First-aid method and system based on 5G communication and edge device

Abstract

The invention provides a first-aid method and system based on 5G communication and an edge device. The method comprises the following steps: determining a communication protocol target adaptation protocol with a 5G base station based on the edge device; obtaining multi-modal data according to the target adaptation protocol based on the edge device, and performing priority classification on the multi-modal data to obtain a priority classification result; evaluating the 5G network resources of the edge device, determining a resource evaluation result, and determining a cloud transmission strategy based on the resource evaluation result and the priority classification result; performing association analysis on the vital sign data, the medical image data and the voice record data to obtain a calculation task and task complexity, processing the calculation task based on the task complexity and a cloud transmission strategy, and determining a data processing result; and data processing results are transmitted to the first-aid smart center and the mobile terminal in a grading manner. According to the method and the device, the compatibility problem caused by non-uniformity of device interfaces is solved, and the edge device processing capability is improved.

Description

Technical Field

[0001] The present invention relates to the field of communication technologies, and in particular to a first aid method and system based on 5G communication and edge devices. Background Art

[0002] With the rapid development and widespread application of 5G communication technology, the high speed, low latency, and large capacity of 5G communication technology in the field of mobile communication technology have brought new possibilities for data transmission and interaction to emergency scenarios. Edge devices can effectively reduce data transmission pressure and response time by enabling rapid processing at the source of data. The application of 5G communication and edge devices in emergency systems can transmit key information such as patient vital signs and on-site videos in real time, facilitating remote diagnosis and emergency guidance, and greatly improving emergency efficiency.

[0003] In practical applications, edge devices need to closely collaborate with 5G communication networks when pre-processing emergency data. However, the interfaces and protocols between edge devices and 5G networks are not yet fully standardized, leading to potential compatibility issues between devices. For example, edge devices from different manufacturers may not interface smoothly with 5G base stations, impacting data transmission and processing efficiency. Furthermore, edge devices may lack sufficient processing power when processing large amounts of emergency data, especially for data analysis of complex conditions. This can affect subsequent treatment decisions and, in turn, the timeliness of emergency care. Summary of the Invention

[0004] The present invention provides a first aid method and system based on 5G communication and edge devices, which are used to solve the compatibility problem existing in the inconsistency between device interfaces and improve the processing capability of edge devices.

[0005] In a first aspect, the present invention provides a first aid method based on 5G communication and edge devices, including:

[0006] Detecting the communication protocol type of the 5G base station based on the edge device, and performing protocol adaptation between the edge device and the 5G base station based on the detection result to determine the target adaptation protocol;

[0007] Acquiring multimodal data based on the edge device according to the target adaptation protocol, and performing priority classification on the multimodal data to obtain a priority classification result; the multimodal data includes vital sign data, medical imaging data, and voice recording data;

[0008] Evaluate the 5G network resources of the edge device, determine a resource evaluation result, and determine a cloud transmission strategy based on the resource evaluation result and the priority classification result;

[0009] performing correlation analysis on the vital sign data, the medical imaging data, and the voice recording data to obtain a computing task and task complexity, and processing the computing task based on the task complexity and the cloud transmission strategy to determine a data processing result;

[0010] The data processing results are transmitted in a hierarchical manner to the emergency intelligence center and the mobile terminal.

[0011] In a second aspect, the present invention further provides a first aid method system based on 5G communication and edge devices, which is applied to the first aid method based on 5G communication and edge devices as described in the first aspect; the first aid method system based on 5G communication and edge devices includes:

[0012] A protocol adaptation module is used to detect the communication protocol type of the 5G base station based on the edge device, and perform protocol adaptation between the edge device and the 5G base station based on the detection result to determine the target adaptation protocol;

[0013] a priority classification module, configured to acquire multimodal data based on the edge device according to the target adaptation protocol, and perform priority classification on the multimodal data to obtain a priority classification result; the multimodal data includes vital sign data, medical imaging data, and voice recording data;

[0014] a policy determination module, configured to evaluate the 5G network resources of the edge device, determine a resource evaluation result, and determine a cloud transmission policy based on the resource evaluation result and the priority classification result;

[0015] a data processing module, configured to perform correlation analysis on the vital sign data, the medical imaging data, and the voice recording data to obtain a computing task and task complexity, and to process the computing task based on the task complexity and the cloud transmission strategy to determine a data processing result;

[0016] The data transmission module is used to transmit the data processing results in a hierarchical manner to the emergency intelligence center and the mobile terminal.

[0017] In a third aspect, the present invention also provides an electronic device, comprising: a memory for storing a computer software program; and a processor for reading and executing the computer software program, thereby implementing any of the above-mentioned first aid methods based on 5G communication and edge devices.

[0018] In a fourth aspect, the present invention also provides a non-transitory computer-readable storage medium, in which a computer software program is stored. When the computer software program is executed by a processor, it implements any of the above-mentioned first aid methods based on 5G communication and edge devices.

[0019] In a fifth aspect, the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned first aid methods based on 5G communication and edge devices.

[0020] The first aid method based on 5G communication and edge devices provided by the embodiment of the present invention, by adapting the protocol between the edge device and the 5G base station, obtains the target adaptation protocol of the corresponding edge device, ensures the high efficiency of data transmission, and avoids the compatibility problem caused by the inconsistency between device interfaces; further, according to the transmission priority of multimodal data, the evaluation results of the 5G network and the complexity of the tasks processed by the edge device, it can reasonably allocate computing tasks, realize local processing of simple tasks to reduce delays, and cloud processing of complex tasks to ensure the accuracy of data transmission and processing, thereby improving the processing capacity of the edge device, avoiding the situation where the processing capacity of the edge device is insufficient when analyzing the data of complex diseases, and thus ensuring that the first aid decision is not affected, ensuring the timeliness of first aid while improving the efficiency of first aid. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a flowchart of a first aid method based on 5G communication and edge devices provided by an embodiment of the present invention;

[0022] Figure 2 This is a structural diagram of a first aid method system based on 5G communication and edge devices provided by an embodiment of the present invention;

[0023] Figure 3 An embodiment diagram of an electronic device provided by an embodiment of the present invention;

[0024] Figure 4 A diagram of an embodiment of a computer-readable storage medium provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0026] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Therefore, features specified as "first" or "second" may explicitly or implicitly include one or more features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0027] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0028] See Figure 1 , Figure 1 This is a flow chart of a first aid method based on 5G communication and edge devices provided by the present invention. In the embodiment of the present invention, the first aid method based on 5G communication and edge devices is executed by a first aid system. Therefore, the first aid method based on 5G communication and edge devices includes:

[0029] Step 10: Detect the communication protocol type of the 5G base station based on the edge device, and perform protocol adaptation between the edge device and the 5G base station based on the detection result to determine the target adaptation protocol.

[0030] Optionally, since 5G base stations contain multiple protocol types, such as non-standalone networking (NSA) and standalone networking (SA), different protocols differ in bandwidth, latency, reliability, etc. Therefore, after the emergency system is turned on, the emergency system first detects the communication protocol type of the 5G base station based on the edge device. Specifically, the edge device sends a detection signal to the 5G base station and analyzes the signal returned by the 5G base station, and then matches the analysis result with the pre-stored protocol to determine the target adaptation protocol. Specifically, as described in steps 101 to 105. Through protocol adaptation, an efficient and stable communication link is ensured between the edge device and the 5G base station, and protocol compatibility issues between devices from different manufacturers are resolved. Data transmission interruption or inefficiency caused by protocol mismatch is avoided, laying a solid foundation for the subsequent transmission of emergency data.

