Method and device for integrating measured data of operating bed

Abstract

The invention belongs to the technical field of medical data processing, and discloses an operating bed measurement data integration method and device, and the method comprises the steps: obtaining patient physiological data collected by a plurality of sensors on an operating bed, and carrying out the preprocessing of the patient physiological data, and obtaining the preprocessed physiological data; dividing the preprocessed physiological data into key physiological data and non-key physiological data; monitoring the network state information of the wireless network, and dynamically adjusting the allocation bandwidth of the key physiological data and the non-key physiological data according to the network state information, the data volume of the key physiological data and the data volume of the non-key physiological data to obtain a bandwidth allocation scheme; determining a data transmission strategy of the key physiological data and the non-key physiological data according to the bandwidth allocation scheme; transmitting data to a remote medical center according to the data transmission strategy; therefore, in a mobile emergency unit environment with limited and unstable network bandwidth, the data transmission strategy can be dynamically adjusted, and the real-time performance and reliability of key physiological data transmission are ensured.

Description

Technical Field

[0001] This application relates to the technical field of medical data processing, and more particularly, to a method and device for integrating surgical bed measurement data. Background Art

[0002] In response to public health emergencies, mobile emergency units have become a key means to rapidly enhance medical resources and have been widely used. Inside these mobile units, integrated multi-sensor surgical beds are usually deployed to receive and preliminarily evaluate the condition of patients. Especially in emergency scenarios, the condition of patients is often critical, and the amount of data generated is extremely large, including various real-time physiological parameters such as electrocardiogram, blood pressure, and blood oxygen. The remote medical center needs to monitor the patient data from multiple surgical beds in real time to guide on-site medical staff in treatment and make timely decisions on whether emergency surgery is required. However, the computing resources of mobile emergency units are usually limited and rely heavily on temporarily established wireless networks for data transmission, which results in limited network bandwidth and is extremely vulnerable to external environmental interference, with complex and unstable network conditions.

[0003] In the application of existing data integration systems in mobile emergency units, many technical challenges are faced. First, the volatility of wireless network bandwidth makes the data transmission rate extremely unstable, making it difficult to ensure the integrity and real-time nature of all medical data simultaneously. Simply increasing the data compression rate to adapt to limited bandwidth may result in the loss of key medical information, seriously affecting the accuracy of remote diagnosis and even delaying the judgment and treatment of the condition. Second, the traditional static priority queue scheduling mechanism may not be able to effectively cope with the drastic changes in network bandwidth in emergency scenarios. The static priority allocation strategy cannot dynamically adjust the transmission priorities of various types of data according to real-time network conditions, easily causing problems such as increased transmission delay of high-priority data and excessive bandwidth occupancy by low-priority data, resulting in the inability to transmit important emergency data in a timely and reliable manner.

[0004] Therefore, in the special application scenario of mobile emergency units with limited computing resources, complex wireless network environment, and extremely high requirements for data real-time nature, there is an urgent need for a surgical bed measurement data integration system that can dynamically adjust the data transmission strategy according to the wireless network condition and data real-time nature requirements. This system needs to be able to intelligently identify the priorities of different types of medical data and dynamically adjust the transmission strategies of various types of data according to the real-time network bandwidth and congestion degree, so as to ensure that key physiological data can be transmitted in a low-latency and highly reliable manner, while taking into account the transmission requirements of non-critical physiological data, and maintaining the ease of use of system operation and the stability of operation, ultimately effectively guaranteeing the real-time nature and accuracy of remote emergency treatment.

[0005] In view of the above problems, the existing technology urgently needs to be improved. Summary of the Invention

[0006] The purpose of this application is to provide a method and device for integrating surgical bed measurement data, which can dynamically adjust the data transmission strategy in a mobile emergency unit environment with limited and unstable network bandwidth to ensure the real-time and reliability of key physiological data transmission.

[0007] In the first aspect, this application provides a method for integrating surgical bed measurement data for an edge computing module in a mobile emergency unit. The steps of this method include: A1. Obtain the patient physiological data collected by multiple sensors on the surgical bed, perform preprocessing, and obtain the preprocessed physiological data; A2. Classify the preprocessed physiological data to divide the preprocessed physiological data into key physiological data and non-key physiological data; A3. Monitor the network status information of the wireless network, and dynamically adjust the allocated bandwidth of the key physiological data and the non-key physiological data according to the network status information, the data volume of the key physiological data, and the data volume of the non-key physiological data to obtain a bandwidth allocation scheme; the network status information includes available bandwidth and network congestion degree; A4. Determine the data transmission strategies for the key physiological data and the non-key physiological data according to the bandwidth allocation scheme; A5. Transmit data to the remote medical center according to the data transmission strategy.

[0008] Further, this application also proposes that step A2 includes: A201. Extract the feature vectors of each item of preprocessed physiological data; A202. For each item of preprocessed physiological data, calculate the similarity between the feature vector of the preprocessed physiological data and the typical feature vectors of the corresponding physiological data in the physiological data feature library to obtain a similarity set; the physiological data feature library records the typical feature vectors of each physiological data in various emergency situations; A203. Determine whether the preprocessed physiological data is key physiological data or non-key physiological data according to the similarity set of each item of preprocessed physiological data.

[0009] Further, this application also proposes that step A201 includes: For each item of preprocessed physiological data, use a feature extraction algorithm based on wavelet transform to decompose it into wavelet coefficients in multiple frequency bands; Calculate the energy values of the wavelet coefficients in each frequency band to form an energy feature vector; Normalize the energy feature vector to obtain the feature vector of each item of preprocessed physiological data.

[0010] Further, the present application also proposes that step A203 includes: If there is at least one similarity in the similarity set that is greater than a preset similarity threshold, then determine the corresponding preprocessed physiological data as critical physiological data; If the similarities in the similarity set are all not greater than the preset similarity threshold, then estimate the probability that the corresponding preprocessed physiological data is physiological data in an unknown emergency situation based on the similarity set; If the probability is greater than a preset probability threshold, then determine the corresponding preprocessed physiological data as critical physiological data; otherwise, determine the corresponding preprocessed physiological data as non-critical physiological data.

[0011] Further, the present application also proposes that if the similarities in the similarity set are all not greater than the preset similarity threshold, then the steps of estimating the probability that the corresponding preprocessed physiological data is physiological data in an unknown emergency situation based on the similarity set include: Calculate the variance of the similarity set to obtain the similarity variance; If the similarity variance is less than a preset variance threshold, then use the Bayesian estimation method to estimate the probability that the corresponding preprocessed physiological data is physiological data in an unknown emergency situation based on the similarity set; If the similarity variance is not less than the preset variance threshold, then use the kernel density estimation method to estimate the probability that the corresponding preprocessed physiological data is physiological data in an unknown emergency situation based on the similarity set.

[0012] Further, the present application also proposes that step A3 includes: A301. Monitor the available bandwidth and network congestion degree of the wireless network, and calculate the network quality score; A302. Obtain the data volumes of critical physiological and non-critical physiological data, and calculate the data volume ratio of critical physiological data to non-critical physiological data; A303. According to the network quality score and the data volume ratio, use the fuzzy control algorithm to determine the target bandwidth allocation ratio of critical physiological data and non-critical physiological data; A304. According to the target bandwidth allocation ratio and the available bandwidth of the wireless network, calculate the allocated bandwidth of critical physiological data and the allocated bandwidth of non-critical physiological data to obtain the bandwidth allocation scheme.

