures do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0133] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow from the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the claims.

[0134] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An emergency rescue method based on brain-computer interface, characterized in that: The method comprises: Using a preset device, real-time telemetry rescue image data is displayed to rescuers in a preset manner, EEG data of the rescuers is collected, and event-related potential (ERP) components are extracted therefrom; After preprocessing the event-related potential (ERP) data and the electroencephalogram (EEG) data, the data are used as inputs of a two-headed LSTM model to perform target classification and task load detection on the event-related potential (ERP) data and the electroencephalogram (EEG) data to generate target information and task load status; After prioritizing the target information, the emergency rescue task allocation is updated based on the task load status.

2. The method according to claim 1, wherein The method further comprises: Using AR glasses, real-time telemetry rescue image data is encoded into image sequences in chronological order and displayed to rescuers at a rate of 10 Hz.

3. The method according to claim 2, wherein The method further comprises: Collecting EEG data of the rescuer based on Neuroscan 64-lead EEG instrument and extracting event-related potential (ERP) components therefrom; Based on the MQTT communication protocol, the real-time collected event-related potential ERP data and electroencephalogram (EEG) data are sent to the rescue information comprehensive processing system.

4. The method according to claim 1, wherein The method further comprises: After preprocessing of EEG data by removing artifacts and filtering, time-frequency analysis was performed, and the energy characteristics of the α-wave, β-wave and γ-wave frequency bands were extracted based on wavelet transform and short-time Fourier transform.

5. The method according to claim 1, wherein The method further comprises: The P300 features of event-related potential ERP data are extracted and the extracted features are fused to generate a high-dimensional feature vector.

6. The method according to claim 1, wherein The dual-head LSTM model of the method also includes: The target classification head is used to identify target stimuli in the input signal. The network structure includes a preset number of LSTM layers, followed by a fully connected layer and a softmax activation function, and outputs the probability distribution of each category; The load detection head is used to evaluate the user's cognitive load level. The network structure includes a preset number of LSTM layers, followed by a fully connected layer, and an output layer regression method to predict the load score.

7. The method according to claim 1, wherein The method further comprises: Prioritizing the target information; Filter target information based on preset task load status thresholds; The emergency rescue task allocation is updated based on the priority sorting and screening results.

8. An emergency rescue system based on brain-computer interface, characterized in that: The system comprises: An EEG data acquisition module is used to display real-time telemetry rescue image data to rescuers in a preset manner using a preset device, collect EEG data of the rescuers, and extract event-related potential (ERP) components therefrom; An EEG data analysis module is used to pre-process the event-related potential (ERP) data and the electroencephalogram (EEG) data, respectively, and use them as inputs of a two-headed LSTM model to perform target classification and task load detection on the event-related potential (ERP) data and the electroencephalogram (EEG) data, thereby generating target information and task load status. The rescue mission update module is used to update the emergency rescue mission allocation based on the mission load status after prioritizing the target information.

9. An electronic device, characterized in that: include processor; and A memory having computer-readable instructions stored thereon, wherein the computer-readable instructions are executed by the processor to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images