[0031] Furthermore, in one embodiment, in a certain emergency scenario, the edge device on the ambulance or emergency equipment sends a detection signal packet to a nearby 5G base station, and the base station returns a signal. The edge device detects and analyzes the returned signal and matches it with the protocol in the system's built-in protocol library. It finally determines to adjust the signal modulation method to the orthogonal frequency division multiplexing (OFDM) method suitable for the TDD protocol, completes the protocol adaptation, and successfully establishes a high-speed and stable connection.

[0032] In step 20, the edge device obtains multimodal data according to the target adaptation protocol, and prioritizes the multimodal data to obtain a priority classification result; the multimodal data includes vital sign data, medical imaging data, and voice recording data.

[0033] Optionally, after determining the target adaptation protocol, the edge devices within the emergency system acquire multimodal data through various sensors and acquisition devices. For example, vital signs data (heart rate, blood pressure, blood oxygen, etc.) are acquired through electrocardiogram sensors, medical imaging data are acquired through portable ultrasound equipment, and voice recording data (conversations between medical staff and patients, descriptions of on-site situations, etc.) are acquired through microphones. After acquiring the data, priority classification is performed based on the urgency of the data and the timeliness requirements for emergency decision-making, as described in steps 201 to 204. Prioritizing multimodal data enables the transmission of urgent and critical data in priority when 5G network resources are limited.

[0034] Step 30: Evaluate the 5G network resources of the edge device, determine the resource evaluation results, and determine the cloud transmission strategy based on the resource evaluation results and priority classification results.

[0035] Optionally, after the edge device in the emergency system starts collecting multimodal data of the patient, it starts uploading the data. At this time, before uploading the data, the edge device starts to evaluate the 5G network resources in this area. The 5G network resources include resource indicator data such as network bandwidth, delay, packet loss rate and node load. For example, the larger the bandwidth, the lower the delay and the smaller the packet loss rate, the more sufficient the network resources are, and other evaluation results are specifically described in steps 301 to 305.

[0036] Furthermore, after the emergency system obtains the resource assessment results, it formulates a cloud transmission strategy based on the priority classification results obtained in the previous step. For example, if network resources are sufficient, all data can be transmitted to the cloud in order of priority; if network resources are tight, high-priority vital signs data will be transmitted first, and medium and low-priority data will be compressed, cached, or delayed for transmission. For example, medical imaging data is compressed using a compression algorithm before transmission, and voice recording data is temporarily cached in the edge device and sent when network resources are idle. This allows the data transmission strategy to be dynamically adjusted according to the actual network conditions, fully utilizing network resources to ensure timely transmission of important data, avoid data loss or delays due to network congestion, and improve the efficiency and stability of data transmission.

[0037] Furthermore, in one embodiment, taking an on-site emergency response scenario at a large-scale outdoor event as an example, a large number of devices simultaneously accessing the 5G network strains network resources. Consequently, the edge device assesses that network bandwidth has dropped to 50% of its normal level, increasing latency. In this case, the edge device prioritizes transmitting the patient's vital signs to the cloud based on its transmission strategy, and then transmits medical imaging and voice recordings once the network conditions improve.

[0038] Step 40: perform correlation analysis on the vital sign data, medical imaging data, and voice recording data to obtain computing tasks and task complexity, and process the computing tasks based on the task complexity and cloud transmission strategy to determine the data processing results.

[0039] Optionally, after determining the cloud transmission strategy and acquiring the original multimodal data, the emergency system can more accurately grasp the patient's condition through correlation analysis between multimodal data, as single-modal data may not fully reflect the patient's condition. However, different tasks have different task complexities, and when processing tasks of different complexities, different data processing methods will also result in different processing efficiencies. Therefore, the emergency system can select an appropriate data processing method based on actual conditions to improve overall processing capabilities. Specifically, the system can first determine the computing task and the corresponding task complexity, such as disease diagnosis or condition prediction, based on the correlation analysis between vital sign data, medical imaging data, and voice recording data. This is described in detail in steps 4011 to 4015.

[0040] Furthermore, after determining the computing task and task complexity, the emergency system allocates the processing of the computing task based on the cloud transmission strategy and task complexity, decomposing the computing task into several subtasks. Then, based on the edge device's own load and network status, the data is processed in combination with the subtasks. This can better utilize the computing power of the edge device. For tasks that the edge device cannot complete, the data processed by the edge device and the remaining subtasks are combined and processed on the edge device in the cloud server. Finally, the processing process of the entire task is completed, and the data processing results are obtained for the final transmission to the emergency smart center and mobile terminal, etc., as described in steps 4021 to 4024. This fully utilizes the computing resources of the edge device and the cloud server, improving computing efficiency and accuracy.

[0041] Furthermore, in one embodiment, for example, a patient experiencing chest pain receives vital sign data from an edge device, revealing abnormal heart rate and fluctuating blood pressure. Medical imaging reveals possible coronary artery stenosis, and a voice recording of the patient describing chest pain symptoms. Correlation analysis identifies the computational task as diagnosing coronary artery disease, a task with high complexity. The computational task is then transmitted to a cloud server, where it is analyzed using a cloud-based medical diagnostic model, ultimately yielding a preliminary diagnosis of coronary artery disease and treatment recommendations.

[0042] Step 50: Transmit the data processing results to the emergency intelligence center and mobile terminal in a hierarchical manner.

[0043] Optionally, the emergency system can perform hierarchical transmission based on the acquired data processing results, their importance, and the intended users. Specifically, urgent and critical diagnostic results and treatment recommendations are transmitted directly to the emergency intelligence center with the highest priority, allowing the hospital's emergency team to quickly develop treatment plans. Auxiliary information, such as the disease analysis process and relevant medical knowledge, is transmitted to mobile terminals (such as medical staff's mobile phones and tablets) with lower priority, allowing medical staff to view and reference them at any time. During the transmission process, encryption technology is used to ensure data security and privacy to prevent data leakage.

[0044] Furthermore, the embodiments of the present invention can enable different users to obtain the most needed information in a timely manner through hierarchical transmission, improve the efficiency of information use, help the emergency team make decisions quickly, and at the same time ensure data security and protect patient privacy.

[0045] Furthermore, in one embodiment, for example, a patient with a sudden heart attack in emergency medical care requires immediate coronary bypass surgery. This result is marked as high priority and immediately transmitted to the emergency medical center, which rapidly dispatches surgical resources and specialists. Simultaneously, a brief description of the patient's condition and first aid measures is transmitted to the on-site medical staff's mobile device to guide the emergency response. Detailed information such as the patient's condition analysis and subsequent rehabilitation recommendations are marked as low priority and transmitted to the emergency medical center and mobile device when the network is idle.

[0046] The embodiment of the present invention adapts the protocol between the edge device and the 5G base station to obtain the target adaptation protocol of the corresponding edge device, thereby ensuring the high efficiency of data transmission and avoiding the compatibility problem caused by the inconsistency between device interfaces; further, according to the transmission priority of multimodal data, the evaluation results of the 5G network and the complexity of the tasks at the edge device, it can reasonably allocate computing tasks, realize local processing of simple tasks to reduce delays, and cloud processing of complex tasks to ensure the accuracy of data transmission and processing, thereby improving the processing capability of the edge device, avoiding the situation where the processing capability of the edge device is insufficient when analyzing the data of complex diseases, and thus ensuring that the emergency decision is not affected, ensuring the timeliness of emergency treatment while improving the efficiency of emergency treatment.