[0013] Further, the present application also proposes that step A303 includes: According to the network quality score and the data volume ratio, a fuzzy inference algorithm is adopted to select applicable fuzzy rules from the fuzzy rule base, calculate the activation strength of each fuzzy rule based on the network quality score and the data volume ratio, and obtain the fuzzy inference result; the fuzzy rule base contains multiple fuzzy rules, and the fuzzy rules define the mapping relationship between the network quality score, the data volume ratio, and the target bandwidth allocation ratio. Perform weighted average defuzzification on the fuzzy inference result, and calculate the target bandwidth allocation ratio of the critical physiological data and the non-critical physiological data according to the activation strength of each fuzzy rule and the corresponding target bandwidth allocation ratio.

[0014] Furthermore, the present application also proposes that step A4 includes: A401. Determine the priority queues of the critical physiological data and the non-critical physiological data according to the bandwidth allocation scheme; A402. For each priority queue, divide the data into multiple data packets according to the data volume of the data to be transmitted in the queue, and determine the maximum transmission unit of each data packet according to the bandwidth allocation scheme; A403. Schedule the data packets in the queue according to the priority order of the priority queues, encapsulate the data packets according to the determined maximum transmission unit, perform error control coding on the data packets of the critical physiological data using Turbo codes, and perform error control coding on the data packets of the non-critical physiological data using parity check codes.

[0015] Furthermore, the present application also proposes that before step A401, the following steps are further included: A400a. Calculate the ratio of the allocated bandwidth of the non-critical physiological data to the data volume of the non-critical physiological data, denoted as the ratio density; A400b. If the ratio density is lower than the preset ratio density threshold, select at least part of the non-critical physiological data as the object to be replaced, extract the characteristic data of the object to be replaced to replace the corresponding non-critical physiological data, so that the ratio density is not lower than the preset ratio density threshold.

[0016] In a second aspect, the present application also proposes an integrated device for surgical bed measurement data, which is used for an edge computing module in a mobile emergency unit. The device includes: A data acquisition module, which is used to acquire the patient physiological data collected by multiple sensors on the surgical bed, perform preprocessing, and obtain the preprocessed physiological data; A data classification module, which is used to classify the preprocessed physiological data to divide the preprocessed physiological data into critical physiological data and non-critical physiological data; A bandwidth allocation module, which is used to monitor the network status information of a wireless network, and dynamically adjust the allocated bandwidths of critical physiological data and non-critical physiological data according to the network status information, the data volume of the critical physiological data, and the data volume of the non-critical physiological data, so as to obtain a bandwidth allocation scheme; the network status information includes available bandwidth and network congestion degree; A transmission strategy adjustment module, which is used to determine the data transmission strategies of the critical physiological data and the non-critical physiological data according to the bandwidth allocation scheme; A data transmission module, which is used to transmit data to a remote medical center according to the data transmission strategy.

[0017] Advantageous effects: A method and device for integrating surgical bed measurement data provided by this application classify physiological data and dynamically adjust bandwidth allocation and transmission strategies according to the network status, achieving real-time and reliable transmission of critical physiological data in a mobile emergency unit with limited network, and improving the efficiency and accuracy of remote medical treatment. Description of the Drawings

[0018] Figure 1 It is a flowchart of the method for integrating surgical bed measurement data provided by an embodiment of this application.

[0019] Figure 2 It is a schematic structural diagram of the device for integrating surgical bed measurement data provided by an embodiment of this application.

[0020] Label description: 1. Data acquisition module; 2. Data classification module; 3. Bandwidth allocation module; 4. Transmission strategy adjustment module; 5. Data transmission module. Detailed Embodiments

[0021] Next, the technical solutions in this application will be clearly and completely described in conjunction with the drawings in this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. The components of this application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of this application that is required to be protected, but only represents the selected embodiments of this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of this application.

[0022] It should be noted that: Similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, terms such as "first", "second", etc. are only used for distinguishing descriptions, and cannot be understood as indicating or implying relative importance.

[0023] Reference Figure 1 , this application proposes a method for integrating surgical bed measurement data for an edge computing module in a mobile emergency unit. The steps of this method include: A1. Obtain the physiological data of the patient collected by multiple sensors on the surgical bed, perform preprocessing, and obtain the preprocessed physiological data; A2. Classify the preprocessed physiological data to divide the preprocessed physiological data into critical physiological data and non-critical physiological data; A3. Monitor the network status information of the wireless network, and dynamically adjust the allocated bandwidths of the critical physiological data and the non-critical physiological data according to the network status information, the data volume of the critical physiological data, and the data volume of the non-critical physiological data, to obtain a bandwidth allocation scheme; the network status information includes available bandwidth and network congestion level; A4. Determine the data transmission strategies for the critical physiological data and the non-critical physiological data according to the bandwidth allocation scheme; A5. Transmit data to the remote medical center according to the data transmission strategy.

[0024] Among them, in step A1, multiple sensors on the surgical bed are used to collect the physiological data of the patient. The physiological data may include electrocardiogram data, blood pressure data, blood oxygen data, heart rate data, body temperature data, etc. The edge computing module is used to perform local processing on the physiological data collected by multiple sensors on the surgical bed and then send it to the remote medical center. Then, preprocessing operations are performed on the collected original physiological data. The preprocessing may include some or all of the links such as noise removal, interference filtering, data smoothing, baseline correction, outlier processing, data format conversion, unit unification, etc., to improve the data quality and lay a foundation for subsequent data classification and transmission; different physiological data may adopt different preprocessing methods. For example, electrocardiogram data is processed by a band-pass filter to remove power frequency interference and electromyogram noise, blood pressure data and heart rate data are processed by outlier detection and correction to eliminate measurement errors, blood oxygen data is corrected for baseline drift, and body temperature data is processed by data smoothing to reduce noise interference. The preprocessed physiological data can provide higher-quality and more standardized data input for subsequent steps.

[0025] Among them, in step A2, the preprocessed physiological data is classified to distinguish key physiological data and non-key physiological data. Specifically, the following methods can be used to achieve this: Classification rules or classification models can be preset, and the physiological data can be divided according to characteristics such as the type and importance of the physiological data. For example, data directly reflecting the patient's vital signs, such as electrocardiogram data and blood pressure data, can be classified as key physiological data, while body temperature data, heart rate data, etc. can be classified as non-key physiological data. The purpose of classification is to adopt different processing strategies for different types of data in subsequent steps, ensuring that key data is given priority in processing and transmission, and non-key data is also transmitted when network resources permit, so as to balance data integrity and transmission efficiency. The data classification result provides a data basis for subsequent dynamic bandwidth allocation and transmission strategy adjustment.

[0026] Among them, in step A3, the wireless network status is monitored, and the bandwidth allocation for key and non-key physiological data is dynamically adjusted according to the network status and the data volume of various types of data. Specifically, the following methods can be used to achieve this: First, through network monitoring tools or protocols, network status information such as the available bandwidth and network congestion degree of the wireless network is monitored in real time. The network status information reflects the quality and transmission capacity of the current wireless network. Then, combined with the data volume sizes of the current key physiological data and non-key physiological data to be transmitted, it is used as a reference basis for bandwidth allocation. The larger the data volume, the higher the required bandwidth. Further, a bandwidth dynamic adjustment algorithm can be designed, such as a fuzzy control algorithm, a PID control algorithm, etc. According to the network status information and the data volume, the bandwidth ratio or specific bandwidth value to be allocated for key physiological data and non-key physiological data is dynamically calculated to generate a bandwidth allocation plan. The bandwidth allocation plan reflects how to reasonably allocate limited bandwidth resources under the current network conditions to ensure the priority transmission of key data to the greatest extent while taking into account the transmission requirements of non-key data. Dynamic bandwidth adjustment is the core of this solution and can effectively cope with the instability of the wireless network environment.