[0047] In one embodiment, steps 101 to 105 are described as follows:

[0048] Step 101: Analyze the transmission information of the 5G base station based on the edge device to obtain a time domain signal.

[0049] Optionally, the emergency system relies on a signal acquisition and receiving device installed on the edge device, such as a wideband spectrum analyzer. When the edge device receives a signal transmitted by a 5G base station, the analyzer monitors the signal in real time and converts the received RF signal into a processable electrical signal after preprocessing, such as amplification and filtering. The system then analyzes the temporal variations of parameters such as the amplitude and phase of the electrical signal to generate a time-domain signal. For example, the signal transmitted by the base station may contain carrier signals of different frequencies. The receiving device converts this mixed signal into a time-varying voltage or current signal, thereby generating a time-domain signal.

[0050] Step 102 : Perform short-time Fourier transform on the time domain signal to obtain a three-dimensional spectrum matrix, and perform feature spectrum extraction on the three-dimensional spectrum matrix to obtain initial spectrum fingerprint data.

[0051] Optionally, after determining the time domain signal, the emergency system uses the short-time Fourier transform (STFT) time-frequency analysis method to transform the time domain signal. Specifically, the obtained time domain signal is divided into several short time windows. Within each time window, the signal is Fourier transformed. The time domain signal is decomposed into a superposition of sine waves and cosine waves of different frequency components to obtain the frequency component information of the signal within each time window. As the time window slides on the time domain signal, a frequency information matrix that changes with time is obtained, that is, a three-dimensional spectrum matrix (time-frequency-power).

[0052] After obtaining the three-dimensional spectrum matrix, image recognition and feature extraction algorithms, such as principal component analysis (PCA) and scale-invariant feature transform (SIFT), are used to extract patterns representing the unique characteristics of the signal from the matrix. These patterns are then combined into the initial spectrum fingerprint data. For example, signals from different 5G communication protocols have different distribution characteristics in the spectrum. For example, the power distribution of the NSA and SA protocols in certain frequency bands differs significantly. These differences can be captured through feature pattern extraction.

[0053] Step 103: Match the initial spectrum fingerprint data with the templates in the protocol fingerprint library to obtain similarity scores, and screen the similarity scores to obtain a preliminary adaptation protocol.

[0054] Optionally, a protocol fingerprint library is pre-set in the emergency system, which stores standard spectrum templates of various 5G communication protocols in different scenarios. Each template contains the spectrum characteristic parameter range corresponding to the protocol. After obtaining the initial spectrum fingerprint data, it is matched with the template in the protocol fingerprint library. For example, Euclidean distance matching is performed to calculate the distance between the initial spectrum fingerprint data and each template in the characteristic parameter space. The closer the distance, the higher the similarity score. And according to the set similarity threshold, the protocols with scores higher than the threshold are screened out to form a preliminary adaptation protocol set. By matching with the protocol fingerprint library template and similarity screening, it is possible to quickly find a preliminary adaptation protocol that matches the current signal characteristics from a large number of protocols, narrowing the adaptation range, improving the efficiency of protocol adaptation, and laying the foundation for the subsequent precise determination of the target adaptation protocol.

[0055] Step 104 : Perform a secondary screening of the preliminary adaptation protocols based on the current network load and the resource status of the edge device to obtain candidate adaptation protocols.

[0056] Optionally, the emergency system monitors the current network load based on the edge device, such as by monitoring indicators such as data traffic and the number of connected devices in the network to evaluate whether the network is busy, and monitors its own resource status, such as computing resources (such as CPU usage, memory occupancy), storage resources (remaining storage space), etc. For each protocol in the obtained preliminary adaptation protocol set, a secondary screening is performed in combination with the current network load and edge device resource status. If the current network load is high, protocols with low network resource requirements are given priority; if the computing power of the edge device is limited, protocols with excessively high computing resource requirements are excluded. This ensures that the selected protocol can operate stably and efficiently in the current actual environment, avoids communication interruption or performance degradation due to mismatch between the protocol and actual resources, and improves the reliability and stability of communication.

[0057] Step 105: Perform performance evaluation on each of the candidate adaptation protocols to determine the target adaptation protocol.

[0058] Optionally, the emergency system establishes a test connection between the edge device and the 5G base station for each protocol in turn from the candidate adaptation protocols obtained, and monitors the response information of the base station by sending a probe data packet in a specific format, including indicators such as latency (i.e., the time required for the data packet to be sent from the edge device to the base station and then back), packet loss rate (the proportion of data packets sent that are not successfully received), and data transmission rate. And based on preset performance evaluation standards, such as requiring the latency to be less than a certain threshold (such as 5 milliseconds), the packet loss rate to be lower than a certain proportion (such as 1%), and the data transmission rate to reach a certain value (such as 100Mbps), it is determined whether the protocol meets the current communication needs. If it meets the requirements, the next protocol is selected from the candidate adaptation protocols for verification until the optimal adaptation protocol, i.e., the target adaptation protocol, is found.

[0059] The embodiments of the present invention comprehensively and deeply mine the signal characteristics of 5G base stations through signal analysis, feature extraction, matching screening and performance evaluation, accurately identify and adapt protocols, and reduce the possibility of misjudgment and mismatching; and take into account the network environment (such as network load) and the resource status of the edge device itself, and can dynamically adjust the protocol adaptation process according to actual conditions, adapt to complex and changeable 5G communication scenarios, and ensure the stability of emergency communications; finally, the protocol adaptation process is dynamically adjusted according to different network environments and device statuses to adapt to complex and changeable 5G communication scenarios, and has strong environmental adaptability.

[0060] In one embodiment, steps 201 to 204 are described as follows:

[0061] Step 201 : parse the vital sign data, medical image data, and voice recording data respectively, and extract features based on the parsing results to obtain a data feature set.

[0062] Optionally, the emergency system first analyzes data such as heart rate, blood pressure, and blood oxygen saturation collected by sensors, analyzing the data. For example, it analyzes the frequency of heart rate fluctuations and blood pressure trends. Using methods such as time series analysis, it extracts features such as real-time monitoring indicators and their changing trends. For medical imaging data such as CT and MRI, image recognition technology is used to identify key lesion areas within the images, such as abnormal shadow areas in lung CT images. Image quality parameters such as image resolution and contrast are also extracted. These key lesion areas and image quality parameters constitute the features of the medical image data. For acquired speech recordings, speech recognition technology is used to convert the speech into text. Natural language processing technology is then used to extract diagnostic keywords, such as "myocardial infarction" and "fracture," as well as keywords describing the urgency of the condition, such as "sudden onset" and "severe pain." These keywords are then used to form the features of the speech recording data. Finally, the features extracted from the three data types are integrated to form a data feature set.

[0063] Step 202 : judging each data feature in the data feature set based on a preset urgency assessment library to obtain an urgency assessment result.

[0064] Optionally, the emergency system stores emergency judgment criteria corresponding to various data features in a pre-set emergency assessment library. For vital sign data features, such as a heart rate exceeding 160 beats / minute (for adults) or less than 40 beats / minute, it is judged as an emergency based on the risk index threshold. For medical imaging data showing large-scale hemorrhage lesions in key areas of the brain, it is assessed as an emergency based on the nature and location of the lesions. For voice recording data, if emergency keywords such as "cardiac arrest" appear, the emergency level is determined through semantic analysis. According to these emergency judgment criteria, each data feature in the data feature set is judged one by one, and the data is divided into three levels: emergency, relatively urgent, and routine to obtain an emergency assessment result. This provides a unified and clear standard for emergency assessment, reduces the subjectivity and uncertainty of human judgment, and can quickly and accurately classify the urgency of the data, providing a reliable basis for subsequent priority determination.

[0065] Step 203 : Based on the data type and clinical application scenario, the timeliness weights of the vital sign data, medical imaging data, and voice recording data are determined, and based on the data collection time and the timeliness weight, the timeliness score of each data is determined.

[0066] Optionally, because the role of different types of data in the emergency care process varies over time, the emergency care system determines timeliness weights for vital signs data, medical imaging data, and voice recording data based on the data type and clinical application scenario. Specifically, vital signs data, which significantly impacts emergency care decisions due to the need for real-time monitoring of the patient's vital status, has extremely high timeliness requirements in clinical applications, and is therefore assigned the highest timeliness weight. Medical imaging data is crucial for determining the condition in the early stages of diagnosis, but its influence on subsequent treatment decisions diminishes over time, and therefore has a moderate timeliness weight. Voice recording data is primarily valuable for documenting the condition, but its subsequent reference value gradually decreases, and therefore has a lower timeliness weight. For example, the timeliness weight for vital signs data is set to 0.6, for medical imaging data to 0.3, and for voice recording data to 0.1. Subsequently, scores are calculated based on the data collection time and the timeliness weights. Assume that the vital signs data are collected at the current time, denoted as t0, the medical imaging data are collected at time t1 (t1 is 10 minutes away from t0), and the voice recording data are collected at time t2 (t2 is 15 minutes away from t0). Introduce the time decay function, such as (where λ represents the decay constant, which can be set based on clinical experience). Then the timeliness score of vital signs data is T score1=0.6×1 (current acquisition, no attenuation); Medical imaging data timeliness score T score2 =0.3×e -λ×10 ; Voice recording data timeliness score T score3 =0.1×e -λ×15 . And as the time difference increases, the timeliness score gradually decreases.

[0067] Step 204 : Cross-analyze the urgency evaluation result and the timeliness score to obtain a priority classification result.

[0068] Optionally, the emergency system will first prioritize the data with an urgency level of "urgent" to achieve priority processing and transmission of data that has a significant impact on the patient's life safety. For "relatively urgent" and "routine" data, the system will use the formula based on the timeliness score. Calculate the priority score, where n represents the number of data, E level Expressed as the urgency level, T score This is expressed as a timeliness score, and the final priority classification is determined based on the calculated priority score. All data is sorted from high to low according to priority score and divided into different priority categories. By cross-analyzing urgency and timeliness, we can comprehensively and comprehensively consider the importance and time value of data, making the priority classification results more scientific and reasonable.

[0069] The embodiment of the present invention comprehensively considers key factors such as the urgency and timeliness of data, can accurately determine data priority, and provide reliable data support for emergency decision-making.

[0070] In one embodiment, steps 301 to 305 are described as follows:

[0071] Step 301 : combining the network bandwidth, delay, packet loss rate and node load resource indicator data with the timestamp of data collection and node geographic location information to obtain an original data set.

[0072] Optionally, in a 5G network, the emergency system's edge devices monitor resource metrics such as network bandwidth, latency, packet loss rate, and node load in real time. The devices also record the timestamp of data collection to identify the specific moment of data collection, and the device's built-in positioning module also obtains its own geographic location information. This resource metric data is integrated with the corresponding timestamp and geographic location information to form a raw data set containing resource metrics, time, and space information.

[0073] In step 302, the original data set is divided based on the time interval with time as the horizontal axis to obtain a time window, and the edge devices are divided into regions based on the geographical area with space as the vertical axis to obtain different regions. Based on the time window and the different regions, a two-dimensional space-time window is constructed.

[0074] Optionally, the emergency system groups the data in the original data set at fixed time intervals (e.g., 5 minutes) using time as the horizontal axis. Each set of data corresponds to a time window, so that each time window contains the network resource indicator data of all edge devices collected during that time period. Using space as the vertical axis, edge devices are classified according to geographical regions (such as different administrative districts in a city, different subdivisions in a park, etc.) to divide different areas. For example, a city can be divided into multiple areas such as the city center and suburbs. Finally, the time window and the area are cross-combined to form a two-dimensional space-time window. Each two-dimensional space-time window corresponds to a set of network resource indicator data at a specific time and in a specific area. By constructing a two-dimensional space-time window, network resource data can be structured and organized from both the time and space dimensions. This facilitates subsequent targeted analysis of network resources at different times and regions, and uncovers the changing characteristics and patterns of network resources in the space-time dimensions.

[0075] In step 303, entropy processing is performed on each resource data of the 5G network resources in each space-time window in the space-time two-dimensional window to obtain a resource entropy value; and each resource data of the 5G network resources in each space-time window in the space-time two-dimensional window is converted to obtain a resource indicator vector.

[0076] Optionally, when the emergency system performs entropy processing on each resource data of the 5G network resources in each spatiotemporal window, taking the network bandwidth as an example, for the bandwidth data x in each spatiotemporal window, ij (i represents the time window number, j represents the region number), first calculate the probability of each data appearing in the window (n represents the number of data in the window). Then, by the formula Calculate the entropy of bandwidth within this window. Use the same method to calculate the entropy of other resource metrics, such as latency, packet loss rate, and node load, within the corresponding spatiotemporal window. A higher entropy indicates greater volatility and uncertainty in the corresponding resource metric within that window.

[0077] Furthermore, after obtaining the corresponding resource entropy value, the resource data such as network bandwidth, delay, packet loss rate and node load in each spatiotemporal window are normalized (such as normalized to the [0,1] interval) and then arranged in a certain order to form a vector, namely the resource index vector. For example, the normalized bandwidth, delay, packet loss rate and node load data are arranged in sequence to obtain the resource index vector

[0078] Step 304 : constructing a spatiotemporal correlation matrix based on the similarities between resource indicator vectors in different spatiotemporal windows, and determining the spatiotemporal correlation degree based on the spatiotemporal correlation matrix.

[0079] Optionally, the emergency system uses the cosine similarity formula Calculate the similarity between resource indicator vectors in different spatiotemporal windows. Where A and B are resource indicator vectors of two spatiotemporal windows, a k and b k The corresponding resource indicator values are represented respectively. The calculated similarity values between all two spatiotemporal windows are arranged in a certain order to construct a spatiotemporal correlation matrix. Each element in the matrix represents the similarity of resource indicators between two spatiotemporal windows. The spatiotemporal correlation matrix is then analyzed to determine the spatiotemporal correlation between different spatiotemporal windows. Higher similarity indicates higher spatiotemporal correlation.

[0080] Step 305: Determine a resource evaluation result based on the resource entropy value and the spatiotemporal correlation.

[0081] Optionally, the emergency system combines resource entropy and spatiotemporal correlation to categorize network resource status into three levels: stable, general, and unstable. A low resource entropy indicates minimal fluctuations in resource indicators and a low spatiotemporal correlation, indicating significant differences in resource status across spatiotemporal windows and relative stability. In this case, the network resource status is considered stable. A high resource entropy indicates significant fluctuations in resource indicators and a high spatiotemporal correlation, indicating similar and unstable resource status across spatiotemporal windows. Otherwise, the status is considered general. For example, if a region has low entropy for resource indicators such as network bandwidth over a period of time and low correlation with other spatiotemporal windows, the region's network resource status is considered stable during that period.