[0027] Among them, in step A4, according to the bandwidth allocation plan obtained in step A3, the specific transmission strategies for key and non-key physiological data are determined. Specifically, the transmission strategies can include: determining some or all of the priorities, packet sizes, transmission rates, coding methods, retransmission mechanisms, etc. of various types of data. For example, a higher transmission priority can be set for key physiological data to ensure priority transmission in case of network congestion; the packet size can be adjusted according to the allocated bandwidth to avoid congestion caused by overly large packets in a low-bandwidth network; different error control coding methods can be adopted, such as using Turbo codes with higher reliability for key data and parity check codes with lower overhead for non-key data. The transmission strategy is to implement the bandwidth allocation plan and ensure the reliability and real-time nature of data transmission through refined transmission control.

[0028] Among them, in step A5, according to the data transmission strategy determined in step A4, the classified physiological data is transmitted to the remote medical center. Specifically, wireless communication technologies such as Wi-Fi, 4G / 5G, etc. can be used to send the data to the server of the remote medical center through the wireless network. During the data transmission process, it is necessary to strictly follow the transmission strategy determined in step A4, such as sending data packets in the order of priority and using the set coding method for data encoding, etc., to ensure that the data can be transmitted according to the expected strategy. After the remote medical center receives the physiological data transmitted by the operating bed, medical staff can monitor the physiological state of the patient in real time, providing data support for remote diagnosis and treatment. Data transmission is the ultimate goal of this solution, realizing the remote sharing and application of physiological data.

[0029] Specifically, this solution aims to solve the problem of limited and unstable wireless network bandwidth in the specific application scenario of the mobile emergency unit. First, through step A1, the preliminary collection and preprocessing of data are completed to prepare a high-quality data source for subsequent operations. Step A2 classifies the data, distinguishing critical data and non-critical data, which is the premise for implementing differential processing. Step A3 is the core, by real-time monitoring the network status and combining with the data volume, dynamically adjusting the bandwidth allocation scheme. This dynamic adjustment mechanism enables the system to adapt to the fluctuating wireless network environment, ensuring that critical data can obtain sufficient bandwidth resources for priority transmission under any network condition. Step A4 converts the bandwidth allocation scheme into a specific transmission strategy, refining the control of data transmission, such as priority queue, data packet size, coding method, etc., to ensure the executability and effectiveness of the transmission strategy. Finally, step A5 transmits the data to the remote medical center, realizing the ultimate application value of the data.

[0030] Through the above technical solution, this application realizes the low-latency and high-reliable transmission of critical physiological data under the condition of limited and unstable wireless network bandwidth in the mobile emergency unit, and takes into account the transmission requirements of non-critical physiological data. The dynamic bandwidth allocation mechanism can adaptively adjust according to the change of network conditions, ensuring that critical data is always given priority to be transmitted under various network conditions, improving the reliability and real-time performance of data transmission, providing stable and reliable data support for remote medical treatment, and enhancing the efficiency and accuracy of remote emergency treatment.

[0031] Furthermore, this application also proposes that step A2 includes: A201. Extract the feature vectors of each preprocessed physiological data; A202. For each piece of preprocessed physiological data, calculate the similarity between the feature vector of the preprocessed physiological data and each typical feature vector of the corresponding physiological data in the physiological data feature library to obtain a similarity set; the physiological data feature library records the typical feature vectors of each physiological data in various emergency situations. A203. Based on the similarity sets of each piece of preprocessed physiological data, determine whether the preprocessed physiological data is critical physiological data or non-critical physiological data.

[0032] Among them, step A201 refers to extracting the feature vectors of each piece of preprocessed physiological data. Specifically, a feature extraction algorithm based on wavelet transform can be used to decompose it into wavelet coefficients in multiple frequency bands. Fourier transform, discrete cosine transform, etc. can also be used. Through these transforms, the physiological data is converted from the time domain to the frequency domain or other domains to extract feature vectors that can represent the characteristics of the physiological data, such as energy features, frequency features, statistical features, etc. The dimension and type of the feature vectors can be selected and adjusted according to the specific type of physiological data and classification requirements to balance the computational complexity and classification performance.

[0033] Among them, in step A202, the physiological data feature library can be pre-constructed by collecting and organizing a large amount of physiological data, covering the physiological data characteristics in various emergency situations, such as emergency situations like an abnormally rapid heart rate and an abnormally elevated blood pressure. The typical feature vectors can be extracted and screened from these data and stored in the feature library. Similarity calculation can use methods such as cosine similarity, Euclidean distance, and Pearson correlation coefficient to quantify the similarity degree between the physiological data to be classified and the typical feature vectors in the feature library. The similarity set refers to the numerical set obtained by calculating the similarity between a piece of physiological data and multiple typical feature vectors of the same type of physiological data in the feature library. This set can comprehensively reflect the degree of association between the physiological data and various emergency situations.

[0034] Among them, in step A203, a similarity threshold can be set, for example, 0.8. If there is at least one similarity in the similarity set that is greater than this threshold, the corresponding physiological data is determined to be critical physiological data, indicating that this physiological data is very similar to the typical characteristics of a certain emergency situation and needs to be processed and transmitted preferentially. If the similarities in the similarity set are all not greater than the preset similarity threshold, the probability that the corresponding preprocessed physiological data is physiological data in an unknown emergency situation can be further estimated based on the similarity set. For example, by counting the number of similarities in the similarity set that are greater than a certain smaller threshold (such as 0.6), or calculating statistical quantities such as the mean and variance of the similarity set, to comprehensively evaluate the possibility (i.e., probability) that this physiological data belongs to an unknown emergency situation. If the probability is greater than the preset probability threshold, it is also determined to be critical physiological data to cope with potential risks. Otherwise, it is determined to be non-critical physiological data. Thus, automatic classification of physiological data can be achieved, distinguishing between critical and non-critical data, providing a basis for subsequent bandwidth allocation and transmission strategy adjustment.

[0035] Furthermore, steps A201 and A202 are the prerequisites for step A203. Step A201 realizes the quantitative representation of physiological data, step A202 realizes the correlation analysis between physiological data and known emergency situations, and step A203 completes the classification decision based on the previous two steps. Through the synergistic effect of steps A201, A202, and A203, a method for classifying physiological data based on feature vector similarity is provided, realizing the effective classification of physiological data, solving the problem of how to effectively identify critical physiological data mentioned in the background technology, and providing a data basis for subsequent data transmission strategies.

[0036] Through the above technical solutions, the present application realizes the effective classification of preprocessed physiological data, distinguishing critical physiological data and non-critical physiological data, providing a data basis for dynamically adjusting bandwidth allocation and data transmission strategies according to network status and data importance in the future. Thus, in the environment of a network-constrained mobile emergency unit, the transmission of critical physiological data can be preferentially guaranteed, improving the transmission efficiency and reliability of medical data, and providing strong support for remote medical diagnosis and treatment.

[0037] In some possible implementation manners, step A201 includes: For each piece of preprocessed physiological data, a feature extraction algorithm based on wavelet transform is adopted to decompose it into wavelet coefficients in multiple frequency bands; Calculate the energy values of the wavelet coefficients in each frequency band to form an energy feature vector; Perform normalization processing on the energy feature vector to obtain the feature vector of each piece of preprocessed physiological data.

[0038] Among them, for each item of preprocessed physiological data, a feature extraction algorithm based on wavelet transform is executed. Thus, the physiological data is decomposed into wavelet coefficients of multiple frequency bands. As a preferred implementation, the wavelet transform algorithm can select Daubechies wavelet, Symlets wavelet, Coiflets wavelet, etc. Further, the decomposition level of the wavelet transform can be adjusted according to actual application requirements. For example, selecting 5-level wavelet decomposition can decompose the physiological data into one approximation coefficient frequency band containing low-frequency information and five detail coefficient frequency bands containing high-frequency information. Subsequently, for the wavelet coefficients of each frequency band, the energy value is calculated. Specifically, the energy value of the wavelet coefficients of each frequency band can be obtained by calculating the sum of the squares of all wavelet coefficients in that frequency band. Thus, an energy feature vector is constituted. Each element in the energy feature vector represents the energy value of the wavelet coefficients of the corresponding frequency band, which can reflect the energy distribution of the physiological data in different frequency bands. Finally, in order to eliminate the differences in dimension and numerical range between different physiological data, the energy feature vector is normalized. For example, the minimum-maximum normalization method can be used to scale each element of the energy feature vector to between 0 and 1. Through the above steps, the feature vectors of each item of preprocessed physiological data are obtained, providing quantitative features for the subsequent classification of physiological data.