[0082] The embodiments of this invention comprehensively consider the various characteristics of network resources, avoiding the limitations of single-dimensional or single-metric analysis. They also utilize scientific methods such as entropy calculation and cosine similarity to quantify the fluctuations and spatiotemporal correlations of resource indicators, making resource assessment results more accurate and reliable, truly reflecting the actual state of network resources. Finally, by analyzing spatiotemporal correlations, the changing patterns and trends of network resources in both spatiotemporal dimensions are identified, facilitating the preemptive planning and adjustment of data transmission strategies, improving network resource utilization efficiency and the stability of communication systems.

[0083] In one embodiment, steps 4011 to 4015 are described as follows:

[0084] Step 4011: construct a time series tree based on the vital sign data, and extract structural features from the time series tree to obtain a first structural feature.

[0085] Optionally, since vital sign data (such as heart rate, blood pressure, blood oxygen saturation, etc.) changes continuously over time, the emergency system uses time as the order, takes the vital sign feature data collected at each time point as a node, connects these nodes in chronological order, and constructs a time series tree. For example, heart rate data is collected every minute, and the heart rate value collected each time is used as a node to form a time series tree that reflects the change of heart rate over time. Afterwards, structural features are extracted from this time series tree, such as the number of branches, that is, the number of child nodes extending from a certain node, which reflects the change branching of the vital sign data at that time point; the node depth, that is, the number of edges passing from the root node to the node, can reflect the depth information in time. Constructing the vital sign data as a time series tree and extracting structural features can clearly present the change pattern and structural characteristics of the vital sign data in the time dimension.

[0086] Step 4012: construct a regional topology map based on the medical image data, and extract graph structure features from the regional topology map to obtain a second structural feature.

[0087] Optionally, since medical imaging data (such as CT and MRI images) contain different anatomical regions and lesion information, the emergency system regards different regions in the image as nodes, and the relationships between regions (such as adjacent, contained, etc.) as edges to construct a regional topology map. For example, in a lung CT image, different regions such as lung lobes, lung blood vessels, and lesions are set as nodes, and connected into edges according to their spatial position relationships in the image to form a regional topology map. Afterwards, graph structural features are extracted from the regional topology map, such as the node degree, that is, the number of edges connected to a node, which reflects the degree of association of the region in the entire image structure; the shortest path, that is, the path between two nodes with the least number of edges, can reflect the distance and degree of connection between different regions. By constructing a regional topology map and extracting graph structural features, the spatial relationship and structural characteristics of different regions in the medical image can be intuitively displayed.

[0088] Step 4013: construct a semantic hierarchy tree based on the voice recording data, and perform feature extraction on the semantic hierarchy tree to obtain a third structural feature.

[0089] Optionally, after the first aid system converts the voice recording data into text through voice recognition, it performs semantic analysis on the text. The analyzed semantic units (such as words, phrases, sentences, etc.) are used as nodes and connected into a semantic hierarchy tree according to the semantic hierarchy relationship (such as subordination, parallelism, etc.). For example, in a voice recording describing a patient's condition, semantic units such as "patient", "symptoms", and "treatment" can be used as nodes at different levels to construct a semantic hierarchy tree. Afterwards, the hierarchical depth is extracted from the semantic hierarchy tree, that is, the number of edges passing from the root node to a certain node, reflecting the depth of semantic nesting; the node association degree can be obtained by calculating the closeness of the semantic association between nodes, such as by calculating the semantic similarity through word vectors. By constructing a semantic hierarchy tree and extracting features, the semantic structure and hierarchical relationship of the voice recording data can be clearly sorted out.

[0090] Step 4014: perform similarity processing on the first structural feature, the second structural feature, and the third structural feature to obtain a structural similarity score between any two structural features.

[0091] Optionally, the emergency system uses a graph edit distance algorithm to calculate the similarity between different types of data structures. For the time series tree of vital signs data and the semantic hierarchy tree of voice recording data, the structural similarity score of the two is obtained by calculating the number of node addition, deletion, and modification operations. For example, when comparing the node structure reflecting heart rate changes in the time series tree and the node structure of the semantic hierarchy tree for the semantic description of abnormal heartbeat, if fewer node addition, deletion, and modification operations are required to make the two structures similar, it means that their similarity is high and the score is also high. The specific formula is Where G1 and G2 represent two data structures (such as time series tree and semantic hierarchy tree), m represents the number of operations; w i It is expressed as the operation weight (set according to the importance of different operations, such as deleting important nodes has a higher weight), o i It is expressed as the cost of the ith operation (such as insertion, deletion, modification) (which can be determined based on factors such as the difficulty of the operation). The same method is used to calculate the similarity scores between the structural features of vital sign data and medical imaging data, and between medical imaging data and voice recording data.

[0092] Step 4015: Analyze the structural similarity scores to obtain the computational tasks and task complexity.

[0093] Optionally, the emergency system pre-sets a structural similarity threshold. When the similarity score of two data structures exceeds the threshold, it indicates that the two data have a strong structural correlation, and the joint analysis of the two data is divided into one computing task. For example, if the structural similarity score of the medical image region topology map and the vital signs time series tree meets the standard, the comprehensive analysis of the patient's images and vital signs can be divided into one computing task. The calculation task complexity is calculated using the formula Where S represents the number of data types involved in the task, D i is the average similarity distance between the data structure and other data structures, with k representing the number of data structures. Complexity is assessed from the perspective of data structure differences. The more data types involved in a task and the greater the average similarity distance between data structures, the higher the task complexity. This results in the computational task and its complexity.

[0094] By constructing specific structures of data of different modalities and extracting features, and then calculating structural similarity, the embodiments of the present invention can deeply explore the intrinsic structural relationships of the data, discover the associations between data more comprehensively and accurately than traditional methods, and provide more valuable information for emergency decision-making; and divide computing tasks according to structural similarity scores, so that the organization of computing tasks is more reasonable, blind analysis is avoided, the efficiency of data processing and analysis is improved, and meaningful results are obtained more quickly.

[0095] In one embodiment, steps 4021 to 4024 are described as follows:

[0096] Step 4021, based on the resource parameters of the edge device, determine the task load, and build a hierarchical task strategy based on the task complexity, task load and cloud transmission strategy.

[0097] Optionally, the edge device of the emergency system first determines the task load that the edge device can bear based on its own resource parameters, such as computing power (measured by the number of instructions that can be executed per second), storage capacity, network bandwidth, etc. Based on these resource parameters, the task load that the edge device can bear is determined. For example, if the computing power of the edge device is limited and it can only process a certain number of computing instructions per second, then the task load that it can bear can be determined based on the expected computing amount of the task. Then, based on the complexity of the task, the higher the complexity of the task, the greater the computing amount and the higher the difficulty. Combined with the obtained cloud transmission strategy, a hierarchical task strategy is comprehensively constructed. Specifically, as described in steps 40211 to 40214. Determining the task load based on the resource parameters of the edge device can make full use of the capabilities of the edge device and avoid resource waste or overload. By constructing a hierarchical task strategy, combined with task complexity and cloud transmission strategy, tasks can be reasonably allocated to edge devices and cloud servers, improving overall processing efficiency, and ensuring that tasks can be efficiently processed under different network and resource conditions.

[0098] Furthermore, taking the edge device on an ambulance as an example, its computing power is 10 million instructions per second and its storage capacity is 10GB. For a simple analysis task of vital signs data, the estimated computing power is 5 million instructions per second and the storage requirement is 1GB. Based on the resource parameters, it can be determined that the load of this task is within the acceptable range of the edge device. Combined with the complexity of the task (this task complexity is low) and the current sufficient network bandwidth (the cloud transmission strategy tends to prioritize the use of cloud resources), it is divided into a task layer that can be processed on the edge device; for a complex medical image analysis task, the estimated computing power and storage requirements are far beyond the capabilities of the edge device, and the task complexity is high, so it is divided into a task layer that needs to be processed in the cloud.

[0099] Step 4022: Decompose the computing task based on the hierarchical task strategy, obtain the task decomposition result, and send the task decomposition result to the cloud server and edge device.

[0100] Optionally, the emergency system decomposes the computing tasks according to the hierarchical task strategy obtained in the previous step. For tasks assigned to the edge device processing layer, they are further subdivided into multiple subtasks to ensure that each subtask can be efficiently executed within the resource range of the edge device. For example, for simple analysis tasks of vital signs data, they can be decomposed into data cleaning subtasks, basic statistical analysis subtasks, etc. For tasks assigned to the cloud processing layer, they are also reasonably decomposed. For example, complex analysis tasks of medical images can be decomposed into image segmentation subtasks, lesion identification subtasks, etc. After the decomposition is completed, the task decomposition results (including information such as the content of the subtasks and the order of execution) are sent to the cloud server and edge devices, so that they can clearly understand the tasks they need to process.

[0101] In step 4023, the edge device preprocesses the multimodal data according to the task decomposition result to obtain the preprocessing result, and sends the preprocessing result to the cloud server, so that the cloud server integrates and analyzes the preprocessing result based on the task decomposition result, obtains the task processing result, and returns the task processing result to the edge device.

[0102] Optionally, after receiving the task decomposition results, the edge devices in the emergency system pre-process the multimodal data according to the subtasks assigned to them. For example, for vital signs data, filtering may be performed to remove noise, and normalization may be performed to bring the data into an appropriate range; for medical imaging data, image enhancement operations may be performed to increase contrast, and cropping operations may be performed to remove irrelevant areas. After the preprocessing is completed, the preprocessing results are sent to the cloud server. Based on the task decomposition results, the cloud server receives the preprocessing results sent by the edge device and integrates and analyzes them. For example, the medical imaging data pre-processed by the edge device is integrated with other relevant data (such as medical records), and the powerful computing resources and deep learning models of the cloud are used to accurately identify lesions and analyze the condition to obtain the task processing results, which are then returned to the edge device.

[0103] The embodiments of the present invention utilize edge devices for preprocessing, reducing data volume and complexity, alleviating processing pressure on cloud servers while simultaneously leveraging the local processing capabilities of edge devices to increase processing speed. Cloud servers then perform integrated analysis, leveraging their powerful computing and storage resources to implement complex data analysis and model calculations, ensuring the accuracy and comprehensiveness of analytical results. This collaborative approach improves the efficiency and quality of overall task processing.

[0104] Step 4024: Combine the task processing result with the multimodal data based on the edge device to determine the data processing result.

[0105] Optionally, after receiving the task processing results returned by the cloud server, the edge devices within the emergency system combine them with the original multimodal data. For example, the diagnosis results provided by the cloud server can be linked with the patient's vital signs data, medical imaging data, voice recording data, etc. to form a complete data processing result. The diagnosis results can be annotated on the medical images, or the changing trends of the vital signs data can be compared and analyzed with the diagnosis results, ultimately presenting a comprehensive and intuitive data processing result that is easy for medical staff to view and understand.

[0106] The embodiment of the present invention determines the task load based on the resource parameters of the edge device and constructs a hierarchical task strategy to rationally allocate tasks to the edge device and cloud server, fully utilizing the resource advantages of both, avoiding resource waste and overload, and improving resource utilization efficiency. It also refines complex tasks through task decomposition, facilitating efficient execution by the edge device and cloud server, respectively. The pre-processing of the edge device and the integrated analysis of the cloud server work together to accelerate task processing and improve overall processing efficiency. Finally, based on the collaboration between the edge device and the cloud server, it not only utilizes the local processing advantages of the edge device, but also brings into play the powerful computing and analysis capabilities of the cloud server, ensuring the accuracy of the task processing results.

[0107] In one embodiment, steps 42011 to 40214 are described as follows:

[0108] Step 42011, determine the initial priority based on the importance, urgency and business needs of the computing task.

[0109] Optionally, the emergency medical system first analyzes the importance of computing tasks to the emergency medical service. For example, diagnostic tasks directly related to patient safety, such as acute myocardial infarction, are highly important because they are crucial for subsequent patient treatment and life support. Routine medical data statistics tasks, such as counting the number of patients visiting a department in a week, are relatively less important. Next, the system considers the urgency of the task. For example, emergency computing tasks for patients with sudden cardiac arrest require immediate attention and are therefore highly urgent. Regular condition analysis tasks for patients with chronic diseases are less urgent. Finally, the system considers business needs. For example, computing tasks related to the hospital's current key research projects may be given a certain priority level even if they are not highly urgent. Based on these three factors, the initial priority of computing tasks is categorized as high, medium, and low. For example, acute myocardial infarction diagnostic tasks are assigned high priority, routine condition analysis tasks are assigned medium priority, and general data statistics tasks are assigned low priority.

[0110] Step 42012: Modify the initial priority based on the task complexity and task load to obtain the target priority.

[0111] Optionally, the emergency system combines the task complexity value. If the task complexity is high, it means that more computing resources and time are required to process it. For example, the complex three-dimensional reconstruction and analysis tasks of medical images are of high complexity. When the task load of each node in the system (such as edge devices and cloud servers) is low, it indicates that there are sufficient resources to handle high-complexity tasks. At this time, in order to ensure that important high-complexity tasks can be processed first, their priority can be appropriately increased; on the contrary, if the task complexity is low, such as a simple vital sign data mean calculation task, and the node load is high and resources are tight, its priority can be lowered. By adjusting the initial priority in combination with the task complexity and the task load, a target priority that is more in line with the actual resource situation is obtained. For example, a high-complexity task that originally had an initial priority of medium can be corrected to a high priority when the node load is low.

[0112] Step 42013: Build a priority association relationship based on the cloud transmission strategy and the target priority of the computing task.

[0113] Optionally, the emergency system uses previously acquired cloud transmission strategies. These strategies include latency-prioritized transmission, which prioritizes low data latency and is suitable for tasks with high real-time requirements, and bandwidth-prioritized transmission, which prioritizes full utilization of network bandwidth and is suitable for tasks with large data volumes but relatively low real-time requirements. The system then establishes a correlation between the computing task and the cloud transmission strategy based on its target priority. For tasks with high target priority, a latency-prioritized transmission strategy is preferred to ensure rapid transmission to the processing node. For example, for tasks transmitting vital signs from critically ill patients, which require rapid cloud-based analysis, a latency-prioritized transmission strategy is employed. For tasks with lower target priority, a bandwidth-prioritized transmission strategy can be employed to fully utilize network bandwidth resources, such as for batch uploads of historical medical data. Furthermore, the transmission strategy priorities are refined based on the task's data size. For high-priority tasks with smaller data volumes, the transmission strategy can be further optimized to ensure more efficient transmission.