[0039] Specifically, in the emergency scene, the collected physiological data contains rich physiological feature information. If an inappropriate feature extraction method is used, these feature information cannot be effectively extracted, thus affecting the accuracy of subsequent physiological data classification. Through the feature extraction algorithm based on wavelet transform proposed in this application, the above problems can be effectively solved. First, through wavelet transform, the physiological data is decomposed into wavelet coefficients of multiple frequency bands, realizing the time-frequency domain analysis of the physiological data and being able to extract more comprehensively the feature information contained in the physiological data. Then, by calculating the energy value of the wavelet coefficients of each frequency band, an energy feature vector is constructed, and the energy feature vector can effectively represent the energy distribution of the physiological data in different frequency bands, thus highlighting the key features of the physiological data. Finally, by normalizing the energy feature vector, the differences in dimension and numerical range between different physiological data are eliminated, improving the accuracy and stability of subsequent data classification. Thus, high-quality feature data can be provided for the subsequent classification of physiological data, and further improving the accuracy of physiological data classification in the emergency scene.

[0040] In some specific embodiments, for electrocardiogram data, firstly, the db4 wavelet basis can be used to perform 5-layer wavelet decomposition on it, obtaining 1 approximation coefficient CA5 and 5 detail coefficients CD1 - CD5. Then, the energy values of the wavelet coefficients in these 6 frequency bands, namely CA5 and CD1 - CD5, are calculated respectively to form a 6-dimensional energy feature vector. Further, the minimum-maximum normalization method is used to normalize this energy feature vector, scaling each element in the vector to the interval [0, 1]. For example, if the original energy feature vector is [100, 25, 10, 5, 2, 1], the normalized energy feature vector can be [1, 0.25, 0.1, 0.05, 0.02, 0.01]. Thus, the feature vector of the electrocardiogram signal is obtained for subsequent physiological data classification. Using a similar method, the feature vectors of other physiological data such as blood pressure data, blood oxygen data, heart rate data, body temperature data, etc. can be extracted.

[0041] In some possible real-time modes, step A203 includes: If there is at least one similarity in the similarity set greater than a preset similarity threshold, it is determined that the corresponding preprocessed physiological data is critical physiological data; If the similarities in the similarity set are all not greater than the preset similarity threshold, the probability that the corresponding preprocessed physiological data is physiological data in an unknown emergency situation is estimated according to the similarity set; If the probability is greater than a preset probability threshold, it is determined that the corresponding preprocessed physiological data is critical physiological data, otherwise, it is determined that the corresponding preprocessed physiological data is non-critical physiological data.

[0042] Among them, the preset similarity threshold is a numerical standard for initially judging the level of similarity. This threshold can be set according to specific application scenarios and data characteristics. For example, it can be set to 0.8, 0.9, etc. The setting of the similarity threshold needs to balance the accuracy and sensitivity of data classification. If there is at least one similarity in the similarity set greater than the preset similarity threshold, determining that the corresponding preprocessed physiological data is critical physiological data means that when the preprocessed physiological data is similar enough to at least one typical feature vector in the physiological data feature library, even if the specific type of emergency situation cannot be completely determined, it is regarded as critical physiological data. This processing method can quickly identify physiological data highly related to known emergency situations and ensure a rapid response to known emergency situations.

[0043] Among them, if the similarities in the similarity set are all not greater than a preset similarity threshold, estimating the probability that the corresponding preprocessed physiological data is physiological data in an unknown emergency situation based on the similarity set means that when the similarities between the preprocessed physiological data and all typical feature vectors in the physiological data feature library are not high, considering the possible "unknown emergency situations" not covered by the feature library, further evaluating the possibility that it is physiological data in an unknown emergency situation. Probability estimation can use various statistical methods, such as Bayesian estimation, kernel density estimation, etc. The similarity values in the similarity set can be used as input parameters for probability estimation.

[0044] Among them, the preset probability threshold is a numerical standard for judging the level of the probability of an unknown emergency situation. This threshold can be set according to the tolerance of the misjudgment risk. For example, it can be set to 0.6, 0.7, etc. The setting of the probability threshold affects the recognition sensitivity of unknown emergency situations. If the probability is greater than the preset probability threshold, it is determined that the corresponding preprocessed physiological data is critical physiological data; otherwise, it is determined that the corresponding preprocessed physiological data is non-critical physiological data, which means that based on the estimated probability of the unknown emergency situation and combined with the probability threshold, the category of the preprocessed physiological data is finally determined. Even if the similarity is not high, but if the probability of the unknown emergency situation is high, it is still determined as critical physiological data, reflecting the anticipation and prevention of potential risks. On the contrary, if the probability is not high, it is determined as non-critical physiological data, avoiding data misjudgment caused by over-sensitivity.

[0045] Specifically, when classifying the preprocessed physiological data in this solution, first calculate the similarity set between its feature vector and the typical feature vectors in the physiological data feature library. If there are high similarities in the similarity set, it is quickly determined as critical physiological data, ensuring the rapid recognition of known emergency situations. When all similarities are not high, the solution does not directly determine it as non-critical data, but further estimates the probability that it is an unknown emergency situation. By introducing a probability estimation mechanism, the potential risks of the data can be evaluated more comprehensively, avoiding the omission of critical data caused by the limitations of the feature library. This processing method improves the intelligence and robustness of data classification while ensuring the accuracy of data classification. Especially in complex and changeable emergency scenarios, it can more accurately identify critical physiological data, providing a more reliable data basis for subsequent data transmission strategy adjustment and remote medical decision-making.

[0046] Through the above technical solution, in the case of low similarity, this application can further accurately judge whether the corresponding preprocessed physiological data is critical physiological data, thereby avoiding misjudging potential critical physiological data as non-critical physiological data, ensuring the accuracy of data classification, and providing a more reliable data basis for subsequent data transmission strategy adjustment and remote medical decision-making.

[0047] In some preferred embodiments, if the similarities in the similarity set are all not greater than a preset similarity threshold, the steps of estimating the probability that the corresponding preprocessed physiological data is physiological data in an unknown emergency situation based on the similarity set include: Calculate the variance of the similarity set to obtain the similarity variance; If the similarity variance is less than a preset variance threshold, use the Bayesian estimation method to estimate the probability that the corresponding preprocessed physiological data is physiological data in an unknown emergency situation based on the similarity set; If the similarity variance is not less than a preset variance threshold, use the kernel density estimation method to estimate the probability that the corresponding preprocessed physiological data is physiological data in an unknown emergency situation based on the similarity set.

[0048] Among them, the variance of the similarity set can be calculated using the sample variance formula. For example, for a set {s1, s2,..., sn} containing n similarity values, where s1 to sn are the similarity values in the similarity set, the similarity variance can be calculated as: V = Σ(si - μ)^2 / (n - 1), where V is the variance of the similarity set, si is the i-th variance in the similarity set, and μ is the mean of the similarity set.

[0049] Among them, the preset variance threshold is a reference value for judging the dispersion degree of the similarity set. Specifically, it can be preset in advance through experimental analysis or statistical methods according to the actual application scenario and data characteristics.

[0050] Among them, the Bayesian estimation method is a parameter estimation method based on Bayesian theory. Specifically, specific Bayesian estimation models such as naive Bayes and Gaussian Bayes can be used. In the solution, the Bayesian estimation method is used to estimate the probability of physiological data in an unknown emergency situation when the similarity variance is small, that is, when the similarity values are relatively concentrated. The Bayesian estimation method can combine prior knowledge and sample data to obtain a posterior probability estimate, thereby more accurately estimating the probability. The specific calculation process is prior art and will not be elaborated here.

[0051] Among them, the kernel density estimation method is a non-parametric estimation method used to estimate the probability density function of a random variable. Specifically, kernel functions such as Gaussian kernel function and Epanechnikov kernel function can be used. In the solution, the kernel density estimation method is used to estimate the probability of physiological data in an unknown emergency situation when the similarity variance is large, that is, when the similarity values are relatively dispersed. The kernel density estimation method does not depend on specific assumptions about the data distribution and can better adapt to various data distribution situations, thereby more robustly estimating the probability. The specific calculation process is prior art and will not be elaborated here.

[0052] Among them, the probability is estimated by using the Bayesian estimation method or the kernel density estimation method, and the probability value that the preprocessed physiological data is the physiological data in an unknown emergency situation is calculated according to the selected estimation method and the specific values of the similarity set. For example, through the Bayesian estimation method, the probability value P_bayes can be obtained; through the kernel density estimation method, the probability value P_kde can be obtained.

[0053] Specifically, this solution refines the step of "if the similarities in the similarity set are all not greater than the preset similarity threshold, then estimate the probability that the corresponding preprocessed physiological data is the physiological data in an unknown emergency situation according to the similarity set".

[0054] First, calculate the variance of the similarity set to obtain the similarity variance. The similarity variance can reflect the degree of dispersion among the similarity values in the similarity set. When the similarity variance is small, it indicates that the similarity values in the similarity set are relatively concentrated, which may mean that the overall similarity degree between the preprocessed physiological data and the typical feature vectors in the physiological data feature library is not high but relatively stable. At this time, using the Bayesian estimation method can effectively utilize these relatively concentrated similarity information, so as to estimate the probability more accurately. On the contrary, when the similarity variance is large, it indicates that the similarity values in the similarity set are relatively dispersed, which may mean that the similarity degree between the preprocessed physiological data and the typical feature vectors in the physiological data feature library fluctuates greatly. At this time, using the kernel density estimation method, because the kernel density estimation method has no specific assumption about the data distribution, it can better adapt to the situation where the similarity values are dispersed, so as to estimate the probability more robustly.

[0055] By dynamically selecting an appropriate probability estimation method according to the size of the similarity variance, it is possible to more accurately evaluate the probability that the physiological data belongs to an unknown emergency situation even when the similarity is not high. This dynamic selection mechanism fully considers the distribution characteristics of the similarity set, improves the accuracy and reliability of probability estimation, and then improves the accuracy of data classification, provides more accurate data support for the formulation of subsequent data transmission strategies, and finally ensures the real-time and accuracy of remote emergency treatment.

[0056] Through the above technical solution, this application can dynamically select the Bayesian estimation method or the kernel density estimation method to estimate the probability of physiological data in an unknown emergency situation according to the variance size of the similarity set, improve the accuracy and robustness of probability estimation, and then improve the accuracy of data classification, providing more accurate data support for the formulation of subsequent data transmission strategies.

[0057] In some embodiments, step A3 includes: A301. Monitor the available bandwidth and network congestion degree of the wireless network, and calculate the network quality score; A302. Obtain the data volumes of critical physiological data and non-critical physiological data, and calculate the ratio of the data volume of critical physiological data to that of non-critical physiological data; A303. According to the network quality score and the data volume ratio, adopt a fuzzy control algorithm to determine the target bandwidth allocation ratios for critical physiological data and non-critical physiological data; A304. According to the target bandwidth allocation ratios and the available bandwidth of the wireless network, calculate the allocated bandwidths for critical physiological data and non-critical physiological data to obtain a bandwidth allocation scheme.

[0058] Among them, in step A301, the network quality score is calculated from the available bandwidth and the network congestion degree. Specifically, the available bandwidth can be directly obtained by a network monitoring tool, and the network congestion degree can be evaluated by parameters such as packet loss rate and latency (that is, by monitoring the packet loss rate and latency, and using the packet loss rate and latency to evaluate the network congestion degree. For example, a weighted sum calculation is performed using the packet loss rate and latency to obtain the network congestion degree). The network quality score can be designed as a weighted combination of the available bandwidth and the network congestion degree. For example, the higher the available bandwidth and the lower the network congestion degree, the higher the network quality score. Specifically, the network quality score can be calculated using the following formula: network quality score = α × available bandwidth score + β × (1 - network congestion degree score), where α and β are weight coefficients used to adjust the relative importance of the available bandwidth and the network congestion degree in the network quality score. The available bandwidth score and the network congestion degree score are standardized scores converted from the original data to between 0 and 1 (the original data can be converted to a standardized score between 0 and 1 using a linear scaling method or a Sigmoid function) for unified calculation.

[0059] Among them, in step A302, the data volume ratio is calculated by dividing the data volume of critical physiological data by the data volume of non-critical physiological data.

[0060] Among them, in step A303, a fuzzy control algorithm is used to determine the target bandwidth allocation ratio. The mapping relationship between the network quality score, the data volume ratio, and the target bandwidth allocation ratio is predefined in the fuzzy rule base of the fuzzy control algorithm. For example, when the network quality score is high and the data volume ratio is high, the fuzzy rule may set a higher target bandwidth allocation ratio. The fuzzy inference process is based on the current network quality score and data volume ratio, activates the corresponding fuzzy rules, and performs fuzzy inference to obtain a fuzzy inference result. The defuzzification process is used to convert the fuzzy inference result into an exact numerical value of the target bandwidth allocation ratio.

[0061] Among them, in step A304, the allocated bandwidths of the critical physiological data and the non-critical physiological data are calculated based on the target bandwidth allocation ratio and the available bandwidth of the wireless network. For example, if the target bandwidth allocation ratios of the critical physiological data and the non-critical physiological data are 70% and 30% respectively, and the available bandwidth of the wireless network is 10 Mbps, then the allocated bandwidth of the critical physiological data is 7 Mbps, and the allocated bandwidth of the non-critical physiological data is 3 Mbps.

[0062] Specifically, in this solution, first, in step A301, the network status is monitored and the network quality score is calculated to quantify the current network condition. Second, in step A302, the data volume of various types of data is obtained and the data volume ratio is calculated to reflect the data volume relationship of different types of data. Then, in step A303, a fuzzy control algorithm is introduced to determine the target bandwidth allocation ratios of the critical physiological data and the non-critical physiological data according to the network quality score and the data volume ratio. The fuzzy control algorithm can effectively handle the uncertainty and fuzziness of the network status and the data volume ratio, and thus can more reasonably determine the bandwidth allocation ratio. Finally, in step A304, based on the target bandwidth allocation ratio and the available bandwidth, the specific allocated bandwidths of various types of data are calculated to obtain a bandwidth allocation scheme. Through the above steps, step A3 can dynamically adjust the bandwidth allocation scheme according to the changes in the network status and the data volume, so as to more effectively respond to the changes in the network status and the data volume and obtain a more reasonable bandwidth allocation scheme.