[0114] Step 42014: construct a hierarchical task queue based on the target priority of the computing task, and construct a hierarchical task strategy based on each queue, task complexity, task load and priority association in the hierarchical task queue.

[0115] Optionally, the emergency system divides tasks into high-priority queues, medium-priority queues, and low-priority queues based on the target priority of the computing tasks, and constructs a hierarchical task queue. For example, tasks with a high target priority are placed in the high-priority queue and wait for processing. Then, for each queue in the hierarchical task queue, a hierarchical task strategy is constructed based on the task complexity, task load, and priority association relationship. For tasks in the high-priority queue, due to their high priority, when allocating processing nodes and transmission strategies, priority is given to nodes with sufficient resources and that can meet their transmission strategy requirements. If the task complexity is high, the cloud server is given priority for processing, and a delayed-first transmission strategy is adopted based on the priority association relationship; if the task complexity is low, it can be reasonably allocated to the edge device or cloud server based on the node load, while following the associated transmission strategy. A similar approach is used for tasks in the medium and low priority queues, and various factors are comprehensively considered for reasonable allocation and processing.

[0116] Furthermore, in one embodiment, the high-priority queue contains diagnostic computing tasks for patients with acute cerebral infarction, and the task complexity is high. Based on the task load, it is found that the current cloud server resources are sufficient, and combined with the priority association relationship (using a delay-first transmission strategy), the task is assigned to the cloud server for processing, and the data is transmitted in a low-latency manner. In the medium-priority queue, there are routine examination report analysis tasks for ordinary patients, which are assigned to edge devices for preliminary processing based on task complexity and load, and adopt appropriate transmission strategies. Tasks in the low-priority queue, such as historical medical data backup tasks, are processed when system resources are idle.

[0117] The embodiment of the present invention determines the initial priority based on the importance, urgency and business needs of the task, and then makes corrections based on the complexity and load of the task, taking into full consideration the characteristics of the task itself and the status of system resources, so that the priority determination is more accurate and reasonable; and by establishing a correlation between the cloud transmission strategy and the task priority, and constructing a hierarchical task queue and strategy, it can reasonably allocate processing nodes and transmission strategies according to the task priority and characteristics, realize the optimal configuration of system resources, and improve resource utilization efficiency; finally, the construction of the hierarchical task queue and strategy enables tasks of different priorities to be managed in an orderly manner, ensuring that high-priority tasks are processed first, while taking into account medium and low-priority tasks, thereby improving the overall efficiency of task processing and the reliability of the system, and having good adaptability in complex and changing task environments.

[0118] Furthermore, the first aid method system based on 5G communication and edge equipment provided by the present invention is described below. The first aid method system based on 5G communication and edge equipment described below and the first aid method based on 5G communication and edge equipment described above can be referenced to each other.

[0119] Optional, see Figure 2 , Figure 2 This is a structural diagram of a first aid method system based on 5G communication and edge devices provided by the present invention. The first aid method system based on 5G communication and edge devices includes:

[0120] The protocol adaptation module is used to detect the communication protocol type of the 5G base station based on the edge device, and to perform protocol adaptation between the edge device and the 5G base station based on the detection results to determine the target adaptation protocol;

[0121] A priority classification module is used to obtain multimodal data based on the target adaptation protocol based on the edge device, and to prioritize the multimodal data to obtain priority classification results; the multimodal data includes vital sign data, medical imaging data, and voice recording data;

[0122] A policy determination module is used to evaluate the 5G network resources of edge devices, determine the resource evaluation results, and determine the cloud transmission strategy based on the resource evaluation results and priority classification results;

[0123] The data processing module is used to perform correlation analysis on vital sign data, medical imaging data, and voice recording data to obtain computing tasks and task complexity, and then process the computing tasks based on the task complexity and cloud transmission strategy to determine the data processing results;

[0124] The data transmission module is used to transmit the data processing results in a hierarchical manner to the emergency intelligence center and mobile terminals.

[0125] The embodiment of the present invention adapts the protocol between the edge device and the 5G base station to obtain the target adaptation protocol of the corresponding edge device, thereby ensuring the high efficiency of data transmission and avoiding the compatibility problem caused by the inconsistency between device interfaces; further, according to the transmission priority of multimodal data, the evaluation results of the 5G network and the complexity of the tasks at the edge device, it can reasonably allocate computing tasks, realize local processing of simple tasks to reduce delays, and cloud processing of complex tasks to ensure the accuracy of data transmission and processing, thereby improving the processing capability of the edge device, avoiding the situation where the processing capability of the edge device is insufficient when analyzing the data of complex diseases, and thus ensuring that the emergency decision is not affected, ensuring the timeliness of emergency treatment while improving the efficiency of emergency treatment.

[0126] See also Figure 3 , Figure 3 This is a diagram of an embodiment of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, the following steps are implemented:

[0127] Detect the communication protocol type of the 5G base station based on the edge device, and perform protocol adaptation between the edge device and the 5G base station based on the detection results to determine the target adaptation protocol;

[0128] Based on the edge device, multimodal data is acquired according to the target adaptation protocol, and priority classification is performed on the multimodal data to obtain priority classification results; the multimodal data includes vital signs data, medical imaging data, and voice recording data;

[0129] Evaluate the 5G network resources of edge devices, determine the resource evaluation results, and determine the cloud transmission strategy based on the resource evaluation results and priority classification results;

[0130] Perform correlation analysis on vital sign data, medical imaging data, and voice recording data to obtain computing tasks and task complexity. Then, process the computing tasks based on task complexity and cloud transmission strategy to determine the data processing results.

[0131] The data processing results are transmitted hierarchically to the emergency intelligence center and mobile terminals.

[0132] See also Figure 4 , Figure 4 Detailed description of an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 400 on which a computer program 311 is stored. When the computer program 311 is executed by a processor, the following steps are implemented:

[0133] Detect the communication protocol type of the 5G base station based on the edge device, and perform protocol adaptation between the edge device and the 5G base station based on the detection results to determine the target adaptation protocol;

[0134] Based on the edge device, multimodal data is acquired according to the target adaptation protocol, and priority classification is performed on the multimodal data to obtain priority classification results; the multimodal data includes vital signs data, medical imaging data, and voice recording data;

[0135] Evaluate the 5G network resources of edge devices, determine the resource evaluation results, and determine the cloud transmission strategy based on the resource evaluation results and priority classification results;

[0136] Perform correlation analysis on vital sign data, medical imaging data, and voice recording data to obtain computing tasks and task complexity. Then, process the computing tasks based on task complexity and cloud transmission strategy to determine the data processing results.

[0137] The data processing results are transmitted hierarchically to the emergency intelligence center and mobile terminals.

[0138] On the other hand, the present invention further provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the first aid method based on 5G communication and edge devices provided by the above methods, which includes:

[0139] Detect the communication protocol type of the 5G base station based on the edge device, and perform protocol adaptation between the edge device and the 5G base station based on the detection results to determine the target adaptation protocol;

[0140] Based on the edge device, multimodal data is acquired according to the target adaptation protocol, and priority classification is performed on the multimodal data to obtain priority classification results; the multimodal data includes vital signs data, medical imaging data, and voice recording data;

[0141] Evaluate the 5G network resources of edge devices, determine the resource evaluation results, and determine the cloud transmission strategy based on the resource evaluation results and priority classification results;

[0142] Perform correlation analysis on vital sign data, medical imaging data, and voice recording data to obtain computing tasks and task complexity. Then, process the computing tasks based on task complexity and cloud transmission strategy to determine the data processing results.