[0063] In some specific embodiments, it is assumed that the available bandwidth of the wireless network where the mobile emergency unit is located is 5 Mbps, and the network congestion level rating is medium. In step A301, the network quality score is calculated to be 60 points (on a 100-point scale). At the same time, in step A302, the data volume of the critical physiological data is 2 MB, the data volume of the non-critical physiological data is 1 MB, and the data volume ratio is calculated to be 2. In step A303, based on the network quality score of 60 points and the data volume ratio of 2, the fuzzy control algorithm determines the target bandwidth allocation ratios of the critical physiological data and the non-critical physiological data to be 70% and 30% by referring to the fuzzy rule base and fuzzy inference. The fuzzy rule base may contain the following rules: If the network quality score is medium and the data volume ratio is high, then the target bandwidth allocation ratio is high. In step A304, according to the target bandwidth allocation ratios of 70% and 30%, and the available bandwidth of 5 Mbps, the allocated bandwidth of the critical physiological data is calculated to be 3.5 Mbps, and the allocated bandwidth of the non-critical physiological data is calculated to be 1.5 Mbps, thereby obtaining a bandwidth allocation scheme. Through this bandwidth allocation scheme, the critical physiological data is allocated a higher bandwidth to ensure the priority transmission of the critical physiological data, and the non-critical physiological data can also obtain a certain bandwidth for transmission, realizing the balance of the transmission requirements of the critical physiological data and the non-critical physiological data under the condition of limited network resources.

[0064] In some preferred embodiments, step A303 includes: According to the network quality score and the data volume ratio, using a fuzzy inference algorithm, select applicable fuzzy rules from the fuzzy rule base, calculate the activation strength of each fuzzy rule based on the network quality score and the data volume ratio, and obtain a fuzzy inference result; the fuzzy rule base contains multiple fuzzy rules, and the fuzzy rules define the mapping relationship between the network quality score, the data volume ratio, and the target bandwidth allocation ratio; Perform weighted average defuzzification on the fuzzy inference result, and calculate the target bandwidth allocation ratio for critical physiological data and non-critical physiological data according to the activation strength of each fuzzy rule and the corresponding target bandwidth allocation ratio.

[0065] Among them, the construction method of the fuzzy rule base can be preset. Specifically, the fuzzy rule base can contain multiple fuzzy rules, and each fuzzy rule defines the mapping relationship between the network quality score, the data volume ratio, and the target bandwidth allocation ratio. For example, a fuzzy rule can be: if the network quality score is high and the data volume ratio is low, then the target bandwidth allocation ratio is high. The selection of fuzzy rules can be based on expert experience or experimental data. The selection of the fuzzy inference algorithm can be any one of various fuzzy inference methods. For example, the Mamdani fuzzy inference algorithm or the Takagi-Sugeno fuzzy inference algorithm. The calculation of the activation strength can be performed according to the antecedent of the fuzzy rule and the membership function of the input variable. Weighted average defuzzification is a commonly used defuzzification method, and the final target bandwidth allocation ratio is obtained by calculating the weighted average of the activation strength of each fuzzy rule and the corresponding target bandwidth allocation ratio.

[0066] Specifically, for the broadness problem of the fuzzy control algorithm, the solution of step A303 adopts a fuzzy inference algorithm. The fuzzy inference algorithm defines the mapping relationship between the network quality score, the data volume ratio, and the target bandwidth allocation ratio by establishing a fuzzy rule base. When making a decision on the bandwidth allocation ratio, first select applicable fuzzy rules from the fuzzy rule base, then calculate the activation strength of each fuzzy rule based on the network quality score and the data volume ratio to obtain a fuzzy inference result, and finally obtain an accurate target bandwidth allocation ratio through weighted average defuzzification. This method realizes the accurate mapping from the network state and data volume to the bandwidth allocation ratio through a specific fuzzy inference algorithm and fuzzy rule base, improves the rationality and effectiveness of bandwidth allocation, and thus enhances the efficiency and reliability of data transmission. In a scenario such as a mobile emergency unit where resources are limited, the network environment is complex, and the real-time requirement is extremely high, it can dynamically adjust the data transmission strategy according to the wireless network condition and the real-time requirement of data, ensure that critical real-time physiological data can be transmitted with low latency and high reliability, while taking into account the transmission requirements of non-real-time data, and maintain the usability and operation stability of the system to ensure the real-time and accuracy of remote emergency treatment.

[0067] Furthermore, the present application also proposes that step A4 includes: A401. Determine the priority queues of critical physiological data and non-critical physiological data according to the bandwidth allocation scheme; A402. For each priority queue, divide the data into multiple data packets according to the data volume of the data to be transmitted in the queue, and determine the maximum transmission unit of each data packet according to the bandwidth allocation scheme; A403. Schedule the data packets in the queue according to the priority order of the priority queues, encapsulate the data packets according to the determined maximum transmission unit, perform error control coding on the data packets of critical physiological data using Turbo codes, and perform error control coding on the data packets of non-critical physiological data using parity check codes.

[0068] Among them, in step A401, the determination of the priority queue is completed based on the bandwidth allocation scheme. Specifically, according to the bandwidth allocation ratio of critical physiological data and non-critical physiological data in the bandwidth allocation scheme, the corresponding number of priority queues is established. For example, if a higher proportion of bandwidth is allocated to critical physiological data in the allocation scheme, the critical physiological data is placed in a higher-priority queue, and the non-critical physiological data is placed in a lower-priority queue. In this way, it is ensured that critical physiological data has priority during transmission.

[0069] Among them, in step A402, the division of data packets and the determination of the maximum transmission unit are performed independently for each priority queue. For a higher-priority queue, the data is divided into multiple data packets, and the maximum transmission unit of each data packet is determined according to the bandwidth allocated to critical physiological data. When the allocated bandwidth is higher, the maximum transmission unit can be set to a larger value to improve the transmission efficiency. On the contrary, when the allocated bandwidth is lower, the maximum transmission unit is set to a smaller value to adapt to the current bandwidth condition. For a lower-priority queue, a similar process of data division and maximum transmission unit determination is also performed, but the determination of the maximum transmission unit takes into account the bandwidth allocated to non-critical physiological data. In this way, the size of the data packets can be dynamically adjusted according to the bandwidth allocation of different priority queues, thereby optimizing the utilization of network bandwidth.

[0070] Among them, in step A403, the scheduling of data packets is carried out in the order of the priority queue. Packets in the higher-priority queue are preferentially scheduled for transmission, and packets in the lower-priority queue are scheduled after the transmission of the higher-priority queue is completed. In the data packet encapsulation link, the data packets are encapsulated according to the maximum transmission unit determined in step A402 to ensure that the data packet size does not exceed the maximum transmission unit allowed by the network. In addition, different error control coding methods are adopted for data packets of different priorities. For data packets of critical physiological data, Turbo codes are used for error control coding. Turbo code is a high-performance channel coding technology that provides strong error correction ability and can effectively guarantee the reliability of the transmission of critical physiological data. For data packets of non-critical physiological data, parity check codes with lower computational complexity are used for error control coding, which can reduce the computational overhead of the system while providing basic error detection ability. Thus, while ensuring the reliable transmission of critical data, the transmission requirements of non-critical data and the effective utilization of system resources are taken into account.

[0071] Specifically, for the problem of low data transmission efficiency and reliability in scenarios with limited bandwidth and complex network conditions such as mobile emergency units, the data transmission strategy proposed in this application realizes the priority and reliable transmission of critical physiological data under limited bandwidth through technical means such as priority queue, dynamic maximum transmission unit adjustment, and differential error control coding. First, by establishing a priority queue, it is ensured that critical physiological data enjoys a higher priority during data transmission and obtains the transmission opportunity first, thereby reducing the transmission delay of critical data and ensuring the real-time nature of the data. Second, by dynamically adjusting the maximum transmission unit according to the bandwidth allocation scheme, the data packet size can be matched with the current network bandwidth conditions. When the bandwidth is sufficient, data packets with a larger maximum transmission unit are used for transmission to improve the transmission efficiency; when the bandwidth is limited, data packets with a smaller maximum transmission unit are used for transmission to avoid network congestion and optimize the bandwidth utilization rate. In addition, different error control coding methods are adopted for critical physiological data and non-critical physiological data. On the premise of ensuring the reliability of critical data, the coding overhead of non-critical data is reduced, and the reliability of data transmission and the consumption of system resources are balanced. Through the comprehensive application of the above strategies, the integrated transmission performance of the operating bed measurement data can be improved in resource-constrained environments such as mobile emergency units, providing more timely and reliable data support for telemedicine.

[0072] In some specific embodiments, the priority of critical physiological data can be preset to be higher than that of non-critical physiological data. After the bandwidth allocation scheme is determined, the data packets of critical physiological data are placed in the queue with priority 1, and the data packets of non-critical physiological data are placed in the queue with priority 2. Suppose the bandwidth allocated to critical physiological data is 5 Mbps, and the bandwidth allocated to non-critical physiological data is 2 Mbps. For the queue with priority 1, if the amount of data to be transmitted in the queue is 10 MB, then the 10 MB of data is split into, for example, 1000 data packets. According to the 5 Mbps bandwidth, the maximum transmission unit of each data packet is determined, for example, set to 625 bytes. For the queue with priority 2, if the amount of data to be transmitted in the queue is 5 MB, the data packets are also split, and the maximum transmission unit is determined according to the 2 Mbps bandwidth, for example, set to 250 bytes. During data transmission, the system preferentially schedules the data packets in the queue with priority 1 for transmission. For the data packets in the queue with priority 1, Turbo codes are used for encoding, and for the data packets in the queue with priority 2, parity check codes are used for encoding. Thus, in the case of limited total bandwidth, critical physiological data can be preferentially transmitted and reliably guaranteed due to its higher priority and bandwidth allocation. Although the priority of non-critical physiological data is lower, it can still obtain bandwidth for transmission, ensuring the integrity of the data.

[0073] Preferably, before step A401, the following steps may further be included: A400a. Calculate the ratio of the allocated bandwidth of non-critical physiological data to the amount of non-critical physiological data, denoted as the ratio density; A400b. If the ratio density is lower than the preset ratio density threshold, then select at least part of the non-critical physiological data as the object to be replaced, and extract the feature data of the object to be replaced to replace the corresponding non-critical physiological data, so that the ratio density is not lower than the preset ratio density threshold.

[0074] Among them, the ratio density refers to the ratio of the allocated bandwidth of non-critical physiological data to the amount of non-critical physiological data, and is used to measure the bandwidth resources that can be obtained per unit data volume. Specifically, it can be calculated by dividing the numerical value of the bandwidth allocated to non-critical physiological data by the numerical value of the amount of non-critical physiological data. The allocated bandwidth can be obtained according to the bandwidth allocation scheme, and the amount of data can be obtained by counting the data size of non-critical physiological data.

[0075] Among them, the preset ratio density threshold is a reference value preset for judging whether the ratio density is too low. Specifically, it can be set according to the actual application scenario and requirements. The setting of the preset ratio density threshold needs to balance the data transmission efficiency and the integrity of data information. If the threshold is set too high, it may lead to excessive data replacement and loss of too much information; if the threshold is set too low, it may not effectively solve the problem of low transmission efficiency of non-critical physiological data.

[0076] Among them, selecting at least part of the non-critical physiological data as the object to be replaced means that when the ratio density is lower than the preset ratio density threshold, a part or all of the data is selected from the non-critical physiological data for replacement processing. Specifically, the selection strategy of the object to be replaced can be determined according to factors such as the data volume and importance of the non-critical physiological data. For example, non-critical physiological data with a larger data volume or relatively less importance is preferentially selected as the object to be replaced.

[0077] Among them, extracting the feature data of the object to be replaced to replace the corresponding non-critical physiological data means processing the object to be replaced, extracting the feature data that can represent the main information of the object and has a smaller data volume, and using these feature data to replace the original non-critical physiological data. Specifically, the extraction methods of feature data can adopt data compression algorithms, feature extraction algorithms, or data simplification algorithms, etc. For example, for waveform data, feature parameters such as wave peaks, wave valleys, and frequencies can be extracted; for image data, feature parameters such as textures, colors, and contours can be extracted. The data compression algorithm can adopt methods such as wavelet transform and discrete cosine transform. The feature extraction algorithm can adopt methods such as principal component analysis and linear discriminant analysis. The data simplification algorithm can adopt methods such as downsampling and data smoothing. Through the replacement of feature data, the data volume of non-critical physiological data can be effectively reduced, and the ratio density can be improved.

[0078] Among them, making the ratio density not lower than the preset ratio density threshold means that through data replacement operations, the data volume of non-critical physiological data is adjusted so that the recalculated ratio density value can reach or exceed the preset ratio density threshold. Specifically, if the ratio density is still lower than the preset ratio density threshold after one data replacement, the data replacement operation can be repeated until the ratio density meets the requirements.

[0079] Furthermore, the above steps A400a and A400b are executed before step A401 determines the priority queue. The purpose is to judge and adjust the ratio density before dividing the priority queue, so as to optimize the data transmission efficiency. By first calculating the ratio density and judging whether data replacement is needed based on the ratio density, the transmission efficiency problem that may be caused by the too large data volume of non-critical physiological data can be solved in advance, laying a foundation for the subsequent division of the priority queue and the formulation of the data transmission strategy. The combination of steps A400a and A400b with step A401 further realizes the dynamic adjustment of the data volume on the basis of bandwidth allocation, making the data transmission strategy more refined and intelligent.

[0080] Specifically, for the problem of the transmission efficiency of non-critical physiological data in this solution, the specific gravity calculation and data replacement steps are added. First, step A400a calculates the specific gravity of non-critical physiological data to evaluate the transmission efficiency of non-critical physiological data under the current bandwidth allocation. If the specific gravity is lower than the preset threshold, it indicates that the data volume of non-critical physiological data is too large relative to the allocated bandwidth, which may affect the transmission efficiency. At this time, step A400b starts the data replacement mechanism, selects some non-critical physiological data as the data to be replaced, extracts its characteristic data for replacement, so as to reduce the data volume and increase the specific gravity. Through data replacement, without losing the main information of non-critical physiological data, the data volume can be effectively reduced, thereby improving the transmission efficiency, avoiding non-critical physiological data from occupying too much bandwidth resources and affecting the overall data integration efficiency. After the specific gravity of non-critical physiological data is adjusted, it enters the subsequent priority queue division and data transmission process, which can ensure that both critical physiological data and non-critical physiological data can be efficiently transmitted under limited bandwidth conditions, and finally improve the overall performance of the surgical bed measurement data integration method in the mobile emergency unit.

[0081] Through the above technical solution, on the basis of claim 8, this application further considers the problem of the transmission efficiency of non-critical physiological data. By calculating the specific gravity and data replacement operations, it effectively solves the problem of low data transmission efficiency when the allocated bandwidth of non-critical physiological data is relatively too low compared to its data volume, ensuring that non-critical physiological data can be efficiently transmitted under limited bandwidth conditions, avoiding it from becoming a data transmission bottleneck, and finally improving the efficiency and real-time performance of the entire data integration method.