[0143] The data processing results are transmitted hierarchically to the emergency intelligence center and mobile terminals.

[0144] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units. That is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0145] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus the necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or certain parts of the embodiment.

[0146] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A first aid method based on 5G communication and edge devices, characterized in that: include: Detecting the communication protocol type of the 5G base station based on the edge device, and performing protocol adaptation between the edge device and the 5G base station based on the detection result to determine the target adaptation protocol; Acquiring multimodal data based on the edge device according to the target adaptation protocol, and performing priority classification on the multimodal data to obtain a priority classification result; the multimodal data includes vital sign data, medical imaging data, and voice recording data; Evaluate the 5G network resources of the edge device, determine a resource evaluation result, and determine a cloud transmission strategy based on the resource evaluation result and the priority classification result; performing correlation analysis on the vital sign data, the medical imaging data, and the voice recording data to obtain a computing task and task complexity, and processing the computing task based on the task complexity and the cloud transmission strategy to determine a data processing result; The data processing results are transmitted in a hierarchical manner to the emergency intelligence center and the mobile terminal.

2. The first aid method based on 5G communication and edge devices according to claim 1, characterized in that: The performing correlation analysis on the vital sign data, the medical image data, and the voice recording data to obtain a computing task and task complexity includes: Based on the vital sign data, a time series tree is constructed, and structural features are extracted from the time series tree to obtain a first structural feature; Based on the medical image data, construct a regional topology map, and extract graph structure features from the regional topology map to obtain a second structural feature; constructing a semantic hierarchy tree based on the voice recording data, and performing feature extraction on the semantic hierarchy tree to obtain a third structural feature; Performing similarity processing on each of the first structural feature, the second structural feature, and the third structural feature to obtain a structural similarity score between any two structural features; The structural similarity scores are analyzed to obtain the computational tasks and the task complexity.

3. The first aid method based on 5G communication and edge devices according to claim 2, characterized in that: The processing of the computing task based on the task complexity and the cloud transmission strategy to determine the data processing result includes: Determine the task load based on the resource parameters of the edge device, and build a hierarchical task strategy based on the task complexity, the task load, and the cloud transmission strategy; Decomposing the computing task based on the hierarchical task strategy to obtain a task decomposition result, and sending the task decomposition result to the cloud server and the edge device; Preprocessing the multimodal data based on the task decomposition result by the edge device to obtain a preprocessing result, and sending the preprocessing result to the cloud server, so that the cloud server integrates and analyzes the preprocessing result based on the task decomposition result to obtain a task processing result, and returns the task processing result to the edge device; The edge device combines the task processing result with the multimodal data to determine the data processing result.

4. The first aid method based on 5G communication and edge devices according to claim 3, characterized in that: The step of constructing a hierarchical task strategy based on the task complexity, the task load, and the cloud transmission strategy includes: Determine an initial priority based on the importance, urgency, and business needs of the computing task; Modifying the initial priority based on the task complexity and task load to obtain a target priority; Building a priority association relationship based on the cloud transmission strategy and the target priority of the computing task; A hierarchical task queue is constructed based on the target priority of the computing task, and the hierarchical task strategy is constructed based on each queue in the hierarchical task queue, the task complexity, the task load and the priority association relationship.

5. The first aid method based on 5G communication and edge devices according to claim 1, characterized in that: The detecting the communication protocol type of the 5G base station based on the edge device, and performing protocol adaptation on the edge device and the 5G base station based on the detection result to determine the target adaptation protocol includes: Analyze the transmission information of the 5G base station based on the edge device to obtain the time domain signal; Performing short-time Fourier transform on the time domain signal to obtain a three-dimensional spectrum matrix, and performing feature spectrum extraction on the three-dimensional spectrum matrix to obtain initial spectrum fingerprint data; Matching the initial spectrum fingerprint data with templates in a protocol fingerprint library to obtain similarity scores, and screening the similarity scores to obtain a preliminary adaptation protocol; Performing a secondary screening of the preliminary adaptation protocol based on the current network load and edge device resource status to obtain a candidate adaptation protocol; A performance evaluation is performed on each of the candidate adaptation protocols to determine the target adaptation protocol.

6. The first aid method based on 5G communication and edge devices according to claim 1, characterized in that: The priority classification of the multimodal data to obtain a priority classification result includes: Analyzing the vital sign data, the medical imaging data, and the voice recording data respectively, and performing feature extraction based on the analysis results to obtain a data feature set; Based on a preset urgency assessment library, each data feature in the data feature set is judged to obtain an urgency assessment result; Determining the timeliness weights of the vital sign data, the medical imaging data, and the voice recording data based on the data type and clinical application scenario, and determining the timeliness score of each data based on the data collection time and the timeliness weight; The urgency assessment result and the timeliness score are cross-analyzed to obtain a priority classification result.

7. The first aid method based on 5G communication and edge devices according to claim 1, characterized in that: The 5G network resources include network bandwidth, delay, packet loss rate, and node load. The evaluating the 5G network resources of the edge device and determining the resource evaluation result include: The network bandwidth, delay, packet loss rate and node load resource indicator data are combined with the data collection timestamp and node geographic location information to obtain the original data set; Taking time as the horizontal axis, the original data set is divided based on time intervals to obtain time windows. Taking space as the vertical axis, the edge devices are divided into regions based on geographical regions to obtain different regions. Based on the time windows and different regions, a spatiotemporal two-dimensional window is constructed. Performing entropy processing on each resource data of the 5G network resources in each spatiotemporal window in the two-dimensional spatiotemporal window to obtain a resource entropy value; and converting each resource data of the 5G network resources in each spatiotemporal window in the two-dimensional spatiotemporal window to obtain a resource indicator vector; constructing a spatiotemporal correlation matrix based on similarities between the resource indicator vectors in different spatiotemporal windows, and determining the spatiotemporal correlation degree based on the spatiotemporal correlation matrix; A resource evaluation result is determined based on the resource entropy value and the spatiotemporal correlation.

8. A first aid method system based on 5G communication and edge devices, characterized in that: The first aid method based on 5G communication and edge devices according to any one of claims 1 to 7 is applied; the first aid method system based on 5G communication and edge devices comprises: A protocol adaptation module is used to detect the communication protocol type of the 5G base station based on the edge device, and perform protocol adaptation between the edge device and the 5G base station based on the detection result to determine the target adaptation protocol; a priority classification module, configured to acquire multimodal data based on the edge device according to the target adaptation protocol, and perform priority classification on the multimodal data to obtain a priority classification result; the multimodal data includes vital sign data, medical imaging data, and voice recording data; a policy determination module, configured to evaluate the 5G network resources of the edge device, determine a resource evaluation result, and determine a cloud transmission policy based on the resource evaluation result and the priority classification result; a data processing module, configured to perform correlation analysis on the vital sign data, the medical imaging data, and the voice recording data to obtain a computing task and task complexity, and to process the computing task based on the task complexity and the cloud transmission strategy to determine a data processing result; The data transmission module is used to transmit the data processing results in a hierarchical manner to the emergency intelligence center and the mobile terminal.

9. An electronic device comprising: Memory for storing computer software programs; A processor for reading and executing the computer software program, characterized in that when the processor executes the computer software program, it implements the first aid method based on 5G communication and edge equipment as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing a computer software program, wherein: When the computer software program is executed by the processor, the first aid method based on 5G communication and edge device as described in any one of claims 1 to 7 is implemented.

Images