[0082] Reference Figure 2 , this application also proposes a surgical bed measurement data integration device for the edge computing module in the mobile emergency unit. The device includes: A data acquisition module 1, configured to acquire the patient's physiological data collected by multiple sensors on the surgical bed, perform preprocessing, and obtain the preprocessed physiological data (the specific process refers to step A1 in the previous text); A data classification module 2, configured to classify the preprocessed physiological data to divide the preprocessed physiological data into critical physiological data and non-critical physiological data (the specific process refers to step A2 in the previous text); A bandwidth allocation module 3, configured to monitor the network status information of the wireless network, and dynamically adjust the allocated bandwidths of critical physiological data and non-critical physiological data according to the network status information, the data volume of critical physiological data, and the data volume of non-critical physiological data, to obtain a bandwidth allocation scheme; the network status information includes the available bandwidth and the network congestion degree (the specific process refers to step A3 in the previous text); The transmission strategy adjustment module 4 is used to determine the data transmission strategies for critical physiological data and non-critical physiological data according to the bandwidth allocation scheme (for the specific process, refer to step A4 in the previous text). The data transmission module 5 is used to transmit data to the remote medical center according to the data transmission strategy (for the specific process, refer to step A5 in the previous text).

[0083] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some communication interfaces. The indirect coupling or communication connection of the devices or units can be in electrical, mechanical or other forms.

[0084] In addition, the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0085] Furthermore, in each embodiment of the present application, the functional modules can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0086] In this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0087] The above are only the embodiments of the present application and are not used to limit the protection scope of the present application. For those skilled in the art, the present application can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for integrating surgical bed measurement data, which is used for an edge computing module in a mobile emergency unit, is characterized in that The steps of the method include: A1. Obtain the physiological data of the patient collected by multiple sensors on the operating table, perform preprocessing, and obtain the preprocessed physiological data; A2. Classify the preprocessed physiological data to divide the preprocessed physiological data into critical physiological data and non-critical physiological data; A3. Monitor the network status information of the wireless network, and dynamically adjust the allocated bandwidths of the critical physiological data and the non-critical physiological data according to the network status information, the data volume of the critical physiological data, and the data volume of the non-critical physiological data, to obtain a bandwidth allocation scheme; the network status information includes available bandwidth and network congestion degree; A4. Determine the data transmission strategies for the critical physiological data and the non-critical physiological data according to the bandwidth allocation scheme; A5. Transmit data to the remote medical center according to the data transmission strategy.

2. The integrated method for measuring data of an operating bed according to claim 1, wherein Step A2 includes: A201. Extract the feature vectors of each item of preprocessed physiological data; A202. For each item of preprocessed physiological data, calculate the similarity between the feature vector of the preprocessed physiological data and each typical feature vector of the corresponding physiological data in the physiological data feature library, to obtain a similarity set; the physiological data feature library records the typical feature vectors of each physiological data in various emergency situations; A203. Determine whether the preprocessed physiological data is critical physiological data or non-critical physiological data according to the similarity set of each item of preprocessed physiological data.

3. The integrated method for surgical bed measurement data according to claim 2, characterized in that, Step A201 includes: For each item of preprocessed physiological data, use a feature extraction algorithm based on wavelet transform to decompose it into wavelet coefficients of multiple frequency bands; Calculate the energy values of the wavelet coefficients of each frequency band to form an energy feature vector; Normalize the energy feature vector to obtain the feature vector of each item of preprocessed physiological data.

4. The integrated method for surgical bed measurement data according to claim 2, wherein Step A203 includes: If there is at least one similarity in the similarity set that is greater than a preset similarity threshold, determine that the corresponding preprocessed physiological data is critical physiological data; If the similarities in the similarity set are all not greater than the preset similarity threshold, estimate the probability that the corresponding preprocessed physiological data is physiological data in an unknown emergency situation according to the similarity set; If the probability is greater than a preset probability threshold, determine that the corresponding preprocessed physiological data is critical physiological data, otherwise, determine that the corresponding preprocessed physiological data is non-critical physiological data.

5. A method for integrating surgical bed measurement data according to claim 4, characterized in that, The step of if the similarities in the similarity set are all not greater than the preset similarity threshold, then estimate the probability that the corresponding preprocessed physiological data is physiological data in an unknown emergency situation according to the similarity set includes: Calculate the variance of the similarity set to obtain a similarity variance; If the similarity variance is less than a preset variance threshold, use the Bayesian estimation method to estimate the probability that the corresponding preprocessed physiological data is physiological data in an unknown emergency situation according to the similarity set; If the similarity variance is not less than the preset variance threshold, use the kernel density estimation method to estimate the probability that the corresponding preprocessed physiological data is physiological data in an unknown emergency situation according to the similarity set.

6. The integrated method for measuring data of an operating bed according to claim 1, wherein Step A3 includes: A301. Monitor the available bandwidth and network congestion degree of the wireless network, and calculate the network quality score; A302. Obtain the data volumes of critical physiological data and non-critical physiological data, and calculate the ratio of the data volume of critical physiological data to that of non-critical physiological data; A303. According to the network quality score and the data volume ratio, adopt a fuzzy control algorithm to determine the target bandwidth allocation ratio of critical physiological data and non-critical physiological data; A304. According to the target bandwidth allocation ratio and the available bandwidth of the wireless network, calculate the allocated bandwidth of critical physiological data and the allocated bandwidth of non-critical physiological data to obtain a bandwidth allocation scheme.

7. A method for integrating measurement data of an operating table according to claim 6, characterized in that, Step A303 includes: According to the network quality score and the data volume ratio, adopt a fuzzy inference algorithm to select applicable fuzzy rules from the fuzzy rule base, calculate the activation strength of each fuzzy rule according to the network quality score and the data volume ratio, and obtain a fuzzy inference result; the fuzzy rule base contains multiple fuzzy rules, and the fuzzy rules define the mapping relationship between the network quality score, the data volume ratio and the target bandwidth allocation ratio; Perform weighted average defuzzification processing on the fuzzy inference result, and calculate the target bandwidth allocation ratio of critical physiological data and non-critical physiological data according to the activation strength of each fuzzy rule and the corresponding target bandwidth allocation ratio.

8. A method for integrating measurement data of an operating table according to claim 1, characterized in that Step A4 includes: A401. According to the bandwidth allocation scheme, determine the priority queues of critical physiological data and non-critical physiological data; A402. For each priority queue, divide the data into multiple data packets according to the data volume of the data to be transmitted in the queue, and determine the maximum transmission unit of each data packet according to the bandwidth allocation scheme; A403. According to the priority order of the priority queues, schedule the data packets in the queues, encapsulate the data packets according to the determined maximum transmission unit, perform error control coding on the data packets of critical physiological data using Turbo codes, and perform error control coding on the data packets of non-critical physiological data using parity check codes.

9. The integrated method for measuring data of an operating table according to claim 8, wherein Before step A401, it further includes the step of: A400a. Calculate the ratio of the allocated bandwidth of non-critical physiological data to the data volume of non-critical physiological data, denoted as the ratio density; A400b. If the ratio density is lower than a preset ratio density threshold, select at least part of the non-critical physiological data as the object to be replaced, extract the characteristic data of the object to be replaced to replace the corresponding non-critical physiological data, so that the ratio density is not lower than the preset ratio density threshold.

10. A surgical bed measurement data integration device for moving an edge computing module in a mobile emergency unit, characterized in that, The device includes: A data acquisition module, configured to acquire the physiological data of a patient collected by multiple sensors on the operating bed, perform preprocessing, and obtain the preprocessed physiological data; A data classification module, configured to perform classification processing on the preprocessed physiological data to divide the preprocessed physiological data into critical physiological data and non-critical physiological data; A bandwidth allocation module, configured to monitor the network status information of the wireless network, and dynamically adjust the allocated bandwidths of critical physiological data and non-critical physiological data according to the network status information, the data volume of critical physiological data, and the data volume of non-critical physiological data to obtain a bandwidth allocation scheme; the network status information includes the available bandwidth and the network congestion degree; A transmission policy adjustment module, which is used to determine the data transmission policies for critical physiological data and non-critical physiological data according to the bandwidth allocation scheme; A data transmission module, which is used to transmit data to a remote medical center according to the data transmission policy.

Images